python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 20 -a ' -a 3318 ' -s datou_3318 -M 0 -S 0 -U 95,95,120 import MySQLdb succeeded Import error (python version) ['/Users/moilerat/Documents/Fotonower/install/caffe/distribute/python', '/home/admin/workarea/git/Velours/python/prod', '/home/admin/workarea/install/caffe_cuda8_python3/python', '/home/admin/workarea/install/darknet', '/home/admin/workarea/git/Velours/python', '/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python', '/home/admin/mtr/.credentials', '/home/admin/workarea/install/caffe/python', '/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools', '/home/admin/workarea/git/fotonowerpip', '/home/admin/workarea/install/segment-anything', '/home/admin/workarea/git/pyfvs', '/usr/lib/python38.zip', '/usr/lib/python3.8', '/usr/lib/python3.8/lib-dynload', '/home/admin/.local/lib/python3.8/site-packages', '/usr/local/lib/python3.8/dist-packages', '/usr/lib/python3/dist-packages'] process id : 351592 load datou : 3318 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 3318, datou_cur_ids : ['2964573'] with mtr_portfolio_ids : ['23370929'] and first list_photo_ids : [] new path : /proc/351592/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, crop_condition, rle_unique_nms_with_priority, ventilate_hashtags_in_portfolio, final, blur_detection, brightness, velours_tree, send_mail_cod, split_time_score over limit max, limiting to limit_max 40 list_input_json : [] origin We have 1 , BFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 37 ; length of list_pids : 37 ; length of list_args : 37 time to download the photos : 7.381702184677124 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 10 step1:mask_detect Tue May 27 13:30:37 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3033 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-05-27 13:30:40.036288: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-05-27 13:30:40.063235: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-05-27 13:30:40.065325: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fdba8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-05-27 13:30:40.065385: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-05-27 13:30:40.069144: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-05-27 13:30:40.320902: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x43010920 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-05-27 13:30:40.320976: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-05-27 13:30:40.321883: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-05-27 13:30:40.322362: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-05-27 13:30:40.326551: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-05-27 13:30:40.329943: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-05-27 13:30:40.331072: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-05-27 13:30:40.334559: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-05-27 13:30:40.336134: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-05-27 13:30:40.342522: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-05-27 13:30:40.347960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-05-27 13:30:40.348077: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-05-27 13:30:40.348746: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-05-27 13:30:40.348766: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-05-27 13:30:40.348792: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-05-27 13:30:40.349890: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2581 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-05-27 13:30:40.648258: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-05-27 13:30:40.648337: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-05-27 13:30:40.648353: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-05-27 13:30:40.648368: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-05-27 13:30:40.648382: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-05-27 13:30:40.648396: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-05-27 13:30:40.648410: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-05-27 13:30:40.648423: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-05-27 13:30:40.649187: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-05-27 13:30:40.650032: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-05-27 13:30:40.650061: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-05-27 13:30:40.650076: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-05-27 13:30:40.650090: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-05-27 13:30:40.650104: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-05-27 13:30:40.650118: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-05-27 13:30:40.650132: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-05-27 13:30:40.650146: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-05-27 13:30:40.650967: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-05-27 13:30:40.650994: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-05-27 13:30:40.651002: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-05-27 13:30:40.651009: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-05-27 13:30:40.651867: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2581 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-05-27 13:30:54.173861: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-05-27 13:30:54.387818: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-05-27 13:30:56.127486: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.127547: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.134038: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.134090: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.185641: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.185709: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.226754: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.226824: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.277106: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.277170: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-05-27 13:30:56.601918: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 37 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 20 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 41 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 19 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 21 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 33 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 27 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 32 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 36 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 40 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 34 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 29 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 25 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 47 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 31 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 30 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 40 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 36 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 36 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 31 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 30 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 34 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 42 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 33 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 56 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 39 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 41 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 20 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 25 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 34 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 46 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 39 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 26 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 30 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 33 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 36 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 26 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 27 Detection mask done ! Trying to reset tf kernel 352383 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 3569 tf kernel not reseted sub process len(results) : 37 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 37 len(list_Values) 0 process is alive process is alive process is alive process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 6810 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2847 Catched exception ! Connect or reconnect ! thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] time for calcul the mask position with numpy : 0.09906530380249023 nb_pixel_total : 83349 time to create 1 rle with old method : 0.09284186363220215 length of segment : 409 time for calcul the mask position with numpy : 0.172288179397583 nb_pixel_total : 169317 time to create 1 rle with new method : 0.008634805679321289 length of segment : 522 time for calcul the mask position with numpy : 0.039635419845581055 nb_pixel_total : 25171 time to create 1 rle with old method : 0.03338623046875 length of segment : 228 time for calcul the mask position with numpy : 0.04924893379211426 nb_pixel_total : 28633 time to create 1 rle with old method : 0.03684568405151367 length of segment : 246 time for calcul the mask position with numpy : 0.05931210517883301 nb_pixel_total : 53817 time to create 1 rle with old method : 0.06487369537353516 length of segment : 265 time for calcul the mask position with numpy : 0.08300232887268066 nb_pixel_total : 77648 time to create 1 rle with old method : 0.08618044853210449 length of segment : 375 time for calcul the mask position with numpy : 0.06307458877563477 nb_pixel_total : 71681 time to create 1 rle with old method : 0.11242794990539551 length of segment : 310 time for calcul the mask position with numpy : 0.002334117889404297 nb_pixel_total : 19313 time to create 1 rle with old method : 0.024733781814575195 length of segment : 197 time for calcul the mask position with numpy : 0.1996746063232422 nb_pixel_total : 313588 time to create 1 rle with new method : 0.013890266418457031 length of segment : 744 time for calcul the mask position with numpy : 0.05997633934020996 nb_pixel_total : 83210 time to create 1 rle with old method : 0.10279989242553711 length of segment : 332 time for calcul the mask position with numpy : 0.021668434143066406 nb_pixel_total : 19864 time to create 1 rle with old method : 0.028038978576660156 length of segment : 188 time for calcul the mask position with numpy : 0.12007331848144531 nb_pixel_total : 155928 time to create 1 rle with new method : 0.010034799575805664 length of segment : 454 time for calcul the mask position with numpy : 0.13425469398498535 nb_pixel_total : 121867 time to create 1 rle with old method : 0.13710761070251465 length of segment : 365 time for calcul the mask position with numpy : 0.09083390235900879 nb_pixel_total : 23358 time to create 1 rle with old method : 0.03154706954956055 length of segment : 265 time for calcul the mask position with numpy : 0.0742499828338623 nb_pixel_total : 29762 time to create 1 rle with old method : 0.040068864822387695 length of segment : 178 time for calcul the mask position with numpy : 0.18880224227905273 nb_pixel_total : 193399 time to create 1 rle with new method : 0.009828329086303711 length of segment : 389 time for calcul the mask position with numpy : 0.13035869598388672 nb_pixel_total : 74348 time to create 1 rle with old method : 0.09174871444702148 length of segment : 321 time for calcul the mask position with numpy : 0.0329585075378418 nb_pixel_total : 52652 time to create 1 rle with old method : 0.06274294853210449 length of segment : 257 time for calcul the mask position with numpy : 0.007634878158569336 nb_pixel_total : 14011 time to create 1 rle with old method : 0.01868414878845215 length of segment : 106 time for calcul the mask position with numpy : 0.07674860954284668 nb_pixel_total : 62696 time to create 1 rle with old method : 0.07410645484924316 length of segment : 329 time for calcul the mask position with numpy : 0.11194324493408203 nb_pixel_total : 63760 time to create 1 rle with old method : 0.07884979248046875 length of segment : 352 time for calcul the mask position with numpy : 0.1884615421295166 nb_pixel_total : 103858 time to create 1 rle with old method : 0.12055611610412598 length of segment : 474 time for calcul the mask position with numpy : 0.13473773002624512 nb_pixel_total : 117103 time to create 1 rle with old method : 0.13322186470031738 length of segment : 420 time for calcul the mask position with numpy : 0.0004620552062988281 nb_pixel_total : 6885 time to create 1 rle with old method : 0.008244037628173828 length of segment : 79 time for calcul the mask position with numpy : 0.05396223068237305 nb_pixel_total : 46539 time to create 1 rle with old method : 0.05801653861999512 length of segment : 333 time for calcul the mask position with numpy : 0.15854191780090332 nb_pixel_total : 135358 time to create 1 rle with old method : 0.16175603866577148 length of segment : 519 time for calcul the mask position with numpy : 0.005880832672119141 nb_pixel_total : 65573 time to create 1 rle with old method : 0.07910823822021484 length of segment : 315 time for calcul the mask position with numpy : 0.10639119148254395 nb_pixel_total : 156726 time to create 1 rle with new method : 0.012430667877197266 length of segment : 347 time for calcul the mask position with numpy : 0.14243292808532715 nb_pixel_total : 83167 time to create 1 rle with old method : 0.09385156631469727 length of segment : 381 time for calcul the mask position with numpy : 0.09695839881896973 nb_pixel_total : 51141 time to create 1 rle with old method : 0.06024980545043945 length of segment : 311 time for calcul the mask position with numpy : 0.07482123374938965 nb_pixel_total : 39225 time to create 1 rle with old method : 0.04466509819030762 length of segment : 206 time for calcul the mask position with numpy : 0.18079638481140137 nb_pixel_total : 112421 time to create 1 rle with old method : 0.1276381015777588 length of segment : 494 time for calcul the mask position with numpy : 0.005574941635131836 nb_pixel_total : 21164 time to create 1 rle with old method : 0.023262739181518555 length of segment : 218 time for calcul the mask position with numpy : 0.05378556251525879 nb_pixel_total : 62454 time to create 1 rle with old method : 0.07196187973022461 length of segment : 245 time for calcul the mask position with numpy : 0.007828235626220703 nb_pixel_total : 6193 time to create 1 rle with old method : 0.009272336959838867 length of segment : 75 time for calcul the mask position with numpy : 0.003039836883544922 nb_pixel_total : 18377 time to create 1 rle with old method : 0.030285120010375977 length of segment : 416 time for calcul the mask position with numpy : 0.10645437240600586 nb_pixel_total : 88067 time to create 1 rle with old method : 0.1054983139038086 length of segment : 328 time for calcul the mask position with numpy : 0.020965576171875 nb_pixel_total : 14834 time to create 1 rle with old method : 0.022987842559814453 length of segment : 122 time for calcul the mask position with numpy : 0.016921520233154297 nb_pixel_total : 35939 time to create 1 rle with old method : 0.0428009033203125 length of segment : 266 time for calcul the mask position with numpy : 0.18790602684020996 nb_pixel_total : 159270 time to create 1 rle with new method : 0.013117551803588867 length of segment : 567 time for calcul the mask position with numpy : 0.14888548851013184 nb_pixel_total : 94670 time to create 1 rle with old method : 0.10990238189697266 length of segment : 698 time for calcul the mask position with numpy : 0.03566789627075195 nb_pixel_total : 19792 time to create 1 rle with old method : 0.02669358253479004 length of segment : 237 time for calcul the mask position with numpy : 0.021927356719970703 nb_pixel_total : 49247 time to create 1 rle with old method : 0.060437679290771484 length of segment : 308 time for calcul the mask position with numpy : 0.09842324256896973 nb_pixel_total : 90408 time to create 1 rle with old method : 0.10643219947814941 length of segment : 725 time for calcul the mask position with numpy : 0.04284930229187012 nb_pixel_total : 145326 time to create 1 rle with old method : 0.16654014587402344 length of segment : 568 time for calcul the mask position with numpy : 0.09698987007141113 nb_pixel_total : 45012 time to create 1 rle with old method : 0.05028390884399414 length of segment : 373 time for calcul the mask position with numpy : 0.1514883041381836 nb_pixel_total : 108688 time to create 1 rle with old method : 0.1298961639404297 length of segment : 585 time for calcul the mask position with numpy : 0.0339353084564209 nb_pixel_total : 23477 time to create 1 rle with old method : 0.03127646446228027 length of segment : 190 time for calcul the mask position with numpy : 0.02092909812927246 nb_pixel_total : 23118 time to create 1 rle with old method : 0.031709909439086914 length of segment : 252 time for calcul the mask position with numpy : 0.12839579582214355 nb_pixel_total : 143653 time to create 1 rle with old method : 0.16766929626464844 length of segment : 376 time for calcul the mask position with numpy : 0.27950167655944824 nb_pixel_total : 327205 time to create 1 rle with new method : 0.029543638229370117 length of segment : 850 time for calcul the mask position with numpy : 0.1266465187072754 nb_pixel_total : 141416 time to create 1 rle with old method : 0.1605968475341797 length of segment : 457 time for calcul the mask position with numpy : 0.05023837089538574 nb_pixel_total : 36240 time to create 1 rle with old method : 0.045479774475097656 length of segment : 545 time for calcul the mask position with numpy : 0.1137700080871582 nb_pixel_total : 46199 time to create 1 rle with old method : 0.053609609603881836 length of segment : 337 time for calcul the mask position with numpy : 0.08811044692993164 nb_pixel_total : 61790 time to create 1 rle with old method : 0.0767064094543457 length of segment : 321 time for calcul the mask position with numpy : 0.18657970428466797 nb_pixel_total : 180112 time to create 1 rle with new method : 0.012648582458496094 length of segment : 449 time for calcul the mask position with numpy : 0.10763740539550781 nb_pixel_total : 56597 time to create 1 rle with old method : 0.07203960418701172 length of segment : 404 time for calcul the mask position with numpy : 0.025241374969482422 nb_pixel_total : 15633 time to create 1 rle with old method : 0.0350797176361084 length of segment : 89 time for calcul the mask position with numpy : 0.031229257583618164 nb_pixel_total : 12656 time to create 1 rle with old method : 0.017072677612304688 length of segment : 141 time for calcul the mask position with numpy : 0.02305746078491211 nb_pixel_total : 8556 time to create 1 rle with old method : 0.015488862991333008 length of segment : 128 time for calcul the mask position with numpy : 0.2931840419769287 nb_pixel_total : 340531 time to create 1 rle with new method : 0.09149456024169922 length of segment : 773 time for calcul the mask position with numpy : 0.02787041664123535 nb_pixel_total : 22672 time to create 1 rle with old method : 0.03240799903869629 length of segment : 175 time for calcul the mask position with numpy : 0.018347740173339844 nb_pixel_total : 13624 time to create 1 rle with old method : 0.0218355655670166 length of segment : 128 time for calcul the mask position with numpy : 0.008659601211547852 nb_pixel_total : 43595 time to create 1 rle with old method : 0.057051658630371094 length of segment : 276 time for calcul the mask position with numpy : 0.04810190200805664 nb_pixel_total : 17854 time to create 1 rle with old method : 0.024976730346679688 length of segment : 224 time for calcul the mask position with numpy : 0.02488541603088379 nb_pixel_total : 22307 time to create 1 rle with old method : 0.03007197380065918 length of segment : 164 time for calcul the mask position with numpy : 0.11291670799255371 nb_pixel_total : 40040 time to create 1 rle with old method : 0.0665583610534668 length of segment : 452 time for calcul the mask position with numpy : 0.023140430450439453 nb_pixel_total : 18274 time to create 1 rle with old method : 0.02462148666381836 length of segment : 152 time for calcul the mask position with numpy : 0.06259894371032715 nb_pixel_total : 34965 time to create 1 rle with old method : 0.04387617111206055 length of segment : 318 time for calcul the mask position with numpy : 0.02796792984008789 nb_pixel_total : 26125 time to create 1 rle with old method : 0.033598899841308594 length of segment : 161 time for calcul the mask position with numpy : 0.16614484786987305 nb_pixel_total : 120504 time to create 1 rle with old method : 0.14103245735168457 length of segment : 392 time for calcul the mask position with numpy : 0.033286094665527344 nb_pixel_total : 17927 time to create 1 rle with old method : 0.02582859992980957 length of segment : 135 time for calcul the mask position with numpy : 0.19495677947998047 nb_pixel_total : 172148 time to create 1 rle with new method : 0.013036489486694336 length of segment : 547 time for calcul the mask position with numpy : 0.03395271301269531 nb_pixel_total : 12408 time to create 1 rle with old method : 0.019516706466674805 length of segment : 191 time for calcul the mask position with numpy : 0.12556242942810059 nb_pixel_total : 142772 time to create 1 rle with old method : 0.15897130966186523 length of segment : 421 time for calcul the mask position with numpy : 0.022249937057495117 nb_pixel_total : 10593 time to create 1 rle with old method : 0.017249584197998047 length of segment : 148 time for calcul the mask position with numpy : 0.020149707794189453 nb_pixel_total : 21998 time to create 1 rle with old method : 0.028567790985107422 length of segment : 252 time for calcul the mask position with numpy : 0.011359930038452148 nb_pixel_total : 8877 time to create 1 rle with old method : 0.014148950576782227 length of segment : 143 time for calcul the mask position with numpy : 0.06515145301818848 nb_pixel_total : 91843 time to create 1 rle with old method : 0.11507534980773926 length of segment : 413 time for calcul the mask position with numpy : 0.13450908660888672 nb_pixel_total : 81632 time to create 1 rle with old method : 0.0957028865814209 length of segment : 416 time for calcul the mask position with numpy : 0.09622430801391602 nb_pixel_total : 40483 time to create 1 rle with old method : 0.045610666275024414 length of segment : 342 time for calcul the mask position with numpy : 0.1037297248840332 nb_pixel_total : 50859 time to create 1 rle with old method : 0.06084942817687988 length of segment : 348 time for calcul the mask position with numpy : 0.046966552734375 nb_pixel_total : 40935 time to create 1 rle with old method : 0.05055427551269531 length of segment : 437 time for calcul the mask position with numpy : 0.05906176567077637 nb_pixel_total : 37923 time to create 1 rle with old method : 0.04479074478149414 length of segment : 288 time for calcul the mask position with numpy : 0.1522989273071289 nb_pixel_total : 156807 time to create 1 rle with new method : 0.015050172805786133 length of segment : 633 time for calcul the mask position with numpy : 0.02468252182006836 nb_pixel_total : 12789 time to create 1 rle with old method : 0.02092576026916504 length of segment : 81 time for calcul the mask position with numpy : 0.032201290130615234 nb_pixel_total : 15990 time to create 1 rle with old method : 0.022955656051635742 length of segment : 166 time for calcul the mask position with numpy : 0.050882577896118164 nb_pixel_total : 25930 time to create 1 rle with old method : 0.03299689292907715 length of segment : 278 time for calcul the mask position with numpy : 0.027370691299438477 nb_pixel_total : 25220 time to create 1 rle with old method : 0.031481266021728516 length of segment : 145 time for calcul the mask position with numpy : 0.20858502388000488 nb_pixel_total : 233633 time to create 1 rle with new method : 0.015047550201416016 length of segment : 794 time for calcul the mask position with numpy : 0.10641026496887207 nb_pixel_total : 78904 time to create 1 rle with old method : 0.09561514854431152 length of segment : 475 time for calcul the mask position with numpy : 0.013529539108276367 nb_pixel_total : 5041 time to create 1 rle with old method : 0.008540868759155273 length of segment : 123 time for calcul the mask position with numpy : 0.12001490592956543 nb_pixel_total : 112929 time to create 1 rle with old method : 0.12829256057739258 length of segment : 527 time for calcul the mask position with numpy : 0.0799558162689209 nb_pixel_total : 37716 time to create 1 rle with old method : 0.046755075454711914 length of segment : 315 time for calcul the mask position with numpy : 0.07937955856323242 nb_pixel_total : 48099 time to create 1 rle with old method : 0.05736351013183594 length of segment : 327 time for calcul the mask position with numpy : 0.09219717979431152 nb_pixel_total : 84352 time to create 1 rle with old method : 0.10186100006103516 length of segment : 206 time for calcul the mask position with numpy : 0.09660792350769043 nb_pixel_total : 37578 time to create 1 rle with old method : 0.04772591590881348 length of segment : 298 time for calcul the mask position with numpy : 0.061153411865234375 nb_pixel_total : 25950 time to create 1 rle with old method : 0.03717398643493652 length of segment : 269 time for calcul the mask position with numpy : 0.13347744941711426 nb_pixel_total : 84712 time to create 1 rle with old method : 0.09344267845153809 length of segment : 435 time for calcul the mask position with numpy : 0.040941715240478516 nb_pixel_total : 15757 time to create 1 rle with old method : 0.01966381072998047 length of segment : 193 time for calcul the mask position with numpy : 0.05048727989196777 nb_pixel_total : 22251 time to create 1 rle with old method : 0.028187036514282227 length of segment : 324 time for calcul the mask position with numpy : 0.016819000244140625 nb_pixel_total : 15225 time to create 1 rle with old method : 0.023459911346435547 length of segment : 125 time for calcul the mask position with numpy : 0.1567234992980957 nb_pixel_total : 184562 time to create 1 rle with new method : 0.013832807540893555 length of segment : 750 time for calcul the mask position with numpy : 0.061255455017089844 nb_pixel_total : 43663 time to create 1 rle with old method : 0.05597829818725586 length of segment : 233 time for calcul the mask position with numpy : 0.0670928955078125 nb_pixel_total : 78673 time to create 1 rle with old method : 0.08981728553771973 length of segment : 423 time for calcul the mask position with numpy : 0.03300166130065918 nb_pixel_total : 17293 time to create 1 rle with old method : 0.025229692459106445 length of segment : 154 time for calcul the mask position with numpy : 0.1665327548980713 nb_pixel_total : 156079 time to create 1 rle with new method : 0.012827157974243164 length of segment : 581 time for calcul the mask position with numpy : 0.019881725311279297 nb_pixel_total : 18200 time to create 1 rle with old method : 0.02489161491394043 length of segment : 150 time for calcul the mask position with numpy : 0.16919994354248047 nb_pixel_total : 74090 time to create 1 rle with old method : 0.08155369758605957 length of segment : 413 time for calcul the mask position with numpy : 0.03850698471069336 nb_pixel_total : 12462 time to create 1 rle with old method : 0.019555330276489258 length of segment : 137 time for calcul the mask position with numpy : 0.08884191513061523 nb_pixel_total : 58105 time to create 1 rle with old method : 0.06835055351257324 length of segment : 299 time for calcul the mask position with numpy : 0.10584735870361328 nb_pixel_total : 41744 time to create 1 rle with old method : 0.05289816856384277 length of segment : 379 time for calcul the mask position with numpy : 0.06481814384460449 nb_pixel_total : 28873 time to create 1 rle with old method : 0.036269426345825195 length of segment : 229 time for calcul the mask position with numpy : 0.04959368705749512 nb_pixel_total : 14718 time to create 1 rle with old method : 0.02165079116821289 length of segment : 193 time for calcul the mask position with numpy : 0.1964435577392578 nb_pixel_total : 124995 time to create 1 rle with old method : 0.14354443550109863 length of segment : 463 time for calcul the mask position with numpy : 0.0663766860961914 nb_pixel_total : 52874 time to create 1 rle with old method : 0.06306624412536621 length of segment : 271 time for calcul the mask position with numpy : 0.07218241691589355 nb_pixel_total : 21836 time to create 1 rle with old method : 0.02760934829711914 length of segment : 218 time for calcul the mask position with numpy : 0.07489132881164551 nb_pixel_total : 57909 time to create 1 rle with old method : 0.08388400077819824 length of segment : 151 time for calcul the mask position with numpy : 0.04137468338012695 nb_pixel_total : 20176 time to create 1 rle with old method : 0.026595115661621094 length of segment : 191 time for calcul the mask position with numpy : 0.01576519012451172 nb_pixel_total : 20022 time to create 1 rle with old method : 0.021733522415161133 length of segment : 178 time for calcul the mask position with numpy : 0.08179402351379395 nb_pixel_total : 85524 time to create 1 rle with old method : 0.09781289100646973 length of segment : 484 time for calcul the mask position with numpy : 0.25299906730651855 nb_pixel_total : 135124 time to create 1 rle with old method : 0.15970492362976074 length of segment : 667 time for calcul the mask position with numpy : 0.04618525505065918 nb_pixel_total : 58734 time to create 1 rle with old method : 0.07138562202453613 length of segment : 286 time for calcul the mask position with numpy : 0.043914794921875 nb_pixel_total : 28060 time to create 1 rle with old method : 0.03807353973388672 length of segment : 274 time for calcul the mask position with numpy : 0.039343833923339844 nb_pixel_total : 52409 time to create 1 rle with old method : 0.060482025146484375 length of segment : 504 time for calcul the mask position with numpy : 0.00884556770324707 nb_pixel_total : 6060 time to create 1 rle with old method : 0.008890151977539062 length of segment : 105 time for calcul the mask position with numpy : 0.03181719779968262 nb_pixel_total : 9889 time to create 1 rle with old method : 0.017557859420776367 length of segment : 145 time for calcul the mask position with numpy : 0.03657937049865723 nb_pixel_total : 16741 time to create 1 rle with old method : 0.02375006675720215 length of segment : 184 time for calcul the mask position with numpy : 0.034020423889160156 nb_pixel_total : 17512 time to create 1 rle with old method : 0.02217555046081543 length of segment : 160 time for calcul the mask position with numpy : 0.03888726234436035 nb_pixel_total : 20990 time to create 1 rle with old method : 0.027498960494995117 length of segment : 140 time for calcul the mask position with numpy : 0.07282280921936035 nb_pixel_total : 47649 time to create 1 rle with old method : 0.05514359474182129 length of segment : 289 time for calcul the mask position with numpy : 0.05075502395629883 nb_pixel_total : 22186 time to create 1 rle with old method : 0.02678513526916504 length of segment : 245 time for calcul the mask position with numpy : 0.05150771141052246 nb_pixel_total : 27304 time to create 1 rle with old method : 0.03377985954284668 length of segment : 219 time for calcul the mask position with numpy : 0.06385016441345215 nb_pixel_total : 27964 time to create 1 rle with old method : 0.036400794982910156 length of segment : 302 time for calcul the mask position with numpy : 0.024753093719482422 nb_pixel_total : 10874 time to create 1 rle with old method : 0.017371416091918945 length of segment : 106 time for calcul the mask position with numpy : 0.20465469360351562 nb_pixel_total : 144053 time to create 1 rle with old method : 0.16469168663024902 length of segment : 496 time for calcul the mask position with numpy : 0.06734633445739746 nb_pixel_total : 31807 time to create 1 rle with old method : 0.04122757911682129 length of segment : 259 time for calcul the mask position with numpy : 0.014240264892578125 nb_pixel_total : 9146 time to create 1 rle with old method : 0.01700448989868164 length of segment : 119 time for calcul the mask position with numpy : 0.1151435375213623 nb_pixel_total : 90458 time to create 1 rle with old method : 0.1125028133392334 length of segment : 420 time for calcul the mask position with numpy : 0.018491268157958984 nb_pixel_total : 5474 time to create 1 rle with old method : 0.00967264175415039 length of segment : 99 time for calcul the mask position with numpy : 0.04054141044616699 nb_pixel_total : 16037 time to create 1 rle with old method : 0.02461099624633789 length of segment : 155 time for calcul the mask position with numpy : 0.13954830169677734 nb_pixel_total : 75375 time to create 1 rle with old method : 0.0881502628326416 length of segment : 415 time for calcul the mask position with numpy : 0.07050871849060059 nb_pixel_total : 50011 time to create 1 rle with old method : 0.06069016456604004 length of segment : 285 time for calcul the mask position with numpy : 0.03583049774169922 nb_pixel_total : 29996 time to create 1 rle with old method : 0.03852963447570801 length of segment : 131 time for calcul the mask position with numpy : 0.038643598556518555 nb_pixel_total : 60302 time to create 1 rle with old method : 0.0870201587677002 length of segment : 380 time for calcul the mask position with numpy : 0.08710312843322754 nb_pixel_total : 133041 time to create 1 rle with old method : 0.15901899337768555 length of segment : 440 time for calcul the mask position with numpy : 0.03838181495666504 nb_pixel_total : 23157 time to create 1 rle with old method : 0.02670741081237793 length of segment : 196 time for calcul the mask position with numpy : 0.16321849822998047 nb_pixel_total : 160897 time to create 1 rle with new method : 0.00893855094909668 length of segment : 378 time for calcul the mask position with numpy : 0.07427239418029785 nb_pixel_total : 116014 time to create 1 rle with old method : 0.1317460536956787 length of segment : 452 time for calcul the mask position with numpy : 0.01471853256225586 nb_pixel_total : 8870 time to create 1 rle with old method : 0.014543771743774414 length of segment : 82 time for calcul the mask position with numpy : 0.041857242584228516 nb_pixel_total : 18979 time to create 1 rle with old method : 0.02667093276977539 length of segment : 234 time for calcul the mask position with numpy : 0.03903627395629883 nb_pixel_total : 27232 time to create 1 rle with old method : 0.038370370864868164 length of segment : 188 time for calcul the mask position with numpy : 0.1677541732788086 nb_pixel_total : 123743 time to create 1 rle with old method : 0.14163446426391602 length of segment : 610 time for calcul the mask position with numpy : 0.2959308624267578 nb_pixel_total : 388220 time to create 1 rle with new method : 0.05605268478393555 length of segment : 1177 time for calcul the mask position with numpy : 0.029530048370361328 nb_pixel_total : 18609 time to create 1 rle with old method : 0.02104783058166504 length of segment : 191 time for calcul the mask position with numpy : 0.04420948028564453 nb_pixel_total : 54270 time to create 1 rle with old method : 0.06896495819091797 length of segment : 272 time for calcul the mask position with numpy : 0.09169578552246094 nb_pixel_total : 101065 time to create 1 rle with old method : 0.12009263038635254 length of segment : 269 time for calcul the mask position with numpy : 0.021121501922607422 nb_pixel_total : 39786 time to create 1 rle with old method : 0.05014491081237793 length of segment : 290 time for calcul the mask position with numpy : 0.03544735908508301 nb_pixel_total : 20196 time to create 1 rle with old method : 0.02933979034423828 length of segment : 107 time for calcul the mask position with numpy : 0.024605274200439453 nb_pixel_total : 9356 time to create 1 rle with old method : 0.01598954200744629 length of segment : 90 time for calcul the mask position with numpy : 0.08623790740966797 nb_pixel_total : 49487 time to create 1 rle with old method : 0.07330584526062012 length of segment : 358 time for calcul the mask position with numpy : 0.007059335708618164 nb_pixel_total : 9972 time to create 1 rle with old method : 0.016761064529418945 length of segment : 86 time for calcul the mask position with numpy : 0.0402069091796875 nb_pixel_total : 13135 time to create 1 rle with old method : 0.018274784088134766 length of segment : 202 time for calcul the mask position with numpy : 0.041347503662109375 nb_pixel_total : 18480 time to create 1 rle with old method : 0.02432990074157715 length of segment : 159 time for calcul the mask position with numpy : 0.031035900115966797 nb_pixel_total : 10764 time to create 1 rle with old method : 0.017019033432006836 length of segment : 111 time for calcul the mask position with numpy : 0.12237763404846191 nb_pixel_total : 52618 time to create 1 rle with old method : 0.06537485122680664 length of segment : 448 time for calcul the mask position with numpy : 0.09687519073486328 nb_pixel_total : 59268 time to create 1 rle with old method : 0.07210087776184082 length of segment : 422 time for calcul the mask position with numpy : 0.02977919578552246 nb_pixel_total : 7457 time to create 1 rle with old method : 0.012876510620117188 length of segment : 158 time for calcul the mask position with numpy : 0.10427474975585938 nb_pixel_total : 58045 time to create 1 rle with old method : 0.09403085708618164 length of segment : 322 time for calcul the mask position with numpy : 0.04575657844543457 nb_pixel_total : 24368 time to create 1 rle with old method : 0.0318140983581543 length of segment : 198 time for calcul the mask position with numpy : 0.02661442756652832 nb_pixel_total : 9753 time to create 1 rle with old method : 0.015336751937866211 length of segment : 111 time for calcul the mask position with numpy : 0.080963134765625 nb_pixel_total : 37169 time to create 1 rle with old method : 0.04764723777770996 length of segment : 258 time for calcul the mask position with numpy : 0.08169269561767578 nb_pixel_total : 56067 time to create 1 rle with old method : 0.07251572608947754 length of segment : 378 time for calcul the mask position with numpy : 0.05300545692443848 nb_pixel_total : 30898 time to create 1 rle with old method : 0.041558265686035156 length of segment : 179 time for calcul the mask position with numpy : 0.1709003448486328 nb_pixel_total : 146764 time to create 1 rle with old method : 0.18247151374816895 length of segment : 340 time for calcul the mask position with numpy : 0.018286466598510742 nb_pixel_total : 15082 time to create 1 rle with old method : 0.02287745475769043 length of segment : 143 time for calcul the mask position with numpy : 0.15112781524658203 nb_pixel_total : 59485 time to create 1 rle with old method : 0.08127570152282715 length of segment : 471 time for calcul the mask position with numpy : 0.052768707275390625 nb_pixel_total : 20804 time to create 1 rle with old method : 0.032021284103393555 length of segment : 193 time for calcul the mask position with numpy : 0.03426241874694824 nb_pixel_total : 30715 time to create 1 rle with old method : 0.04408740997314453 length of segment : 157 time for calcul the mask position with numpy : 0.03553438186645508 nb_pixel_total : 22025 time to create 1 rle with old method : 0.030863523483276367 length of segment : 214 time for calcul the mask position with numpy : 0.018575191497802734 nb_pixel_total : 22471 time to create 1 rle with old method : 0.03145933151245117 length of segment : 167 time for calcul the mask position with numpy : 0.03076338768005371 nb_pixel_total : 13490 time to create 1 rle with old method : 0.019366741180419922 length of segment : 213 time for calcul the mask position with numpy : 0.01474761962890625 nb_pixel_total : 27912 time to create 1 rle with old method : 0.041963815689086914 length of segment : 198 time for calcul the mask position with numpy : 0.07807517051696777 nb_pixel_total : 29117 time to create 1 rle with old method : 0.05482816696166992 length of segment : 409 time for calcul the mask position with numpy : 0.026142597198486328 nb_pixel_total : 36377 time to create 1 rle with old method : 0.04808688163757324 length of segment : 346 time for calcul the mask position with numpy : 0.1239631175994873 nb_pixel_total : 64488 time to create 1 rle with old method : 0.07635760307312012 length of segment : 402 time for calcul the mask position with numpy : 0.13330674171447754 nb_pixel_total : 125987 time to create 1 rle with old method : 0.1368849277496338 length of segment : 473 time for calcul the mask position with numpy : 0.11605095863342285 nb_pixel_total : 100042 time to create 1 rle with old method : 0.11324334144592285 length of segment : 428 time for calcul the mask position with numpy : 0.04127335548400879 nb_pixel_total : 12563 time to create 1 rle with old method : 0.018537044525146484 length of segment : 115 time for calcul the mask position with numpy : 0.25250244140625 nb_pixel_total : 270498 time to create 1 rle with new method : 0.016662120819091797 length of segment : 730 time for calcul the mask position with numpy : 0.051053762435913086 nb_pixel_total : 37358 time to create 1 rle with old method : 0.04310178756713867 length of segment : 237 time for calcul the mask position with numpy : 0.012894153594970703 nb_pixel_total : 9317 time to create 1 rle with old method : 0.010591506958007812 length of segment : 82 time for calcul the mask position with numpy : 0.00017642974853515625 nb_pixel_total : 8587 time to create 1 rle with old method : 0.009657144546508789 length of segment : 98 time for calcul the mask position with numpy : 0.07312726974487305 nb_pixel_total : 64826 time to create 1 rle with old method : 0.0773932933807373 length of segment : 278 time for calcul the mask position with numpy : 0.0463252067565918 nb_pixel_total : 22998 time to create 1 rle with old method : 0.030739307403564453 length of segment : 209 time for calcul the mask position with numpy : 0.032363176345825195 nb_pixel_total : 13828 time to create 1 rle with old method : 0.022961139678955078 length of segment : 159 time for calcul the mask position with numpy : 0.030338764190673828 nb_pixel_total : 11454 time to create 1 rle with old method : 0.01310420036315918 length of segment : 139 time for calcul the mask position with numpy : 0.054262638092041016 nb_pixel_total : 112086 time to create 1 rle with old method : 0.12165188789367676 length of segment : 568 time for calcul the mask position with numpy : 0.04325413703918457 nb_pixel_total : 46405 time to create 1 rle with old method : 0.05494546890258789 length of segment : 342 time for calcul the mask position with numpy : 0.07009363174438477 nb_pixel_total : 34567 time to create 1 rle with old method : 0.04242253303527832 length of segment : 242 time for calcul the mask position with numpy : 0.14094138145446777 nb_pixel_total : 61997 time to create 1 rle with old method : 0.06761550903320312 length of segment : 639 time for calcul the mask position with numpy : 0.10693502426147461 nb_pixel_total : 79394 time to create 1 rle with old method : 0.08834719657897949 length of segment : 285 time for calcul the mask position with numpy : 0.03438067436218262 nb_pixel_total : 23490 time to create 1 rle with old method : 0.029254913330078125 length of segment : 203 time for calcul the mask position with numpy : 0.12642312049865723 nb_pixel_total : 55782 time to create 1 rle with old method : 0.06597137451171875 length of segment : 361 time for calcul the mask position with numpy : 0.017502307891845703 nb_pixel_total : 19796 time to create 1 rle with old method : 0.026663780212402344 length of segment : 143 time for calcul the mask position with numpy : 0.4146857261657715 nb_pixel_total : 313375 time to create 1 rle with new method : 0.0752108097076416 length of segment : 1188 time for calcul the mask position with numpy : 0.14447712898254395 nb_pixel_total : 105249 time to create 1 rle with old method : 0.11524462699890137 length of segment : 563 time for calcul the mask position with numpy : 0.008353471755981445 nb_pixel_total : 52220 time to create 1 rle with old method : 0.06124711036682129 length of segment : 390 time for calcul the mask position with numpy : 0.0666954517364502 nb_pixel_total : 50516 time to create 1 rle with old method : 0.07030844688415527 length of segment : 417 time for calcul the mask position with numpy : 0.10295915603637695 nb_pixel_total : 73833 time to create 1 rle with old method : 0.0853888988494873 length of segment : 547 time for calcul the mask position with numpy : 0.01490473747253418 nb_pixel_total : 9934 time to create 1 rle with old method : 0.015636920928955078 length of segment : 153 time for calcul the mask position with numpy : 0.09769892692565918 nb_pixel_total : 52931 time to create 1 rle with old method : 0.061701059341430664 length of segment : 342 time for calcul the mask position with numpy : 0.12028145790100098 nb_pixel_total : 66359 time to create 1 rle with old method : 0.07645487785339355 length of segment : 327 time for calcul the mask position with numpy : 0.05572366714477539 nb_pixel_total : 26109 time to create 1 rle with old method : 0.0327451229095459 length of segment : 202 time for calcul the mask position with numpy : 0.05788230895996094 nb_pixel_total : 21211 time to create 1 rle with old method : 0.026110172271728516 length of segment : 179 time for calcul the mask position with numpy : 0.21690034866333008 nb_pixel_total : 111078 time to create 1 rle with old method : 0.12040281295776367 length of segment : 617 time for calcul the mask position with numpy : 0.15518975257873535 nb_pixel_total : 62151 time to create 1 rle with old method : 0.06967973709106445 length of segment : 409 time for calcul the mask position with numpy : 0.023273944854736328 nb_pixel_total : 16611 time to create 1 rle with old method : 0.02202630043029785 length of segment : 144 time for calcul the mask position with numpy : 0.06453633308410645 nb_pixel_total : 70690 time to create 1 rle with old method : 0.07920289039611816 length of segment : 327 time for calcul the mask position with numpy : 0.03748917579650879 nb_pixel_total : 23503 time to create 1 rle with old method : 0.031412363052368164 length of segment : 178 time for calcul the mask position with numpy : 0.09546589851379395 nb_pixel_total : 51658 time to create 1 rle with old method : 0.06087470054626465 length of segment : 298 time for calcul the mask position with numpy : 0.0044558048248291016 nb_pixel_total : 4919 time to create 1 rle with old method : 0.005450010299682617 length of segment : 51 time for calcul the mask position with numpy : 0.029895544052124023 nb_pixel_total : 13493 time to create 1 rle with old method : 0.02093219757080078 length of segment : 154 time for calcul the mask position with numpy : 0.044321537017822266 nb_pixel_total : 17239 time to create 1 rle with old method : 0.025573253631591797 length of segment : 152 time for calcul the mask position with numpy : 0.17035269737243652 nb_pixel_total : 75999 time to create 1 rle with old method : 0.08760881423950195 length of segment : 432 time for calcul the mask position with numpy : 0.042284488677978516 nb_pixel_total : 23310 time to create 1 rle with old method : 0.032454729080200195 length of segment : 138 time for calcul the mask position with numpy : 0.06250309944152832 nb_pixel_total : 26139 time to create 1 rle with old method : 0.03257942199707031 length of segment : 264 time for calcul the mask position with numpy : 0.0765225887298584 nb_pixel_total : 58358 time to create 1 rle with old method : 0.06900358200073242 length of segment : 303 time for calcul the mask position with numpy : 0.02083420753479004 nb_pixel_total : 89010 time to create 1 rle with old method : 0.10354161262512207 length of segment : 450 time for calcul the mask position with numpy : 0.03634905815124512 nb_pixel_total : 14448 time to create 1 rle with old method : 0.022292613983154297 length of segment : 140 time for calcul the mask position with numpy : 0.043548583984375 nb_pixel_total : 12146 time to create 1 rle with old method : 0.01990032196044922 length of segment : 192 time for calcul the mask position with numpy : 0.09964871406555176 nb_pixel_total : 53633 time to create 1 rle with old method : 0.06193399429321289 length of segment : 332 time for calcul the mask position with numpy : 0.0417478084564209 nb_pixel_total : 17647 time to create 1 rle with old method : 0.023122072219848633 length of segment : 156 time for calcul the mask position with numpy : 0.04471325874328613 nb_pixel_total : 20415 time to create 1 rle with old method : 0.027617216110229492 length of segment : 166 time for calcul the mask position with numpy : 0.06213998794555664 nb_pixel_total : 42065 time to create 1 rle with old method : 0.052954912185668945 length of segment : 236 time for calcul the mask position with numpy : 0.1365065574645996 nb_pixel_total : 68166 time to create 1 rle with old method : 0.0788416862487793 length of segment : 317 time for calcul the mask position with numpy : 0.042173147201538086 nb_pixel_total : 22022 time to create 1 rle with old method : 0.028551816940307617 length of segment : 126 time for calcul the mask position with numpy : 0.15331196784973145 nb_pixel_total : 61710 time to create 1 rle with old method : 0.07186627388000488 length of segment : 418 time for calcul the mask position with numpy : 0.04922628402709961 nb_pixel_total : 16124 time to create 1 rle with old method : 0.027396202087402344 length of segment : 183 time for calcul the mask position with numpy : 0.3524775505065918 nb_pixel_total : 175384 time to create 1 rle with new method : 0.017539024353027344 length of segment : 634 time for calcul the mask position with numpy : 0.0322117805480957 nb_pixel_total : 12893 time to create 1 rle with old method : 0.019911766052246094 length of segment : 156 time for calcul the mask position with numpy : 0.02712416648864746 nb_pixel_total : 16286 time to create 1 rle with old method : 0.023418903350830078 length of segment : 152 time for calcul the mask position with numpy : 0.10807061195373535 nb_pixel_total : 98761 time to create 1 rle with old method : 0.11592912673950195 length of segment : 399 time for calcul the mask position with numpy : 0.03659939765930176 nb_pixel_total : 16447 time to create 1 rle with old method : 0.023328781127929688 length of segment : 160 time for calcul the mask position with numpy : 0.05027151107788086 nb_pixel_total : 22423 time to create 1 rle with old method : 0.028950929641723633 length of segment : 171 time for calcul the mask position with numpy : 0.07779598236083984 nb_pixel_total : 60870 time to create 1 rle with old method : 0.07224345207214355 length of segment : 485 time for calcul the mask position with numpy : 0.07692885398864746 nb_pixel_total : 59562 time to create 1 rle with old method : 0.06891989707946777 length of segment : 271 time for calcul the mask position with numpy : 0.24271631240844727 nb_pixel_total : 211305 time to create 1 rle with new method : 0.015686750411987305 length of segment : 639 time for calcul the mask position with numpy : 0.01918482780456543 nb_pixel_total : 18301 time to create 1 rle with old method : 0.02611517906188965 length of segment : 162 time for calcul the mask position with numpy : 0.034011125564575195 nb_pixel_total : 20234 time to create 1 rle with old method : 0.0283966064453125 length of segment : 176 time for calcul the mask position with numpy : 0.05680537223815918 nb_pixel_total : 60184 time to create 1 rle with old method : 0.0679473876953125 length of segment : 283 time for calcul the mask position with numpy : 0.04951047897338867 nb_pixel_total : 27039 time to create 1 rle with old method : 0.03155517578125 length of segment : 176 time for calcul the mask position with numpy : 0.07212519645690918 nb_pixel_total : 32693 time to create 1 rle with old method : 0.04001975059509277 length of segment : 185 time for calcul the mask position with numpy : 0.03424668312072754 nb_pixel_total : 16439 time to create 1 rle with old method : 0.022029638290405273 length of segment : 144 time for calcul the mask position with numpy : 0.0757448673248291 nb_pixel_total : 23939 time to create 1 rle with old method : 0.03168988227844238 length of segment : 271 time for calcul the mask position with numpy : 0.020536422729492188 nb_pixel_total : 7033 time to create 1 rle with old method : 0.012415647506713867 length of segment : 101 time for calcul the mask position with numpy : 0.03259420394897461 nb_pixel_total : 39214 time to create 1 rle with old method : 0.04529690742492676 length of segment : 220 time for calcul the mask position with numpy : 0.025730371475219727 nb_pixel_total : 20593 time to create 1 rle with old method : 0.027718544006347656 length of segment : 107 time for calcul the mask position with numpy : 0.021267414093017578 nb_pixel_total : 20145 time to create 1 rle with old method : 0.025949954986572266 length of segment : 148 time for calcul the mask position with numpy : 0.053048133850097656 nb_pixel_total : 24296 time to create 1 rle with old method : 0.031926870346069336 length of segment : 288 time for calcul the mask position with numpy : 0.04770159721374512 nb_pixel_total : 23447 time to create 1 rle with old method : 0.031064271926879883 length of segment : 183 time for calcul the mask position with numpy : 0.06174898147583008 nb_pixel_total : 38923 time to create 1 rle with old method : 0.052512407302856445 length of segment : 174 time for calcul the mask position with numpy : 0.07284140586853027 nb_pixel_total : 56267 time to create 1 rle with old method : 0.06545448303222656 length of segment : 408 time for calcul the mask position with numpy : 0.03275799751281738 nb_pixel_total : 102204 time to create 1 rle with old method : 0.11964011192321777 length of segment : 375 time for calcul the mask position with numpy : 0.019866466522216797 nb_pixel_total : 77976 time to create 1 rle with old method : 0.10660195350646973 length of segment : 273 time for calcul the mask position with numpy : 0.0034470558166503906 nb_pixel_total : 28933 time to create 1 rle with old method : 0.03404712677001953 length of segment : 189 time for calcul the mask position with numpy : 0.005730628967285156 nb_pixel_total : 35106 time to create 1 rle with old method : 0.04481315612792969 length of segment : 287 time for calcul the mask position with numpy : 0.001146078109741211 nb_pixel_total : 2232 time to create 1 rle with old method : 0.002672433853149414 length of segment : 63 time for calcul the mask position with numpy : 0.0011377334594726562 nb_pixel_total : 10713 time to create 1 rle with old method : 0.012458324432373047 length of segment : 149 time for calcul the mask position with numpy : 0.027793407440185547 nb_pixel_total : 42046 time to create 1 rle with old method : 0.0589289665222168 length of segment : 348 time for calcul the mask position with numpy : 0.00916290283203125 nb_pixel_total : 97095 time to create 1 rle with old method : 0.11500787734985352 length of segment : 570 time for calcul the mask position with numpy : 0.0017728805541992188 nb_pixel_total : 13134 time to create 1 rle with old method : 0.015251398086547852 length of segment : 115 time for calcul the mask position with numpy : 0.00400853157043457 nb_pixel_total : 53389 time to create 1 rle with old method : 0.060118913650512695 length of segment : 223 time for calcul the mask position with numpy : 0.04068422317504883 nb_pixel_total : 27438 time to create 1 rle with old method : 0.0351560115814209 length of segment : 191 time for calcul the mask position with numpy : 0.010403871536254883 nb_pixel_total : 12429 time to create 1 rle with old method : 0.017594337463378906 length of segment : 201 time for calcul the mask position with numpy : 0.03466200828552246 nb_pixel_total : 110172 time to create 1 rle with old method : 0.15234684944152832 length of segment : 231 time for calcul the mask position with numpy : 0.0047760009765625 nb_pixel_total : 47159 time to create 1 rle with old method : 0.052875518798828125 length of segment : 250 time for calcul the mask position with numpy : 0.017859458923339844 nb_pixel_total : 34071 time to create 1 rle with old method : 0.041368722915649414 length of segment : 227 time for calcul the mask position with numpy : 0.010695219039916992 nb_pixel_total : 95070 time to create 1 rle with old method : 0.10796499252319336 length of segment : 338 time for calcul the mask position with numpy : 0.006064891815185547 nb_pixel_total : 35831 time to create 1 rle with old method : 0.042058706283569336 length of segment : 249 time for calcul the mask position with numpy : 0.012277364730834961 nb_pixel_total : 175498 time to create 1 rle with new method : 0.012018442153930664 length of segment : 554 time for calcul the mask position with numpy : 0.0022830963134765625 nb_pixel_total : 32180 time to create 1 rle with old method : 0.03585028648376465 length of segment : 210 time for calcul the mask position with numpy : 0.008867740631103516 nb_pixel_total : 33691 time to create 1 rle with old method : 0.04472970962524414 length of segment : 253 time for calcul the mask position with numpy : 0.04359865188598633 nb_pixel_total : 168508 time to create 1 rle with new method : 0.011787652969360352 length of segment : 500 time for calcul the mask position with numpy : 0.0024175643920898438 nb_pixel_total : 62873 time to create 1 rle with old method : 0.08119535446166992 length of segment : 311 time for calcul the mask position with numpy : 0.015393257141113281 nb_pixel_total : 40210 time to create 1 rle with old method : 0.0784761905670166 length of segment : 246 time for calcul the mask position with numpy : 0.001500844955444336 nb_pixel_total : 15732 time to create 1 rle with old method : 0.020075559616088867 length of segment : 121 time for calcul the mask position with numpy : 0.01655888557434082 nb_pixel_total : 81642 time to create 1 rle with old method : 0.17608189582824707 length of segment : 538 time for calcul the mask position with numpy : 0.02795886993408203 nb_pixel_total : 131540 time to create 1 rle with old method : 0.14937305450439453 length of segment : 432 time for calcul the mask position with numpy : 0.0023186206817626953 nb_pixel_total : 5627 time to create 1 rle with old method : 0.0066111087799072266 length of segment : 117 time for calcul the mask position with numpy : 0.014161348342895508 nb_pixel_total : 40504 time to create 1 rle with old method : 0.05113577842712402 length of segment : 201 time for calcul the mask position with numpy : 0.02830982208251953 nb_pixel_total : 89589 time to create 1 rle with old method : 0.16788482666015625 length of segment : 461 time for calcul the mask position with numpy : 0.03801536560058594 nb_pixel_total : 68914 time to create 1 rle with old method : 0.08205223083496094 length of segment : 284 time for calcul the mask position with numpy : 0.004185914993286133 nb_pixel_total : 90703 time to create 1 rle with old method : 0.10376620292663574 length of segment : 258 time for calcul the mask position with numpy : 0.003079652786254883 nb_pixel_total : 15090 time to create 1 rle with old method : 0.01967644691467285 length of segment : 237 time for calcul the mask position with numpy : 0.016974449157714844 nb_pixel_total : 151706 time to create 1 rle with new method : 0.008776426315307617 length of segment : 614 time for calcul the mask position with numpy : 0.002474069595336914 nb_pixel_total : 20144 time to create 1 rle with old method : 0.02352738380432129 length of segment : 158 time for calcul the mask position with numpy : 0.004225015640258789 nb_pixel_total : 52450 time to create 1 rle with old method : 0.06304359436035156 length of segment : 324 time for calcul the mask position with numpy : 0.0060040950775146484 nb_pixel_total : 27638 time to create 1 rle with old method : 0.034887075424194336 length of segment : 238 time for calcul the mask position with numpy : 0.004767894744873047 nb_pixel_total : 74613 time to create 1 rle with old method : 0.08375692367553711 length of segment : 277 time for calcul the mask position with numpy : 0.0008521080017089844 nb_pixel_total : 14900 time to create 1 rle with old method : 0.017151832580566406 length of segment : 140 time for calcul the mask position with numpy : 0.003314971923828125 nb_pixel_total : 17512 time to create 1 rle with old method : 0.02149677276611328 length of segment : 141 time for calcul the mask position with numpy : 0.009482860565185547 nb_pixel_total : 68888 time to create 1 rle with old method : 0.08246850967407227 length of segment : 354 time for calcul the mask position with numpy : 0.05163121223449707 nb_pixel_total : 51422 time to create 1 rle with old method : 0.06186056137084961 length of segment : 241 time for calcul the mask position with numpy : 0.21874308586120605 nb_pixel_total : 342961 time to create 1 rle with new method : 0.020952701568603516 length of segment : 634 time for calcul the mask position with numpy : 0.029464244842529297 nb_pixel_total : 18904 time to create 1 rle with old method : 0.02626180648803711 length of segment : 175 time for calcul the mask position with numpy : 0.06587338447570801 nb_pixel_total : 174104 time to create 1 rle with new method : 0.009040117263793945 length of segment : 574 time for calcul the mask position with numpy : 0.07261061668395996 nb_pixel_total : 143360 time to create 1 rle with old method : 0.16800880432128906 length of segment : 492 time for calcul the mask position with numpy : 0.04382467269897461 nb_pixel_total : 75540 time to create 1 rle with old method : 0.08697915077209473 length of segment : 717 time for calcul the mask position with numpy : 0.02543497085571289 nb_pixel_total : 46037 time to create 1 rle with old method : 0.07320928573608398 length of segment : 232 time for calcul the mask position with numpy : 0.0054209232330322266 nb_pixel_total : 44488 time to create 1 rle with old method : 0.05169558525085449 length of segment : 251 time for calcul the mask position with numpy : 0.010445594787597656 nb_pixel_total : 96509 time to create 1 rle with old method : 0.11235284805297852 length of segment : 336 time for calcul the mask position with numpy : 0.0015497207641601562 nb_pixel_total : 15012 time to create 1 rle with old method : 0.016541242599487305 length of segment : 115 time for calcul the mask position with numpy : 0.0030584335327148438 nb_pixel_total : 68812 time to create 1 rle with old method : 0.08207273483276367 length of segment : 363 time for calcul the mask position with numpy : 0.003317594528198242 nb_pixel_total : 8945 time to create 1 rle with old method : 0.009943246841430664 length of segment : 169 time for calcul the mask position with numpy : 0.001687765121459961 nb_pixel_total : 36184 time to create 1 rle with old method : 0.040566444396972656 length of segment : 176 time for calcul the mask position with numpy : 0.0021982192993164062 nb_pixel_total : 7513 time to create 1 rle with old method : 0.008056402206420898 length of segment : 111 time for calcul the mask position with numpy : 0.03812146186828613 nb_pixel_total : 123239 time to create 1 rle with old method : 0.1383371353149414 length of segment : 451 time for calcul the mask position with numpy : 0.04636716842651367 nb_pixel_total : 144188 time to create 1 rle with old method : 0.1618950366973877 length of segment : 619 time for calcul the mask position with numpy : 0.0034210681915283203 nb_pixel_total : 14620 time to create 1 rle with old method : 0.01824188232421875 length of segment : 160 time for calcul the mask position with numpy : 0.02171802520751953 nb_pixel_total : 125371 time to create 1 rle with old method : 0.14922690391540527 length of segment : 316 time for calcul the mask position with numpy : 0.0870964527130127 nb_pixel_total : 101887 time to create 1 rle with old method : 0.11423563957214355 length of segment : 405 time for calcul the mask position with numpy : 0.005982637405395508 nb_pixel_total : 8815 time to create 1 rle with old method : 0.01602959632873535 length of segment : 138 time for calcul the mask position with numpy : 0.007687091827392578 nb_pixel_total : 156333 time to create 1 rle with new method : 0.00995326042175293 length of segment : 543 time for calcul the mask position with numpy : 0.0020656585693359375 nb_pixel_total : 50420 time to create 1 rle with old method : 0.0560612678527832 length of segment : 251 time for calcul the mask position with numpy : 0.013888835906982422 nb_pixel_total : 119897 time to create 1 rle with old method : 0.13426733016967773 length of segment : 958 time for calcul the mask position with numpy : 0.0009243488311767578 nb_pixel_total : 21228 time to create 1 rle with old method : 0.023818492889404297 length of segment : 164 time for calcul the mask position with numpy : 0.0330657958984375 nb_pixel_total : 41023 time to create 1 rle with old method : 0.050943851470947266 length of segment : 306 time for calcul the mask position with numpy : 0.013712167739868164 nb_pixel_total : 131269 time to create 1 rle with old method : 0.1481006145477295 length of segment : 874 time for calcul the mask position with numpy : 0.004876613616943359 nb_pixel_total : 37398 time to create 1 rle with old method : 0.04292726516723633 length of segment : 197 time for calcul the mask position with numpy : 0.008385896682739258 nb_pixel_total : 63816 time to create 1 rle with old method : 0.07138538360595703 length of segment : 327 time for calcul the mask position with numpy : 0.023715496063232422 nb_pixel_total : 294079 time to create 1 rle with new method : 0.029138803482055664 length of segment : 769 time for calcul the mask position with numpy : 0.014272689819335938 nb_pixel_total : 69003 time to create 1 rle with old method : 0.07724475860595703 length of segment : 305 time for calcul the mask position with numpy : 0.006379604339599609 nb_pixel_total : 86776 time to create 1 rle with old method : 0.0967562198638916 length of segment : 292 time for calcul the mask position with numpy : 0.0061626434326171875 nb_pixel_total : 7066 time to create 1 rle with old method : 0.009630441665649414 length of segment : 120 time for calcul the mask position with numpy : 0.004040241241455078 nb_pixel_total : 44496 time to create 1 rle with old method : 0.04972028732299805 length of segment : 372 time for calcul the mask position with numpy : 0.0057220458984375 nb_pixel_total : 27973 time to create 1 rle with old method : 0.03430747985839844 length of segment : 247 time for calcul the mask position with numpy : 0.0022101402282714844 nb_pixel_total : 35056 time to create 1 rle with old method : 0.03939461708068848 length of segment : 178 time for calcul the mask position with numpy : 0.008084774017333984 nb_pixel_total : 14863 time to create 1 rle with old method : 0.01933145523071289 length of segment : 229 time for calcul the mask position with numpy : 0.0028960704803466797 nb_pixel_total : 19075 time to create 1 rle with old method : 0.024120092391967773 length of segment : 179 time for calcul the mask position with numpy : 0.10103726387023926 nb_pixel_total : 113709 time to create 1 rle with old method : 0.12797856330871582 length of segment : 617 time for calcul the mask position with numpy : 0.07499957084655762 nb_pixel_total : 98573 time to create 1 rle with old method : 0.11272788047790527 length of segment : 414 time for calcul the mask position with numpy : 0.0014481544494628906 nb_pixel_total : 8157 time to create 1 rle with old method : 0.009501218795776367 length of segment : 89 time for calcul the mask position with numpy : 0.004194736480712891 nb_pixel_total : 33576 time to create 1 rle with old method : 0.039366722106933594 length of segment : 286 time for calcul the mask position with numpy : 0.07440376281738281 nb_pixel_total : 359678 time to create 1 rle with new method : 0.04349017143249512 length of segment : 993 time for calcul the mask position with numpy : 0.00208282470703125 nb_pixel_total : 23592 time to create 1 rle with old method : 0.025481700897216797 length of segment : 227 time for calcul the mask position with numpy : 0.0007348060607910156 nb_pixel_total : 9151 time to create 1 rle with old method : 0.010368824005126953 length of segment : 69 time for calcul the mask position with numpy : 0.008885383605957031 nb_pixel_total : 11870 time to create 1 rle with old method : 0.018779516220092773 length of segment : 149 time for calcul the mask position with numpy : 0.010063886642456055 nb_pixel_total : 15161 time to create 1 rle with old method : 0.021439552307128906 length of segment : 256 time for calcul the mask position with numpy : 0.028148412704467773 nb_pixel_total : 83648 time to create 1 rle with old method : 0.09347081184387207 length of segment : 616 time for calcul the mask position with numpy : 0.0035631656646728516 nb_pixel_total : 23395 time to create 1 rle with old method : 0.02642536163330078 length of segment : 234 time for calcul the mask position with numpy : 0.007551908493041992 nb_pixel_total : 17365 time to create 1 rle with old method : 0.021534442901611328 length of segment : 300 time for calcul the mask position with numpy : 0.03599214553833008 nb_pixel_total : 41729 time to create 1 rle with old method : 0.05393028259277344 length of segment : 206 time for calcul the mask position with numpy : 0.02269291877746582 nb_pixel_total : 96077 time to create 1 rle with old method : 0.1105964183807373 length of segment : 629 time for calcul the mask position with numpy : 0.00465846061706543 nb_pixel_total : 11548 time to create 1 rle with old method : 0.014742612838745117 length of segment : 187 time for calcul the mask position with numpy : 0.0050427913665771484 nb_pixel_total : 19736 time to create 1 rle with old method : 0.022953510284423828 length of segment : 194 time for calcul the mask position with numpy : 0.0007610321044921875 nb_pixel_total : 12431 time to create 1 rle with old method : 0.014222860336303711 length of segment : 203 time for calcul the mask position with numpy : 0.00695347785949707 nb_pixel_total : 19292 time to create 1 rle with old method : 0.026183605194091797 length of segment : 264 time for calcul the mask position with numpy : 0.001722574234008789 nb_pixel_total : 16418 time to create 1 rle with old method : 0.018396854400634766 length of segment : 153 time for calcul the mask position with numpy : 0.007097721099853516 nb_pixel_total : 88551 time to create 1 rle with old method : 0.09945440292358398 length of segment : 432 time for calcul the mask position with numpy : 0.03626060485839844 nb_pixel_total : 100284 time to create 1 rle with old method : 0.10937047004699707 length of segment : 946 time for calcul the mask position with numpy : 0.008847236633300781 nb_pixel_total : 28649 time to create 1 rle with old method : 0.03257036209106445 length of segment : 312 time for calcul the mask position with numpy : 0.010787248611450195 nb_pixel_total : 23983 time to create 1 rle with old method : 0.02987384796142578 length of segment : 208 time for calcul the mask position with numpy : 0.0011858940124511719 nb_pixel_total : 29427 time to create 1 rle with old method : 0.031897544860839844 length of segment : 235 time for calcul the mask position with numpy : 0.001725912094116211 nb_pixel_total : 13901 time to create 1 rle with old method : 0.015674114227294922 length of segment : 220 time for calcul the mask position with numpy : 0.0015463829040527344 nb_pixel_total : 14190 time to create 1 rle with old method : 0.01648569107055664 length of segment : 108 time for calcul the mask position with numpy : 0.009601593017578125 nb_pixel_total : 286839 time to create 1 rle with new method : 0.015223979949951172 length of segment : 812 time for calcul the mask position with numpy : 0.002470731735229492 nb_pixel_total : 56305 time to create 1 rle with old method : 0.06364083290100098 length of segment : 341 time for calcul the mask position with numpy : 0.0072057247161865234 nb_pixel_total : 12570 time to create 1 rle with old method : 0.01624441146850586 length of segment : 146 time for calcul the mask position with numpy : 0.012244939804077148 nb_pixel_total : 101747 time to create 1 rle with old method : 0.11109566688537598 length of segment : 530 time for calcul the mask position with numpy : 0.0007143020629882812 nb_pixel_total : 18072 time to create 1 rle with old method : 0.020850658416748047 length of segment : 210 time for calcul the mask position with numpy : 0.0016417503356933594 nb_pixel_total : 12255 time to create 1 rle with old method : 0.01408529281616211 length of segment : 116 time for calcul the mask position with numpy : 0.0088043212890625 nb_pixel_total : 108203 time to create 1 rle with old method : 0.12171769142150879 length of segment : 400 time for calcul the mask position with numpy : 0.0019025802612304688 nb_pixel_total : 47572 time to create 1 rle with old method : 0.05177569389343262 length of segment : 303 time for calcul the mask position with numpy : 0.0011916160583496094 nb_pixel_total : 35051 time to create 1 rle with old method : 0.03998255729675293 length of segment : 218 time for calcul the mask position with numpy : 0.004220485687255859 nb_pixel_total : 46851 time to create 1 rle with old method : 0.057030677795410156 length of segment : 341 time for calcul the mask position with numpy : 0.0033791065216064453 nb_pixel_total : 119988 time to create 1 rle with old method : 0.13796186447143555 length of segment : 381 time for calcul the mask position with numpy : 0.00498509407043457 nb_pixel_total : 45432 time to create 1 rle with old method : 0.05113053321838379 length of segment : 286 time for calcul the mask position with numpy : 0.0008206367492675781 nb_pixel_total : 18433 time to create 1 rle with old method : 0.02060699462890625 length of segment : 149 time for calcul the mask position with numpy : 0.0024890899658203125 nb_pixel_total : 62165 time to create 1 rle with old method : 0.06750011444091797 length of segment : 325 time for calcul the mask position with numpy : 0.004406929016113281 nb_pixel_total : 21318 time to create 1 rle with old method : 0.025432825088500977 length of segment : 152 time for calcul the mask position with numpy : 0.0005724430084228516 nb_pixel_total : 12779 time to create 1 rle with old method : 0.014134645462036133 length of segment : 186 time for calcul the mask position with numpy : 0.0009634494781494141 nb_pixel_total : 24200 time to create 1 rle with old method : 0.026230812072753906 length of segment : 190 time for calcul the mask position with numpy : 0.0012443065643310547 nb_pixel_total : 21563 time to create 1 rle with old method : 0.02369999885559082 length of segment : 184 time for calcul the mask position with numpy : 0.002383708953857422 nb_pixel_total : 64668 time to create 1 rle with old method : 0.06788372993469238 length of segment : 362 time for calcul the mask position with numpy : 0.002197742462158203 nb_pixel_total : 92270 time to create 1 rle with old method : 0.09910941123962402 length of segment : 420 time for calcul the mask position with numpy : 0.0012733936309814453 nb_pixel_total : 19842 time to create 1 rle with old method : 0.021754026412963867 length of segment : 261 time for calcul the mask position with numpy : 0.0028791427612304688 nb_pixel_total : 78010 time to create 1 rle with old method : 0.09580302238464355 length of segment : 344 time for calcul the mask position with numpy : 0.003103017807006836 nb_pixel_total : 136356 time to create 1 rle with old method : 0.1448824405670166 length of segment : 714 time for calcul the mask position with numpy : 0.0009496212005615234 nb_pixel_total : 28603 time to create 1 rle with old method : 0.031077861785888672 length of segment : 324 time for calcul the mask position with numpy : 0.0004527568817138672 nb_pixel_total : 28381 time to create 1 rle with old method : 0.031207561492919922 length of segment : 326 time for calcul the mask position with numpy : 0.0024123191833496094 nb_pixel_total : 78356 time to create 1 rle with old method : 0.08385348320007324 length of segment : 390 time for calcul the mask position with numpy : 0.0010571479797363281 nb_pixel_total : 28634 time to create 1 rle with old method : 0.030954837799072266 length of segment : 268 time for calcul the mask position with numpy : 0.006496429443359375 nb_pixel_total : 89863 time to create 1 rle with old method : 0.09885311126708984 length of segment : 349 time for calcul the mask position with numpy : 0.0003867149353027344 nb_pixel_total : 10729 time to create 1 rle with old method : 0.01180720329284668 length of segment : 104 time for calcul the mask position with numpy : 0.002660989761352539 nb_pixel_total : 104602 time to create 1 rle with old method : 0.13625741004943848 length of segment : 442 time for calcul the mask position with numpy : 0.0017006397247314453 nb_pixel_total : 41128 time to create 1 rle with old method : 0.053716182708740234 length of segment : 326 time for calcul the mask position with numpy : 0.14069080352783203 nb_pixel_total : 705457 time to create 1 rle with new method : 0.06696271896362305 length of segment : 1718 time for calcul the mask position with numpy : 0.0031228065490722656 nb_pixel_total : 119726 time to create 1 rle with old method : 0.12962055206298828 length of segment : 515 time for calcul the mask position with numpy : 0.0017359256744384766 nb_pixel_total : 35723 time to create 1 rle with old method : 0.06299901008605957 length of segment : 397 time for calcul the mask position with numpy : 0.0043604373931884766 nb_pixel_total : 155861 time to create 1 rle with new method : 0.0066416263580322266 length of segment : 449 time for calcul the mask position with numpy : 0.0009074211120605469 nb_pixel_total : 47112 time to create 1 rle with old method : 0.05070829391479492 length of segment : 376 time for calcul the mask position with numpy : 0.0010361671447753906 nb_pixel_total : 36258 time to create 1 rle with old method : 0.03984260559082031 length of segment : 446 time for calcul the mask position with numpy : 0.0007011890411376953 nb_pixel_total : 14786 time to create 1 rle with old method : 0.01676177978515625 length of segment : 216 time for calcul the mask position with numpy : 0.0011603832244873047 nb_pixel_total : 30266 time to create 1 rle with old method : 0.033203840255737305 length of segment : 298 time for calcul the mask position with numpy : 0.0016338825225830078 nb_pixel_total : 46427 time to create 1 rle with old method : 0.052712202072143555 length of segment : 262 time for calcul the mask position with numpy : 0.003908395767211914 nb_pixel_total : 121688 time to create 1 rle with old method : 0.1347956657409668 length of segment : 344 time for calcul the mask position with numpy : 0.0007901191711425781 nb_pixel_total : 22590 time to create 1 rle with old method : 0.024479150772094727 length of segment : 164 time for calcul the mask position with numpy : 0.005408287048339844 nb_pixel_total : 219221 time to create 1 rle with new method : 0.006549358367919922 length of segment : 374 time for calcul the mask position with numpy : 0.00209808349609375 nb_pixel_total : 47297 time to create 1 rle with old method : 0.051802635192871094 length of segment : 307 time for calcul the mask position with numpy : 0.001310586929321289 nb_pixel_total : 32471 time to create 1 rle with old method : 0.0372006893157959 length of segment : 166 time for calcul the mask position with numpy : 0.0010650157928466797 nb_pixel_total : 23073 time to create 1 rle with old method : 0.024863719940185547 length of segment : 258 time for calcul the mask position with numpy : 0.0010373592376708984 nb_pixel_total : 30445 time to create 1 rle with old method : 0.033798933029174805 length of segment : 242 time for calcul the mask position with numpy : 0.0032699108123779297 nb_pixel_total : 65311 time to create 1 rle with old method : 0.07197952270507812 length of segment : 1069 time for calcul the mask position with numpy : 0.0020143985748291016 nb_pixel_total : 68450 time to create 1 rle with old method : 0.07557177543640137 length of segment : 266 time for calcul the mask position with numpy : 0.001346588134765625 nb_pixel_total : 26529 time to create 1 rle with old method : 0.02971482276916504 length of segment : 152 time for calcul the mask position with numpy : 0.0033402442932128906 nb_pixel_total : 62314 time to create 1 rle with old method : 0.07062554359436035 length of segment : 302 time for calcul the mask position with numpy : 0.0005822181701660156 nb_pixel_total : 13769 time to create 1 rle with old method : 0.015935182571411133 length of segment : 141 time for calcul the mask position with numpy : 0.001291513442993164 nb_pixel_total : 38414 time to create 1 rle with old method : 0.04285383224487305 length of segment : 205 time for calcul the mask position with numpy : 0.0004723072052001953 nb_pixel_total : 10217 time to create 1 rle with old method : 0.01206517219543457 length of segment : 85 time for calcul the mask position with numpy : 0.0009391307830810547 nb_pixel_total : 24271 time to create 1 rle with old method : 0.026799917221069336 length of segment : 218 time for calcul the mask position with numpy : 0.0005996227264404297 nb_pixel_total : 10130 time to create 1 rle with old method : 0.011499643325805664 length of segment : 113 time for calcul the mask position with numpy : 0.001556396484375 nb_pixel_total : 46382 time to create 1 rle with old method : 0.05025839805603027 length of segment : 323 time for calcul the mask position with numpy : 0.0005834102630615234 nb_pixel_total : 9868 time to create 1 rle with old method : 0.01104426383972168 length of segment : 133 time for calcul the mask position with numpy : 0.00107574462890625 nb_pixel_total : 25009 time to create 1 rle with old method : 0.028298616409301758 length of segment : 275 time for calcul the mask position with numpy : 0.0009398460388183594 nb_pixel_total : 22272 time to create 1 rle with old method : 0.0253293514251709 length of segment : 141 time for calcul the mask position with numpy : 0.0005288124084472656 nb_pixel_total : 10861 time to create 1 rle with old method : 0.012596368789672852 length of segment : 82 time for calcul the mask position with numpy : 0.0007774829864501953 nb_pixel_total : 27781 time to create 1 rle with old method : 0.031458139419555664 length of segment : 181 time for calcul the mask position with numpy : 0.0005333423614501953 nb_pixel_total : 11712 time to create 1 rle with old method : 0.01347804069519043 length of segment : 164 time for calcul the mask position with numpy : 0.0012536048889160156 nb_pixel_total : 30879 time to create 1 rle with old method : 0.03420758247375488 length of segment : 188 time for calcul the mask position with numpy : 0.0007011890411376953 nb_pixel_total : 11044 time to create 1 rle with old method : 0.012310028076171875 length of segment : 173 time for calcul the mask position with numpy : 0.001016855239868164 nb_pixel_total : 29365 time to create 1 rle with old method : 0.03319096565246582 length of segment : 244 time for calcul the mask position with numpy : 0.00485539436340332 nb_pixel_total : 73022 time to create 1 rle with old method : 0.07982063293457031 length of segment : 499 time for calcul the mask position with numpy : 0.0018126964569091797 nb_pixel_total : 31396 time to create 1 rle with old method : 0.036102294921875 length of segment : 291 time for calcul the mask position with numpy : 0.0012502670288085938 nb_pixel_total : 26020 time to create 1 rle with old method : 0.028534889221191406 length of segment : 210 time for calcul the mask position with numpy : 0.003220081329345703 nb_pixel_total : 113056 time to create 1 rle with old method : 0.15071368217468262 length of segment : 347 time for calcul the mask position with numpy : 0.0016016960144042969 nb_pixel_total : 37240 time to create 1 rle with old method : 0.04157543182373047 length of segment : 267 time for calcul the mask position with numpy : 0.0004646778106689453 nb_pixel_total : 10551 time to create 1 rle with old method : 0.011413812637329102 length of segment : 116 time for calcul the mask position with numpy : 0.0009257793426513672 nb_pixel_total : 23830 time to create 1 rle with old method : 0.026393890380859375 length of segment : 189 time for calcul the mask position with numpy : 0.0006880760192871094 nb_pixel_total : 15915 time to create 1 rle with old method : 0.017101287841796875 length of segment : 215 time for calcul the mask position with numpy : 0.0013675689697265625 nb_pixel_total : 31584 time to create 1 rle with old method : 0.035006046295166016 length of segment : 271 time for calcul the mask position with numpy : 0.001111745834350586 nb_pixel_total : 21611 time to create 1 rle with old method : 0.02484893798828125 length of segment : 153 time for calcul the mask position with numpy : 0.0006234645843505859 nb_pixel_total : 12437 time to create 1 rle with old method : 0.014271259307861328 length of segment : 109 time for calcul the mask position with numpy : 0.0002315044403076172 nb_pixel_total : 4399 time to create 1 rle with old method : 0.0051496028900146484 length of segment : 67 time for calcul the mask position with numpy : 0.00030493736267089844 nb_pixel_total : 3679 time to create 1 rle with old method : 0.0040264129638671875 length of segment : 86 time for calcul the mask position with numpy : 0.001127481460571289 nb_pixel_total : 30167 time to create 1 rle with old method : 0.03252768516540527 length of segment : 136 time for calcul the mask position with numpy : 0.003648996353149414 nb_pixel_total : 99898 time to create 1 rle with old method : 0.10806417465209961 length of segment : 445 time for calcul the mask position with numpy : 0.0009593963623046875 nb_pixel_total : 30490 time to create 1 rle with old method : 0.032799482345581055 length of segment : 253 time for calcul the mask position with numpy : 0.003842592239379883 nb_pixel_total : 149880 time to create 1 rle with old method : 0.1618058681488037 length of segment : 384 time for calcul the mask position with numpy : 0.002031564712524414 nb_pixel_total : 81963 time to create 1 rle with old method : 0.08986425399780273 length of segment : 184 time for calcul the mask position with numpy : 0.003624439239501953 nb_pixel_total : 139470 time to create 1 rle with old method : 0.15525436401367188 length of segment : 508 time for calcul the mask position with numpy : 0.0024487972259521484 nb_pixel_total : 102973 time to create 1 rle with old method : 0.11272525787353516 length of segment : 371 time for calcul the mask position with numpy : 0.0006814002990722656 nb_pixel_total : 12056 time to create 1 rle with old method : 0.014343500137329102 length of segment : 152 time for calcul the mask position with numpy : 0.0044019222259521484 nb_pixel_total : 150594 time to create 1 rle with new method : 0.00718998908996582 length of segment : 449 time for calcul the