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 : 576165 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 : ['2675453'] with mtr_portfolio_ids : ['21501459'] and first list_photo_ids : [] new path : /proc/576165/ 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 , BFBFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 12 ; length of list_pids : 12 ; length of list_args : 12 time to download the photos : 2.050542116165161 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 Mon Mar 17 20:20:31 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 : 5525 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-17 20:20:34.664260: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-17 20:20:34.691134: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-17 20:20:34.693357: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f943c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-17 20:20:34.693414: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-17 20:20:34.697664: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-17 20:20:34.966073: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x322ec920 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-17 20:20:34.966133: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-17 20:20:34.967245: 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 2025-03-17 20:20:34.968594: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-17 20:20:34.971717: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-17 20:20:34.975405: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-17 20:20:34.975947: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-17 20:20:34.980119: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-17 20:20:34.981639: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-17 20:20:34.989396: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-17 20:20:34.990810: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-17 20:20:34.990884: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-17 20:20:34.991661: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-17 20:20:34.991681: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-17 20:20:34.991692: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-17 20:20:34.993463: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5051 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. 2025-03-17 20:20:35.312825: 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 2025-03-17 20:20:35.312935: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-17 20:20:35.312963: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-17 20:20:35.312993: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-17 20:20:35.313017: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-17 20:20:35.313039: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-17 20:20:35.313060: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-17 20:20:35.313082: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-17 20:20:35.314340: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-17 20:20:35.315848: 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 2025-03-17 20:20:35.315952: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-17 20:20:35.315986: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-17 20:20:35.316016: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-17 20:20:35.316045: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-17 20:20:35.316065: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-17 20:20:35.316084: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-17 20:20:35.316103: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-17 20:20:35.317411: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-17 20:20:35.317452: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-17 20:20:35.317463: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-17 20:20:35.317473: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-17 20:20:35.318889: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5051 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 : [] 2025-03-17 20:20:46.167950: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-17 20:20:46.374248: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-17 20:20:47.859797: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:47.860510: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:47.861151: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.24G (3478923264 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.667947: 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. 2025-03-17 20:20:48.739848: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.739940: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB 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. 2025-03-17 20:20:48.741050: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.741075: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB 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. 2025-03-17 20:20:48.748002: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.748034: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB 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. 