mask position with numpy : 0.009432554244995117 nb_pixel_total : 450818 time to create 1 rle with new method : 0.0306854248046875 length of segment : 650 time for calcul the mask position with numpy : 0.0007994174957275391 nb_pixel_total : 21647 time to create 1 rle with old method : 0.025206565856933594 length of segment : 176 time for calcul the mask position with numpy : 0.0006906986236572266 nb_pixel_total : 24649 time to create 1 rle with old method : 0.0287930965423584 length of segment : 153 time for calcul the mask position with numpy : 0.00046825408935546875 nb_pixel_total : 14181 time to create 1 rle with old method : 0.017055273056030273 length of segment : 121 time for calcul the mask position with numpy : 0.006896257400512695 nb_pixel_total : 80866 time to create 1 rle with old method : 0.10267353057861328 length of segment : 487 time for calcul the mask position with numpy : 0.004714488983154297 nb_pixel_total : 123168 time to create 1 rle with old method : 0.14554500579833984 length of segment : 463 time for calcul the mask position with numpy : 0.0009171962738037109 nb_pixel_total : 30612 time to create 1 rle with old method : 0.03502345085144043 length of segment : 120 time for calcul the mask position with numpy : 0.0028281211853027344 nb_pixel_total : 81674 time to create 1 rle with old method : 0.09311485290527344 length of segment : 591 time for calcul the mask position with numpy : 0.0010745525360107422 nb_pixel_total : 24677 time to create 1 rle with old method : 0.028831005096435547 length of segment : 198 time for calcul the mask position with numpy : 0.0007917881011962891 nb_pixel_total : 28088 time to create 1 rle with old method : 0.03338956832885742 length of segment : 130 time for calcul the mask position with numpy : 0.0035185813903808594 nb_pixel_total : 100801 time to create 1 rle with old method : 0.13886737823486328 length of segment : 447 time for calcul the mask position with numpy : 0.0011839866638183594 nb_pixel_total : 38119 time to create 1 rle with old method : 0.043854713439941406 length of segment : 220 time for calcul the mask position with numpy : 0.00719761848449707 nb_pixel_total : 217623 time to create 1 rle with new method : 0.011746883392333984 length of segment : 704 time for calcul the mask position with numpy : 0.002796649932861328 nb_pixel_total : 90252 time to create 1 rle with old method : 0.10096096992492676 length of segment : 408 time for calcul the mask position with numpy : 0.0011210441589355469 nb_pixel_total : 44815 time to create 1 rle with old method : 0.053093910217285156 length of segment : 274 time for calcul the mask position with numpy : 0.0008654594421386719 nb_pixel_total : 22445 time to create 1 rle with old method : 0.025495290756225586 length of segment : 205 time for calcul the mask position with numpy : 0.0033931732177734375 nb_pixel_total : 135303 time to create 1 rle with old method : 0.15403485298156738 length of segment : 466 time for calcul the mask position with numpy : 0.0050678253173828125 nb_pixel_total : 175424 time to create 1 rle with new method : 0.006943464279174805 length of segment : 524 time for calcul the mask position with numpy : 0.002286195755004883 nb_pixel_total : 55814 time to create 1 rle with old method : 0.06917715072631836 length of segment : 333 time for calcul the mask position with numpy : 0.003585338592529297 nb_pixel_total : 123436 time to create 1 rle with old method : 0.15674185752868652 length of segment : 387 time for calcul the mask position with numpy : 0.006070375442504883 nb_pixel_total : 174385 time to create 1 rle with new method : 0.00838923454284668 length of segment : 568 time for calcul the mask position with numpy : 0.003300189971923828 nb_pixel_total : 75532 time to create 1 rle with old method : 0.08780407905578613 length of segment : 309 time for calcul the mask position with numpy : 0.0011487007141113281 nb_pixel_total : 31169 time to create 1 rle with old method : 0.03644561767578125 length of segment : 232 time for calcul the mask position with numpy : 0.0006012916564941406 nb_pixel_total : 16987 time to create 1 rle with old method : 0.020150423049926758 length of segment : 122 time for calcul the mask position with numpy : 0.0016179084777832031 nb_pixel_total : 46817 time to create 1 rle with old method : 0.05432701110839844 length of segment : 349 time for calcul the mask position with numpy : 0.0014574527740478516 nb_pixel_total : 24529 time to create 1 rle with old method : 0.030740976333618164 length of segment : 175 time for calcul the mask position with numpy : 0.002557992935180664 nb_pixel_total : 68015 time to create 1 rle with old method : 0.0783689022064209 length of segment : 420 time for calcul the mask position with numpy : 0.000560760498046875 nb_pixel_total : 25717 time to create 1 rle with old method : 0.029780864715576172 length of segment : 155 time for calcul the mask position with numpy : 0.0029058456420898438 nb_pixel_total : 99174 time to create 1 rle with old method : 0.11167716979980469 length of segment : 373 time for calcul the mask position with numpy : 0.0005071163177490234 nb_pixel_total : 15109 time to create 1 rle with old method : 0.017401456832885742 length of segment : 161 time for calcul the mask position with numpy : 0.0006365776062011719 nb_pixel_total : 23283 time to create 1 rle with old method : 0.027135133743286133 length of segment : 124 time for calcul the mask position with numpy : 0.0004291534423828125 nb_pixel_total : 13242 time to create 1 rle with old method : 0.015414953231811523 length of segment : 135 time for calcul the mask position with numpy : 0.0016460418701171875 nb_pixel_total : 46575 time to create 1 rle with old method : 0.053266286849975586 length of segment : 444 time for calcul the mask position with numpy : 0.0008394718170166016 nb_pixel_total : 21150 time to create 1 rle with old method : 0.0239865779876709 length of segment : 172 time for calcul the mask position with numpy : 0.005305767059326172 nb_pixel_total : 77521 time to create 1 rle with old method : 0.08692598342895508 length of segment : 326 time for calcul the mask position with numpy : 0.0049207210540771484 nb_pixel_total : 80164 time to create 1 rle with old method : 0.09023427963256836 length of segment : 543 time for calcul the mask position with numpy : 0.002077817916870117 nb_pixel_total : 44243 time to create 1 rle with old method : 0.04918360710144043 length of segment : 306 time for calcul the mask position with numpy : 0.0005106925964355469 nb_pixel_total : 10847 time to create 1 rle with old method : 0.012428760528564453 length of segment : 117 time for calcul the mask position with numpy : 0.0006132125854492188 nb_pixel_total : 17661 time to create 1 rle with old method : 0.019812822341918945 length of segment : 160 time for calcul the mask position with numpy : 0.0027637481689453125 nb_pixel_total : 73864 time to create 1 rle with old method : 0.07956814765930176 length of segment : 524 time for calcul the mask position with numpy : 0.0020093917846679688 nb_pixel_total : 77070 time to create 1 rle with old method : 0.08452916145324707 length of segment : 242 time for calcul the mask position with numpy : 0.0004031658172607422 nb_pixel_total : 11218 time to create 1 rle with old method : 0.01277017593383789 length of segment : 113 time for calcul the mask position with numpy : 0.0011959075927734375 nb_pixel_total : 35671 time to create 1 rle with old method : 0.03975677490234375 length of segment : 279 time for calcul the mask position with numpy : 0.00047779083251953125 nb_pixel_total : 11026 time to create 1 rle with old method : 0.012513160705566406 length of segment : 100 time for calcul the mask position with numpy : 0.0019054412841796875 nb_pixel_total : 50465 time to create 1 rle with old method : 0.057062625885009766 length of segment : 239 time for calcul the mask position with numpy : 0.0005593299865722656 nb_pixel_total : 10394 time to create 1 rle with old method : 0.011838674545288086 length of segment : 135 time for calcul the mask position with numpy : 0.0044095516204833984 nb_pixel_total : 147883 time to create 1 rle with old method : 0.16637682914733887 length of segment : 412 time for calcul the mask position with numpy : 0.0067522525787353516 nb_pixel_total : 157122 time to create 1 rle with new method : 0.008941411972045898 length of segment : 700 time for calcul the mask position with numpy : 0.0010373592376708984 nb_pixel_total : 31000 time to create 1 rle with old method : 0.034169912338256836 length of segment : 265 time for calcul the mask position with numpy : 0.002208709716796875 nb_pixel_total : 92864 time to create 1 rle with old method : 0.09784746170043945 length of segment : 549 time for calcul the mask position with numpy : 0.0023212432861328125 nb_pixel_total : 82234 time to create 1 rle with old method : 0.09129166603088379 length of segment : 315 time for calcul the mask position with numpy : 0.0032851696014404297 nb_pixel_total : 85378 time to create 1 rle with old method : 0.09508490562438965 length of segment : 529 time for calcul the mask position with numpy : 0.001329660415649414 nb_pixel_total : 27474 time to create 1 rle with old method : 0.031868934631347656 length of segment : 363 time for calcul the mask position with numpy : 0.003742218017578125 nb_pixel_total : 137688 time to create 1 rle with old method : 0.15916180610656738 length of segment : 456 time for calcul the mask position with numpy : 0.0006227493286132812 nb_pixel_total : 16050 time to create 1 rle with old method : 0.017126083374023438 length of segment : 191 time for calcul the mask position with numpy : 0.0015749931335449219 nb_pixel_total : 58875 time to create 1 rle with old method : 0.06292343139648438 length of segment : 388 time for calcul the mask position with numpy : 0.006062507629394531 nb_pixel_total : 195037 time to create 1 rle with new method : 0.009775876998901367 length of segment : 1115 time for calcul the mask position with numpy : 0.0005567073822021484 nb_pixel_total : 18794 time to create 1 rle with old method : 0.02097773551940918 length of segment : 292 time for calcul the mask position with numpy : 0.0015134811401367188 nb_pixel_total : 56314 time to create 1 rle with old method : 0.06370115280151367 length of segment : 418 time for calcul the mask position with numpy : 0.0019180774688720703 nb_pixel_total : 77335 time to create 1 rle with old method : 0.09687209129333496 length of segment : 387 time for calcul the mask position with numpy : 0.0064046382904052734 nb_pixel_total : 272496 time to create 1 rle with new method : 0.00947427749633789 length of segment : 694 time for calcul the mask position with numpy : 0.00032138824462890625 nb_pixel_total : 7838 time to create 1 rle with old method : 0.009337186813354492 length of segment : 70 time for calcul the mask position with numpy : 0.00019860267639160156 nb_pixel_total : 8502 time to create 1 rle with old method : 0.010180234909057617 length of segment : 78 time for calcul the mask position with numpy : 0.0069506168365478516 nb_pixel_total : 196755 time to create 1 rle with new method : 0.009746789932250977 length of segment : 737 time for calcul the mask position with numpy : 0.0031280517578125 nb_pixel_total : 113219 time to create 1 rle with old method : 0.12181591987609863 length of segment : 364 time for calcul the mask position with numpy : 0.0010492801666259766 nb_pixel_total : 21818 time to create 1 rle with old method : 0.02375316619873047 length of segment : 299 time for calcul the mask position with numpy : 0.006206989288330078 nb_pixel_total : 214051 time to create 1 rle with new method : 0.008456707000732422 length of segment : 566 time for calcul the mask position with numpy : 0.0014028549194335938 nb_pixel_total : 59172 time to create 1 rle with old method : 0.06282997131347656 length of segment : 237 time for calcul the mask position with numpy : 0.0015664100646972656 nb_pixel_total : 50898 time to create 1 rle with old method : 0.06158041954040527 length of segment : 267 time for calcul the mask position with numpy : 0.007251262664794922 nb_pixel_total : 293516 time to create 1 rle with new method : 0.011190652847290039 length of segment : 571 time for calcul the mask position with numpy : 0.002573251724243164 nb_pixel_total : 99056 time to create 1 rle with old method : 0.10596108436584473 length of segment : 585 time for calcul the mask position with numpy : 0.002177715301513672 nb_pixel_total : 98118 time to create 1 rle with old method : 0.10915207862854004 length of segment : 332 time for calcul the mask position with numpy : 0.0012764930725097656 nb_pixel_total : 50287 time to create 1 rle with old method : 0.05612802505493164 length of segment : 272 time for calcul the mask position with numpy : 0.002681255340576172 nb_pixel_total : 139106 time to create 1 rle with old method : 0.15209436416625977 length of segment : 346 time for calcul the mask position with numpy : 0.003935098648071289 nb_pixel_total : 151676 time to create 1 rle with new method : 0.0057828426361083984 length of segment : 479 time for calcul the mask position with numpy : 0.002315044403076172 nb_pixel_total : 51881 time to create 1 rle with old method : 0.06322407722473145 length of segment : 327 time spent for convertir_results : 73.42308926582336 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 530 chid ids of type : 3594 Number RLEs to save : 166061 save missing photos in datou_result : time spend for datou_step_exec : 374.6379430294037 time spend to save output : 10.313212633132935 total time spend for step 1 : 384.9511556625366 step2:crop_condition Tue May 27 13:37:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure Loading chi in step crop with photo_hashtag_type : 3594 Loading chi in step crop for list_pids : 37 ! batch 1 Loaded 530 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ begin to crop the class : papier param for this class : {'min_score': 0.7} filtre for class : papier hashtag_id of this class : 492668766 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 308 About to insert : list_path_to_insert length 308 new photo from crops ! About to upload 308 photos upload in portfolio : 3736932 init cache_photo without model_param we have 308 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1748345904_351592 we have uploaded 308 photos in the portfolio 3736932 time of upload the photos Elapsed time : 81.18894267082214 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.7} filtre for class : carton hashtag_id of this class : 492774966 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 45 About to insert : list_path_to_insert length 45 new photo from crops ! About to upload 45 photos upload in portfolio : 3736932 init cache_photo without model_param we have 45 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1748346002_351592 we have uploaded 45 photos in the portfolio 3736932 time of upload the photos Elapsed time : 13.346557140350342 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.7} filtre for class : metal hashtag_id of this class : 492628673 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 6 About to insert : list_path_to_insert length 6 new photo from crops ! About to upload 6 photos upload in portfolio : 3736932 init cache_photo without model_param we have 6 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1748346022_351592 we have uploaded 6 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.8255255222320557 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.7} filtre for class : pet_clair hashtag_id of this class : 2107755846 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 147 About to insert : list_path_to_insert length 147 new photo from crops ! About to upload 147 photos upload in portfolio : 3736932 init cache_photo without model_param we have 147 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1748346097_351592 we have uploaded 147 photos in the portfolio 3736932 time of upload the photos Elapsed time : 67.89112687110901 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.7} filtre for class : autre hashtag_id of this class : 494826614 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 9 About to insert : list_path_to_insert length 9 new photo from crops ! About to upload 9 photos upload in portfolio : 3736932 init cache_photo without model_param we have 9 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1748346173_351592 we have uploaded 9 photos in the portfolio 3736932 time of upload the photos Elapsed time : 3.060474395751953 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.7} filtre for class : pehd hashtag_id of this class : 628944319 we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 3736932 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1748346181_351592 we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.6013321876525879 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.7} filtre for class : pet_fonce hashtag_id of this class : 2107755900 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 14 About to insert : list_path_to_insert length 14 new photo from crops ! About to upload 14 photos upload in portfolio : 3736932 init cache_photo without model_param we have 14 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1748346192_351592 we have uploaded 14 photos in the portfolio 3736932 time of upload the photos Elapsed time : 6.585439205169678 we have finished the crop for the class : pet_fonce delete rles from all chi we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1360703512, 1360703507, 1360703504, 1360703497, 1360703494, 1360703490, 1360703454, 1360703451, 1360703447, 1360703443, 1360703440, 1360703418, 1360703414, 1360703411, 1360703406, 1360703400, 1360703377, 1360703374, 1360703368, 1360703362, 1360703358, 1360703353, 1360703327, 1360703323, 1360703320, 1360703313, 1360703286, 1360703283, 1360703279, 1360703276, 1360703274, 1360703272, 1360703250, 1360703246, 1360703244, 1360703241, 1360703240] Looping around the photos to save general results len do output : 530 /1361294599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294656Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361294988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295392Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295396Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295399Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295401Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295404Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295405Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295407Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295408Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295409Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295412Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295413Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295415Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295416Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295417Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295419Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295421Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295422Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295424Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295426Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295427Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295474Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1361295712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703512', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703507', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703504', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703497', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703494', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703490', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703454', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703451', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703447', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703443', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703440', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703418', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703414', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703411', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703406', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703400', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703377', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703374', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703368', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703362', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703358', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703353', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703327', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703323', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703320', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703313', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703286', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703283', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703279', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703276', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703274', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703272', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703250', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703246', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703244', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703241', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703240', None, None, None, None, None, '2964573') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1627 time used for this insertion : 0.1016383171081543 save_final save missing photos in datou_result : time spend for datou_step_exec : 377.78088188171387 time spend to save output : 0.15200352668762207 total time spend for step 2 : 377.9328854084015 step3:rle_unique_nms_with_priority Tue May 27 13:43:20 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 530 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 12 nb_hashtags : 4 time to prepare the origin masks : 6.77936577796936 time for calcul the mask position with numpy : 0.5150010585784912 nb_pixel_total : 7198275 time to create 1 rle with new method : 0.9937653541564941 time for calcul the mask position with numpy : 0.040750980377197266 nb_pixel_total : 155928 time to create 1 rle with new method : 0.655226469039917 time for calcul the mask position with numpy : 0.04031538963317871 nb_pixel_total : 19864 time to create 1 rle with old method : 0.021763086318969727 time for calcul the mask position with numpy : 0.041501760482788086 nb_pixel_total : 83210 time to create 1 rle with old method : 0.09156584739685059 time for calcul the mask position with numpy : 0.04264521598815918 nb_pixel_total : 313588 time to create 1 rle with new method : 1.1282448768615723 time for calcul the mask position with numpy : 0.04041647911071777 nb_pixel_total : 13919 time to create 1 rle with old method : 0.015500068664550781 time for calcul the mask position with numpy : 0.04033708572387695 nb_pixel_total : 71681 time to create 1 rle with old method : 0.08082175254821777 time for calcul the mask position with numpy : 0.040132999420166016 nb_pixel_total : 77648 time to create 1 rle with old method : 0.08675050735473633 time for calcul the mask position with numpy : 0.039591073989868164 nb_pixel_total : 53817 time to create 1 rle with old method : 0.05997896194458008 time for calcul the mask position with numpy : 0.040413618087768555 nb_pixel_total : 28633 time to create 1 rle with old method : 0.031975507736206055 time for calcul the mask position with numpy : 0.040209293365478516 nb_pixel_total : 25171 time to create 1 rle with old method : 0.02817559242248535 time for calcul the mask position with numpy : 0.03965616226196289 nb_pixel_total : 169317 time to create 1 rle with new method : 0.5514905452728271 time for calcul the mask position with numpy : 0.04038739204406738 nb_pixel_total : 83349 time to create 1 rle with old method : 0.09162521362304688 create new chi : 4.959856271743774 time to delete rle : 0.018382549285888672 batch 1 Loaded 25 chid ids of type : 3594 ++++++++++++Number RLEs to save : 10565 TO DO : save crop sub photo not yet done ! save time : 0.7234773635864258 nb_obj : 24 nb_hashtags : 4 time to prepare the origin masks : 10.965885162353516 time for calcul the mask position with numpy : 0.44423604011535645 nb_pixel_total : 6687000 time to create 1 rle with new method : 1.0410068035125732 time for calcul the mask position with numpy : 0.03176450729370117 nb_pixel_total : 18377 time to create 1 rle with old method : 0.020705699920654297 time for calcul the mask position with numpy : 0.02806830406188965 nb_pixel_total : 6193 time to create 1 rle with old method : 0.16829872131347656 time for calcul the mask position with numpy : 0.02972269058227539 nb_pixel_total : 62454 time to create 1 rle with old method : 0.07480692863464355 time for calcul the mask position with numpy : 0.027317047119140625 nb_pixel_total : 21164 time to create 1 rle with old method : 0.028934955596923828 time for calcul the mask position with numpy : 0.032280683517456055 nb_pixel_total : 112421 time to create 1 rle with old method : 0.13090729713439941 time for calcul the mask position with numpy : 0.025122404098510742 nb_pixel_total : 39225 time to create 1 rle with old method : 0.04456949234008789 time for calcul the mask position with numpy : 0.025443315505981445 nb_pixel_total : 51141 time to create 1 rle with old method : 0.05839371681213379 time for calcul the mask position with numpy : 0.029492855072021484 nb_pixel_total : 83167 time to create 1 rle with old method : 0.09217214584350586 time for calcul the mask position with numpy : 0.025557518005371094 nb_pixel_total : 156726 time to create 1 rle with new method : 2.4120943546295166 time for calcul the mask position with numpy : 0.024521589279174805 nb_pixel_total : 11102 time to create 1 rle with old method : 0.012479543685913086 time for calcul the mask position with numpy : 0.02554464340209961 nb_pixel_total : 135358 time to create 1 rle with old method : 0.14961957931518555 time for calcul the mask position with numpy : 0.026901960372924805 nb_pixel_total : 46539 time to create 1 rle with old method : 0.050282955169677734 time for calcul the mask position with numpy : 0.039550065994262695 nb_pixel_total : 6885 time to create 1 rle with old method : 0.007536172866821289 time for calcul the mask position with numpy : 0.040297746658325195 nb_pixel_total : 117016 time to create 1 rle with old method : 0.12833142280578613 time for calcul the mask position with numpy : 0.03211069107055664 nb_pixel_total : 103858 time to create 1 rle with old method : 0.11786031723022461 time for calcul the mask position with numpy : 0.03266096115112305 nb_pixel_total : 63760 time to create 1 rle with old method : 0.06773161888122559 time for calcul the mask position with numpy : 0.03595447540283203 nb_pixel_total : 62696 time to create 1 rle with old method : 0.06837010383605957 time for calcul the mask position with numpy : 0.03537750244140625 nb_pixel_total : 14011 time to create 1 rle with old method : 0.015436172485351562 time for calcul the mask position with numpy : 0.03281116485595703 nb_pixel_total : 52573 time to create 1 rle with old method : 0.0585169792175293 time for calcul the mask position with numpy : 0.025873184204101562 nb_pixel_total : 74348 time to create 1 rle with old method : 0.08736777305603027 time for calcul the mask position with numpy : 0.02741384506225586 nb_pixel_total : 193399 time to create 1 rle with new method : 0.6099464893341064 time for calcul the mask position with numpy : 0.027876615524291992 nb_pixel_total : 29762 time to create 1 rle with old method : 0.03331756591796875 time for calcul the mask position with numpy : 0.025660037994384766 nb_pixel_total : 23358 time to create 1 rle with old method : 0.026254653930664062 time for calcul the mask position with numpy : 0.02546858787536621 nb_pixel_total : 121867 time to create 1 rle with old method : 0.13659167289733887 create new chi : 6.909287929534912 time to delete rle : 0.002614259719848633 batch 1 Loaded 49 chid ids of type : 3594 +++++++++++++++++++++++++++++Number RLEs to save : 16711 TO DO : save crop sub photo not yet done ! save time : 1.2187302112579346 nb_obj : 9 nb_hashtags : 3 time to prepare the origin masks : 6.328404188156128 time for calcul the mask position with numpy : 0.7854804992675781 nb_pixel_total : 7598293 time to create 1 rle with new method : 1.0031542778015137 time for calcul the mask position with numpy : 0.025990724563598633 nb_pixel_total : 143880 time to create 1 rle with old method : 0.15858793258666992 time for calcul the mask position with numpy : 0.02419114112854004 nb_pixel_total : 90408 time to create 1 rle with old method : 0.1005868911743164 time for calcul the mask position with numpy : 0.02579641342163086 nb_pixel_total : 49247 time to create 1 rle with old method : 0.05481886863708496 time for calcul the mask position with numpy : 0.025343894958496094 nb_pixel_total : 19792 time to create 1 rle with old method : 0.022144079208374023 time for calcul the mask position with numpy : 0.0257415771484375 nb_pixel_total : 94670 time to create 1 rle with old method : 0.1547255516052246 time for calcul the mask position with numpy : 0.03163719177246094 nb_pixel_total : 159270 time to create 1 rle with new method : 1.433424949645996 time for calcul the mask position with numpy : 0.0271914005279541 nb_pixel_total : 35939 time to create 1 rle with old method : 0.040255069732666016 time for calcul the mask position with numpy : 0.026065826416015625 nb_pixel_total : 14834 time to create 1 rle with old method : 0.01661086082458496 time for calcul the mask position with numpy : 0.028000354766845703 nb_pixel_total : 88067 time to create 1 rle with old method : 0.09794354438781738 create new chi : 4.183054685592651 time to delete rle : 0.0018458366394042969 batch 1 Loaded 19 chid ids of type : 3594 ++++++++++++Number RLEs to save : 9685 TO DO : save crop sub photo not yet done ! save time : 0.6368348598480225 nb_obj : 8 nb_hashtags : 3 time to prepare the origin masks : 5.700075387954712 time for calcul the mask position with numpy : 0.6535201072692871 nb_pixel_total : 7445591 time to create 1 rle with new method : 1.4960994720458984 time for calcul the mask position with numpy : 0.025249719619750977 nb_pixel_total : 36240 time to create 1 rle with old method : 0.04096698760986328 time for calcul the mask position with numpy : 0.028208017349243164 nb_pixel_total : 141416 time to create 1 rle with old method : 0.1851208209991455 time for calcul the mask position with numpy : 0.02956080436706543 nb_pixel_total : 327205 time to create 1 rle with new method : 1.2782797813415527 time for calcul the mask position with numpy : 0.027463674545288086 nb_pixel_total : 143653 time to create 1 rle with old method : 0.18381047248840332 time for calcul the mask position with numpy : 0.03026270866394043 nb_pixel_total : 23118 time to create 1 rle with old method : 0.034284114837646484 time for calcul the mask position with numpy : 0.04401040077209473 nb_pixel_total : 23477 time to create 1 rle with old method : 0.027024507522583008 time for calcul the mask position with numpy : 0.04463648796081543 nb_pixel_total : 108688 time to create 1 rle with old method : 0.12395286560058594 time for calcul the mask position with numpy : 0.04519963264465332 nb_pixel_total : 45012 time to create 1 rle with old method : 0.05110454559326172 create new chi : 4.424362659454346 time to delete rle : 0.0014603137969970703 batch 1 Loaded 17 chid ids of type : 3594 ++++++++++++Number RLEs to save : 9416 TO DO : save crop sub photo not yet done ! save time : 0.6076545715332031 nb_obj : 13 nb_hashtags : 5 time to prepare the origin masks : 8.509868383407593 time for calcul the mask position with numpy : 0.8649678230285645 nb_pixel_total : 7452574 time to create 1 rle with new method : 0.8473050594329834 time for calcul the mask position with numpy : 0.03741097450256348 nb_pixel_total : 22307 time to create 1 rle with old method : 0.026889562606811523 time for calcul the mask position with numpy : 0.04248499870300293 nb_pixel_total : 17854 time to create 1 rle with old method : 0.02173447608947754 time for calcul the mask position with numpy : 0.04041290283203125 nb_pixel_total : 43295 time to create 1 rle with old method : 0.047583580017089844 time for calcul the mask position with numpy : 0.0402376651763916 nb_pixel_total : 13624 time to create 1 rle with old method : 0.016385555267333984 time for calcul the mask position with numpy : 0.04293322563171387 nb_pixel_total : 22672 time to create 1 rle with old method : 0.028642654418945312 time for calcul the mask position with numpy : 0.04457449913024902 nb_pixel_total : 340531 time to create 1 rle with new method : 1.7021269798278809 time for calcul the mask position with numpy : 0.041876792907714844 nb_pixel_total : 8556 time to create 1 rle with old method : 0.009910345077514648 time for calcul the mask position with numpy : 0.04501223564147949 nb_pixel_total : 12656 time to create 1 rle with old method : 0.015217065811157227 time for calcul the mask position with numpy : 0.04591822624206543 nb_pixel_total : 15633 time to create 1 rle with old method : 0.019541501998901367 time for calcul the mask position with numpy : 0.042465925216674805 nb_pixel_total : 56597 time to create 1 rle with old method : 0.08234882354736328 time for calcul the mask position with numpy : 0.04125571250915527 nb_pixel_total : 180112 time to create 1 rle with new method : 0.8684766292572021 time for calcul the mask position with numpy : 0.041168212890625 nb_pixel_total : 61790 time to create 1 rle with old method : 0.0670480728149414 time for calcul the mask position with numpy : 0.03974461555480957 nb_pixel_total : 46199 time to create 1 rle with old method : 0.05380892753601074 create new chi : 5.361496686935425 time to delete rle : 0.0023839473724365234 batch 1 Loaded 27 chid ids of type : 3594 ++++++++++++++Number RLEs to save : 9339 TO DO : save crop sub photo not yet done ! save time : 0.6133768558502197 nb_obj : 13 nb_hashtags : 4 time to prepare the origin masks : 6.656147718429565 time for calcul the mask position with numpy : 0.526240348815918 nb_pixel_total : 7576534 time to create 1 rle with new method : 1.1530523300170898 time for calcul the mask position with numpy : 0.04243731498718262 nb_pixel_total : 91843 time to create 1 rle with old method : 0.10181283950805664 time for calcul the mask position with numpy : 0.039838552474975586 nb_pixel_total : 8877 time to create 1 rle with old method : 0.009819746017456055 time for calcul the mask position with numpy : 0.03904986381530762 nb_pixel_total : 21998 time to create 1 rle with old method : 0.023938417434692383 time for calcul the mask position with numpy : 0.03762984275817871 nb_pixel_total : 10593 time to create 1 rle with old method : 0.011547327041625977 time for calcul the mask position with numpy : 0.036435842514038086 nb_pixel_total : 142772 time to create 1 rle with old method : 0.15224647521972656 time for calcul the mask position with numpy : 0.03741931915283203 nb_pixel_total : 12408 time to create 1 rle with old method : 0.013872623443603516 time for calcul the mask position with numpy : 0.02557516098022461 nb_pixel_total : 172148 time to create 1 rle with new method : 0.9508728981018066 time for calcul the mask position with numpy : 0.02556467056274414 nb_pixel_total : 17927 time to create 1 rle with old method : 0.01994919776916504 time for calcul the mask position with numpy : 0.025083065032958984 nb_pixel_total : 120504 time to create 1 rle with old method : 0.13170933723449707 time for calcul the mask position with numpy : 0.02447819709777832 nb_pixel_total : 26125 time to create 1 rle with old method : 0.02834010124206543 time for calcul the mask position with numpy : 0.025522708892822266 nb_pixel_total : 34965 time to create 1 rle with old method : 0.03888702392578125 time for calcul the mask position with numpy : 0.025845050811767578 nb_pixel_total : 17666 time to create 1 rle with old method : 0.019688844680786133 time for calcul the mask position with numpy : 0.03902006149291992 nb_pixel_total : 40040 time to create 1 rle with old method : 0.044699668884277344 create new chi : 3.7226455211639404 time to delete rle : 0.0016052722930908203 batch 1 Loaded 27 chid ids of type : 3594 +++++++++++++++Number RLEs to save : 9573 TO DO : save crop sub photo not yet done ! save time : 0.6278657913208008 nb_obj : 14 nb_hashtags : 3 time to prepare the origin masks : 9.571438312530518 time for calcul the mask position with numpy : 0.8007102012634277 nb_pixel_total : 7375325 time to create 1 rle with new method : 0.961777925491333 time for calcul the mask position with numpy : 0.025313854217529297 nb_pixel_total : 112929 time to create 1 rle with old method : 0.12069463729858398 time for calcul the mask position with numpy : 0.02371835708618164 nb_pixel_total : 5041 time to create 1 rle with old method : 0.005448579788208008 time for calcul the mask position with numpy : 0.02445054054260254 nb_pixel_total : 78904 time to create 1 rle with old method : 0.11041855812072754 time for calcul the mask position with numpy : 0.02609848976135254 nb_pixel_total : 233633 time to create 1 rle with new method : 0.9154341220855713 time for calcul the mask position with numpy : 0.02831411361694336 nb_pixel_total : 25220 time to create 1 rle with old method : 0.02762317657470703 time for calcul the mask position with numpy : 0.025719642639160156 nb_pixel_total : 25930 time to create 1 rle with old method : 0.02855968475341797 time for calcul the mask position with numpy : 0.025075912475585938 nb_pixel_total : 15990 time to create 1 rle with old method : 0.017224788665771484 time for calcul the mask position with numpy : 0.024949312210083008 nb_pixel_total : 12789 time to create 1 rle with old method : 0.013976335525512695 time for calcul the mask position with numpy : 0.02758026123046875 nb_pixel_total : 156807 time to create 1 rle with new method : 0.8133335113525391 time for calcul the mask position with numpy : 0.024498939514160156 nb_pixel_total : 37923 time to create 1 rle with old method : 0.040653228759765625 time for calcul the mask position with numpy : 0.024968385696411133 nb_pixel_total : 40935 time to create 1 rle with old method : 0.043900251388549805 time for calcul the mask position with numpy : 0.02374410629272461 nb_pixel_total : 50859 time to create 1 rle with old method : 0.053479909896850586 time for calcul the mask position with numpy : 0.02318286895751953 nb_pixel_total : 40483 time to create 1 rle with old method : 0.04230237007141113 time for calcul the mask position with numpy : 0.024126052856445312 nb_pixel_total : 81632 time to create 1 rle with old method : 0.08783173561096191 create new chi : 4.532408237457275 time to delete rle : 0.0019636154174804688 batch 1 Loaded 29 chid ids of type : 3594 ++++++++++++++++Number RLEs to save : 12266 TO DO : save crop sub photo not yet done ! save time : 0.8276865482330322 nb_obj : 15 nb_hashtags : 2 time to prepare the origin masks : 8.603498697280884 time for calcul the mask position with numpy : 0.6611170768737793 nb_pixel_total : 7424290 time to create 1 rle with new method : 0.512143611907959 time for calcul the mask position with numpy : 0.02614736557006836 nb_pixel_total : 18200 time to create 1 rle with old method : 0.021121978759765625 time for calcul the mask position with numpy : 0.026147842407226562 nb_pixel_total : 156079 time to create 1 rle with new method : 0.5354583263397217 time for calcul the mask position with numpy : 0.024541139602661133 nb_pixel_total : 17293 time to create 1 rle with old method : 0.019315481185913086 time for calcul the mask position with numpy : 0.02492809295654297 nb_pixel_total : 78673 time to create 1 rle with old method : 0.09008002281188965 time for calcul the mask position with numpy : 0.02561044692993164 nb_pixel_total : 43663 time to create 1 rle with old method : 0.047624826431274414 time for calcul the mask position with numpy : 0.025390148162841797 nb_pixel_total : 184562 time to create 1 rle with new method : 1.04777193069458 time for calcul the mask position with numpy : 0.024796247482299805 nb_pixel_total : 15225 time to create 1 rle with old method : 0.018051862716674805 time for calcul the mask position with numpy : 0.024867534637451172 nb_pixel_total : 22251 time to create 1 rle with old method : 0.024887561798095703 time for calcul the mask position with numpy : 0.02605915069580078 nb_pixel_total : 15757 time to create 1 rle with old method : 0.017948150634765625 time for calcul the mask position with numpy : 0.026181936264038086 nb_pixel_total : 84712 time to create 1 rle with old method : 0.09558296203613281 time for calcul the mask position with numpy : 0.025483131408691406 nb_pixel_total : 25950 time to create 1 rle with old method : 0.03350329399108887 time for calcul the mask position with numpy : 0.02645277976989746 nb_pixel_total : 37578 time to create 1 rle with old method : 0.04338574409484863 time for calcul the mask position with numpy : 0.025339126586914062 nb_pixel_total : 84352 time to create 1 rle with old method : 0.09375524520874023 time for calcul the mask position with numpy : 0.027434587478637695 nb_pixel_total : 48099 time to create 1 rle with old method : 0.05587935447692871 time for calcul the mask position with numpy : 0.026747465133666992 nb_pixel_total : 37716 time to create 1 rle with old method : 0.04254865646362305 create new chi : 3.850111484527588 time to delete rle : 0.0031843185424804688 batch 1 Loaded 31 chid ids of type : 3594 ++++++++++++++++++++++++Number RLEs to save : 11726 TO DO : save crop sub photo not yet done ! save time : 0.7532229423522949 nb_obj : 18 nb_hashtags : 5 time to prepare the origin masks : 8.45720386505127 time for calcul the mask position with numpy : 0.7544035911560059 nb_pixel_total : 7402390 time to create 1 rle with new method : 1.388672113418579 time for calcul the mask position with numpy : 0.02530074119567871 nb_pixel_total : 6060 time to create 1 rle with old method : 0.006916522979736328 time for calcul the mask position with numpy : 0.026308774948120117 nb_pixel_total : 51889 time to create 1 rle with old method : 0.05958127975463867 time for calcul the mask position with numpy : 0.026604413986206055 nb_pixel_total : 28060 time to create 1 rle with old method : 0.03164935111999512 time for calcul the mask position with numpy : 0.025223493576049805 nb_pixel_total : 58734 time to create 1 rle with old method : 0.06690740585327148 time for calcul the mask position with numpy : 0.02643132209777832 nb_pixel_total : 134683 time to create 1 rle with old method : 0.14899802207946777 time for calcul the mask position with numpy : 0.026427268981933594 nb_pixel_total : 84895 time to create 1 rle with old method : 0.09474325180053711 time for calcul the mask position with numpy : 0.028092622756958008 nb_pixel_total : 20022 time to create 1 rle with old method : 0.022727489471435547 time for calcul the mask position with numpy : 0.02799201011657715 nb_pixel_total : 20176 time to create 1 rle with old method : 0.023069381713867188 time for calcul the mask position with numpy : 0.04054141044616699 nb_pixel_total : 57909 time to create 1 rle with old method : 0.06558513641357422 time for calcul the mask position with numpy : 0.04099869728088379 nb_pixel_total : 21836 time to create 1 rle with old method : 0.025184154510498047 time for calcul the mask position with numpy : 0.041773080825805664 nb_pixel_total : 52777 time to create 1 rle with old method : 0.059633493423461914 time for calcul the mask position with numpy : 0.02666497230529785 nb_pixel_total : 124995 time to create 1 rle with old method : 0.13628029823303223 time for calcul the mask position with numpy : 0.02592158317565918 nb_pixel_total : 14700 time to create 1 rle with old method : 0.01646590232849121 time for calcul the mask position with numpy : 0.02531599998474121 nb_pixel_total : 28873 time to create 1 rle with old method : 0.03154492378234863 time for calcul the mask position with numpy : 0.025427818298339844 nb_pixel_total : 41744 time to create 1 rle with old method : 0.04631495475769043 time for calcul the mask position with numpy : 0.026694059371948242 nb_pixel_total : 58105 time to create 1 rle with old method : 0.06456327438354492 time for calcul the mask position with numpy : 0.02589130401611328 nb_pixel_total : 12462 time to create 1 rle with old method : 0.013761758804321289 time for calcul the mask position with numpy : 0.024010896682739258 nb_pixel_total : 74090 time to create 1 rle with old method : 0.10811281204223633 create new chi : 3.7267098426818848 time to delete rle : 0.00194549560546875 batch 1 Loaded 37 chid ids of type : 3594 +++++++++++++++++++++++Number RLEs to save : 12832 TO DO : save crop sub photo not yet done ! save time : 0.8398809432983398 nb_obj : 12 nb_hashtags : 3 time to prepare the origin masks : 7.823549032211304 time for calcul the mask position with numpy : 0.9475507736206055 nb_pixel_total : 7908285 time to create 1 rle with new method : 0.6864399909973145 time for calcul the mask position with numpy : 0.04261279106140137 nb_pixel_total : 9146 time to create 1 rle with old method : 0.014794349670410156 time for calcul the mask position with numpy : 0.04814577102661133 nb_pixel_total : 31807 time to create 1 rle with old method : 0.035593509674072266 time for calcul the mask position with numpy : 0.04026937484741211 nb_pixel_total : 144053 time to create 1 rle with old method : 0.16036295890808105 time for calcul the mask position with numpy : 0.026860952377319336 nb_pixel_total : 10874 time to create 1 rle with old method : 0.012224674224853516 time for calcul the mask position with numpy : 0.026860952377319336 nb_pixel_total : 27964 time to create 1 rle with old method : 0.03258943557739258 time for calcul the mask position with numpy : 0.02509617805480957 nb_pixel_total : 27304 time to create 1 rle with old method : 0.03039693832397461 time for calcul the mask position with numpy : 0.026087284088134766 nb_pixel_total : 22186 time to create 1 rle with old method : 0.024654865264892578 time for calcul the mask position with numpy : 0.02494502067565918 nb_pixel_total : 47649 time to create 1 rle with old method : 0.05329608917236328 time for calcul the mask position with numpy : 0.026403188705444336 nb_pixel_total : 20990 time to create 1 rle with old method : 0.024225473403930664 time for calcul the mask position with numpy : 0.024569988250732422 nb_pixel_total : 17512 time to create 1 rle with old method : 0.018872499465942383 time for calcul the mask position with numpy : 0.024158000946044922 nb_pixel_total : 16741 time to create 1 rle with old method : 0.018220901489257812 time for calcul the mask position with numpy : 0.02543020248413086 nb_pixel_total : 9889 time to create 1 rle with old method : 0.010996341705322266 create new chi : 2.4807283878326416 time to delete rle : 0.002054452896118164 batch 1 Loaded 25 chid ids of type : 3594 +++++++++++++Number RLEs to save : 7488 TO DO : save crop sub photo not yet done ! save time : 0.5085515975952148 nb_obj : 11 nb_hashtags : 4 time to prepare the origin masks : 6.075397968292236 time for calcul the mask position with numpy : 0.8127462863922119 nb_pixel_total : 7534554 time to create 1 rle with new method : 0.9630656242370605 time for calcul the mask position with numpy : 0.028717041015625 nb_pixel_total : 116014 time to create 1 rle with old method : 0.14617013931274414 time for calcul the mask position with numpy : 0.027453184127807617 nb_pixel_total : 160897 time to create 1 rle with new method : 0.8539371490478516 time for calcul the mask position with numpy : 0.025599002838134766 nb_pixel_total : 23157 time to create 1 rle with old method : 0.025969266891479492 time for calcul the mask position with numpy : 0.02636122703552246 nb_pixel_total : 132125 time to create 1 rle with old method : 0.1464252471923828 time for calcul the mask position with numpy : 0.026346206665039062 nb_pixel_total : 60302 time to create 1 rle with old method : 0.07017064094543457 time for calcul the mask position with numpy : 0.023816823959350586 nb_pixel_total : 29996 time to create 1 rle with old method : 0.032798051834106445 time for calcul the mask position with numpy : 0.024643421173095703 nb_pixel_total : 50011 time to create 1 rle with old method : 0.05562710762023926 time for calcul the mask position with numpy : 0.02668905258178711 nb_pixel_total : 75375 time to create 1 rle with old method : 0.08395552635192871 time for calcul the mask position with numpy : 0.033365488052368164 nb_pixel_total : 16037 time to create 1 rle with old method : 0.017989158630371094 time for calcul the mask position with numpy : 0.040944814682006836 nb_pixel_total : 5474 time to create 1 rle with old method : 0.0065081119537353516 time for calcul the mask position with numpy : 0.042696475982666016 nb_pixel_total : 90458 time to create 1 rle with old method : 0.09939146041870117 create new chi : 3.7169346809387207 time to delete rle : 0.0013730525970458984 batch 1 Loaded 23 chid ids of type : 3594 +++++++++++Number RLEs to save : 8809 TO DO : save crop sub photo not yet done ! save time : 0.5832703113555908 nb_obj : 9 nb_hashtags : 3 time to prepare the origin masks : 6.387192964553833 time for calcul the mask position with numpy : 0.8933570384979248 nb_pixel_total : 7513626 time to create 1 rle with new method : 0.7006649971008301 time for calcul the mask position with numpy : 0.024408817291259766 nb_pixel_total : 39786 time to create 1 rle with old method : 0.046369075775146484 time for calcul the mask position with numpy : 0.027013778686523438 nb_pixel_total : 101065 time to create 1 rle with old method : 0.1528489589691162 time for calcul the mask position with numpy : 0.026536941528320312 nb_pixel_total : 54270 time to create 1 rle with old method : 0.06020045280456543 time for calcul the mask position with numpy : 0.02648186683654785 nb_pixel_total : 18609 time to create 1 rle with old method : 0.020735502243041992 time for calcul the mask position with numpy : 0.02824115753173828 nb_pixel_total : 388220 time to create 1 rle with new method : 1.0357515811920166 time for calcul the mask position with numpy : 0.0266115665435791 nb_pixel_total : 123743 time to create 1 rle with old method : 0.15872836112976074 time for calcul the mask position with numpy : 0.02798008918762207 nb_pixel_total : 27232 time to create 1 rle with old method : 0.030505895614624023 time for calcul the mask position with numpy : 0.0287168025970459 nb_pixel_total : 18979 time to create 1 rle with old method : 0.02129197120666504 time for calcul the mask position with numpy : 0.026188135147094727 nb_pixel_total : 8870 time to create 1 rle with old method : 0.009973526000976562 create new chi : 3.445371389389038 time to delete rle : 0.0014636516571044922 batch 1 Loaded 19 chid ids of type : 3594 +++++++++Number RLEs to save : 8786 TO DO : save crop sub photo not yet done ! save time : 0.5870559215545654 nb_obj : 27 nb_hashtags : 4 time to prepare the origin masks : 4.01340126991272 time for calcul the mask position with numpy : 0.8597960472106934 nb_pixel_total : 7403306 time to create 1 rle with new method : 0.9411211013793945 time for calcul the mask position with numpy : 0.03307628631591797 nb_pixel_total : 20804 time to create 1 rle with old method : 0.022424936294555664 time for calcul the mask position with numpy : 0.03300118446350098 nb_pixel_total : 30898 time to create 1 rle with old method : 0.034099578857421875 time for calcul the mask position with numpy : 0.03383660316467285 nb_pixel_total : 18480 time to create 1 rle with old method : 0.020435094833374023 time for calcul the mask position with numpy : 0.034291744232177734 nb_pixel_total : 59485 time to create 1 rle with old method : 0.06553912162780762 time for calcul the mask position with numpy : 0.0332643985748291 nb_pixel_total : 10764 time to create 1 rle with old method : 0.01189112663269043 time for calcul the mask position with numpy : 0.03306722640991211 nb_pixel_total : 58045 time to create 1 rle with old method : 0.062222957611083984 time for calcul the mask position with numpy : 0.03303170204162598 nb_pixel_total : 13490 time to create 1 rle with old method : 0.01471853256225586 time for calcul the mask position with numpy : 0.03309273719787598 nb_pixel_total : 30715 time to create 1 rle with old method : 0.03325080871582031 time for calcul the mask position with numpy : 0.03244948387145996 nb_pixel_total : 24368 time to create 1 rle with old method : 0.026663541793823242 time for calcul the mask position with numpy : 0.032468557357788086 nb_pixel_total : 59268 time to create 1 rle with old method : 0.0659017562866211 time for calcul the mask position with numpy : 0.03644609451293945 nb_pixel_total : 52618 time to create 1 rle with old method : 0.0630502700805664 time for calcul the mask position with numpy : 0.03621387481689453 nb_pixel_total : 56067 time to create 1 rle with old method : 0.062110185623168945 time for calcul the mask position with numpy : 0.034830331802368164 nb_pixel_total : 49487 time to create 1 rle with old method : 0.05471014976501465 time for calcul the mask position with numpy : 0.03437399864196777 nb_pixel_total : 29117 time to create 1 rle with old method : 0.0325624942779541 time for calcul the mask position with numpy : 0.0355226993560791 nb_pixel_total : 15082 time to create 1 rle with old method : 0.017326831817626953 time for calcul the mask position with numpy : 0.03587651252746582 nb_pixel_total : 13135 time to create 1 rle with old method : 0.01561880111694336 time for calcul the mask position with numpy : 0.03546953201293945 nb_pixel_total : 37169 time to create 1 rle with old method : 0.05038046836853027 time for calcul the mask position with numpy : 0.04871511459350586 nb_pixel_total : 146764 time to create 1 rle with old method : 0.193526029586792 time for calcul the mask position with numpy : 0.034528255462646484 nb_pixel_total : 7457 time to create 1 rle with old method : 0.00838780403137207 time for calcul the mask position with numpy : 0.03434443473815918 nb_pixel_total : 9791 time to create 1 rle with old method : 0.011184453964233398 time for calcul the mask position with numpy : 0.03427720069885254 nb_pixel_total : 27912 time to create 1 rle with old method : 0.03108835220336914 time for calcul the mask position with numpy : 0.033194780349731445 nb_pixel_total : 9753 time to create 1 rle with old method : 0.010765314102172852 time for calcul the mask position with numpy : 0.033333539962768555 nb_pixel_total : 36377 time to create 1 rle with old method : 0.04009675979614258 time for calcul the mask position with numpy : 0.03324389457702637 nb_pixel_total : 22471 time to create 1 rle with old method : 0.024707317352294922 time for calcul the mask position with numpy : 0.03354811668395996 nb_pixel_total : 22025 time to create 1 rle with old method : 0.023734569549560547 time for calcul the mask position with numpy : 0.03288531303405762 nb_pixel_total : 20196 time to create 1 rle with old method : 0.025763988494873047 time for calcul the mask position with numpy : 0.03966712951660156 nb_pixel_total : 9356 time to create 1 rle with old method : 0.015333890914916992 create new chi : 3.8126070499420166 time to delete rle : 0.0031120777130126953 batch 1 Loaded 55 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++Number RLEs to save : 15028 TO DO : save crop sub photo not yet done ! save time : 0.9869339466094971 nb_obj : 14 nb_hashtags : 2 time to prepare the origin masks : 6.402865171432495 time for calcul the mask position with numpy : 0.7707693576812744 nb_pixel_total : 7394812 time to create 1 rle with new method : 0.8593015670776367 time for calcul the mask position with numpy : 0.03816652297973633 nb_pixel_total : 46405 time to create 1 rle with old method : 0.05068492889404297 time for calcul the mask position with numpy : 0.025127410888671875 nb_pixel_total : 111237 time to create 1 rle with old method : 0.1206672191619873 time for calcul the mask position with numpy : 0.02657151222229004 nb_pixel_total : 11454 time to create 1 rle with old method : 0.012462377548217773 time for calcul the mask position with numpy : 0.025367021560668945 nb_pixel_total : 13828 time to create 1 rle with old method : 0.014932632446289062 time for calcul the mask position with numpy : 0.026465892791748047 nb_pixel_total : 22998 time to create 1 rle with old method : 0.025068998336791992 time for calcul the mask position with numpy : 0.026785850524902344 nb_pixel_total : 64826 time to create 1 rle with old method : 0.07018756866455078 time for calcul the mask position with numpy : 0.02580428123474121 nb_pixel_total : 8587 time to create 1 rle with old method : 0.009508609771728516 time for calcul the mask position with numpy : 0.025139808654785156 nb_pixel_total : 9317 time to create 1 rle with old method : 0.010466814041137695 time for calcul the mask position with numpy : 0.027071237564086914 nb_pixel_total : 37358 time to create 1 rle with old method : 0.041281938552856445 time for calcul the mask position with numpy : 0.027466297149658203 nb_pixel_total : 270498 time to create 1 rle with new method : 0.947561502456665 time for calcul the mask position with numpy : 0.0261232852935791 nb_pixel_total : 12563 time to create 1 rle with old method : 0.016899585723876953 time for calcul the mask position with numpy : 0.02970123291015625 nb_pixel_total : 100042 time to create 1 rle with old method : 0.1216120719909668 time for calcul the mask position with numpy : 0.025527477264404297 nb_pixel_total : 125987 time to create 1 rle with old method : 0.13548636436462402 time for calcul the mask position with numpy : 0.025089263916015625 nb_pixel_total : 64488 time to create 1 rle with old method : 0.06844758987426758 create new chi : 3.94516658782959 time to delete rle : 0.0013756752014160156 batch 1 Loaded 29 chid ids of type : 3594 ++++++++++++++++++++Number RLEs to save : 10627 TO DO : save crop sub photo not yet done ! save time : 0.7025518417358398 nb_obj : 12 nb_hashtags : 2 time to prepare the origin masks : 5.073901653289795 time for calcul the mask position with numpy : 1.0766303539276123 nb_pixel_total : 7452326 time to create 1 rle with new method : 0.8750317096710205 time for calcul the mask position with numpy : 0.027112245559692383 nb_pixel_total : 9934 time to create 1 rle with old method : 0.01127934455871582 time for calcul the mask position with numpy : 0.03197598457336426 nb_pixel_total : 73833 time to create 1 rle with old method : 0.08213973045349121 time for calcul the mask position with numpy : 0.026924848556518555 nb_pixel_total : 50516 time to create 1 rle with old method : 0.05657315254211426 time for calcul the mask position with numpy : 0.02575397491455078 nb_pixel_total : 20182 time to create 1 rle with old method : 0.023421764373779297 time for calcul the mask position with numpy : 0.02570199966430664 nb_pixel_total : 105249 time to create 1 rle with old method : 0.11578917503356934 time for calcul the mask position with numpy : 0.02762579917907715 nb_pixel_total : 308744 time to create 1 rle with new method : 1.0198311805725098 time for calcul the mask position with numpy : 0.02995467185974121 nb_pixel_total : 18386 time to create 1 rle with old method : 0.020847082138061523 time for calcul the mask position with numpy : 0.042088985443115234 nb_pixel_total : 55782 time to create 1 rle with old method : 0.0625450611114502 time for calcul the mask position with numpy : 0.0416867733001709 nb_pixel_total : 23490 time to create 1 rle with old method : 0.026366233825683594 time for calcul the mask position with numpy : 0.04713034629821777 nb_pixel_total : 79394 time to create 1 rle with old method : 0.08833622932434082 time for calcul the mask position with numpy : 0.040651559829711914 nb_pixel_total : 61997 time to create 1 rle with old method : 0.06967687606811523 time for calcul the mask position with numpy : 0.04128837585449219 nb_pixel_total : 34567 time to create 1 rle with old method : 0.03867840766906738 create new chi : 4.062057733535767 time to delete rle : 0.002023458480834961 batch 1 Loaded 25 chid ids of type : 3594 +++++++++++++++Number RLEs to save : 11894 TO DO : save crop sub photo not yet done ! save time : 0.7951972484588623 nb_obj : 20 nb_hashtags : 4 time to prepare the origin masks : 10.569731950759888 time for calcul the mask position with numpy : 1.057762622833252 nb_pixel_total : 7532000 time to create 1 rle with new method : 1.165144443511963 time for calcul the mask position with numpy : 0.04100322723388672 nb_pixel_total : 12146 time to create 1 rle with old method : 0.013269424438476562 time for calcul the mask position with numpy : 0.03977394104003906 nb_pixel_total : 14448 time to create 1 rle with old method : 0.016547441482543945 time for calcul the mask position with numpy : 0.04013490676879883 nb_pixel_total : 14048 time to create 1 rle with old method : 0.016131162643432617 time for calcul the mask position with numpy : 0.04108619689941406 nb_pixel_total : 58358 time to create 1 rle with old method : 0.0655202865600586 time for calcul the mask position with numpy : 0.04088306427001953 nb_pixel_total : 26139 time to create 1 rle with old method : 0.02913355827331543 time for calcul the mask position with numpy : 0.041230201721191406 nb_pixel_total : 23310 time to create 1 rle with old method : 0.026575088500976562 time for calcul the mask position with numpy : 0.040511369705200195 nb_pixel_total : 75999 time to create 1 rle with old method : 0.0839238166809082 time for calcul the mask position with numpy : 0.025809049606323242 nb_pixel_total : 17239 time to create 1 rle with old method : 0.019324064254760742 time for calcul the mask position with numpy : 0.02582716941833496 nb_pixel_total : 13493 time to create 1 rle with old method : 0.01512765884399414 time for calcul the mask position with numpy : 0.025819778442382812 nb_pixel_total : 4919 time to create 1 rle with old method : 0.005622386932373047 time for calcul the mask position with numpy : 0.025962352752685547 nb_pixel_total : 51658 time to create 1 rle with old method : 0.05732107162475586 time for calcul the mask position with numpy : 0.02470541000366211 nb_pixel_total : 23503 time to create 1 rle with old method : 0.025419950485229492 time for calcul the mask position with numpy : 0.0253448486328125 nb_pixel_total : 70690 time to create 1 rle with old method : 0.0773458480834961 time for calcul the mask position with numpy : 0.025979995727539062 nb_pixel_total : 16611 time to create 1 rle with old method : 0.018783092498779297 time for calcul the mask position with numpy : 0.025313615798950195 nb_pixel_total : 62151 time to create 1 rle with old method : 0.06872415542602539 time for calcul the mask position with numpy : 0.02594923973083496 nb_pixel_total : 111078 time to create 1 rle with old method : 0.12441062927246094 time for calcul the mask position with numpy : 0.02473306655883789 nb_pixel_total : 21211 time to create 1 rle with old method : 0.02381157875061035 time for calcul the mask position with numpy : 0.027981042861938477 nb_pixel_total : 26109 time to create 1 rle with old method : 0.028975486755371094 time for calcul the mask position with numpy : 0.039623260498046875 nb_pixel_total : 66359 time to create 1 rle with old method : 0.07304978370666504 time for calcul the mask position with numpy : 0.03986620903015137 nb_pixel_total : 52931 time to create 1 rle with old method : 0.059046268463134766 create new chi : 3.764047384262085 time to delete rle : 0.002029895782470703 batch 1 Loaded 41 chid ids of type : 3594 ++++++++++++++++++++Number RLEs to save : 12521 TO DO : save crop sub photo not yet done ! save time : 0.831357479095459 nb_obj : 20 nb_hashtags : 4 time to prepare the origin masks : 11.827049732208252 time for calcul the mask position with numpy : 1.4677813053131104 nb_pixel_total : 7219998 time to create 1 rle with new method : 1.0091266632080078 time for calcul the mask position with numpy : 0.04070782661437988 nb_pixel_total : 60184 time to create 1 rle with old method : 0.06677746772766113 time for calcul the mask position with numpy : 0.04057025909423828 nb_pixel_total : 20234 time to create 1 rle with old method : 0.022890090942382812 time for calcul the mask position with numpy : 0.04063677787780762 nb_pixel_total : 18271 time to create 1 rle with old method : 0.020475149154663086 time for calcul the mask position with numpy : 0.04273700714111328 nb_pixel_total : 211305 time to create 1 rle with new method : 0.7811934947967529 time for calcul the mask position with numpy : 0.04021716117858887 nb_pixel_total : 59562 time to create 1 rle with old method : 0.06652593612670898 time for calcul the mask position with numpy : 0.03965878486633301 nb_pixel_total : 60870 time to create 1 rle with old method : 0.0676116943359375 time for calcul the mask position with numpy : 0.03835630416870117 nb_pixel_total : 22423 time to create 1 rle with old method : 0.02566075325012207 time for calcul the mask position with numpy : 0.033461809158325195 nb_pixel_total : 16447 time to create 1 rle with old method : 0.018796205520629883 time for calcul the mask position with numpy : 0.03765082359313965 nb_pixel_total : 98761 time to create 1 rle with old method : 0.11249351501464844 time for calcul the mask position with numpy : 0.0348505973815918 nb_pixel_total : 16286 time to create 1 rle with old method : 0.018233060836791992 time for calcul the mask position with numpy : 0.032454729080200195 nb_pixel_total : 12893 time to create 1 rle with old method : 0.014397621154785156 time for calcul the mask position with numpy : 0.029921770095825195 nb_pixel_total : 175384 time to create 1 rle with new method : 0.732405424118042 time for calcul the mask position with numpy : 0.026948213577270508 nb_pixel_total : 16124 time to create 1 rle with old method : 0.018178939819335938 time for calcul the mask position with numpy : 0.02753138542175293 nb_pixel_total : 61710 time to create 1 rle with old method : 0.07015657424926758 time for calcul the mask position with numpy : 0.026043176651000977 nb_pixel_total : 22022 time to create 1 rle with old method : 0.025057554244995117 time for calcul the mask position with numpy : 0.028670072555541992 nb_pixel_total : 68166 time to create 1 rle with old method : 0.07997989654541016 time for calcul the mask position with numpy : 0.03966927528381348 nb_pixel_total : 42065 time to create 1 rle with old method : 0.04641914367675781 time for calcul the mask position with numpy : 0.04483532905578613 nb_pixel_total : 20415 time to create 1 rle with old method : 0.0333561897277832 time for calcul the mask position with numpy : 0.03954148292541504 nb_pixel_total : 17647 time to create 1 rle with old method : 0.019781112670898438 time for calcul the mask position with numpy : 0.03931093215942383 nb_pixel_total : 53633 time to create 1 rle with old method : 0.05923056602478027 create new chi : 5.604027986526489 time to delete rle : 0.0023958683013916016 batch 1 Loaded 41 chid ids of type : 3594 ++++++++++++++++++++Number RLEs to save : 13392 TO DO : save crop sub photo not yet done ! save time : 0.8612034320831299 nb_obj : 12 nb_hashtags : 4 time to prepare the origin masks : 6.654055118560791 time for calcul the mask position with numpy : 0.8557672500610352 nb_pixel_total : 7964372 time to create 1 rle with new method : 1.2717032432556152 time for calcul the mask position with numpy : 0.025516748428344727 nb_pixel_total : 56267 time to create 1 rle with old method : 0.06768393516540527 time for calcul the mask position with numpy : 0.025079727172851562 nb_pixel_total : 38923 time to create 1 rle with old method : 0.045903682708740234 time for calcul the mask position with numpy : 0.02496623992919922 nb_pixel_total : 23447 time to create 1 rle with old method : 0.0261380672454834 time for calcul the mask position with numpy : 0.02510833740234375 nb_pixel_total : 24296 time to create 1 rle with old method : 0.027370929718017578 time for calcul the mask position with numpy : 0.025662660598754883 nb_pixel_total : 20145 time to create 1 rle with old method : 0.02255702018737793 time for calcul the mask position with numpy : 0.025896310806274414 nb_pixel_total : 20593 time to create 1 rle with old method : 0.028398752212524414 time for calcul the mask position with numpy : 0.026210308074951172 nb_pixel_total : 39214 time to create 1 rle with old method : 0.04426431655883789 time for calcul the mask position with numpy : 0.026423215866088867 nb_pixel_total : 7033 time to create 1 rle with old method : 0.007958173751831055 time for calcul the mask position with numpy : 0.026933670043945312 nb_pixel_total : 23939 time to create 1 rle with old method : 0.027308940887451172 time for calcul the mask position with numpy : 0.02669501304626465 nb_pixel_total : 16439 time to create 1 rle with old method : 0.019353628158569336 time for calcul the mask position with numpy : 0.02645564079284668 nb_pixel_total : 32693 time to create 1 rle with old method : 0.037672996520996094 time for calcul the mask position with numpy : 0.025847196578979492 nb_pixel_total : 27039 time to create 1 rle with old method : 0.031189680099487305 create new chi : 2.8695647716522217 time to delete rle : 0.0012233257293701172 batch 1 Loaded 25 chid ids of type : 3594 ++++++++++++++Number RLEs to save : 6970 TO DO : save crop sub photo not yet done ! save time : 0.4691164493560791 nb_obj : 11 nb_hashtags : 5 time to prepare the origin masks : 8.055934190750122 time for calcul the mask position with numpy : 0.7793617248535156 nb_pixel_total : 7804134 time to create 1 rle with new method : 0.7433967590332031 time for calcul the mask position with numpy : 0.02417469024658203 nb_pixel_total : 27438 time to create 1 rle with old method : 0.028712034225463867 time for calcul the mask position with numpy : 0.024767398834228516 nb_pixel_total : 53389 time to create 1 rle with old method : 0.05626249313354492 time for calcul the mask position with numpy : 0.024231910705566406 nb_pixel_total : 13134 time to create 1 rle with old method : 0.014557838439941406 time for calcul the mask position with numpy : 0.02457141876220703 nb_pixel_total : 97095 time to create 1 rle with old method : 0.10228896141052246 time for calcul the mask position with numpy : 0.025110244750976562 nb_pixel_total : 42046 time to create 1 rle with old method : 0.045900583267211914 time for calcul the mask position with numpy : 0.02503681182861328 nb_pixel_total : 10713 time to create 1 rle with old method : 0.011466264724731445 time for calcul the mask position with numpy : 0.027573823928833008 nb_pixel_total : 2232 time to create 1 rle with old method : 0.003695249557495117 time for calcul the mask position with numpy : 0.02835536003112793 nb_pixel_total : 35106 time to create 1 rle with old method : 0.045853614807128906 time for calcul the mask position with numpy : 0.023913145065307617 nb_pixel_total : 28933 time to create 1 rle with old method : 0.031503915786743164 time for calcul the mask position with numpy : 0.024329423904418945 nb_pixel_total : 77976 time to create 1 rle with old method : 0.08368039131164551 time for calcul the mask position with numpy : 0.024634599685668945 nb_pixel_total : 102204 time to create 1 rle with old method : 0.11151528358459473 create new chi : 2.377406120300293 time to delete rle : 0.001268625259399414 batch 1 Loaded 23 chid ids of type : 3594 ++++++++++++++++Number RLEs to save : 7726 TO DO : save crop sub photo not yet done ! save time : 0.5257284641265869 nb_obj : 12 nb_hashtags : 2 time to prepare the origin masks : 5.013965845108032 time for calcul the mask position with numpy : 0.8658969402313232 nb_pixel_total : 7446708 time to create 1 rle with new method : 1.5614430904388428 time for calcul the mask position with numpy : 0.025567054748535156 nb_pixel_total : 40210 time to create 1 rle with old method : 0.04549217224121094 time for calcul the mask position with numpy : 0.02684783935546875 nb_pixel_total : 62873 time to create 1 rle with old method : 0.0928030014038086 time for calcul the mask position with numpy : 0.026446819305419922 nb_pixel_total : 168508 time to create 1 rle with new method : 1.0631747245788574 time for calcul the mask position with numpy : 0.02777719497680664 nb_pixel_total : 33691 time to create 1 rle with old method : 0.037891387939453125 time for calcul the mask position with numpy : 0.0262758731842041 nb_pixel_total : 32180 time to create 1 rle with old method : 0.036069631576538086 time for calcul the mask position with numpy : 0.0326380729675293 nb_pixel_total : 175498 time to create 1 rle with new method : 0.6669890880584717 time for calcul the mask position with numpy : 0.04517817497253418 nb_pixel_total : 35831 time to create 1 rle with old method : 0.05547142028808594 time for calcul the mask position with numpy : 0.04250454902648926 nb_pixel_total : 95070 time to create 1 rle with old method : 0.1352674961090088 time for calcul the mask position with numpy : 0.04161214828491211 nb_pixel_total : 34071 time to create 1 rle with old method : 0.0392153263092041 time for calcul the mask position with numpy : 0.04477357864379883 nb_pixel_total : 47159 time to create 1 rle with old method : 0.053365468978881836 time for calcul the mask position with numpy : 0.040216684341430664 nb_pixel_total : 110172 time to create 1 rle with old method : 0.12420392036437988 time for calcul the mask position with numpy : 0.04117012023925781 nb_pixel_total : 12429 time to create 1 rle with old method : 0.014209747314453125 create new chi : 5.319626331329346 time to delete rle : 0.0025374889373779297 batch 1 Loaded 25 chid ids of type : 3594 +++++++++++++Number RLEs to save : 9300 TO DO : save crop sub photo not yet done ! save time : 0.597315788269043 nb_obj : 17 nb_hashtags : 4 time to prepare the origin masks : 7.69767951965332 time for calcul the mask position with numpy : 0.8202357292175293 nb_pixel_total : 7327719 time to create 1 rle with new method : 1.0296227931976318 time for calcul the mask position with numpy : 0.03686690330505371 nb_pixel_total : 68888 time to create 1 rle with old method : 0.0749506950378418 time for calcul the mask position with numpy : 0.03932332992553711 nb_pixel_total : 17512 time to create 1 rle with old method : 0.022493839263916016 time for calcul the mask position with numpy : 0.03897428512573242 nb_pixel_total : 14900 time to create 1 rle with old method : 0.016201257705688477 time for calcul the mask position with numpy : 0.034554481506347656 nb_pixel_total : 74102 time to create 1 rle with old method : 0.08058547973632812 time for calcul the mask position with numpy : 0.04003262519836426 nb_pixel_total : 27638 time to create 1 rle with old method : 0.044783830642700195 time for calcul the mask position with numpy : 0.029596328735351562 nb_pixel_total : 52450 time to create 1 rle with old method : 0.057940006256103516 time for calcul the mask position with numpy : 0.02483963966369629 nb_pixel_total : 20144 time to create 1 rle with old method : 0.02197718620300293 time for calcul the mask position with numpy : 0.026336669921875 nb_pixel_total : 151706 time to create 1 rle with new method : 0.7789206504821777 time for calcul the mask position with numpy : 0.024671554565429688 nb_pixel_total : 15090 time to create 1 rle with old method : 0.016752004623413086 time for calcul the mask position with numpy : 0.025485754013061523 nb_pixel_total : 90703 time to create 1 rle with old method : 0.10459566116333008 time for calcul the mask position with numpy : 0.04058980941772461 nb_pixel_total : 68914 time to create 1 rle with old method : 0.07625436782836914 time for calcul the mask position with numpy : 0.039862632751464844 nb_pixel_total : 89589 time to create 1 rle with old method : 0.09985733032226562 time for calcul the mask position with numpy : 0.04066610336303711 nb_pixel_total : 40504 time to create 1 rle with old method : 0.04540300369262695 time for calcul the mask position with numpy : 0.03917694091796875 nb_pixel_total : 5627 time to create 1 rle with old method : 0.006354808807373047 time for calcul the mask position with numpy : 0.041847944259643555 nb_pixel_total : 131540 time to create 1 rle with old method : 0.1456303596496582 time for calcul the mask position with numpy : 0.03994631767272949 nb_pixel_total : 81642 time to create 1 rle with old method : 0.0889427661895752 time for calcul the mask position with numpy : 0.03829813003540039 nb_pixel_total : 15732 time to create 1 rle with old method : 0.01719188690185547 create new chi : 4.221135854721069 time to delete rle : 0.0019328594207763672 batch 1 Loaded 35 chid ids of type : 3594 ++++++++++++++++++Number RLEs to save : 11928 TO DO : save crop sub photo not yet done ! save time : 0.7907288074493408 nb_obj : 17 nb_hashtags : 3 time to prepare the origin masks : 6.967749834060669 time for calcul the mask position with numpy : 0.4694042205810547 nb_pixel_total : 6893149 time to create 1 rle with new method : 1.2331242561340332 time for calcul the mask position with numpy : 0.024441957473754883 nb_pixel_total : 14547 time to create 1 rle with old method : 0.016262292861938477 time for calcul the mask position with numpy : 0.026230335235595703 nb_pixel_total : 144188 time to create 1 rle with old method : 0.16666579246520996 time for calcul the mask position with numpy : 0.03325510025024414 nb_pixel_total : 123239 time to create 1 rle with old method : 0.17655062675476074 time for calcul the mask position with numpy : 0.02643132209777832 nb_pixel_total : 7513 time to create 1 rle with old method : 0.008349895477294922 time for calcul the mask position with numpy : 0.024779558181762695 nb_pixel_total : 36184 time to create 1 rle with old method : 0.03942751884460449 time for calcul the mask position with numpy : 0.02490234375 nb_pixel_total : 8945 time to create 1 rle with old method : 0.009567737579345703 time for calcul the mask position with numpy : 0.024547100067138672 nb_pixel_total : 68806 time to create 1 rle with old method : 0.0743098258972168 time for calcul the mask position with numpy : 0.026612281799316406 nb_pixel_total : 15012 time to create 1 rle with old method : 0.024227380752563477 time for calcul the mask position with numpy : 0.0288240909576416 nb_pixel_total : 93020 time to create 1 rle with old method : 0.10710000991821289 time for calcul the mask position with numpy : 0.025004863739013672 nb_pixel_total : 44488 time to create 1 rle with old method : 0.048490285873413086 time for calcul the mask position with numpy : 0.024465560913085938 nb_pixel_total : 46037 time to create 1 rle with old method : 0.050298213958740234 time for calcul the mask position with numpy : 0.02531147003173828 nb_pixel_total : 68521 time to create 1 rle with old method : 0.0748605728149414 time for calcul the mask position with numpy : 0.025652408599853516 nb_pixel_total : 143360 time to create 1 rle with old method : 0.15570855140686035 time for calcul the mask position with numpy : 0.025936126708984375 nb_pixel_total : 174104 time to create 1 rle with new method : 1.069535255432129 time for calcul the mask position with numpy : 0.025234699249267578 nb_pixel_total : 18904 time to create 1 rle with old method : 0.020595073699951172 time for calcul the mask position with numpy : 0.026618480682373047 nb_pixel_total : 342961 time to create 1 rle with new method : 0.7759742736816406 time for calcul the mask position with numpy : 0.03854012489318848 nb_pixel_total : 51422 time to create 1 rle with old method : 0.05570363998413086 create new chi : 5.1230857372283936 time to delete rle : 0.002126455307006836 batch 1 Loaded 35 chid ids of type : 3594 ++++++++++++++++++++++Number RLEs to save : 13450 TO DO : save crop sub photo not yet done ! save time : 0.856142520904541 nb_obj : 12 nb_hashtags : 2 time to prepare the origin masks : 4.555524587631226 time for calcul the mask position with numpy : 1.3364887237548828 nb_pixel_total : 7161802 time to create 1 rle with new method : 0.8832621574401855 time for calcul the mask position with numpy : 0.03996086120605469 nb_pixel_total : 294079 time to create 1 rle with new method : 0.8992300033569336 time for calcul the mask position with numpy : 0.044272422790527344 nb_pixel_total : 63816 time to create 1 rle with old method : 0.0723872184753418 time for calcul the mask position with numpy : 0.024470806121826172 nb_pixel_total : 37398 time to create 1 rle with old method : 0.04066920280456543 time for calcul the mask position with numpy : 0.024827003479003906 nb_pixel_total : 131269 time to create 1 rle with old method : 0.14453887939453125 time for calcul the mask position with numpy : 0.024745941162109375 nb_pixel_total : 41023 time to create 1 rle with old method : 0.04519534111022949 time for calcul the mask position with numpy : 0.02391958236694336 nb_pixel_total : 2290 time to create 1 rle with old method : 0.0024788379669189453 time for calcul the mask position with numpy : 0.025220155715942383 nb_pixel_total : 119897 time to create 1 rle with old method : 0.15592312812805176 time for calcul the mask position with numpy : 0.025668859481811523 nb_pixel_total : 50420 time to create 1 rle with old method : 0.05499744415283203 time for calcul the mask position with numpy : 0.025660276412963867 nb_pixel_total : 156333 time to create 1 rle with new method : 0.8725588321685791 time for calcul the mask position with numpy : 0.025478124618530273 nb_pixel_total : 8815 time to create 1 rle with old method : 0.009979963302612305 time for calcul the mask position with numpy : 0.02686452865600586 nb_pixel_total : 101887 time to create 1 rle with old method : 0.11188101768493652 time for calcul the mask position with numpy : 0.026148319244384766 nb_pixel_total : 125371 time to create 1 rle with old method : 0.1410536766052246 create new chi : 5.203728675842285 time to delete rle : 0.001928091049194336 batch 1 Loaded 25 chid ids of type : 3594 ++++++++++++++Number RLEs to save : 12491 TO DO : save crop sub photo not yet done ! save time : 0.7810966968536377 nb_obj : 20 nb_hashtags : 3 time to prepare the origin masks : 8.957700729370117 time for calcul the mask position with numpy : 0.49077320098876953 nb_pixel_total : 7195477 time to create 1 rle with new method : 0.9386329650878906 time for calcul the mask position with numpy : 0.02441716194152832 nb_pixel_total : 14828 time to create 1 rle with old method : 0.016644954681396484 time for calcul the mask position with numpy : 0.02533745765686035 nb_pixel_total : 23395 time to create 1 rle with old method : 0.025662660598754883 time for calcul the mask position with numpy : 0.02463245391845703 nb_pixel_total : 82925 time to create 1 rle with old method : 0.0885171890258789 time for calcul the mask position with numpy : 0.025058269500732422 nb_pixel_total : 15161 time to create 1 rle with old method : 0.016979455947875977 time for calcul the mask position with numpy : 0.02542257308959961 nb_pixel_total : 11870 time to create 1 rle with old method : 0.01331949234008789 time for calcul the mask position with numpy : 0.025018692016601562 nb_pixel_total : 9151 time to create 1 rle with old method : 0.01045989990234375 time for calcul the mask position with numpy : 0.02457880973815918 nb_pixel_total : 23592 time to create 1 rle with old method : 0.026221752166748047 time for calcul the mask position with numpy : 0.03299117088317871 nb_pixel_total : 359678 time to create 1 rle with new method : 1.220499038696289 time for calcul the mask position with numpy : 0.025844335556030273 nb_pixel_total : 33576 time to create 1 rle with old method : 0.037531375885009766 time for calcul the mask position with numpy : 0.027503013610839844 nb_pixel_total : 8157 time to create 1 rle with old method : 0.00915074348449707 time for calcul the mask position with numpy : 0.025697708129882812 nb_pixel_total : 98573 time to create 1 rle with old method : 0.10744071006774902 time for calcul the mask position with numpy : 0.026601076126098633 nb_pixel_total : 113709 time to create 1 rle with old method : 0.12556099891662598 time for calcul the mask position with numpy : 0.02591395378112793 nb_pixel_total : 19075 time to create 1 rle with old method : 0.021150827407836914 time for calcul the mask position with numpy : 0.025537967681884766 nb_pixel_total : 14863 time to create 1 rle with old method : 0.016839265823364258 time for calcul the mask position with numpy : 0.030378103256225586 nb_pixel_total : 35056 time to create 1 rle with old method : 0.03925204277038574 time for calcul the mask position with numpy : 0.02581644058227539 nb_pixel_total : 27973 time to create 1 rle with old method : 0.03156471252441406 time for calcul the mask position with numpy : 0.035422325134277344 nb_pixel_total : 44496 time to create 1 rle with old method : 0.05019664764404297 time for calcul the mask position with numpy : 0.02639627456665039 nb_pixel_total : 7066 time to create 1 rle with old method : 0.008067131042480469 time for calcul the mask position with numpy : 0.02724003791809082 nb_pixel_total : 86776 time to create 1 rle with old method : 0.09739446640014648 time for calcul the mask position with numpy : 0.024291515350341797 nb_pixel_total : 69003 time to create 1 rle with old method : 0.07552838325500488 create new chi : 4.073535203933716 time to delete rle : 0.0025110244750976562 batch 1 Loaded 41 chid ids of type : 3594 +++++++++++++++++++++++++++Number RLEs to save : 14301 TO DO : save crop sub photo not yet done ! save time : 0.971998929977417 nb_obj : 14 nb_hashtags : 3 time to prepare the origin masks : 8.270324230194092 time for calcul the mask position with numpy : 0.5368132591247559 nb_pixel_total : 7813281 time to create 1 rle with new method : 0.5041515827178955 time for calcul the mask position with numpy : 0.024793148040771484 nb_pixel_total : 14190 time to create 1 rle with old method : 0.016249418258666992 time for calcul the mask position with numpy : 0.02734827995300293 nb_pixel_total : 13901 time to create 1 rle with old method : 0.015322446823120117 time for calcul the mask position with numpy : 0.02502727508544922 nb_pixel_total : 29427 time to create 1 rle with old method : 0.03274345397949219 time for calcul the mask position with numpy : 0.026099681854248047 nb_pixel_total : 23983 time to create 1 rle with old method : 0.02678680419921875 time for calcul the mask position with numpy : 0.027059078216552734 nb_pixel_total : 28508 time to create 1 rle with old method : 0.03508901596069336 time for calcul the mask position with numpy : 0.03137397766113281 nb_pixel_total : 100284 time to create 1 rle with old method : 0.14695382118225098 time for calcul the mask position with numpy : 0.03080010414123535 nb_pixel_total : 53860 time to create 1 rle with old method : 0.06130337715148926 time for calcul the mask position with numpy : 0.035593509674072266 nb_pixel_total : 16153 time to create 1 rle with old method : 0.01775360107421875 time for calcul the mask position with numpy : 0.028873682022094727 nb_pixel_total : 19292 time to create 1 rle with old method : 0.03130221366882324 