2025-03-17 20:20:48.749004: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.749025: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB 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. 2025-03-17 20:20:48.773932: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.774019: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 19.91MiB 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. 2025-03-17 20:20:48.774030: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-03-17 20:20:48.774854: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.774873: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 16.00MiB 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. 2025-03-17 20:20:48.775678: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.775697: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 16.00MiB 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. 2025-03-17 20:20:48.782619: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.782643: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB 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. 2025-03-17 20:20:48.783442: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.783462: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB 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. 2025-03-17 20:20:48.784300: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.784318: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB 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. 2025-03-17 20:20:48.785095: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.793146: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.793933: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.811575: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.812800: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.813683: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.814540: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.819130: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.819961: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.820744: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.821525: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.822865: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.833182: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.833994: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.843236: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.844049: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.844876: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.845655: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.846444: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-17 20:20:48.847234: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 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 : 12 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 48 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 59 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 62 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 43 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 60 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 54 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 84 NEW PHOTO Processing 1 images image shape: (2160, 3264, 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: 3264.00000 nb d'objets trouves : 19 Detection mask done ! Trying to reset tf kernel 576704 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2918 tf kernel not reseted sub process len(results) : 12 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 12 len(list_Values) 0 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 : 4111 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 : 0.03578662872314453 nb_pixel_total : 8063 time to create 1 rle with old method : 0.014436006546020508 length of segment : 106 time for calcul the mask position with numpy : 0.11056900024414062 nb_pixel_total : 43415 time to create 1 rle with old method : 0.058851003646850586 length of segment : 271 time for calcul the mask position with numpy : 0.22459125518798828 nb_pixel_total : 85647 time to create 1 rle with old method : 0.10306143760681152 length of segment : 573 time for calcul the mask position with numpy : 0.1986253261566162 nb_pixel_total : 119149 time to create 1 rle with old method : 0.14585661888122559 length of segment : 228 time for calcul the mask position with numpy : 0.22939705848693848 nb_pixel_total : 147585 time to create 1 rle with old method : 0.19178128242492676 length of segment : 338 time for calcul the mask position with numpy : 0.4795708656311035 nb_pixel_total : 291657 time to create 1 rle with new method : 0.01659250259399414 length of segment : 628 time for calcul the mask position with numpy : 0.3903048038482666 nb_pixel_total : 246468 time to create 1 rle with new method : 0.017871618270874023 length of segment : 802 time for calcul the mask position with numpy : 0.23369932174682617 nb_pixel_total : 107481 time to create 1 rle with old method : 0.13363313674926758 length of segment : 396 time for calcul