time for calcul the mask position with numpy : 0.02712392807006836 nb_pixel_total : 12431 time to create 1 rle with old method : 0.014277935028076172 time for calcul the mask position with numpy : 0.02577686309814453 nb_pixel_total : 19736 time to create 1 rle with old method : 0.022211313247680664 time for calcul the mask position with numpy : 0.026539087295532227 nb_pixel_total : 11548 time to create 1 rle with old method : 0.01311039924621582 time for calcul the mask position with numpy : 0.026642322540283203 nb_pixel_total : 96077 time to create 1 rle with old method : 0.1077268123626709 time for calcul the mask position with numpy : 0.026492834091186523 nb_pixel_total : 41729 time to create 1 rle with old method : 0.04561734199523926 create new chi : 2.0697624683380127 time to delete rle : 0.0016331672668457031 batch 1 Loaded 29 chid ids of type : 3594 +++++++++++++++++++++++++++++Number RLEs to save : 10372 TO DO : save crop sub photo not yet done ! save time : 0.7099606990814209 nb_obj : 18 nb_hashtags : 3 time to prepare the origin masks : 8.165133714675903 time for calcul the mask position with numpy : 0.7919502258300781 nb_pixel_total : 7243057 time to create 1 rle with new method : 1.1415624618530273 time for calcul the mask position with numpy : 0.02318882942199707 nb_pixel_total : 21563 time to create 1 rle with old method : 0.022699832916259766 time for calcul the mask position with numpy : 0.023915529251098633 nb_pixel_total : 24200 time to create 1 rle with old method : 0.030184507369995117 time for calcul the mask position with numpy : 0.02694559097290039 nb_pixel_total : 12779 time to create 1 rle with old method : 0.020872116088867188 time for calcul the mask position with numpy : 0.026932954788208008 nb_pixel_total : 21318 time to create 1 rle with old method : 0.022476911544799805 time for calcul the mask position with numpy : 0.024118423461914062 nb_pixel_total : 62165 time to create 1 rle with old method : 0.06539535522460938 time for calcul the mask position with numpy : 0.025530576705932617 nb_pixel_total : 18433 time to create 1 rle with old method : 0.019521474838256836 time for calcul the mask position with numpy : 0.024502038955688477 nb_pixel_total : 45432 time to create 1 rle with old method : 0.047429800033569336 time for calcul the mask position with numpy : 0.024671316146850586 nb_pixel_total : 119988 time to create 1 rle with old method : 0.12984371185302734 time for calcul the mask position with numpy : 0.025865554809570312 nb_pixel_total : 46851 time to create 1 rle with old method : 0.050461530685424805 time for calcul the mask position with numpy : 0.025540828704833984 nb_pixel_total : 35051 time to create 1 rle with old method : 0.039015769958496094 time for calcul the mask position with numpy : 0.02727794647216797 nb_pixel_total : 47572 time to create 1 rle with old method : 0.055633544921875 time for calcul the mask position with numpy : 0.02633976936340332 nb_pixel_total : 108203 time to create 1 rle with old method : 0.12114071846008301 time for calcul the mask position with numpy : 0.025508880615234375 nb_pixel_total : 12255 time to create 1 rle with old method : 0.014081478118896484 time for calcul the mask position with numpy : 0.027010679244995117 nb_pixel_total : 18072 time to create 1 rle with old method : 0.02068471908569336 time for calcul the mask position with numpy : 0.02745842933654785 nb_pixel_total : 101747 time to create 1 rle with old method : 0.1141505241394043 time for calcul the mask position with numpy : 0.0246889591217041 nb_pixel_total : 12570 time to create 1 rle with old method : 0.013723611831665039 time for calcul the mask position with numpy : 0.025683879852294922 nb_pixel_total : 56305 time to create 1 rle with old method : 0.06169629096984863 time for calcul the mask position with numpy : 0.027757644653320312 nb_pixel_total : 286839 time to create 1 rle with new method : 1.0417122840881348 create new chi : 4.353623628616333 time to delete rle : 0.0018978118896484375 batch 1 Loaded 37 chid ids of type : 3594 +++++++++++++++++++++++Number RLEs to save : 12700 TO DO : save crop sub photo not yet done ! save time : 0.8501455783843994 nb_obj : 7 nb_hashtags : 3 time to prepare the origin masks : 4.016765117645264 time for calcul the mask position with numpy : 0.6256248950958252 nb_pixel_total : 7874193 time to create 1 rle with new method : 0.8519060611724854 time for calcul the mask position with numpy : 0.023807048797607422 nb_pixel_total : 458 time to create 1 rle with old method : 0.0005967617034912109 time for calcul the mask position with numpy : 0.023832321166992188 nb_pixel_total : 28603 time to create 1 rle with old method : 0.03166961669921875 time for calcul the mask position with numpy : 0.027368545532226562 nb_pixel_total : 136356 time to create 1 rle with old method : 0.1688401699066162 time for calcul the mask position with numpy : 0.02571892738342285 nb_pixel_total : 78010 time to create 1 rle with old method : 0.08653998374938965 time for calcul the mask position with numpy : 0.02443242073059082 nb_pixel_total : 19842 time to create 1 rle with old method : 0.021664857864379883 time for calcul the mask position with numpy : 0.025269269943237305 nb_pixel_total : 92270 time to create 1 rle with old method : 0.10213661193847656 time for calcul the mask position with numpy : 0.02516317367553711 nb_pixel_total : 64668 time to create 1 rle with old method : 0.07062697410583496 create new chi : 2.179215669631958 time to delete rle : 0.001132965087890625 batch 1 Loaded 15 chid ids of type : 3594 +++++++Number RLEs to save : 7196 TO DO : save crop sub photo not yet done ! save time : 0.4589693546295166 nb_obj : 11 nb_hashtags : 2 time to prepare the origin masks : 4.802883148193359 time for calcul the mask position with numpy : 0.5613858699798584 nb_pixel_total : 6899154 time to create 1 rle with new method : 0.925330638885498 time for calcul the mask position with numpy : 0.0233612060546875 nb_pixel_total : 36258 time to create 1 rle with old method : 0.037796974182128906 time for calcul the mask position with numpy : 0.025261402130126953 nb_pixel_total : 155861 time to create 1 rle with new method : 0.8165121078491211 time for calcul the mask position with numpy : 0.025170326232910156 nb_pixel_total : 35723 time to create 1 rle with old method : 0.046480655670166016 time for calcul the mask position with numpy : 0.033532142639160156 nb_pixel_total : 119726 time to create 1 rle with old method : 0.13607454299926758 time for calcul the mask position with numpy : 0.031595706939697266 nb_pixel_total : 694728 time to create 1 rle with new method : 0.9539260864257812 time for calcul the mask position with numpy : 0.02536797523498535 nb_pixel_total : 40766 time to create 1 rle with old method : 0.045052289962768555 time for calcul the mask position with numpy : 0.024827957153320312 nb_pixel_total : 104602 time to create 1 rle with old method : 0.11563706398010254 time for calcul the mask position with numpy : 0.025628328323364258 nb_pixel_total : 10729 time to create 1 rle with old method : 0.011732339859008789 time for calcul the mask position with numpy : 0.026175498962402344 nb_pixel_total : 89863 time to create 1 rle with old method : 0.09829950332641602 time for calcul the mask position with numpy : 0.02372455596923828 nb_pixel_total : 28634 time to create 1 rle with old method : 0.030937671661376953 time for calcul the mask position with numpy : 0.02520895004272461 nb_pixel_total : 78356 time to create 1 rle with old method : 0.08190369606018066 create new chi : 4.244430303573608 time to delete rle : 0.0020685195922851562 batch 1 Loaded 24 chid ids of type : 3594 +++++++++++++++++++Number RLEs to save : 12938 TO DO : save crop sub photo not yet done ! save time : 0.7558102607727051 nb_obj : 12 nb_hashtags : 4 time to prepare the origin masks : 6.002088308334351 time for calcul the mask position with numpy : 0.6703853607177734 nb_pixel_total : 7572375 time to create 1 rle with new method : 0.8554496765136719 time for calcul the mask position with numpy : 0.025394201278686523 nb_pixel_total : 68450 time to create 1 rle with old method : 0.07576179504394531 time for calcul the mask position with numpy : 0.025899410247802734 nb_pixel_total : 65311 time to create 1 rle with old method : 0.07486844062805176 time for calcul the mask position with numpy : 0.026409149169921875 nb_pixel_total : 30445 time to create 1 rle with old method : 0.03355884552001953 time for calcul the mask position with numpy : 0.02441859245300293 nb_pixel_total : 23073 time to create 1 rle with old method : 0.02478790283203125 time for calcul the mask position with numpy : 0.023780345916748047 nb_pixel_total : 32471 time to create 1 rle with old method : 0.035210609436035156 time for calcul the mask position with numpy : 0.027069091796875 nb_pixel_total : 47297 time to create 1 rle with old method : 0.05127525329589844 time for calcul the mask position with numpy : 0.027445077896118164 nb_pixel_total : 219221 time to create 1 rle with new method : 1.0328960418701172 time for calcul the mask position with numpy : 0.02471017837524414 nb_pixel_total : 22590 time to create 1 rle with old method : 0.023617029190063477 time for calcul the mask position with numpy : 0.02568960189819336 nb_pixel_total : 121688 time to create 1 rle with old method : 0.1302497386932373 time for calcul the mask position with numpy : 0.02509617805480957 nb_pixel_total : 46427 time to create 1 rle with old method : 0.05053281784057617 time for calcul the mask position with numpy : 0.025521278381347656 nb_pixel_total : 30266 time to create 1 rle with old method : 0.03287768363952637 time for calcul the mask position with numpy : 0.024873018264770508 nb_pixel_total : 14786 time to create 1 rle with old method : 0.016097545623779297 create new chi : 3.4819295406341553 time to delete rle : 0.0016319751739501953 batch 1 Loaded 25 chid ids of type : 3594 +++++++++++++++++Number RLEs to save : 10092 TO DO : save crop sub photo not yet done ! save time : 0.6388113498687744 nb_obj : 20 nb_hashtags : 4 time to prepare the origin masks : 10.015820503234863 time for calcul the mask position with numpy : 0.6322166919708252 nb_pixel_total : 7758270 time to create 1 rle with new method : 0.8308393955230713 time for calcul the mask position with numpy : 0.024950027465820312 nb_pixel_total : 26020 time to create 1 rle with old method : 0.028989791870117188 time for calcul the mask position with numpy : 0.026123523712158203 nb_pixel_total : 31396 time to create 1 rle with old method : 0.035576581954956055 time for calcul the mask position with numpy : 0.024950504302978516 nb_pixel_total : 73022 time to create 1 rle with old method : 0.08087706565856934 time for calcul the mask position with numpy : 0.02438044548034668 nb_pixel_total : 29365 time to create 1 rle with old method : 0.032621145248413086 time for calcul the mask position with numpy : 0.027676820755004883 nb_pixel_total : 11044 time to create 1 rle with old method : 0.017867326736450195 time for calcul the mask position with numpy : 0.02797698974609375 nb_pixel_total : 30879 time to create 1 rle with old method : 0.04495406150817871 time for calcul the mask position with numpy : 0.04165053367614746 nb_pixel_total : 11712 time to create 1 rle with old method : 0.013179779052734375 time for calcul the mask position with numpy : 0.04338979721069336 nb_pixel_total : 27769 time to create 1 rle with old method : 0.03110051155090332 time for calcul the mask position with numpy : 0.04002809524536133 nb_pixel_total : 10861 time to create 1 rle with old method : 0.012277364730834961 time for calcul the mask position with numpy : 0.03762412071228027 nb_pixel_total : 22272 time to create 1 rle with old method : 0.04209089279174805 time for calcul the mask position with numpy : 0.0355525016784668 nb_pixel_total : 25009 time to create 1 rle with old method : 0.03330588340759277 time for calcul the mask position with numpy : 0.03218817710876465 nb_pixel_total : 9868 time to create 1 rle with old method : 0.013406991958618164 time for calcul the mask position with numpy : 0.02935338020324707 nb_pixel_total : 41269 time to create 1 rle with old method : 0.051239967346191406 time for calcul the mask position with numpy : 0.02858710289001465 nb_pixel_total : 10130 time to create 1 rle with old method : 0.014286994934082031 time for calcul the mask position with numpy : 0.02869725227355957 nb_pixel_total : 24271 time to create 1 rle with old method : 0.027067184448242188 time for calcul the mask position with numpy : 0.02758026123046875 nb_pixel_total : 10217 time to create 1 rle with old method : 0.011693954467773438 time for calcul the mask position with numpy : 0.02889251708984375 nb_pixel_total : 38414 time to create 1 rle with old method : 0.045212507247924805 time for calcul the mask position with numpy : 0.029045581817626953 nb_pixel_total : 13769 time to create 1 rle with old method : 0.019123315811157227 time for calcul the mask position with numpy : 0.028847217559814453 nb_pixel_total : 62314 time to create 1 rle with old method : 0.06938886642456055 time for calcul the mask position with numpy : 0.030843019485473633 nb_pixel_total : 26529 time to create 1 rle with old method : 0.034894704818725586 create new chi : 2.8245415687561035 time to delete rle : 0.0023031234741210938 batch 1 Loaded 41 chid ids of type : 3594 +++++++++++++++++++++++++++++Number RLEs to save : 10245 TO DO : save crop sub photo not yet done ! save time : 0.709463357925415 nb_obj : 13 nb_hashtags : 2 time to prepare the origin masks : 6.63618540763855 time for calcul the mask position with numpy : 0.9285597801208496 nb_pixel_total : 7859543 time to create 1 rle with new method : 0.7971620559692383 time for calcul the mask position with numpy : 0.024777650833129883 nb_pixel_total : 30490 time to create 1 rle with old method : 0.03361248970031738 time for calcul the mask position with numpy : 0.026079416275024414 nb_pixel_total : 99898 time to create 1 rle with old method : 0.11204314231872559 time for calcul the mask position with numpy : 0.04057002067565918 nb_pixel_total : 30167 time to create 1 rle with old method : 0.03366899490356445 time for calcul the mask position with numpy : 0.043356895446777344 nb_pixel_total : 3679 time to create 1 rle with old method : 0.004174232482910156 time for calcul the mask position with numpy : 0.04137301445007324 nb_pixel_total : 4399 time to create 1 rle with old method : 0.00501704216003418 time for calcul the mask position with numpy : 0.02831554412841797 nb_pixel_total : 12437 time to create 1 rle with old method : 0.01408243179321289 time for calcul the mask position with numpy : 0.02606678009033203 nb_pixel_total : 21611 time to create 1 rle with old method : 0.024829626083374023 time for calcul the mask position with numpy : 0.02657151222229004 nb_pixel_total : 31584 time to create 1 rle with old method : 0.036260366439819336 time for calcul the mask position with numpy : 0.02736496925354004 nb_pixel_total : 15915 time to create 1 rle with old method : 0.018326282501220703 time for calcul the mask position with numpy : 0.025827646255493164 nb_pixel_total : 23830 time to create 1 rle with old method : 0.027052879333496094 time for calcul the mask position with numpy : 0.025106191635131836 nb_pixel_total : 10551 time to create 1 rle with old method : 0.011860132217407227 time for calcul the mask position with numpy : 0.026419401168823242 nb_pixel_total : 37240 time to create 1 rle with old method : 0.04170823097229004 time for calcul the mask position with numpy : 0.026950597763061523 nb_pixel_total : 113056 time to create 1 rle with old method : 0.1257333755493164 create new chi : 2.6508066654205322 time to delete rle : 0.0014545917510986328 batch 1 Loaded 27 chid ids of type : 3594 +++++++++++++Number RLEs to save : 7468 TO DO : save crop sub photo not yet done ! save time : 0.4553103446960449 nb_obj : 10 nb_hashtags : 3 time to prepare the origin masks : 6.285066604614258 time for calcul the mask position with numpy : 0.30110597610473633 nb_pixel_total : 7146169 time to create 1 rle with new method : 1.0156915187835693 time for calcul the mask position with numpy : 0.029804229736328125 nb_pixel_total : 14181 time to create 1 rle with old method : 0.01617598533630371 time for calcul the mask position with numpy : 0.03990960121154785 nb_pixel_total : 24649 time to create 1 rle with old method : 0.03276324272155762 time for calcul the mask position with numpy : 0.03924083709716797 nb_pixel_total : 21647 time to create 1 rle with old method : 0.02930426597595215 time for calcul the mask position with numpy : 0.03390836715698242 nb_pixel_total : 450818 time to create 1 rle with new method : 0.8141756057739258 time for calcul the mask position with numpy : 0.02913355827331543 nb_pixel_total : 150594 time to create 1 rle with new method : 1.0133402347564697 time for calcul the mask position with numpy : 0.029881000518798828 nb_pixel_total : 12056 time to create 1 rle with old method : 0.014264822006225586 time for calcul the mask position with numpy : 0.03236961364746094 nb_pixel_total : 102973 time to create 1 rle with old method : 0.1155385971069336 time for calcul the mask position with numpy : 0.02701711654663086 nb_pixel_total : 139470 time to create 1 rle with old method : 0.16272640228271484 time for calcul the mask position with numpy : 0.028876304626464844 nb_pixel_total : 81963 time to create 1 rle with old method : 0.09881901741027832 time for calcul the mask position with numpy : 0.030211687088012695 nb_pixel_total : 149880 time to create 1 rle with old method : 0.167527437210083 create new chi : 4.207120180130005 time to delete rle : 0.0015087127685546875 batch 1 Loaded 21 chid ids of type : 3594 ++++++++++Number RLEs to save : 8456 TO DO : save crop sub photo not yet done ! save time : 0.5416061878204346 nb_obj : 13 nb_hashtags : 4 time to prepare the origin masks : 9.852680206298828 time for calcul the mask position with numpy : 0.6958165168762207 nb_pixel_total : 7275957 time to create 1 rle with new method : 1.8196864128112793 time for calcul the mask position with numpy : 0.04528212547302246 nb_pixel_total : 135303 time to create 1 rle with old method : 0.1655406951904297 time for calcul the mask position with numpy : 0.042981863021850586 nb_pixel_total : 22445 time to create 1 rle with old method : 0.026324033737182617 time for calcul the mask position with numpy : 0.04195570945739746 nb_pixel_total : 44815 time to create 1 rle with old method : 0.05423378944396973 time for calcul the mask position with numpy : 0.049918174743652344 nb_pixel_total : 90252 time to create 1 rle with old method : 0.10156702995300293 time for calcul the mask position with numpy : 0.052201032638549805 nb_pixel_total : 217623 time to create 1 rle with new method : 0.8943901062011719 time for calcul the mask position with numpy : 0.04143214225769043 nb_pixel_total : 38119 time to create 1 rle with old method : 0.04347348213195801 time for calcul the mask position with numpy : 0.04638671875 nb_pixel_total : 100801 time to create 1 rle with old method : 0.11218047142028809 time for calcul the mask position with numpy : 0.04309535026550293 nb_pixel_total : 28088 time to create 1 rle with old method : 0.032250404357910156 time for calcul the mask position with numpy : 0.04552268981933594 nb_pixel_total : 24677 time to create 1 rle with old method : 0.027673959732055664 time for calcul the mask position with numpy : 0.04257702827453613 nb_pixel_total : 81674 time to create 1 rle with old method : 0.0912923812866211 time for calcul the mask position with numpy : 0.04283547401428223 nb_pixel_total : 30612 time to create 1 rle with old method : 0.03805947303771973 time for calcul the mask position with numpy : 0.044030189514160156 nb_pixel_total : 123168 time to create 1 rle with old method : 0.1457982063293457 time for calcul the mask position with numpy : 0.043508052825927734 nb_pixel_total : 80866 time to create 1 rle with old method : 0.09460043907165527 create new chi : 5.002373695373535 time to delete rle : 0.003489255905151367 batch 1 Loaded 27 chid ids of type : 3594 ++++++++++++++++Number RLEs to save : 11586 TO DO : save crop sub photo not yet done ! save time : 0.7107763290405273 nb_obj : 17 nb_hashtags : 2 time to prepare the origin masks : 9.692519664764404 time for calcul the mask position with numpy : 0.795318603515625 nb_pixel_total : 7258042 time to create 1 rle with new method : 0.9077293872833252 time for calcul the mask position with numpy : 0.042913198471069336 nb_pixel_total : 21150 time to create 1 rle with old method : 0.023757457733154297 time for calcul the mask position with numpy : 0.04394388198852539 nb_pixel_total : 46575 time to create 1 rle with old method : 0.07478666305541992 time for calcul the mask position with numpy : 0.03604292869567871 nb_pixel_total : 13242 time to create 1 rle with old method : 0.014965057373046875 time for calcul the mask position with numpy : 0.03207850456237793 nb_pixel_total : 23283 time to create 1 rle with old method : 0.026097536087036133 time for calcul the mask position with numpy : 0.0399782657623291 nb_pixel_total : 15109 time to create 1 rle with old method : 0.024559974670410156 time for calcul the mask position with numpy : 0.03141283988952637 nb_pixel_total : 99174 time to create 1 rle with old method : 0.12523889541625977 time for calcul the mask position with numpy : 0.028757333755493164 nb_pixel_total : 25717 time to create 1 rle with old method : 0.029592514038085938 time for calcul the mask position with numpy : 0.02861332893371582 nb_pixel_total : 68015 time to create 1 rle with old method : 0.08425617218017578 time for calcul the mask position with numpy : 0.027786731719970703 nb_pixel_total : 24529 time to create 1 rle with old method : 0.02844524383544922 time for calcul the mask position with numpy : 0.0258634090423584 nb_pixel_total : 46817 time to create 1 rle with old method : 0.07245874404907227 time for calcul the mask position with numpy : 0.028815269470214844 nb_pixel_total : 16987 time to create 1 rle with old method : 0.019621849060058594 time for calcul the mask position with numpy : 0.02798914909362793 nb_pixel_total : 31169 time to create 1 rle with old method : 0.05048060417175293 time for calcul the mask position with numpy : 0.027701616287231445 nb_pixel_total : 75532 time to create 1 rle with old method : 0.08640241622924805 time for calcul the mask position with numpy : 0.028868913650512695 nb_pixel_total : 174385 time to create 1 rle with new method : 0.883188009262085 time for calcul the mask position with numpy : 0.0457456111907959 nb_pixel_total : 123436 time to create 1 rle with old method : 0.14713335037231445 time for calcul the mask position with numpy : 0.03600287437438965 nb_pixel_total : 55814 time to create 1 rle with old method : 0.061882734298706055 time for calcul the mask position with numpy : 0.04306292533874512 nb_pixel_total : 175424 time to create 1 rle with new method : 1.0168566703796387 create new chi : 5.153689622879028 time to delete rle : 0.0022220611572265625 batch 1 Loaded 35 chid ids of type : 3594 +++++++++++++++++++++Number RLEs to save : 12126 TO DO : save crop sub photo not yet done ! save time : 0.7591061592102051 nb_obj : 15 nb_hashtags : 4 time to prepare the origin masks : 11.182796239852905 time for calcul the mask position with numpy : 0.9028944969177246 nb_pixel_total : 7458251 time to create 1 rle with new method : 0.742328405380249 time for calcul the mask position with numpy : 0.027548551559448242 nb_pixel_total : 31000 time to create 1 rle with old method : 0.03431129455566406 time for calcul the mask position with numpy : 0.029217004776000977 nb_pixel_total : 157122 time to create 1 rle with new method : 0.6449434757232666 time for calcul the mask position with numpy : 0.044107913970947266 nb_pixel_total : 147883 time to create 1 rle with old method : 0.16617870330810547 time for calcul the mask position with numpy : 0.044539451599121094 nb_pixel_total : 10394 time to create 1 rle with old method : 0.011718988418579102 time for calcul the mask position with numpy : 0.043586015701293945 nb_pixel_total : 50465 time to create 1 rle with old method : 0.06018853187561035 time for calcul the mask position with numpy : 0.044318199157714844 nb_pixel_total : 11026 time to create 1 rle with old method : 0.01222681999206543 time for calcul the mask position with numpy : 0.04147982597351074 nb_pixel_total : 35671 time to create 1 rle with old method : 0.040126800537109375 time for calcul the mask position with numpy : 0.04102826118469238 nb_pixel_total : 11218 time to create 1 rle with old method : 0.012596368789672852 time for calcul the mask position with numpy : 0.043268680572509766 nb_pixel_total : 77070 time to create 1 rle with old method : 0.08755302429199219 time for calcul the mask position with numpy : 0.04560446739196777 nb_pixel_total : 73864 time to create 1 rle with old method : 0.0826718807220459 time for calcul the mask position with numpy : 0.04491376876831055 nb_pixel_total : 17661 time to create 1 rle with old method : 0.019781827926635742 time for calcul the mask position with numpy : 0.03603529930114746 nb_pixel_total : 10847 time to create 1 rle with old method : 0.012272357940673828 time for calcul the mask position with numpy : 0.04100847244262695 nb_pixel_total : 44243 time to create 1 rle with old method : 0.0568232536315918 time for calcul the mask position with numpy : 0.04109311103820801 nb_pixel_total : 80164 time to create 1 rle with old method : 0.08885836601257324 time for calcul the mask position with numpy : 0.040403127670288086 nb_pixel_total : 77521 time to create 1 rle with old method : 0.08756041526794434 create new chi : 3.767911195755005 time to delete rle : 0.0028209686279296875 batch 1 Loaded 31 chid ids of type : 3594 ++++++++++++++++Number RLEs to save : 11082 TO DO : save crop sub photo not yet done ! save time : 0.7140822410583496 nb_obj : 14 nb_hashtags : 5 time to prepare the origin masks : 11.674507856369019 time for calcul the mask position with numpy : 0.9645462036132812 nb_pixel_total : 7158317 time to create 1 rle with new method : 0.6412003040313721 time for calcul the mask position with numpy : 0.04636502265930176 nb_pixel_total : 8502 time to create 1 rle with old method : 0.010100126266479492 time for calcul the mask position with numpy : 0.04858517646789551 nb_pixel_total : 7838 time to create 1 rle with old method : 0.009183168411254883 time for calcul the mask position with numpy : 0.051760196685791016 nb_pixel_total : 272496 time to create 1 rle with new method : 1.502582311630249 time for calcul the mask position with numpy : 0.048975467681884766 nb_pixel_total : 77335 time to create 1 rle with old method : 0.08605122566223145 time for calcul the mask position with numpy : 0.045557498931884766 nb_pixel_total : 56314 time to create 1 rle with old method : 0.06386351585388184 time for calcul the mask position with numpy : 0.03810834884643555 nb_pixel_total : 17998 time to create 1 rle with old method : 0.020496606826782227 time for calcul the mask position with numpy : 0.049458980560302734 nb_pixel_total : 195037 time to create 1 rle with new method : 1.2286038398742676 time for calcul the mask position with numpy : 0.0436711311340332 nb_pixel_total : 58875 time to create 1 rle with old method : 0.09950804710388184 time for calcul the mask position with numpy : 0.034906864166259766 nb_pixel_total : 16050 time to create 1 rle with old method : 0.018708467483520508 time for calcul the mask position with numpy : 0.043096065521240234 nb_pixel_total : 137688 time to create 1 rle with old method : 0.15511178970336914 time for calcul the mask position with numpy : 0.04757857322692871 nb_pixel_total : 27474 time to create 1 rle with old method : 0.031827688217163086 time for calcul the mask position with numpy : 0.03921222686767578 nb_pixel_total : 85378 time to create 1 rle with old method : 0.09807443618774414 time for calcul the mask position with numpy : 0.04225945472717285 nb_pixel_total : 82234 time to create 1 rle with old method : 0.09974002838134766 time for calcul the mask position with numpy : 0.04565072059631348 nb_pixel_total : 92864 time to create 1 rle with old method : 0.1358199119567871 create new chi : 6.060492753982544 time to delete rle : 0.0037276744842529297 batch 1 Loaded 29 chid ids of type : 3594 +++++++++++++++++++++Number RLEs to save : 13758 TO DO : save crop sub photo not yet done ! save time : 0.8709924221038818 nb_obj : 13 nb_hashtags : 2 time to prepare the origin masks : 7.4364283084869385 time for calcul the mask position with numpy : 0.4537997245788574 nb_pixel_total : 6754847 time to create 1 rle with new method : 0.6625654697418213 time for calcul the mask position with numpy : 0.04412651062011719 nb_pixel_total : 51881 time to create 1 rle with old method : 0.058434486389160156 time for calcul the mask position with numpy : 0.05797719955444336 nb_pixel_total : 151676 time to create 1 rle with new method : 0.9380805492401123 time for calcul the mask position with numpy : 0.04597616195678711 nb_pixel_total : 139106 time to create 1 rle with old method : 0.15561866760253906 time for calcul the mask position with numpy : 0.04492950439453125 nb_pixel_total : 50287 time to create 1 rle with old method : 0.06118369102478027 time for calcul the mask position with numpy : 0.04184556007385254 nb_pixel_total : 98118 time to create 1 rle with old method : 0.10927009582519531 time for calcul the mask position with numpy : 0.04803895950317383 nb_pixel_total : 99056 time to create 1 rle with old method : 0.13073325157165527 time for calcul the mask position with numpy : 0.05368638038635254 nb_pixel_total : 293516 time to create 1 rle with new method : 0.5159509181976318 time for calcul the mask position with numpy : 0.03782224655151367 nb_pixel_total : 50898 time to create 1 rle with old method : 0.06302094459533691 time for calcul the mask position with numpy : 0.041724205017089844 nb_pixel_total : 59172 time to create 1 rle with old method : 0.06626677513122559 time for calcul the mask position with numpy : 0.04462790489196777 nb_pixel_total : 214051 time to create 1 rle with new method : 0.5145676136016846 time for calcul the mask position with numpy : 0.04656505584716797 nb_pixel_total : 21818 time to create 1 rle with old method : 0.024760007858276367 time for calcul the mask position with numpy : 0.04461836814880371 nb_pixel_total : 113219 time to create 1 rle with old method : 0.1264045238494873 time for calcul the mask position with numpy : 0.04695463180541992 nb_pixel_total : 196755 time to create 1 rle with new method : 0.9263355731964111 create new chi : 5.573458909988403 time to delete rle : 0.0038847923278808594 batch 1 Loaded 27 chid ids of type : 3594 ++++++++++++++++Number RLEs to save : 12924 TO DO : save crop sub photo not yet done ! save time : 0.8164834976196289 map_output_result : {1360703512: (0.0, 'Should be the crop_list due to order', 0), 1360703507: (0.0, 'Should be the crop_list due to order', 0), 1360703504: (0.0, 'Should be the crop_list due to order', 0), 1360703497: (0.0, 'Should be the crop_list due to order', 0), 1360703494: (0.0, 'Should be the crop_list due to order', 0), 1360703490: (0.0, 'Should be the crop_list due to order', 0), 1360703454: (0.0, 'Should be the crop_list due to order', 0), 1360703451: (0.0, 'Should be the crop_list due to order', 0), 1360703447: (0.0, 'Should be the crop_list due to order', 0), 1360703443: (0.0, 'Should be the crop_list due to order', 0), 1360703440: (0.0, 'Should be the crop_list due to order', 0), 1360703418: (0.0, 'Should be the crop_list due to order', 0), 1360703414: (0.0, 'Should be the crop_list due to order', 0), 1360703411: (0.0, 'Should be the crop_list due to order', 0), 1360703406: (0.0, 'Should be the crop_list due to order', 0), 1360703400: (0.0, 'Should be the crop_list due to order', 0), 1360703377: (0.0, 'Should be the crop_list due to order', 0), 1360703374: (0.0, 'Should be the crop_list due to order', 0), 1360703368: (0.0, 'Should be the crop_list due to order', 0), 1360703362: (0.0, 'Should be the crop_list due to order', 0), 1360703358: (0.0, 'Should be the crop_list due to order', 0), 1360703353: (0.0, 'Should be the crop_list due to order', 0), 1360703327: (0.0, 'Should be the crop_list due to order', 0), 1360703323: (0.0, 'Should be the crop_list due to order', 0), 1360703320: (0.0, 'Should be the crop_list due to order', 0), 1360703313: (0.0, 'Should be the crop_list due to order', 0), 1360703286: (0.0, 'Should be the crop_list due to order', 0), 1360703283: (0.0, 'Should be the crop_list due to order', 0), 1360703279: (0.0, 'Should be the crop_list due to order', 0), 1360703276: (0.0, 'Should be the crop_list due to order', 0), 1360703274: (0.0, 'Should be the crop_list due to order', 0), 1360703272: (0.0, 'Should be the crop_list due to order', 0), 1360703250: (0.0, 'Should be the crop_list due to order', 0), 1360703246: (0.0, 'Should be the crop_list due to order', 0), 1360703244: (0.0, 'Should be the crop_list due to order', 0), 1360703241: (0.0, 'Should be the crop_list due to order', 0), 1360703240: (0.0, 'Should be the crop_list due to order', 0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1360703512, 1360703507, 1360703504, 1360703497, 1360703494, 1360703490, 1360703454, 1360703451, 1360703447, 1360703443, 1360703440, 1360703418, 1360703414, 1360703411, 1360703406, 1360703400, 1360703377, 1360703374, 1360703368, 1360703362, 1360703358, 1360703353, 1360703327, 1360703323, 1360703320, 1360703313, 1360703286, 1360703283, 1360703279, 1360703276, 1360703274, 1360703272, 1360703250, 1360703246, 1360703244, 1360703241, 1360703240] Looping around the photos to save general results len do output : 37 /1360703512.Didn't retrieve data . /1360703507.Didn't retrieve data . /1360703504.Didn't retrieve data . /1360703497.Didn't retrieve data . /1360703494.Didn't retrieve data . /1360703490.Didn't retrieve data . /1360703454.Didn't retrieve data . /1360703451.Didn't retrieve data . /1360703447.Didn't retrieve data . /1360703443.Didn't retrieve data . /1360703440.Didn't retrieve data . /1360703418.Didn't retrieve data . /1360703414.Didn't retrieve data . /1360703411.Didn't retrieve data . /1360703406.Didn't retrieve data . /1360703400.Didn't retrieve data . /1360703377.Didn't retrieve data . /1360703374.Didn't retrieve data . /1360703368.Didn't retrieve data . /1360703362.Didn't retrieve data . /1360703358.Didn't retrieve data . /1360703353.Didn't retrieve data . /1360703327.Didn't retrieve data . /1360703323.Didn't retrieve data . /1360703320.Didn't retrieve data . /1360703313.Didn't retrieve data . /1360703286.Didn't retrieve data . /1360703283.Didn't retrieve data . /1360703279.Didn't retrieve data . /1360703276.Didn't retrieve data . /1360703274.Didn't retrieve data . /1360703272.Didn't retrieve data . /1360703250.Didn't retrieve data . /1360703246.Didn't retrieve data . /1360703244.Didn't retrieve data . /1360703241.Didn't retrieve data . /1360703240.Didn't retrieve data . before output type Used above Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703512', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703507', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703504', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703497', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703494', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703490', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703454', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703451', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703447', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703443', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703440', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703418', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703414', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703411', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703406', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703400', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703377', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703374', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703368', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703362', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703358', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703353', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703327', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703323', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703320', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703313', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703286', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703283', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703279', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703276', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703274', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703272', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703250', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703246', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703244', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703241', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703240', None, None, None, None, None, '2964573') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 111 time used for this insertion : 0.020181655883789062 save_final save missing photos in datou_result : time spend for datou_step_exec : 466.84998512268066 time spend to save output : 0.02604365348815918 total time spend for step 3 : 466.8760287761688 step4:ventilate_hashtags_in_portfolio Tue May 27 13:51:07 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure beginning of datou step ventilate_hashtags_in_portfolio : To implement ! Iterating over portfolio : 23370929 get user id for portfolio 23370929 SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23370929 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','pet_clair','pehd','autre','mal_croppe','pet_fonce','environnement','flou','metal','carton','background')) AND mptpi.`min_score`=0.5 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23370929 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','pet_clair','pehd','autre','mal_croppe','pet_fonce','environnement','flou','metal','carton','background')) AND mptpi.