the mask position with numpy : 0.0715494155883789 nb_pixel_total : 26659 time to create 1 rle with old method : 0.03587222099304199 length of segment : 242 time for calcul the mask position with numpy : 0.02486896514892578 nb_pixel_total : 11363 time to create 1 rle with old method : 0.018535137176513672 length of segment : 148 time for calcul the mask position with numpy : 0.04694986343383789 nb_pixel_total : 39371 time to create 1 rle with old method : 0.053044795989990234 length of segment : 149 time for calcul the mask position with numpy : 0.03341031074523926 nb_pixel_total : 17631 time to create 1 rle with old method : 0.026204347610473633 length of segment : 168 time for calcul the mask position with numpy : 0.24758315086364746 nb_pixel_total : 238888 time to create 1 rle with new method : 0.015620708465576172 length of segment : 607 time for calcul the mask position with numpy : 0.1447746753692627 nb_pixel_total : 78119 time to create 1 rle with old method : 0.09763121604919434 length of segment : 316 time for calcul the mask position with numpy : 0.10031652450561523 nb_pixel_total : 73563 time to create 1 rle with old method : 0.09294629096984863 length of segment : 480 time for calcul the mask position with numpy : 0.002827882766723633 nb_pixel_total : 18507 time to create 1 rle with old method : 0.023144245147705078 length of segment : 141 time for calcul the mask position with numpy : 0.015807151794433594 nb_pixel_total : 223609 time to create 1 rle with new method : 0.015350580215454102 length of segment : 571 time for calcul the mask position with numpy : 0.052782535552978516 nb_pixel_total : 63380 time to create 1 rle with old method : 0.08165955543518066 length of segment : 275 time for calcul the mask position with numpy : 0.0002493858337402344 nb_pixel_total : 6935 time to create 1 rle with old method : 0.009325981140136719 length of segment : 79 time for calcul the mask position with numpy : 0.0013806819915771484 nb_pixel_total : 18487 time to create 1 rle with old method : 0.02396535873413086 length of segment : 124 time for calcul the mask position with numpy : 0.6810076236724854 nb_pixel_total : 224391 time to create 1 rle with new method : 0.017910480499267578 length of segment : 801 time for calcul the mask position with numpy : 0.3779587745666504 nb_pixel_total : 141761 time to create 1 rle with old method : 0.16178441047668457 length of segment : 413 time for calcul the mask position with numpy : 0.18154096603393555 nb_pixel_total : 71799 time to create 1 rle with old method : 0.08888101577758789 length of segment : 420 time for calcul the mask position with numpy : 0.5825550556182861 nb_pixel_total : 169530 time to create 1 rle with new method : 0.012906789779663086 length of segment : 508 time for calcul the mask position with numpy : 0.1398792266845703 nb_pixel_total : 24169 time to create 1 rle with old method : 0.040360450744628906 length of segment : 154 time for calcul the mask position with numpy : 0.34369397163391113 nb_pixel_total : 79420 time to create 1 rle with old method : 0.10430622100830078 length of segment : 512 time for calcul the mask position with numpy : 1.4117846488952637 nb_pixel_total : 400671 time to create 1 rle with new method : 0.062253475189208984 length of segment : 1079 time for calcul the mask position with numpy : 0.17180728912353516 nb_pixel_total : 15943 time to create 1 rle with old method : 0.021762371063232422 length of segment : 407 time for calcul the mask position with numpy : 0.13634395599365234 nb_pixel_total : 62082 time to create 1 rle with old method : 0.07604336738586426 length of segment : 388 time for calcul the mask position with numpy : 0.11253809928894043 nb_pixel_total : 36910 time to create 1 rle with old method : 0.049486637115478516 length of segment : 176 time for calcul the mask position with numpy : 0.0708928108215332 nb_pixel_total : 33388 time to create 1 rle with old method : 0.04912614822387695 length of segment : 255 time for calcul the mask position with numpy : 0.10237669944763184 nb_pixel_total : 93715 time to create 1 rle with old method : 0.11146283149719238 length of segment : 454 time for calcul the mask position with numpy : 0.3921198844909668 nb_pixel_total : 214391 time to create 1 rle with new method : 0.039067745208740234 length of segment : 688 time for calcul the mask position with numpy : 0.026607036590576172 nb_pixel_total : 61991 time to create 1 rle with old method : 0.09373092651367188 length of segment : 320 time for calcul the mask position with numpy : 0.15525245666503906 nb_pixel_total : 63020 time to create 1 rle with old method : 0.07840228080749512 length of segment : 367 time for calcul the mask position with numpy : 0.0003027915954589844 nb_pixel_total : 10377 time to create 1 rle with old method : 0.016678571701049805 length of segment : 149 time for calcul the mask position with numpy : 0.12181472778320312 nb_pixel_total : 171101 time to create 1 rle with new method : 0.015538930892944336 length of segment : 818 time for calcul the mask position with numpy : 0.14463472366333008 nb_pixel_total : 171407 time to create 1 rle with new method : 0.0158541202545166 length of segment : 621 time for calcul the mask position with numpy : 0.018314361572265625 nb_pixel_total : 71110 time to create 1 rle with old method : 0.09050154685974121 length of segment : 296 time for calcul the mask position with numpy : 0.030936717987060547 nb_pixel_total : 13307 time to create 1 rle with old method : 0.021500825881958008 length of segment : 114 time for calcul the mask position with numpy : 0.11509943008422852 nb_pixel_total : 4949 time to create 1 rle with old method : 0.009235143661499023 length of segment : 200 time for calcul the mask position with numpy : 0.042999267578125 nb_pixel_total : 9858 time to create 1 rle with old method : 0.018731117248535156 length of segment : 107 time for calcul the mask position with numpy : 0.02260756492614746 nb_pixel_total : 8671 time to create 1 rle with old method : 0.01322174072265625 length of segment : 124 time for calcul the mask position with numpy : 0.439594030380249 nb_pixel_total : 374581 time to create 1 rle with new method : 0.041892051696777344 length of segment : 722 time for calcul the mask position with numpy : 0.00028061866760253906 nb_pixel_total : 11816 time to create 1 rle with old method : 0.014190196990966797 length of segment : 122 time for calcul the mask position with numpy : 0.019452571868896484 nb_pixel_total : 35145 time to create 1 rle with old method : 0.04806351661682129 length of segment : 184 time for calcul the mask position with numpy : 0.003088235855102539 nb_pixel_total : 8382 time to create 1 rle with old method : 0.01306295394897461 length of segment : 125 time for calcul the mask position with numpy : 0.000270843505859375 nb_pixel_total : 10683 time to create 1 rle with old method : 0.013357877731323242 length of segment : 92 time for calcul the mask position with numpy : 0.22946667671203613 nb_pixel_total : 48372 time to create 1 rle with old method : 0.08406448364257812 length of segment : 316 time for calcul the mask position with numpy : 0.0003771781921386719 nb_pixel_total : 14841 time to create 1 rle with old method : 0.02077007293701172 length of segment : 160 time for calcul the mask position with numpy : 0.0005283355712890625 nb_pixel_total : 20376 time to create 1 rle with old method : 0.03418374061584473 length of segment : 159 time for calcul the mask position with numpy : 0.048538923263549805 nb_pixel_total : 32868 time to create 1 rle with old method : 0.05917477607727051 length of segment : 340 time for calcul the mask position with numpy : 0.15485525131225586 nb_pixel_total : 150681 time to create 1 rle with new method : 0.014996051788330078 length of segment : 441 time for calcul the mask position with numpy : 0.4216039180755615 nb_pixel_total : 158231 time to create 1 rle with new method : 0.01533055305480957 length of segment : 1098 time for calcul the mask position with numpy : 0.30599427223205566 nb_pixel_total : 117721 time to create 1 rle with old method : 0.14736104011535645 length of segment : 616 time for calcul the mask position with numpy : 0.05904841423034668 nb_pixel_total : 16303 time to create 1 rle with old method : 0.024630308151245117 length of segment : 162 time for calcul the mask position with numpy : 0.04302167892456055 nb_pixel_total : 10258 time to create 1 rle with old method : 0.016473054885864258 length of segment : 114 time for calcul the mask position with numpy : 0.13848352432250977 nb_pixel_total : 62162 time to create 1 rle with old method : 0.07540154457092285 length of segment : 253 time for calcul the mask position with numpy : 0.20996451377868652 nb_pixel_total : 11931 time to create 1 rle with old method : 0.019166231155395508 length of segment : 183 time for calcul the mask position with numpy : 0.06270503997802734 nb_pixel_total : 16330 time to create 1 rle with old method : 0.0228426456451416 length of segment : 202 time for calcul the mask position with numpy : 0.07471919059753418 nb_pixel_total : 20283 time to create 1 rle with old method : 0.027404069900512695 length of segment : 181 time for calcul the mask position with numpy : 0.005163669586181641 nb_pixel_total : 13027 time to create 1 rle with old method : 0.02110743522644043 length of segment : 144 time for calcul the mask position with numpy : 0.16268396377563477 nb_pixel_total : 38820 time to create 1 rle with old method : 0.052080392837524414 length of segment : 272 time for calcul the mask position with numpy : 0.48985767364501953 nb_pixel_total : 58807 time to create 1 rle with old method : 0.08904504776000977 length of segment : 427 time for calcul the mask position with numpy : 0.06966924667358398 nb_pixel_total : 15243 time to create 1 rle with old method : 0.02462172508239746 length of segment : 154 time for calcul the mask position with numpy : 0.08604121208190918 nb_pixel_total : 32058 time to create 1 rle with old method : 0.04185366630554199 length of segment : 205 time for calcul the mask position with numpy : 0.004083156585693359 nb_pixel_total : 21878 time to create 1 rle with old method : 0.027735471725463867 length of segment : 358 time for calcul the mask position with numpy : 0.19425106048583984 nb_pixel_total : 70651 time to create 1 rle with old method : 0.09122014045715332 length of segment : 219 time for calcul the mask position with numpy : 0.08650088310241699 nb_pixel_total : 9720 time to create 1 rle with old method : 0.015972614288330078 length of segment : 141 time for calcul the mask position with numpy : 0.11244344711303711 nb_pixel_total : 23354 time to create 1 rle with old method : 0.028047561645507812 length of segment : 294 time for calcul the mask position with numpy : 0.1249384880065918 nb_pixel_total : 46128 time to create 1 rle with old method : 0.059384822845458984 length of segment : 506 time for calcul the mask position with numpy : 0.04839158058166504 nb_pixel_total : 7855 time to create 1 rle with old method : 0.015079259872436523 length of segment : 108 time for calcul the mask position with numpy : 0.027529239654541016 nb_pixel_total : 6153 time to create 1 rle with old method : 0.011170625686645508 length of segment : 94 time for calcul the mask position with numpy : 0.09337186813354492 nb_pixel_total : 26940 time to create 1 rle with old method : 0.03643059730529785 length of segment : 239 time for calcul the mask position with numpy : 0.019400835037231445 nb_pixel_total : 40904 time to create 1 rle with old method : 0.051197052001953125 length of segment : 411 time for calcul the mask position with numpy : 0.05524563789367676 nb_pixel_total : 23739 time to create 1 rle with old method : 0.03176593780517578 length of segment : 191 time for calcul the mask position with numpy : 0.04937028884887695 nb_pixel_total : 34953 time to create 1 rle with old method : 0.04674267768859863 length of segment : 225 time for calcul the mask position with numpy : 0.002887725830078125 nb_pixel_total : 4506 time to create 1 rle with old method : 0.005769491195678711 length of segment : 83 time for calcul the mask position with numpy : 0.22007179260253906 nb_pixel_total : 105983 time to create 1 rle with old method : 0.12419533729553223 length of segment : 527 time for calcul the mask position with numpy : 0.018718242645263672 nb_pixel_total : 6758 time to create 1 rle with old method : 0.012329339981079102 length of segment : 149 time for calcul the mask position with numpy : 0.06448960304260254 nb_pixel_total : 22879 time to create 1 rle with old method : 0.030469894409179688 length of segment : 198 time for calcul the mask position with numpy : 0.014339447021484375 nb_pixel_total : 13773 time to create 1 rle with old method : 0.021873950958251953 length of segment : 165 time for calcul the mask position with numpy : 0.007323026657104492 nb_pixel_total : 103122 time to create 1 rle with old method : 0.12325119972229004 length of segment : 541 time for calcul the mask position with numpy : 0.00833749771118164 nb_pixel_total : 17974 time to create 1 rle with old method : 0.02429938316345215 length of segment : 219 time for calcul the mask position with numpy : 0.009876728057861328 nb_pixel_total : 10435 time to create 1 rle with old method : 0.015660524368286133 length of segment : 152 time for calcul the mask position with numpy : 0.05509829521179199 nb_pixel_total : 32098 time to create 1 rle with old method : 0.046840667724609375 length of segment : 268 time for calcul the mask position with numpy : 0.0003743171691894531 nb_pixel_total : 13970 time to create 1 rle with old method : 0.0330197811126709 length of segment : 132 time for calcul the mask position with numpy : 0.40894460678100586 nb_pixel_total : 268509 time to create 1 rle with new method : 0.020937204360961914 length of segment : 631 time for calcul the mask position with numpy : 0.00032329559326171875 nb_pixel_total : 11944 time to create 1 rle with old method : 0.018589019775390625 length of segment : 144 time for calcul the mask position with numpy : 0.00431060791015625 nb_pixel_total : 9367 time to create 1 rle with old method : 0.020029067993164062 length of segment : 102 time for calcul the mask position with numpy : 0.08828282356262207 nb_pixel_total : 186489 time to create 1 rle with new method : 0.011301040649414062 length of segment : 477 time for calcul the mask position with numpy : 0.05955195426940918 nb_pixel_total : 30767 time to create 1 rle with old method : 0.04588580131530762 length of segment : 335 time for calcul the mask position with numpy : 0.04760456085205078 nb_pixel_total : 14009 time to create 1 rle with old method : 0.02259683609008789 length of segment : 153 time for calcul the mask position with numpy : 0.3130378723144531 nb_pixel_total : 91099 time to create 1 rle with old method : 0.10810208320617676 length of segment : 465 time for calcul the mask position with numpy : 0.49852824211120605 nb_pixel_total : 177653 time to create 1 rle with new method : 0.00734710693359375 length of segment : 481 time for calcul the mask position with numpy : 0.014031171798706055 nb_pixel_total : 16533 time to create 1 rle with old method : 0.023028850555419922 length of segment : 141 time