`min_score`=0.5 To do To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23370929 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','pet_clair','pehd','autre','mal_croppe','pet_fonce','environnement','flou','metal','carton','background')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://www.fotonower.com/velours/23377484,23377485,23377486,23377487,23377488,23377489,23377490,23377491,23377492,23377493,23377494?tags=papier,pet_clair,pehd,autre,mal_croppe,pet_fonce,environnement,flou,metal,carton,background Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1360703512, 1360703507, 1360703504, 1360703497, 1360703494, 1360703490, 1360703454, 1360703451, 1360703447, 1360703443, 1360703440, 1360703418, 1360703414, 1360703411, 1360703406, 1360703400, 1360703377, 1360703374, 1360703368, 1360703362, 1360703358, 1360703353, 1360703327, 1360703323, 1360703320, 1360703313, 1360703286, 1360703283, 1360703279, 1360703276, 1360703274, 1360703272, 1360703250, 1360703246, 1360703244, 1360703241, 1360703240] Looping around the photos to save general results len do output : 1 /23370929. before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703512', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703507', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703504', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703497', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703494', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703490', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703454', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703451', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703447', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703443', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703440', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703418', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703414', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703411', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703406', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703400', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703377', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703374', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703368', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703362', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703358', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703353', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703327', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703323', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703320', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703313', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703286', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703283', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703279', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703276', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703274', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703272', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703250', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703246', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703244', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703241', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703240', None, None, None, None, None, '2964573') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 38 time used for this insertion : 0.017616987228393555 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.8990976810455322 time spend to save output : 0.02188396453857422 total time spend for step 4 : 0.9209816455841064 step5:final Tue May 27 13:51:07 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step final ! Catched exception ! Connect or reconnect ! Inside saveOutput : final : False verbose : 0 original output for save of step final : {1360703512: ('0.10723224526609942',), 1360703507: ('0.10723224526609942',), 1360703504: ('0.10723224526609942',), 1360703497: ('0.10723224526609942',), 1360703494: ('0.10723224526609942',), 1360703490: ('0.10723224526609942',), 1360703454: ('0.10723224526609942',), 1360703451: ('0.10723224526609942',), 1360703447: ('0.10723224526609942',), 1360703443: ('0.10723224526609942',), 1360703440: ('0.10723224526609942',), 1360703418: ('0.10723224526609942',), 1360703414: ('0.10723224526609942',), 1360703411: ('0.10723224526609942',), 1360703406: ('0.10723224526609942',), 1360703400: ('0.10723224526609942',), 1360703377: ('0.10723224526609942',), 1360703374: ('0.10723224526609942',), 1360703368: ('0.10723224526609942',), 1360703362: ('0.10723224526609942',), 1360703358: ('0.10723224526609942',), 1360703353: ('0.10723224526609942',), 1360703327: ('0.10723224526609942',), 1360703323: ('0.10723224526609942',), 1360703320: ('0.10723224526609942',), 1360703313: ('0.10723224526609942',), 1360703286: ('0.10723224526609942',), 1360703283: ('0.10723224526609942',), 1360703279: ('0.10723224526609942',), 1360703276: ('0.10723224526609942',), 1360703274: ('0.10723224526609942',), 1360703272: ('0.10723224526609942',), 1360703250: ('0.10723224526609942',), 1360703246: ('0.10723224526609942',), 1360703244: ('0.10723224526609942',), 1360703241: ('0.10723224526609942',), 1360703240: ('0.10723224526609942',)} new output for save of step final : {1360703512: ('0.10723224526609942',), 1360703507: ('0.10723224526609942',), 1360703504: ('0.10723224526609942',), 1360703497: ('0.10723224526609942',), 1360703494: ('0.10723224526609942',), 1360703490: ('0.10723224526609942',), 1360703454: ('0.10723224526609942',), 1360703451: ('0.10723224526609942',), 1360703447: ('0.10723224526609942',), 1360703443: ('0.10723224526609942',), 1360703440: ('0.10723224526609942',), 1360703418: ('0.10723224526609942',), 1360703414: ('0.10723224526609942',), 1360703411: ('0.10723224526609942',), 1360703406: ('0.10723224526609942',), 1360703400: ('0.10723224526609942',), 1360703377: ('0.10723224526609942',), 1360703374: ('0.10723224526609942',), 1360703368: ('0.10723224526609942',), 1360703362: ('0.10723224526609942',), 1360703358: ('0.10723224526609942',), 1360703353: ('0.10723224526609942',), 1360703327: ('0.10723224526609942',), 1360703323: ('0.10723224526609942',), 1360703320: ('0.10723224526609942',), 1360703313: ('0.10723224526609942',), 1360703286: ('0.10723224526609942',), 1360703283: ('0.10723224526609942',), 1360703279: ('0.10723224526609942',), 1360703276: ('0.10723224526609942',), 1360703274: ('0.10723224526609942',), 1360703272: ('0.10723224526609942',), 1360703250: ('0.10723224526609942',), 1360703246: ('0.10723224526609942',), 1360703244: ('0.10723224526609942',), 1360703241: ('0.10723224526609942',), 1360703240: ('0.10723224526609942',)} [1360703512, 1360703507, 1360703504, 1360703497, 1360703494, 1360703490, 1360703454, 1360703451, 1360703447, 1360703443, 1360703440, 1360703418, 1360703414, 1360703411, 1360703406, 1360703400, 1360703377, 1360703374, 1360703368, 1360703362, 1360703358, 1360703353, 1360703327, 1360703323, 1360703320, 1360703313, 1360703286, 1360703283, 1360703279, 1360703276, 1360703274, 1360703272, 1360703250, 1360703246, 1360703244, 1360703241, 1360703240] Looping around the photos to save general results len do output : 37 /1360703512.Didn't retrieve data . /1360703507.Didn't retrieve data . /1360703504.Didn't retrieve data . /1360703497.Didn't retrieve data . /1360703494.Didn't retrieve data . /1360703490.Didn't retrieve data . /1360703454.Didn't retrieve data . /1360703451.Didn't retrieve data . /1360703447.Didn't retrieve data . /1360703443.Didn't retrieve data . /1360703440.Didn't retrieve data . /1360703418.Didn't retrieve data . /1360703414.Didn't retrieve data . /1360703411.Didn't retrieve data . /1360703406.Didn't retrieve data . /1360703400.Didn't retrieve data . /1360703377.Didn't retrieve data . /1360703374.Didn't retrieve data . /1360703368.Didn't retrieve data . /1360703362.Didn't retrieve data . /1360703358.Didn't retrieve data . /1360703353.Didn't retrieve data . /1360703327.Didn't retrieve data . /1360703323.Didn't retrieve data . /1360703320.Didn't retrieve data . /1360703313.Didn't retrieve data . /1360703286.Didn't retrieve data . /1360703283.Didn't retrieve data . /1360703279.Didn't retrieve data . /1360703276.Didn't retrieve data . /1360703274.Didn't retrieve data . /1360703272.Didn't retrieve data . /1360703250.Didn't retrieve data . /1360703246.Didn't retrieve data . /1360703244.Didn't retrieve data . /1360703241.Didn't retrieve data . /1360703240.Didn't retrieve data . before output type Used above Used above Managing all output in save final without adding information in the mtr_datou_result ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703512', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703507', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703504', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703497', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703494', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703490', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703454', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703451', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703447', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703443', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703440', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703418', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703414', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703411', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703406', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703400', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703377', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703374', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703368', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703362', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703358', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703353', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703327', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703323', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703320', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703313', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703286', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703283', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703279', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703276', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703274', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703272', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703250', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703246', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703244', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703241', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703240', None, None, None, None, None, '2964573') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 111 time used for this insertion : 0.015504121780395508 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.13950037956237793 time spend to save output : 0.017608165740966797 total time spend for step 5 : 0.15710854530334473 step6:blur_detection Tue May 27 13:51:08 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b.jpg resize: (2160, 3840) 1360703512 -5.649291646534456 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff.jpg resize: (2160, 3840) 1360703507 -5.8608229688000675 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2.jpg resize: (2160, 3840) 1360703504 -5.944085740074683 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1.jpg resize: (2160, 3840) 1360703497 -5.7165904383668655 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7.jpg resize: (2160, 3840) 1360703494 -5.7789487530332435 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d.jpg resize: (2160, 3840) 1360703490 -5.755682341250878 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8.jpg resize: (2160, 3840) 1360703454 -5.887489712281242 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056.jpg resize: (2160, 3840) 1360703451 -5.882651331630403 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18.jpg resize: (2160, 3840) 1360703447 -5.8088466634114235 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1.jpg resize: (2160, 3840) 1360703443 -5.767272520682633 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772.jpg resize: (2160, 3840) 1360703440 -5.765849944715273 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8.jpg resize: (2160, 3840) 1360703418 -5.731247321633349 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463.jpg resize: (2160, 3840) 1360703414 -5.819856204769151 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af.jpg resize: (2160, 3840) 1360703411 -5.645014433182347 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f.jpg resize: (2160, 3840) 1360703406 -5.801872190500105 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151.jpg resize: (2160, 3840) 1360703400 -5.968754272969779 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6.jpg resize: (2160, 3840) 1360703377 -5.937476480690605 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4.jpg resize: (2160, 3840) 1360703374 -5.836389078601609 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4.jpg resize: (2160, 3840) 1360703368 -5.7872044494445705 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795.jpg resize: (2160, 3840) 1360703362 -5.6808345952634705 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825.jpg resize: (2160, 3840) 1360703358 -5.762121770048614 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb.jpg resize: (2160, 3840) 1360703353 -5.817336950940453 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849.jpg resize: (2160, 3840) 1360703327 -5.764730003747618 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838.jpg resize: (2160, 3840) 1360703323 -5.714207240991041 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07.jpg resize: (2160, 3840) 1360703320 -6.457446898593587 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04.jpg resize: (2160, 3840) 1360703313 -5.87131672036129 treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471.jpg resize: (2160, 3840) 1360703286 -5.738369548591882 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528.jpg resize: (2160, 3840) 1360703283 -5.668240799887292 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc.jpg resize: (2160, 3840) 1360703279 -5.856043562749426 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa.jpg resize: (2160, 3840) 1360703276 -5.858454289677687 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f.jpg resize: (2160, 3840) 1360703274 -5.762489029372882 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757.jpg resize: (2160, 3840) 1360703272 -5.638665479496887 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b.jpg resize: (2160, 3840) 1360703250 -5.780706706612298 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9.jpg resize: (2160, 3840) 1360703246 -5.82125667473822 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190.jpg resize: (2160, 3840) 1360703244 -5.624997827587678 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13.jpg resize: (2160, 3840) 1360703241 -5.619216565335296 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669.jpg resize: (2160, 3840) 1360703240 -5.614674172318717 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081676_0.png resize: (228, 164) 1361294599 -3.138584261735826 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081677_0.png resize: (231, 173) 1361294600 -3.0510511105107194 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081679_0.png resize: (368, 328) 1361294601 -3.6782731205263968 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081683_0.png resize: (327, 367) 1361294602 -2.568515289613367 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081686_0.png resize: (357, 475) 1361294603 -3.3284712967996666 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081687_0.png resize: (248, 210) 1361294604 -3.6480981718032184 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081688_0.png resize: (178, 226) 1361294605 -3.595749189666106 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081689_0.png resize: (387, 622) 1361294606 -4.71399194934194 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081692_0.png resize: (105, 206) 1361294607 -4.625976416706392 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081693_0.png resize: (265, 464) 1361294608 -3.320912716942934 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081695_0.png resize: (470, 327) 1361294609 -1.8728696721265394 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081697_0.png resize: (79, 132) 1361294610 -2.9118366521390815 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081706_0.png resize: (210, 168) 1361294611 -3.933124369793956 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081707_0.png resize: (243, 395) 1361294612 -3.647779158438387 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081708_0.png resize: (65, 144) 1361294613 -3.4509385081356316 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081709_0.png resize: (368, 134) 1361294614 -4.068375336188963 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081713_0.png resize: (567, 429) 1361294615 -0.5073458479398237 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081717_0.png resize: (394, 469) 1361294616 -4.03120030615432 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081718_0.png resize: (474, 533) 1361294617 -3.149807864927457 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081719_0.png resize: (363, 233) 1361294618 -4.021803850692347 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081722_0.png resize: (252, 132) 1361294619 -2.215157238998719 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081724_0.png resize: (745, 733) 1361294621 -3.8360111567937714 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081725_0.png resize: (435, 521) 1361294622 -3.2740871575279695 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081726_0.png resize: (273, 180) 1361294623 -5.411745783094705 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081727_0.png resize: (337, 274) 1361294624 -3.484057416039825 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081729_0.png resize: (408, 667) 1361294625 -2.9629203129173587 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081730_0.png resize: (398, 231) 1361294626 -3.0636879640060672 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081735_0.png resize: (156, 181) 1361294627 -3.353570039058762 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081739_0.png resize: (164, 161) 1361294628 -1.379471640439271 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081740_0.png resize: (450, 187) 1361294629 -1.9353930566016013 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081742_0.png resize: (318, 149) 1361294630 -1.0567658855871715 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081743_0.png resize: (161, 227) 1361294631 -2.089019855185527 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081751_0.png resize: (130, 123) 1361294632 -4.344259313991474 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081753_0.png resize: (416, 302) 1361294633 -2.353223530765411 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081754_0.png resize: (340, 219) 1361294634 -2.3267774411929576 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081756_0.png resize: (317, 205) 1361294635 -4.1643683451491595 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081757_0.png resize: (285, 176) 1361294636 -0.06300360575863381 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081759_0.png resize: (81, 234) 1361294637 -2.5561989004731465 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081760_0.png resize: (146, 160) 1361294638 -4.796012354379597 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081761_0.png resize: (272, 142) 1361294639 -3.867409386488381 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081762_0.png resize: (142, 268) 1361294640 -4.483607584276706 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081763_0.png resize: (632, 578) 1361294641 -4.0199659611494 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081764_0.png resize: (475, 272) 1361294642 -3.677673634910714 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081765_0.png resize: (121, 52) 1361294643 -1.7990022751532486 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081767_0.png resize: (313, 159) 1361294644 0.25006930555196305 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081770_0.png resize: (298, 216) 1361294645 -1.1138987212938762 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081771_0.png resize: (268, 155) 1361294646 -3.6306909836071397 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081772_0.png resize: (435, 300) 1361294647 -2.193187972953554 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081773_0.png resize: (153, 155) 1361294648 -4.843969939729649 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081774_0.png resize: (196, 147) 1361294649 -3.6584911689145607 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081775_0.png resize: (122, 219) 1361294650 -2.7657915864198417 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081776_0.png resize: (643, 503) 1361294651 -3.744196657264655 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081777_0.png resize: (233, 319) 1361294652 -1.8640855717088254 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081778_0.png resize: (331, 384) 1361294653 -4.571167816763855 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081779_0.png resize: (154, 150) 1361294654 -3.6238725500104585 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081781_0.png resize: (141, 189) 1361294655 -2.9521019380438664 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081782_0.png resize: (413, 326) 1361294656 -0.06075624573420949 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081784_0.png resize: (243, 324) 1361294657 -0.8139822676817124 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081785_0.png resize: (375, 151) 1361294658 -4.716628622301409 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081786_0.png resize: (229, 172) 1361294659 -3.487377105697445 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081787_0.png resize: (185, 119) 1361294660 -3.977402824201684 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081789_0.png resize: (251, 336) 1361294661 -4.327351262821462 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081790_0.png resize: (218, 193) 1361294662 -3.179546320508477 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081793_0.png resize: (160, 186) 1361294663 -3.1264845771829344 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081794_0.png resize: (457, 246) 1361294664 -5.228764586824375 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081795_0.png resize: (578, 424) 1361294666 -3.382475656668347 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081796_0.png resize: (244, 339) 1361294667 -3.5912200994102688 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081798_0.png resize: (335, 316) 1361294668 -2.7042820461903556 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081800_0.png resize: (145, 93) 1361294669 -3.5257549877121606 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081801_0.png resize: (184, 119) 1361294670 -3.881322342640838 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081802_0.png resize: (160, 187) 1361294671 -3.6093767514705473 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081803_0.png resize: (140, 239) 1361294672 -2.4351697727786554 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081804_0.png resize: (275, 268) 1361294673 -3.6370529561120275 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081807_0.png resize: (302, 153) 1361294674 -1.8096026643511773 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081808_0.png resize: (106, 157) 1361294675 -2.60719497603805 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081809_0.png resize: (451, 557) 1361294676 -1.924349732734203 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081811_0.png resize: (116, 121) 1361294677 -2.6081851869762067 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081813_0.png resize: (99, 87) 1361294678 -3.689706321044311 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081814_0.png resize: (152, 155) 1361294679 -4.022431923917012 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081815_0.png resize: (408, 367) 1361294680 -3.382712267368869 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081816_0.png resize: (285, 298) 1361294681 -1.2021210888430394 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081817_0.png resize: (130, 325) 1361294682 -2.701067896825024 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081824_0.png resize: (234, 103) 1361294683 -3.812511287936349 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081825_0.png resize: (185, 179) 1361294684 -3.2946204395849117 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081826_0.png resize: (458, 534) 1361294685 -3.726267981660362 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081828_0.png resize: (185, 146) 1361294686 -3.4446497534211735 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081829_0.png resize: (272, 312) 1361294687 -1.172228532468909 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081831_0.png resize: (289, 183) 1361294688 -3.8933369135333042 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081833_0.png resize: (89, 165) 1361294689 -2.63669104640024 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081834_0.png resize: (234, 362) 1361294690 -4.165551398794105 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081835_0.png resize: (85, 144) 1361294691 -2.506685411202162 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081836_0.png resize: (185, 101) 1361294692 -2.5899429218304455 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081837_0.png resize: (159, 169) 1361294693 -3.319726343724207 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081838_0.png resize: (111, 128) 1361294694 -2.8711552520001637 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081839_0.png resize: (363, 210) 1361294695 -3.529402846657589 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081840_0.png resize: (395, 209) 1361294696 -3.9509306794725414 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081841_0.png resize: (156, 69) 1361294697 -3.719892189940331 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081842_0.png resize: (322, 338) 1361294698 -2.623203307543149 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081844_0.png resize: (102, 135) 1361294699 -3.1948547996308383 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081845_0.png resize: (246, 214) 1361294700 -4.403984346687945 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081846_0.png resize: (365, 314) 1361294701 -3.9796538616600072 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081847_0.png resize: (172, 210) 1361294702 2.1464744690238984 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081849_0.png resize: (130, 150) 1361294703 -3.9433317739495295 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081850_0.png resize: (464, 239) 1361294704 -3.8011791210099632 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081853_0.png resize: (147, 197) 1361294705 -4.016823084211786 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081854_0.png resize: (154, 267) 1361294706 -3.7808584723110323 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081856_0.png resize: (198, 193) 1361294707 -4.049850642670738 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081857_0.png resize: (400, 139) 1361294708 -3.6793026408786593 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081858_0.png resize: (270, 201) 1361294709 -3.403010955972556 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081859_0.png resize: (402, 265) 1361294710 -1.258553373467425 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081860_0.png resize: (473, 432) 1361294711 0.7594391988835477 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081861_0.png resize: (375, 393) 1361294712 -0.8404759833785539 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081862_0.png resize: (112, 201) 1361294713 -2.886711511000395 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081863_0.png resize: (704, 634) 1361294714 -3.440018709153591 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081866_0.png resize: (97, 112) 1361294715 -2.182998819049817 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081867_0.png resize: (269, 356) 1361294716 -3.9113531979127756 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081868_0.png resize: (204, 221) 1361294717 -3.694168832011243 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081869_0.png resize: (156, 129) 1361294718 -2.793003588450493 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081870_0.png resize: (139, 116) 1361294719 -2.9768375796103013 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081873_0.png resize: (212, 229) 1361294720 -4.033506297280287 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081874_0.png resize: (595, 164) 1361294721 -2.4315041279781315 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081876_0.png resize: (198, 170) 1361294722 0.020217092182996436 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081877_0.png resize: (361, 276) 1361294723 -1.6439362928120655 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081878_0.png resize: (140, 199) 1361294724 -3.0902710865057257 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081879_0.png resize: (858, 660) 1361294725 -4.0738119327218065 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081880_0.png resize: (547, 342) 1361294726 -4.178943722490586 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081881_0.png resize: (367, 210) 1361294727 -3.7690231058167756 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081882_0.png resize: (317, 255) 1361294728 -2.2410560900493577 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081884_0.png resize: (153, 105) 1361294729 -2.522496892114762 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081885_0.png resize: (338, 217) 1361294730 -0.5529775500462801 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081886_0.png resize: (322, 318) 1361294731 -4.35947531148277 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081888_0.png resize: (178, 181) 1361294732 -2.629102563666883 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081889_0.png resize: (617, 318) 1361294733 -3.5094179097390796 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081890_0.png resize: (407, 256) 1361294734 -2.5415216599844963 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081891_0.png resize: (144, 134) 1361294735 -1.9532383089820275 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081893_0.png resize: (178, 188) 1361294736 -1.440861022139752 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081895_0.png resize: (51, 116) 1361294737 -0.9510092535718395 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081896_0.png resize: (154, 109) 1361294738 -2.382874130860183 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081899_0.png resize: (135, 267) 1361294739 1.2420282371267417 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081900_0.png resize: (264, 177) 1361294740 -2.9902346002410165 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081901_0.png resize: (291, 305) 1361294741 -3.1955545156982024 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081905_0.png resize: (331, 215) 1361294742 -0.9241598172629512 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081907_0.png resize: (166, 176) 1361294743 -2.149255689857006 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081909_0.png resize: (315, 328) 1361294744 -4.389558945381368 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081910_0.png resize: (126, 278) 1361294745 1.2946383006563007 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081911_0.png resize: (408, 211) 1361294746 -2.946132519416394 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081914_0.png resize: (155, 111) 1361294747 -2.5782601031157877 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081915_0.png resize: (152, 126) 1361294748 -2.2234840127349824 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081916_0.png resize: (383, 386) 1361294750 -2.144412217536769 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081917_0.png resize: (160, 141) 1361294751 -2.0420559366591555 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081918_0.png resize: (170, 191) 1361294752 -1.8226059711153928 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081920_0.png resize: (267, 312) 1361294753 -3.260913545472915 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081921_0.png resize: (560, 551) 1361294754 -4.570877212143427 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081922_0.png resize: (162, 180) 1361294755 -2.9589502985597003 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081927_0.png resize: (143, 137) 1361294756 -1.5138031323762908 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081928_0.png resize: (269, 158) 1361294757 -3.862164722432331 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081930_0.png resize: (206, 268) 1361294758 -0.7537026838572373 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081931_0.png resize: (105, 250) 1361294760 -3.89436518591097 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081932_0.png resize: (133, 209) 1361294761 -3.0899709666031576 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081934_0.png resize: (183, 194) 1361294762 0.41290468746368186 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081936_0.png resize: (357, 206) 1361294763 -3.666046841617068 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081937_0.png resize: (374, 481) 1361294764 -0.36360549062382963 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081938_0.png resize: (273, 406) 1361294765 -3.948546739180399 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081941_0.png resize: (63, 54) 1361294766 -2.5252909118145954 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081942_0.png resize: (149, 117) 1361294767 -0.1973874621152064 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081945_0.png resize: (115, 161) 1361294768 -2.858117717836655 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081948_0.png resize: (198, 100) 1361294769 -3.499086930096838 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081950_0.png resize: (249, 250) 1361294770 -4.630062657164775 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081951_0.png resize: (212, 232) 1361294771 -3.1233781718256517 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081952_0.png resize: (335, 346) 1361294772 -0.10786722030404847 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081955_0.png resize: (210, 245) 1361294773 -3.778781818799689 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081956_0.png resize: (253, 188) 1361294774 -4.155168541528555 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081958_0.png resize: (311, 297) 1361294775 -3.4427004019076244 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081959_0.png resize: (244, 202) 1361294776 -5.044355385080216 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081960_0.png resize: (121, 156) 1361294777 -1.1059991099880757 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081961_0.png resize: (499, 346) 1361294778 -2.2676040500265624 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081963_0.png resize: (115, 61) 1361294779 -3.1943559353057878 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081964_0.png resize: (188, 273) 1361294780 0.6090747837148536 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081966_0.png resize: (284, 409) 1361294781 -2.192287326806664 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081968_0.png resize: (237, 100) 1361294782 -3.122695788053208 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081970_0.png resize: (157, 177) 1361294783 -2.554813251525916 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081972_0.png resize: (238, 207) 1361294784 -2.3322377795208755 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081973_0.png resize: (274, 338) 1361294785 0.28052918052716874 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081974_0.png resize: (140, 153) 1361294786 -3.5044134971852685 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081976_0.png resize: (328, 296) 1361294787 -4.829666187725468 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081977_0.png resize: (224, 400) 1361294788 -0.6566432930253935 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081979_0.png resize: (175, 137) 1361294789 -2.15176303497719 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081982_0.png resize: (444, 409) 1361294790 -2.7308487896461773 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081985_0.png resize: (335, 400) 1361294791 -3.855376126758452 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081986_0.png resize: (111, 163) 1361294792 -3.293357637491555 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081988_0.png resize: (169, 80) 1361294793 -3.3965016658361677 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081993_0.png resize: (160, 138) 1361294794 -0.9674407592724227 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081996_0.png resize: (136, 77) 1361294795 -0.2704578832674634 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081998_0.png resize: (247, 256) 1361294796 -2.9870993667786485 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082000_0.png resize: (164, 184) 1361294797 -2.9480153560540088 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082001_0.png resize: (285, 251) 1361294798 -0.6914731388349016 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082003_0.png resize: (185, 270) 1361294799 -2.3406368048011967 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082005_0.png resize: (761, 607) 1361294800 -4.733996802199937 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082006_0.png resize: (305, 294) 1361294801 -3.1823711584537793 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082007_0.png resize: (287, 368) 1361294802 -2.1244023704654285 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082008_0.png resize: (114, 90) 1361294803 -2.225025991756324 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082009_0.png resize: (267, 258) 1361294804 -4.273436956572408 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082011_0.png resize: (178, 244) 1361294805 -3.134020915878078 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082012_0.png resize: (229, 88) 1361294806 -3.826773173044721 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082015_0.png resize: (411, 320) 1361294807 -4.113282217697181 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082016_0.png resize: (89, 133) 1361294808 -0.19886405714401587 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082017_0.png resize: (285, 170) 1361294809 -4.069138533296172 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082018_0.png resize: (955, 620) 1361294810 -3.755084656346811 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082019_0.png resize: (172, 191) 1361294811 -4.344185718819326 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082021_0.png resize: (149, 117) 1361294812 -3.718960873530334 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082022_0.png resize: (255, 91) 1361294813 -3.2655532545897437 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082025_0.png resize: (283, 122) 1361294814 -3.4814019989907394 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082026_0.png resize: (164, 436) 1361294815 -4.3716443145996005 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082027_0.png resize: (472, 449) 1361294816 -3.0549474222178734 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082028_0.png resize: (131, 142) 1361294817 -3.494120815884307 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082029_0.png resize: (184, 145) 1361294818 -2.0049739304356664 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082030_0.png resize: (179, 131) 1361294819 -3.869119302535025 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082032_0.png resize: (153, 160) 1361294820 -3.3491189450580823 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082035_0.png resize: (284, 193) 1361294821 -4.224512991867653 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082036_0.png resize: (206, 181) 1361294822 -3.6238183690506536 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082038_0.png resize: (206, 127) 1361294823 -3.7685145971070857 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082039_0.png resize: (94, 202) 1361294824 -3.3989431091963556 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082041_0.png resize: (290, 297) 1361294825 -3.619899696590208 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082044_0.png resize: (171, 141) 1361294826 -3.851726775388475 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082045_0.png resize: (107, 185) 1361294827 -3.813050753081789 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082046_0.png resize: (353, 498) 1361294828 -4.044289539331396 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082047_0.png resize: (303, 234) 1361294829 -2.8109255585243145 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082049_0.png resize: (305, 226) 1361294830 -3.1375712134842213 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082052_0.png resize: (147, 185) 1361294831 -2.545785345272639 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082055_0.png resize: (186, 94) 1361294832 -2.2437608299634992 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082057_0.png resize: (184, 174) 1361294833 -3.8118514221650135 treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082058_0.png resize: (355, 344) 1361294834 -2.251264468021452 treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082059_0.png resize: (410, 315) 1361294835 -2.79115927006858 treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082060_0.png resize: (256, 111) 1361294836 -3.775646516889349 treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082063_0.png resize: (323, 139) 1361294838 -3.7810225919348026 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082065_0.png resize: (361, 302) 1361294839 -1.7642514335888848 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082066_0.png resize: (254, 188) 1361294840 -4.46700557867649 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082068_0.png resize: (94, 143) 1361294841 -2.616576951427951 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082070_0.png resize: (316, 302) 1361294842 -3.4943408290179434 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082074_0.png resize: (366, 708) 1361294843 0.9623716468585536 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082075_0.png resize: (300, 264) 1361294844 -3.7876358550807816 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082076_0.png resize: (446, 132) 1361294845 -3.5679497338345194 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082077_0.png resize: (214, 96) 1361294846 -2.515796313067225 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082078_0.png resize: (295, 149) 1361294847 -3.3053252233324475 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082081_0.png resize: (164, 197) 1361294848 1.0014658321660654 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082083_0.png resize: (292, 319) 1361294849 -2.7901497660843995 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082084_0.png resize: (166, 323) 1361294850 -1.7718197983386275 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082086_0.png resize: (238, 156) 1361294851 -1.0659937412103295 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082089_0.png resize: (152, 224) 1361294852 -1.1093820693165501 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082091_0.png resize: (140, 116) 1361294853 -2.7942278024943965 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082092_0.png resize: (197, 240) 1361294854 2.1705531610810356 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082093_0.png resize: (68, 226) 1361294855 -3.0872812021249607 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082094_0.png resize: (206, 159) 1361294856 -3.098171649828446 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082095_0.png resize: (111, 163) 1361294857 -4.119140688989849 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082098_0.png resize: (275, 126) 1361294858 -2.638519828712926 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082101_0.png resize: (177, 185) 1361294859 -2.364254352258205 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082102_0.png resize: (151, 144) 1361294860 -2.5109845393388217 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082104_0.png resize: (173, 82) 1361294861 -3.32562442450068 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082106_0.png resize: (432, 360) 1361294862 -3.3692037214317185 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082108_0.png resize: (210, 189) 1361294863 -3.1138472817520757 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082110_0.png resize: (247, 271) 1361294864 -2.070665999361714 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082111_0.png resize: (116, 117) 1361294865 -2.174717637135822 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082112_0.png resize: (182, 190) 1361294866 -3.4774799143442454 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082113_0.png resize: (215, 105) 1361294867 -2.4719125793301693 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082114_0.png resize: (271, 195) 1361294868 -3.4005914912025372 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082115_0.png resize: (151, 217) 1361294869 -4.511151768973856 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082116_0.png resize: (108, 200) 1361294870 -3.6886011997704378 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082117_0.png resize: (67, 80) 1361294871 -0.5784000455056821 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082118_0.png resize: (85, 70) 1361294872 -4.044863848069835 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082119_0.png resize: (136, 296) 1361294873 -3.023753275834646 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082120_0.png resize: (444, 355) 1361294874 -3.526105690819881 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082122_0.png resize: (345, 555) 1361294875 0.5648821066638254 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082125_0.png resize: (360, 336) 1361294876 -2.7901401883330625 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082126_0.png resize: (150, 154) 1361294877 -3.6403611943238334 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082127_0.png resize: (423, 583) 1361294878 -1.7761248150404716 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082130_0.png resize: (153, 196) 1361294879 -3.2457496486465 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082131_0.png resize: (121, 163) 1361294880 -3.9714798484976446 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082132_0.png resize: (543, 435) 1361294881 -1.1501535177088782 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082134_0.png resize: (118, 303) 1361294882 -1.8740393972770777 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082143_0.png resize: (203, 148) 1361294883 -2.553536790716226 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082148_0.png resize: (335, 854) 1361294884 -4.187432193387793 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082149_0.png resize: (308, 504) 1361294885 -2.706153053854192 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082151_0.png resize: (121, 177) 1361294886 -3.1721720638394237 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082152_0.png resize: (283, 239) 1361294887 -3.4631037334157417 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082155_0.png resize: (155, 203) 1361294888 -4.059714354538051 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082156_0.png resize: (373, 392) 1361294889 -3.8918936837492706 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082157_0.png resize: (149, 132) 1361294890 -1.5209997106459339 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082159_0.png resize: (135, 139) 1361294891 -3.4714412757981687 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082161_0.png resize: (172, 180) 1361294892 -2.0618532131627596 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082163_0.png resize: (502, 280) 1361294893 -3.1007775990153648 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082164_0.png resize: (299, 291) 1361294894 -3.4588201551858178 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082169_0.png resize: (112, 135) 1361294895 -1.3642116463372627 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082170_0.png resize: (243, 207) 1361294896 -3.0841790033717116 