for calcul the mask position with numpy : 0.2718794345855713 nb_pixel_total : 178527 time to create 1 rle with new method : 0.005928993225097656 length of segment : 403 time for calcul the mask position with numpy : 0.06941938400268555 nb_pixel_total : 9807 time to create 1 rle with old method : 0.016328096389770508 length of segment : 115 time for calcul the mask position with numpy : 0.0957338809967041 nb_pixel_total : 29482 time to create 1 rle with old method : 0.039069175720214844 length of segment : 168 time for calcul the mask position with numpy : 0.3577089309692383 nb_pixel_total : 146819 time to create 1 rle with old method : 0.17819905281066895 length of segment : 466 time for calcul the mask position with numpy : 0.030422449111938477 nb_pixel_total : 17944 time to create 1 rle with old method : 0.02463364601135254 length of segment : 131 time for calcul the mask position with numpy : 0.2497107982635498 nb_pixel_total : 20911 time to create 1 rle with old method : 0.029675006866455078 length of segment : 153 time for calcul the mask position with numpy : 0.006947755813598633 nb_pixel_total : 16824 time to create 1 rle with old method : 0.023204326629638672 length of segment : 125 time for calcul the mask position with numpy : 0.17356371879577637 nb_pixel_total : 121215 time to create 1 rle with old method : 0.14242267608642578 length of segment : 449 time for calcul the mask position with numpy : 0.0706326961517334 nb_pixel_total : 29567 time to create 1 rle with old method : 0.040091753005981445 length of segment : 389 time for calcul the mask position with numpy : 0.049066781997680664 nb_pixel_total : 30782 time to create 1 rle with old method : 0.040010690689086914 length of segment : 192 time for calcul the mask position with numpy : 0.0002315044403076172 nb_pixel_total : 12472 time to create 1 rle with old method : 0.014865875244140625 length of segment : 136 time for calcul the mask position with numpy : 0.15875506401062012 nb_pixel_total : 100619 time to create 1 rle with old method : 0.121673583984375 length of segment : 376 time for calcul the mask position with numpy : 0.07843399047851562 nb_pixel_total : 87910 time to create 1 rle with old method : 0.10412216186523438 length of segment : 579 time for calcul the mask position with numpy : 0.09341645240783691 nb_pixel_total : 43744 time to create 1 rle with old method : 0.0547327995300293 length of segment : 220 time for calcul the mask position with numpy : 0.0008523464202880859 nb_pixel_total : 19182 time to create 1 rle with old method : 0.022367238998413086 length of segment : 172 time for calcul the mask position with numpy : 0.0003376007080078125 nb_pixel_total : 3635 time to create 1 rle with old method : 0.005158185958862305 length of segment : 107 time for calcul the mask position with numpy : 0.11407923698425293 nb_pixel_total : 169673 time to create 1 rle with new method : 0.007818937301635742 length of segment : 520 time for calcul the mask position with numpy : 0.2667582035064697 nb_pixel_total : 55139 time to create 1 rle with old method : 0.06759333610534668 length of segment : 461 time for calcul the mask position with numpy : 0.00041604042053222656 nb_pixel_total : 23396 time to create 1 rle with old method : 0.026516199111938477 length of segment : 176 time for calcul the mask position with numpy : 0.030953645706176758 nb_pixel_total : 9263 time to create 1 rle with old method : 0.015398979187011719 length of segment : 161 time for calcul the mask position with numpy : 0.06482458114624023 nb_pixel_total : 50015 time to create 1 rle with old method : 0.0601656436920166 length of segment : 178 time for calcul the mask position with numpy : 0.11193728446960449 nb_pixel_total : 4975 time to create 1 rle with old method : 0.008850574493408203 length of segment : 82 time for calcul the mask position with numpy : 0.31685614585876465 nb_pixel_total : 68420 time to create 1 rle with old method : 0.08476495742797852 length of segment : 353 time for calcul the mask position with numpy : 0.5926296710968018 nb_pixel_total : 26704 time to create 1 rle with old method : 0.041259050369262695 length of segment : 281 time for calcul the mask position with numpy : 0.48856115341186523 nb_pixel_total : 36957 time to create 1 rle with old method : 0.06986141204833984 length of segment : 265 time for calcul the mask position with numpy : 0.42447686195373535 nb_pixel_total : 20593 time to create 1 rle with old method : 0.030151844024658203 length of segment : 221 time for calcul the mask position with numpy : 0.03603649139404297 nb_pixel_total : 6363 time to create 1 rle with old method : 0.012158632278442383 length of segment : 76 time for calcul the mask position with numpy : 0.05417633056640625 nb_pixel_total : 8754 time to create 1 rle with old method : 0.01514291763305664 length of segment : 103 time for calcul the mask position with numpy : 0.06301593780517578 nb_pixel_total : 11048 time to create 1 rle with old method : 0.018216609954833984 length of segment : 120 time for calcul the mask position with numpy : 0.09700584411621094 