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082173_0.png resize: (133, 119) 1361294897 -3.312667282205764 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082178_0.png resize: (314, 398) 1361294898 -3.498917524532929 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082179_0.png resize: (484, 226) 1361294899 -2.5438185358374072 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082180_0.png resize: (212, 308) 1361294900 -2.621615271257818 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082181_0.png resize: (412, 497) 1361294901 0.07313130193020083 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082185_0.png resize: (292, 112) 1361294902 -2.24011785651973 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082190_0.png resize: (77, 138) 1361294903 -1.7476790247161584 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082191_0.png resize: (550, 708) 1361294904 -0.8090852240843179 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082193_0.png resize: (270, 147) 1361294905 -2.9016382354487424 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082194_0.png resize: (566, 612) 1361294906 -1.8964475217152934 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082195_0.png resize: (236, 316) 1361294907 -2.6113410189507897 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082196_0.png resize: (267, 269) 1361294908 0.6954154645560939 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082197_0.png resize: (492, 859) 1361294909 -3.2570824274629673 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082201_0.png resize: (341, 587) 1361294910 -0.49631984010093455 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082202_0.png resize: (475, 430) 1361294911 -4.653673275972614 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081678_0.png resize: (219, 346) 1361294931 -4.397357017627244 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081681_0.png resize: (197, 129) 1361294932 -3.9118642336341636 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081682_0.png resize: (652, 544) 1361294934 -5.109917145958757 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081721_0.png resize: (190, 193) 1361294935 -3.10602282366399 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081733_0.png resize: (128, 90) 1361294936 -2.2092181680087197 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081738_0.png resize: (171, 151) 1361294937 1.0932835453695144 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081741_0.png resize: (152, 193) 1361294938 -2.891618994549307 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081749_0.png resize: (146, 88) 1361294939 -3.5782625697297665 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081750_0.png resize: (252, 173) 1361294940 -3.0630052371391936 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081783_0.png resize: (132, 134) 1361294941 -3.8437906184683377 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081799_0.png resize: (81, 138) 1361294942 -2.9008943295882976 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081805_0.png resize: (212, 245) 1361294943 -2.572294167280519 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081812_0.png resize: (333, 383) 1361294944 -3.8641995144208976 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081827_0.png resize: (895, 782) 1361294945 -4.474420321855375 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081832_0.png resize: (107, 251) 1361294946 -2.1288276173483163 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081843_0.png resize: (183, 193) 1361294947 -3.7832868383268194 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081851_0.png resize: (170, 191) 1361294948 -3.583085193282535 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081855_0.png resize: (213, 111) 1361294949 -2.7269995289618207 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081887_0.png resize: (200, 178) 1361294950 -3.807900051153039 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081897_0.png resize: (152, 138) 1361294951 -3.9633838164569197 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081903_0.png resize: (139, 165) 1361294952 -2.4525951955972047 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081904_0.png resize: (192, 132) 1361294953 -3.421917694001319 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081906_0.png resize: (156, 140) 1361294954 -4.055699051218169 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081912_0.png resize: (182, 126) 1361294955 -2.746352544787412 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081919_0.png resize: (485, 188) 1361294956 -3.1562496698777966 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081925_0.png resize: (167, 242) 1361294957 -4.161323513056175 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081929_0.png resize: (96, 103) 1361294958 -2.152163002616448 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081939_0.png resize: (188, 196) 1361294960 -3.7977486406234346 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081975_0.png resize: (141, 168) 1361294961 -2.7324099830424613 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082010_0.png resize: (246, 148) 1361294962 -2.3544781940945363 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082013_0.png resize: (179, 179) 1361294963 -2.809973579946474 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082014_0.png resize: (577, 367) 1361294965 -3.9976171915896477 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082023_0.png resize: (485, 296) 1361294966 -3.8128788302531986 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082031_0.png resize: (220, 128) 1361294967 -3.4699406920742066 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082033_0.png resize: (337, 400) 1361294968 -3.521344903647663 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082048_0.png resize: (217, 260) 1361294969 -3.5150744873283757 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082056_0.png resize: (168, 177) 1361294970 -3.3384685133161778 treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082064_0.png resize: (324, 139) 1361294971 -3.820057241173354 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082085_0.png resize: (206, 169) 1361294972 -2.7391378886079205 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082097_0.png resize: (132, 115) 1361294973 -1.3128640667210665 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082136_0.png resize: (188, 213) 1361294974 -2.463717578774128 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082162_0.png resize: (305, 634) 1361294975 -3.114485955503667 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082167_0.png resize: (504, 255) 1361294976 -4.494393823313165 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082176_0.png resize: (265, 210) 1361294977 -4.07301863320059 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082182_0.png resize: (191, 136) 1361294978 -3.2786037786263 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081703_0.png resize: (301, 214) 1361294983 -4.47807591331375 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081711_0.png resize: (122, 162) 1361294984 -4.438721036671295 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081736_0.png resize: (128, 128) 1361294985 -3.6880628179884263 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081933_0.png resize: (288, 134) 1361294986 -4.026273940137195 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081983_0.png resize: (232, 253) 1361294987 -2.4449504601519583 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082171_0.png resize: (100, 151) 1361294988 -4.035060294541831 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081674_0.png resize: (409, 274) 1361295350 -4.677930205046594 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081675_0.png resize: (498, 400) 1361295351 -5.199485658781949 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081680_0.png resize: (310, 287) 1361295352 -3.068245906128729 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081685_0.png resize: (376, 646) 1361295353 -3.483488741465115 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081690_0.png resize: (320, 300) 1361295354 -4.637465436350446 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081691_0.png resize: (253, 277) 1361295355 -4.4818280176848 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081694_0.png resize: (345, 223) 1361295356 -4.0791948613485856 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081696_0.png resize: (420, 421) 1361295357 -3.7456466590926913 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081698_0.png resize: (331, 195) 1361295358 -4.329747565347955 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081699_0.png resize: (494, 365) 1361295359 -4.203400576523183 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081701_0.png resize: (341, 633) 1361295360 -4.446559000798695 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081702_0.png resize: (345, 326) 1361295361 -3.7475817300320493 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081704_0.png resize: (202, 251) 1361295362 -2.114886305356461 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081705_0.png resize: (405, 408) 1361295363 -3.6035330290331573 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081710_0.png resize: (308, 435) 1361295364 -3.8260274148115245 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081712_0.png resize: (265, 237) 1361295365 -4.507550869244092 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081714_0.png resize: (693, 193) 1361295366 -3.5078951691311255 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081715_0.png resize: (237, 100) 1361295367 -3.9628457876850187 treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081716_0.png resize: (257, 246) 1361295368 -4.492255262797408 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081720_0.png resize: (537, 306) 1361295369 -4.49854945787223 treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081723_0.png resize: (375, 472) 1361295370 -1.2639747037755855 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081728_0.png resize: (321, 268) 1361295371 -3.8633042703119456 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081731_0.png resize: (88, 241) 1361295372 -2.7492909761527944 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081732_0.png resize: (140, 112) 1361295373 -3.710847245687666 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081734_0.png resize: (764, 617) 1361295374 -4.496489066251429 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081744_0.png resize: (374, 452) 1361295375 -4.5325057658780326 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081745_0.png resize: (135, 188) 1361295376 -2.792716111774616 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081746_0.png resize: (453, 606) 1361295377 -3.413194921112704 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081748_0.png resize: (421, 573) 1361295378 -3.6624048637815543 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081752_0.png resize: (352, 419) 1361295379 -3.1678779904231025 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081755_0.png resize: (340, 232) 1361295380 -3.08768815725219 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081758_0.png resize: (630, 422) 1361295381 -3.217941142634255 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081768_0.png resize: (323, 233) 1361295382 -3.2819481804068724 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081769_0.png resize: (202, 588) 1361295383 -4.620840442161258 treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081780_0.png resize: (581, 420) 1361295385 -3.1640755881841023 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081788_0.png resize: (370, 468) 1361295386 -4.604279137825379 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081797_0.png resize: (258, 141) 1361295387 -3.952471231411861 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081806_0.png resize: (218, 148) 1361295388 -4.19962621310183 treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081810_0.png resize: (234, 225) 1361295389 -2.594060533494018 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081818_0.png resize: (380, 182) 1361295390 -4.41049459405802 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081819_0.png resize: (440, 473) 1361295391 -4.862932660357625 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081820_0.png resize: (188, 171) 1361295392 -4.062571081323227 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081822_0.png resize: (387, 405) 1361295393 -4.50464331310979 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081823_0.png resize: (82, 136) 1361295395 -2.7799892075619046 treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081830_0.png resize: (262, 471) 1361295396 -4.532594945901878 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081848_0.png resize: (340, 575) 1361295397 -4.794001430032586 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081864_0.png resize: (237, 195) 1361295399 -3.3090964904157225 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081865_0.png resize: (80, 140) 1361295400 -2.993077263205698 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081871_0.png resize: (494, 319) 1361295401 -3.605107739281923 treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081872_0.png resize: (272, 229) 1361295403 -4.571081647553526 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081875_0.png resize: (282, 335) 1361295404 -2.9588337356349825 treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081883_0.png resize: (547, 206) 1361295405 -3.831654586089611 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081892_0.png resize: (315, 400) 1361295407 -3.4821465600628847 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081894_0.png resize: (294, 253) 1361295408 -3.8791555097647077 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081902_0.png resize: (450, 487) 1361295409 -3.7970245334463026 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081908_0.png resize: (226, 241) 1361295411 -3.8581605624503927 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081913_0.png resize: (601, 427) 1361295412 -4.019446231086685 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081924_0.png resize: (277, 401) 1361295413 -3.5622879031410117 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081926_0.png resize: (178, 297) 1361295415 -3.6715714026524133 treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081935_0.png resize: (165, 286) 1361295416 -4.009652328255403 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081940_0.png resize: (215, 270) 1361295417 -3.5032719845801075 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081944_0.png resize: (569, 227) 1361295419 -3.092636571988208 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081949_0.png resize: (229, 567) 1361295421 -3.9925240207041353 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081953_0.png resize: (249, 189) 1361295422 -4.024002221100497 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081954_0.png resize: (554, 486) 1361295424 -3.6297060881529855 treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081957_0.png resize: (499, 456) 1361295426 -4.1760011536179364 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081962_0.png resize: (378, 520) 1361295427 -3.4388993702192887 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081965_0.png resize: (461, 264) 1361295429 -4.410973886629707 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081969_0.png resize: (546, 354) 1361295431 -4.790320940545826 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081971_0.png resize: (314, 194) 1361295432 -3.7795865881232746 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081978_0.png resize: (631, 757) 1361295435 -4.122084348677987 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081980_0.png resize: (572, 369) 1361295437 -4.671038517172856 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081981_0.png resize: (461, 450) 1361295438 -4.26214549244935 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081984_0.png resize: (231, 275) 1361295440 -3.358129597770239 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081987_0.png resize: (363, 281) 1361295442 -4.404726658409327 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081989_0.png resize: (165, 296) 1361295443 -3.421096557168832 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081990_0.png resize: (111, 98) 1361295444 -3.715136658388757 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081991_0.png resize: (421, 395) 1361295447 -3.376380696785219 treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081992_0.png resize: (528, 449) 1361295448 -2.772564291819298 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081994_0.png resize: (298, 581) 1361295449 -4.163873834151568 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081995_0.png resize: (395, 359) 1361295452 -3.367841654445558 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081997_0.png resize: (541, 395) 1361295453 -4.461017097886816 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081999_0.png resize: (475, 434) 1361295454 -3.4991043363995415 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082002_0.png resize: (629, 353) 1361295457 -2.4564745060372166 treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082004_0.png resize: (327, 317) 1361295458 -4.342629338233703 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082020_0.png resize: (66, 171) 1361295459 -2.096085953859388 treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082024_0.png resize: (234, 222) 1361295462 -2.9618080008557697 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082034_0.png resize: (857, 175) 1361295463 -3.7633266236837213 treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082037_0.png resize: (234, 167) 1361295464 -2.713590394387091 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082040_0.png resize: (811, 524) 1361295467 -4.346308673565398 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082042_0.png resize: (144, 122) 1361295468 -3.1182571217771202 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082043_0.png resize: (407, 390) 1361295469 -4.2635890958232014 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082050_0.png resize: (374, 394) 1361295472 -3.97659063950323 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082051_0.png resize: (286, 192) 1361295473 -4.080509070379204 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082053_0.png resize: (320, 287) 1361295474 -3.202824315828507 treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082054_0.png resize: (150, 169) 1361295477 -2.897080398091289 treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082061_0.png resize: (344, 342) 1361295478 -4.326041551184093 treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082062_0.png resize: (692, 248) 1361295481 -5.27963451873516 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082067_0.png resize: (325, 362) 1361295482 -3.9872984881447033 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082069_0.png resize: (437, 276) 1361295483 -4.427223206724609 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082071_0.png resize: (1010, 1025) 1361295486 -4.534845063827814 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082072_0.png resize: (503, 373) 1361295487 -3.6987216476069165 treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082073_0.png resize: (394, 128) 1361295488 -3.934850727504721 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082080_0.png resize: (307, 563) 1361295491 -2.5929171048666437 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082082_0.png resize: (365, 708) 1361295492 -4.520095146918145 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082087_0.png resize: (740, 177) 1361295493 -4.058382607517979 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082088_0.png resize: (262, 372) 1361295496 -2.4630460525174502 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082090_0.png resize: (297, 309) 1361295497 -4.707177557075727 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082096_0.png resize: (239, 366) 1361295498 -3.6737657416852523 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082100_0.png resize: (79, 202) 1361295501 -2.1337321339906907 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082103_0.png resize: (181, 207) 1361295503 -3.2519319693749136 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082105_0.png resize: (244, 158) 1361295504 -3.4832098562238 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082109_0.png resize: (347, 437) 1361295507 -3.625497782990658 treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082121_0.png resize: (253, 149) 1361295508 -4.477890878656282 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082123_0.png resize: (184, 677) 1361295509 -4.829053462985799 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082124_0.png resize: (506, 365) 1361295512 -3.5041012077456575 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082128_0.png resize: (648, 925) 1361295513 -4.601188776753559 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082133_0.png resize: (460, 406) 1361295514 -3.87541688307677 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082135_0.png resize: (486, 256) 1361295517 -2.9804181235070435 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082137_0.png resize: (126, 249) 1361295518 -3.0737327074180536 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082138_0.png resize: (442, 276) 1361295519 -4.280109883591603 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082139_0.png resize: (219, 251) 1361295522 -1.3168700507396869 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082140_0.png resize: (550, 578) 1361295524 -2.994195150515977 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082141_0.png resize: (252, 531) 1361295526 -4.249784382782718 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082144_0.png resize: (463, 403) 1361295527 -4.562863249308757 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082145_0.png resize: (521, 397) 1361295529 -3.981186554126038 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082146_0.png resize: (324, 231) 1361295531 -4.0694965936258 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082147_0.png resize: (373, 439) 1361295532 -3.503091191397265 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082150_0.png resize: (220, 181) 1361295534 -4.373549499217538 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082153_0.png resize: (177, 322) 1361295536 -2.822942510053379 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082154_0.png resize: (324, 363) 1361295537 -3.7855365383731523 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082158_0.png resize: (123, 232) 1361295538 -3.0955555088224145 treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082160_0.png resize: (299, 260) 1361295540 -3.6827048242014206 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082165_0.png resize: (113, 136) 1361295541 -3.7970383536777033 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082166_0.png resize: (159, 149) 1361295542 -2.248145935606651 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082168_0.png resize: (236, 413) 1361295544 -2.8003598546685704 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082172_0.png resize: (197, 396) 1361295545 -3.0104542558831824 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082174_0.png resize: (412, 425) 1361295546 -4.712252535288357 treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082175_0.png resize: (585, 422) 1361295548 -4.131628887251362 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082183_0.png resize: (294, 355) 1361295549 -4.812685203449776 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082184_0.png resize: (796, 461) 1361295550 -4.305935352453246 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082188_0.png resize: (640, 598) 1361295552 -4.190781781024321 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082192_0.png resize: (343, 449) 1361295553 -4.927760747351369 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082198_0.png resize: (564, 243) 1361295554 -3.0253547869506723 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082199_0.png resize: (336, 405) 1361295556 -3.8963687917766046 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082200_0.png resize: (272, 252) 1361295557 -4.7995225382805025 treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082203_0.png resize: (327, 337) 1361295558 -3.5696007215897634 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081792_0.png resize: (191, 159) 1361295629 -3.4489814841422457 treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081898_0.png resize: (421, 491) 1361295630 -3.8119230972777176 treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081923_0.png resize: (176, 140) 1361295632 -2.838508038017616 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081946_0.png resize: (209, 328) 1361295633 -3.4958984060631315 treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082079_0.png resize: (259, 222) 1361295634 -4.500646740263871 treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082129_0.png resize: (176, 161) 1361295636 -4.353684876036333 treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082142_0.png resize: (245, 257) 1361295637 -3.033052763643312 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082177_0.png resize: (454, 223) 1361295638 -3.3723912877483717 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082189_0.png resize: (70, 141) 1361295639 -2.6233388370981143 treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081684_0.png resize: (188, 170) 1361295667 -1.0413411101838295 treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081700_0.png resize: (284, 484) 1361295698 -3.3244673282561723 treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081737_0.png resize: (275, 220) 1361295699 -4.198291191953827 treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081747_0.png resize: (183, 182) 1361295700 -3.366654824870328 treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081766_0.png resize: (527, 291) 1361295701 -4.514776088135538 treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081791_0.png resize: (150, 442) 1361295702 -2.8795822292468904 treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081821_0.png resize: (376, 539) 1361295703 -3.9400371065797852 treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081852_0.png resize: (102, 446) 1361295704 -0.6746882017575463 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081943_0.png resize: (257, 292) 1361295705 -4.161003984465599 treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081947_0.png resize: (191, 180) 1361295707 -2.2583374180985287 treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081967_0.png resize: (258, 473) 1361295708 -3.9168814524217646 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082099_0.png resize: (141, 199) 1361295709 -2.428078791228136 treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082107_0.png resize: (150, 390) 1361295710 -3.775336318370663 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082186_0.png resize: (409, 187) 1361295711 -4.471045068164145 treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082187_0.png resize: (352, 263) 1361295712 -3.3162082522486056 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 567 time used for this insertion : 0.05569267272949219 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 567 time used for this insertion : 0.12111711502075195 save missing photos in datou_result : time spend for datou_step_exec : 182.56450390815735 time spend to save output : 0.21216273307800293 total time spend for step 6 : 182.77666664123535 step7:brightness Tue May 27 13:54:10 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b.jpg treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff.jpg treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2.jpg treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1.jpg treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7.jpg treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d.jpg treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8.jpg treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056.jpg treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18.jpg treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1.jpg treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772.jpg treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8.jpg treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463.jpg treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af.jpg treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f.jpg treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151.jpg treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6.jpg treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4.jpg treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4.jpg treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795.jpg treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825.jpg treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb.jpg treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849.jpg treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838.jpg treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07.jpg treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04.jpg treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471.jpg treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528.jpg treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc.jpg treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa.jpg treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f.jpg treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757.jpg treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b.jpg treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9.jpg treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190.jpg treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13.jpg treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669.jpg treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081676_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081677_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081679_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081683_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081686_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081687_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081688_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081689_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081692_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081693_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081695_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081697_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081706_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081707_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081708_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081709_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081713_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081717_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081718_0.png treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081719_0.png treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081722_0.png treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081724_0.png treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081725_0.png treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081726_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081727_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081729_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081730_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081735_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081739_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081740_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081742_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081743_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081751_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081753_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081754_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081756_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081757_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081759_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081760_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081761_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081762_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081763_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081764_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081765_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081767_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081770_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081771_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081772_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081773_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081774_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081775_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081776_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081777_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081778_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081779_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081781_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081782_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081784_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081785_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081786_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081787_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081789_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081790_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081793_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081794_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081795_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081796_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081798_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081800_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081801_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081802_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081803_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081804_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081807_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081808_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081809_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081811_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081813_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081814_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081815_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081816_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081817_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081824_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081825_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081826_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081828_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081829_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081831_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081833_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081834_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081835_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081836_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081837_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081838_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081839_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081840_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081841_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081842_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081844_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081845_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081846_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081847_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081849_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081850_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081853_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081854_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081856_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081857_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081858_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081859_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081860_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081861_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081862_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081863_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081866_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081867_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081868_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081869_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081870_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081873_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081874_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081876_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081877_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081878_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081879_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081880_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081881_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081882_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081884_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081885_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081886_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081888_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081889_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081890_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081891_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081893_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081895_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081896_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081899_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081900_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081901_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081905_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081907_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081909_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081910_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081911_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081914_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081915_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081916_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081917_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081918_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081920_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081921_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081922_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081927_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081928_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081930_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081931_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081932_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081934_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081936_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081937_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081938_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081941_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081942_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081945_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081948_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081950_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081951_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081952_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081955_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081956_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081958_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081959_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081960_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081961_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081963_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081964_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081966_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081968_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081970_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081972_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081973_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081974_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081976_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081977_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081979_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081982_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081985_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081986_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081988_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081993_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081996_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081998_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082000_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082001_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082003_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082005_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082006_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082007_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082008_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082009_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082011_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082012_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082015_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082016_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082017_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082018_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082019_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082021_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082022_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082025_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082026_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082027_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082028_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082029_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082030_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082032_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082035_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082036_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082038_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082039_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082041_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082044_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082045_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082046_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082047_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082049_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082052_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082055_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082057_0.png treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082058_0.png treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082059_0.png treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082060_0.png treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082063_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082065_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082066_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082068_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082070_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082074_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082075_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082076_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082077_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082078_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082081_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082083_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082084_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082086_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082089_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082091_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082092_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082093_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082094_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082095_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082098_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082101_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082102_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082104_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082106_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082108_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082110_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082111_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082112_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082113_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082114_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082115_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082116_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082117_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082118_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082119_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082120_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082122_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082125_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082126_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082127_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082130_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082131_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082132_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082134_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082143_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082148_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082149_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082151_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082152_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082155_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082156_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082157_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082159_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082161_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082163_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082164_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082169_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082170_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082173_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082178_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082179_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082180_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082181_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082185_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082190_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082191_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082193_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082194_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082195_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082196_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082197_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082201_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082202_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081678_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081681_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081682_0.png treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081721_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081733_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081738_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081741_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081749_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081750_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081783_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081799_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081805_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081812_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081827_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081832_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081843_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081851_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081855_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081887_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081897_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081903_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081904_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081906_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081912_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081919_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081925_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081929_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081939_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081975_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082010_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082013_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082014_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082023_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082031_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082033_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082048_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082056_0.png treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082064_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082085_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082097_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082136_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082162_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082167_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082176_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082182_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081703_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081711_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081736_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081933_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081983_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082171_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081674_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081675_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081680_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081685_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081690_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081691_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081694_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081696_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081698_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081699_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081701_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081702_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081704_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081705_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081710_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081712_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081714_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081715_0.png treat image : temp/1748345429_351592_1360703504_96bf7c0daa760c9faff2729f6533aaa2_rle_crop_3814081716_0.png treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081720_0.png treat image : temp/1748345429_351592_1360703497_c983670a154a6cf339c7eeccd16888c1_rle_crop_3814081723_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081728_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081731_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081732_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081734_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081744_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081745_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081746_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081748_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081752_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081755_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081758_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081768_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081769_0.png treat image : temp/1748345429_351592_1360703451_5c7c95e53187008138007938b573e056_rle_crop_3814081780_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081788_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081797_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081806_0.png treat image : temp/1748345429_351592_1360703443_ec10c7fb0d015cb9d3326a50ba9c7da1_rle_crop_3814081810_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081818_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081819_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081820_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081822_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081823_0.png treat image : temp/1748345429_351592_1360703418_396b70f684fe6f0393b93f275b4588a8_rle_crop_3814081830_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081848_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081864_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081865_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081871_0.png treat image : temp/1748345429_351592_1360703411_9969d608178a6ac7b64abddc7c4808af_rle_crop_3814081872_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081875_0.png treat image : temp/1748345429_351592_1360703406_ac7f2aad2e16d9d343e4cb6fb810657f_rle_crop_3814081883_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081892_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081894_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081902_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081908_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081913_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081924_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081926_0.png treat image : temp/1748345429_351592_1360703374_7fad6db510843c7b8ba4d44eec8783b4_rle_crop_3814081935_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081940_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081944_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081949_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081953_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081954_0.png treat image : temp/1748345429_351592_1360703362_40b09dec1f923e7c779ea165119af795_rle_crop_3814081957_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081962_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081965_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081969_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081971_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081978_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081980_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081981_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081984_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081987_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081989_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081990_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081991_0.png treat image : temp/1748345429_351592_1360703353_b0a474b74c369eadc3d3b7da7519cfeb_rle_crop_3814081992_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081994_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081995_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081997_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814081999_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082002_0.png treat image : temp/1748345429_351592_1360703327_ef23eb33a521d4bada3eda6d05afd849_rle_crop_3814082004_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082020_0.png treat image : temp/1748345429_351592_1360703323_45bb0ff5f8ed63cdef5b7d509739b838_rle_crop_3814082024_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082034_0.png treat image : temp/1748345429_351592_1360703320_01eaea6b2439779b36b06b5453e74c07_rle_crop_3814082037_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082040_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082042_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082043_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082050_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082051_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082053_0.png treat image : temp/1748345429_351592_1360703313_8ce7160bdd90eeccfa2ffa06bece5d04_rle_crop_3814082054_0.png treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082061_0.png treat image : temp/1748345429_351592_1360703286_5f5d43001938367a4eb883fbc13b4471_rle_crop_3814082062_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082067_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082069_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082071_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082072_0.png treat image : temp/1748345429_351592_1360703283_bf4a7324f77b5b7ab6b32f91ade21528_rle_crop_3814082073_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082080_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082082_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082087_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082088_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082090_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082096_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082100_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082103_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082105_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082109_0.png treat image : temp/1748345429_351592_1360703274_6650ddcb27598ee8c1616e477a79ae6f_rle_crop_3814082121_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082123_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082124_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082128_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082133_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082135_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082137_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082138_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082139_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082140_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082141_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082144_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082145_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082146_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082147_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082150_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082153_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082154_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082158_0.png treat image : temp/1748345429_351592_1360703246_250c28c2cc7287d0003470e2af0078b9_rle_crop_3814082160_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082165_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082166_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082168_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082172_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082174_0.png treat image : temp/1748345429_351592_1360703244_3515ebf8eeba6ea2efab86733170c190_rle_crop_3814082175_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082183_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082184_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082188_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082192_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082198_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082199_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082200_0.png treat image : temp/1748345429_351592_1360703240_ec4dd945cda9ec829319c82154d29669_rle_crop_3814082203_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081792_0.png treat image : temp/1748345429_351592_1360703400_07cd180265edebc1cb225bd6bb89a151_rle_crop_3814081898_0.png treat image : temp/1748345429_351592_1360703377_ae04edeac535c7bcde78d7ef47de5fc6_rle_crop_3814081923_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081946_0.png treat image : temp/1748345429_351592_1360703279_8307ac9a6b9ec6d1cabaf4e74b24e7cc_rle_crop_3814082079_0.png treat image : temp/1748345429_351592_1360703272_6017801129ee02f8f639f1f1a5a33757_rle_crop_3814082129_0.png treat image : temp/1748345429_351592_1360703250_e55b244b8900d3013d485ae8d4795f1b_rle_crop_3814082142_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082177_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082189_0.png treat image : temp/1748345429_351592_1360703512_3e2988a7c49694658cfdc58fd1def35b_rle_crop_3814081684_0.png treat image : temp/1748345429_351592_1360703507_761380f6525a3784cb0affeca98628ff_rle_crop_3814081700_0.png treat image : temp/1748345429_351592_1360703494_553a5f4e24ef90b1a8279d72deb9b8d7_rle_crop_3814081737_0.png treat image : temp/1748345429_351592_1360703490_82be9134ada8b6cdbc234d8853c8126d_rle_crop_3814081747_0.png treat image : temp/1748345429_351592_1360703454_4db909aa298235820a3aebb36e220fb8_rle_crop_3814081766_0.png treat image : temp/1748345429_351592_1360703447_363dba664c87934a8d22a2df5b7cec18_rle_crop_3814081791_0.png treat image : temp/1748345429_351592_1360703440_d2900fbdde8dce4503e18a2d6e2c6772_rle_crop_3814081821_0.png treat image : temp/1748345429_351592_1360703414_04e9903e790c5b141525a438cdee0463_rle_crop_3814081852_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081943_0.png treat image : temp/1748345429_351592_1360703368_3bbbdcad7c35a8cc7d592cc4b529c3d4_rle_crop_3814081947_0.png treat image : temp/1748345429_351592_1360703358_f0e49c0e042f58d86fe8084cfe242825_rle_crop_3814081967_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082099_0.png treat image : temp/1748345429_351592_1360703276_4d03688d9f1bd3070c894f914e05f9aa_rle_crop_3814082107_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082186_0.png treat image : temp/1748345429_351592_1360703241_5695f6d7e1a1588a88c0c118100a6b13_rle_crop_3814082187_0.png Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 567 time used for this insertion : 0.04659867286682129 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 567 time used for this insertion : 0.09581208229064941 save missing photos in datou_result : time spend for datou_step_exec : 47.16295337677002 time spend to save output : 0.1502213478088379 total time spend for step 7 : 47.31317472457886 step8:velours_tree Tue May 27 13:54:58 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure can't find the photo_desc_type Inside saveOutput : final : False verbose : 0 ouput is None No outpout to save, returning out of save general time spend for datou_step_exec : 2.2829678058624268 time spend to save output : 6.556510925292969e-05 total time spend for step 8 : 2.2830333709716797 step9:send_mail_cod Tue May 27 13:55:00 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 2 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 3 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure dans la step send mail cod work_area: /home/admin/workarea/git/Velours/python in order to get the selector url, please entre the license of selector results_Auto_P23370929_27-05-2025_13_55_00.pdf 23377484 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette233774841748346900 23377485 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette233774851748346905 23377486 change filename to text .imagette233774861748346907 23377487 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette233774871748346907 23377488 imagette233774881748346908 23377489 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette233774891748346908 23377491 imagette233774911748346909 23377492 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette233774921748346909 23377493 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette233774931748346910 23377494 imagette233774941748346912 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=23370929 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/23377484,23377485,23377486,23377487,23377488,23377489,23377490,23377491,23377492,23377493,23377494?tags=papier,pet_clair,pehd,autre,mal_croppe,pet_fonce,environnement,flou,metal,carton,background args[1360703512] : ((1360703512, -5.649291646534456, 492609224), (1360703512, 0.17979952733310742, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703507] : ((1360703507, -5.8608229688000675, 492609224), (1360703507, 0.4743352708784219, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703504] : ((1360703504, -5.944085740074683, 492609224), (1360703504, 0.4349579499554167, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703497] : ((1360703497, -5.7165904383668655, 492609224), (1360703497, 0.4069776111713786, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703494] : ((1360703494, -5.7789487530332435, 492609224), (1360703494, 0.3744923243583319, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703490] : ((1360703490, -5.755682341250878, 492609224), (1360703490, 0.5050032631471529, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703454] : ((1360703454, -5.887489712281242, 492609224), (1360703454, 0.4690866384304477, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703451] : ((1360703451, -5.882651331630403, 492609224), (1360703451, 0.4652640530147123, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703447] : ((1360703447, -5.8088466634114235, 492609224), (1360703447, 0.5056041454681515, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703443] : ((1360703443, -5.767272520682633, 492609224), (1360703443, 0.3841433329881233, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703440] : ((1360703440, -5.765849944715273, 492609224), (1360703440, 0.41328394777557065, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703418] : ((1360703418, -5.731247321633349, 492609224), (1360703418, 0.35372147897573974, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703414] : ((1360703414, -5.819856204769151, 492609224), (1360703414, 0.48247586886224153, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703411] : ((1360703411, -5.645014433182347, 492609224), (1360703411, 0.6088079331961026, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703406] : ((1360703406, -5.801872190500105, 492609224), (1360703406, 0.5197015772839011, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703400] : ((1360703400, -5.968754272969779, 492609224), (1360703400, 0.5666797456187175, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703377] : ((1360703377, -5.937476480690605, 492609224), (1360703377, 0.5757672850954021, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703374] : ((1360703374, -5.836389078601609, 492609224), (1360703374, 0.5667216569751208, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703368] : ((1360703368, -5.7872044494445705, 492609224), (1360703368, 0.43515381130043, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703362] : ((1360703362, -5.6808345952634705, 492609224), (1360703362, 0.4750859478607314, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703358] : ((1360703358, -5.762121770048614, 492609224), (1360703358, 0.5103676821595262, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703353] : ((1360703353, -5.817336950940453, 492609224), (1360703353, 0.5387760293038644, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703327] : ((1360703327, -5.764730003747618, 492609224), (1360703327, 0.532580775247219, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703323] : ((1360703323, -5.714207240991041, 492609224), (1360703323, 0.5747591108674814, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703320] : ((1360703320, -6.457446898593587, 492609224), (1360703320, 0.5152717443687979, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703313] : ((1360703313, -5.87131672036129, 492609224), (1360703313, 0.46198196801086416, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703286] : ((1360703286, -5.738369548591882, 492609224), (1360703286, 0.4095890354061938, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703283] : ((1360703283, -5.668240799887292, 492609224), (1360703283, 0.5685588304032553, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703279] : ((1360703279, -5.856043562749426, 492609224), (1360703279, 0.6248515579754074, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703276] : ((1360703276, -5.858454289677687, 492609224), (1360703276, 0.5602130049319347, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703274] : ((1360703274, -5.762489029372882, 492609224), (1360703274, 0.4862959126128705, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703272] : ((1360703272, -5.638665479496887, 492609224), (1360703272, 0.43636141853422616, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703250] : ((1360703250, -5.780706706612298, 492609224), (1360703250, 0.6123020801975932, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703246] : ((1360703246, -5.82125667473822, 492609224), (1360703246, 0.5463355124939737, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703244] : ((1360703244, -5.624997827587678, 492609224), (1360703244, 0.5105185613263235, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703241] : ((1360703241, -5.619216565335296, 492609224), (1360703241, 0.5196393094443511, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com args[1360703240] : ((1360703240, -5.614674172318717, 492609224), (1360703240, 0.5611199811890251, 2107752395), '0.10723224526609942') We are sending mail with results at report@fotonower.com refus_total : 0.10723224526609942 2022-04-13 10:29:59 0 SELECT ph.photo_id,ph.url,ph.username,ph.uploaded_at,ph.text FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=23370929 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23370929_27-05-2025_13_55_00.pdf results_Auto_P23370929_27-05-2025_13_55_00.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23370929_27-05-2025_13_55_00.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('3318','23370929','results_Auto_P23370929_27-05-2025_13_55_00.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23370929_27-05-2025_13_55_00.pdf','pdf','','1.73','0.10723224526609942') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/23370929

https://www.fotonower.com/image?json=false&list_photos_id=1360703512
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703507
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703504
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703497
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703494
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703490
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703454
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703451
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703447
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703443
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703440
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703418
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703414
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703411
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703406
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703400
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703377
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703374
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703368
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703362
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703358
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703353
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703327
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703323
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703320
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703313
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703286
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703283
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703279
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703276
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703274
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703272
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703250
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703246
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703244
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703241
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1360703240
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 10.72%
Veuillez trouver les photos des contaminants.

exemples de contaminants: papier: https://www.fotonower.com/view/23377484?limit=200
exemples de contaminants: pet_clair: https://www.fotonower.com/view/23377485?limit=200
exemples de contaminants: pehd: https://www.fotonower.com/view/23377486?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/23377487?limit=200
exemples de contaminants: pet_fonce: https://www.fotonower.com/view/23377489?limit=200
exemples de contaminants: metal: https://www.fotonower.com/view/23377492?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/23377493?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23370929_27-05-2025_13_55_00.pdf.

Lien vers velours :https://www.fotonower.com/velours/23377484,23377485,23377486,23377487,23377488,23377489,23377490,23377491,23377492,23377493,23377494?tags=papier,pet_clair,pehd,autre,mal_croppe,pet_fonce,environnement,flou,metal,carton,background.


L'équipe Fotonower 202 b'' Server: nginx Date: Tue, 27 May 2025 11:55:18 GMT Content-Length: 0 Connection: close X-Message-Id: seZdp4vMQtqSr83IygwHIQ Access-Control-Allow-Origin: https://sendgrid.api-docs.io Access-Control-Allow-Methods: POST Access-Control-Allow-Headers: Authorization, Content-Type, On-behalf-of, x-sg-elas-acl Access-Control-Max-Age: 600 X-No-CORS-Reason: https://sendgrid.com/docs/Classroom/Basics/API/cors.html Strict-Transport-Security: max-age=31536000; includeSubDomains Content-Security-Policy: frame-ancestors 'none' Cache-Control: no-cache X-Content-Type-Options: no-sniff Referrer-Policy: strict-origin-when-cross-origin Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1360703512, 1360703507, 1360703504, 1360703497, 1360703494, 1360703490, 1360703454, 1360703451, 1360703447, 1360703443, 1360703440, 1360703418, 1360703414, 1360703411, 1360703406, 1360703400, 1360703377, 1360703374, 1360703368, 1360703362, 1360703358, 1360703353, 1360703327, 1360703323, 1360703320, 1360703313, 1360703286, 1360703283, 1360703279, 1360703276, 1360703274, 1360703272, 1360703250, 1360703246, 1360703244, 1360703241, 1360703240] Looping around the photos to save general results len do output : 0 before output type Used above Managing all output in save final without adding information in the mtr_datou_result ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703512', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703507', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703504', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703497', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703494', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703490', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703454', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703451', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703447', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703443', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703440', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703418', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703414', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703411', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703406', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703400', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703377', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703374', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703368', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703362', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703358', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703353', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703327', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703323', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703320', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703313', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703286', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703283', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703279', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703276', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703274', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703272', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703250', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703246', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703244', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703241', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703240', None, None, None, None, None, '2964573') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 37 time used for this insertion : 0.017181396484375 save_final save missing photos in datou_result : time spend for datou_step_exec : 18.135573148727417 time spend to save output : 0.01757025718688965 total time spend for step 9 : 18.153143405914307 step10:split_time_score Tue May 27 13:55:18 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 1 VR 22-3-18 : For now we do not clean correctly the datou structure begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 861, 'mtr_user_id': 31, 'name': 'Rungis_class_dechets_1212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Rungis_Aluminium,Rungis_Carton,Rungis_Papier,Rungis_Plastique_clair,Rungis_Plastique_dur,Rungis_Plastique_fonce,Rungis_Tapis_vide,Rungis_Tetrapak', 'svm_portfolios_learning': '1160730,571842,571844,571839,571933,571840,571841,572307', 'photo_hashtag_type': 999, 'photo_desc_type': 3963, 'type_classification': 'caffe', 'hashtag_id_list': '2107751280,2107750907,2107750908,2107750909,2107750910,2107750911,2107750912,2107750913'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('09', 37),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 23052025 23370929 Nombre de photos uploadées : 37 / 23040 (0%) 23052025 23370929 Nombre de photos taguées (types de déchets): 0 / 37 (0%) 23052025 23370929 Nombre de photos taguées (volume) : 0 / 37 (0%) elapsed_time : load_data_split_time_score 1.1920928955078125e-06 elapsed_time : order_list_meta_photo_and_scores 4.0531158447265625e-06 ????????????????????????????????????? elapsed_time : fill_and_build_computed_from_old_data 0.0009260177612304688 elapsed_time : insert_dashboard_record_day_entry 0.024364471435546875 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23370864 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23370869 order by id desc limit 1 Qualite : 0.10918088831018526 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23370910 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23370910 AND mptpi.`type`=3594 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23370920 order by id desc limit 1 Qualite : 0.10723224526609942 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23370929_27-05-2025_13_55_00.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23370929 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23370929 AND mptpi.`type`=3594 To do Qualite : 0.09557225356867284 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23370974_27-05-2025_13_21_14.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23370974 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23370974 AND mptpi.`type`=3594 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23370979 order by id desc limit 1 Qualite : 0.11415013227513227 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23370994_27-05-2025_12_12_45.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23370994 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23370994 AND mptpi.`type`=3594 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23371002 order by id desc limit 1 Qualite : 0.11478374495052658 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23371004_27-05-2025_11_12_30.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23371004 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23371004 AND mptpi.`type`=3594 To do Qualite : 0.20263053988233026 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23371013_27-05-2025_11_01_10.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23371013 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23371013 AND mptpi.`type`=3594 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23371159 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23371208 order by id desc limit 1 Qualite : 0.11329729094328704 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23371209_27-05-2025_11_32_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23371209 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23371209 AND mptpi.`type`=3594 To do Qualite : 0.11686973138503085 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23371232_27-05-2025_10_42_12.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23371232 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23371232 AND mptpi.`type`=3594 To do Qualite : 0.1380144779265873 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23333502_26-05-2025_14_25_48.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23333502 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23333502 AND mptpi.`type`=3594 To do Qualite : 0.1024788804599437 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23333505_26-05-2025_18_36_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23333505 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23333505 AND mptpi.`type`=3594 To do Qualite : 0.12909760400591566 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23333535_26-05-2025_16_04_49.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23333535 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23333535 AND mptpi.`type`=3594 To do Qualite : 0.1140376036844136 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P23333560_26-05-2025_13_14_29.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 23333560 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=23333560 AND mptpi.`type`=3594 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'23052025': {'nb_upload': 37, 'nb_taggue_class': 0, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1360703512, 1360703507, 1360703504, 1360703497, 1360703494, 1360703490, 1360703454, 1360703451, 1360703447, 1360703443, 1360703440, 1360703418, 1360703414, 1360703411, 1360703406, 1360703400, 1360703377, 1360703374, 1360703368, 1360703362, 1360703358, 1360703353, 1360703327, 1360703323, 1360703320, 1360703313, 1360703286, 1360703283, 1360703279, 1360703276, 1360703274, 1360703272, 1360703250, 1360703246, 1360703244, 1360703241, 1360703240] Looping around the photos to save general results len do output : 1 /23370929Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703512', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703507', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703504', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703497', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703494', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703490', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703454', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703451', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703447', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703443', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703440', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703418', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703414', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703411', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703406', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703400', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703377', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703374', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703368', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703362', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703358', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703353', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703327', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703323', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703320', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703313', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703286', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703283', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703279', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703276', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703274', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703272', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703250', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703246', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703244', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703241', None, None, None, None, None, '2964573') ('3318', None, None, None, None, None, None, None, '2964573') ('3318', '23370929', '1360703240', None, None, None, None, None, '2964573') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 38 time used for this insertion : 0.01746368408203125 save_final save missing photos in datou_result : time spend for datou_step_exec : 7.933735609054565 time spend to save output : 0.01787877082824707 total time spend for step 10 : 7.9516143798828125 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 37 set_done_treatment 582.82user 635.08system 25:01.34elapsed 81%CPU (0avgtext+0avgdata 10790400maxresident)k 23818384inputs+481736outputs (722377major+59316320minor)pagefaults 0swaps