nb_pixel_total : 18397 time to create 1 rle with old method : 0.0257110595703125 length of segment : 171 time for calcul the mask position with numpy : 0.08314681053161621 nb_pixel_total : 17315 time to create 1 rle with old method : 0.026783466339111328 length of segment : 165 time for calcul the mask position with numpy : 0.02280902862548828 nb_pixel_total : 5086 time to create 1 rle with old method : 0.010784387588500977 length of segment : 71 time for calcul the mask position with numpy : 0.09640717506408691 nb_pixel_total : 22436 time to create 1 rle with old method : 0.03397798538208008 length of segment : 192 time for calcul the mask position with numpy : 0.017223596572875977 nb_pixel_total : 4302 time to create 1 rle with old method : 0.007024288177490234 length of segment : 43 time for calcul the mask position with numpy : 0.044307708740234375 nb_pixel_total : 6250 time to create 1 rle with old method : 0.011346578598022461 length of segment : 78 time for calcul the mask position with numpy : 0.9106931686401367 nb_pixel_total : 177457 time to create 1 rle with new method : 0.013257026672363281 length of segment : 715 time for calcul the mask position with numpy : 0.11218810081481934 nb_pixel_total : 6477 time to create 1 rle with old method : 0.010414838790893555 length of segment : 84 time for calcul the mask position with numpy : 0.0823211669921875 nb_pixel_total : 16750 time to create 1 rle with old method : 0.02349257469177246 length of segment : 160 time for calcul the mask position with numpy : 0.4611210823059082 nb_pixel_total : 128933 time to create 1 rle with old method : 0.3141038417816162 length of segment : 526 time for calcul the mask position with numpy : 0.11268138885498047 nb_pixel_total : 23645 time to create 1 rle with old method : 0.03237318992614746 length of segment : 190 time for calcul the mask position with numpy : 0.2055056095123291 nb_pixel_total : 37421 time to create 1 rle with old method : 0.04853034019470215 length of segment : 305 time for calcul the mask position with numpy : 0.13573741912841797 nb_pixel_total : 27455 time to create 1 rle with old method : 0.035939693450927734 length of segment : 171 time for calcul the mask position with numpy : 0.027779340744018555 nb_pixel_total : 15259 time to create 1 rle with old method : 0.021136045455932617 length of segment : 239 time for calcul the mask position with numpy : 0.0781106948852539 nb_pixel_total : 14397 time to create 1 rle with old method : 0.023328304290771484 length of segment : 164 time for calcul the mask position with numpy : 0.0879678726196289 nb_pixel_total : 34411 time to create 1 rle with old method : 0.0469663143157959 length of segment : 248 time for calcul the mask position with numpy : 0.12414717674255371 nb_pixel_total : 28751 time to create 1 rle with old method : 0.04808664321899414 length of segment : 275 time for calcul the mask position with numpy : 0.00927591323852539 nb_pixel_total : 6041 time to create 1 rle with old method : 0.0070879459381103516 length of segment : 87 time for calcul the mask position with numpy : 0.039481163024902344 nb_pixel_total : 14038 time to create 1 rle with old method : 0.016590118408203125 length of segment : 172 time for calcul the mask position with numpy : 0.045828819274902344 nb_pixel_total : 8228 time to create 1 rle with old method : 0.01677703857421875 length of segment : 89 time for calcul the mask position with numpy : 0.1509261131286621 nb_pixel_total : 37298 time to create 1 rle with old method : 0.047510623931884766 length of segment : 363 time for calcul the mask position with numpy : 0.051435232162475586 nb_pixel_total : 18859 time to create 1 rle with old method : 0.02557969093322754 length of segment : 221 time for calcul the mask position with numpy : 0.0827631950378418 nb_pixel_total : 26318 time to create 1 rle with old method : 0.03590798377990723 length of segment : 140 time for calcul the mask position with numpy : 0.007645130157470703 nb_pixel_total : 5528 time to create 1 rle with old method : 0.008796215057373047 length of segment : 100 time for calcul the mask position with numpy : 0.04995918273925781 nb_pixel_total : 10473 time to create 1 rle with old method : 0.017467737197875977 length of segment : 105 time for calcul the mask position with numpy : 0.05310320854187012 nb_pixel_total : 12336 time to create 1 rle with old method : 0.019542932510375977 length of segment : 150 time for calcul the mask position with numpy : 0.31950879096984863 nb_pixel_total : 38833 time to create 1 rle with old method : 0.05047011375427246 length of segment : 302 time for calcul the mask position with numpy : 0.4919402599334717 nb_pixel_total : 137218 time to create 1 rle with old method : 0.16142702102661133 length of segment : 603 time for calcul the mask position with numpy : 0.010829448699951172 nb_pixel_total : 21733 time to create 1 rle with old method : 0.030569791793823242 length of segment : 164 time for calcul the mask position with numpy : 0.06886410713195801 nb_pixel_total : 22224 time to create 1 rle with old method : 0.036173105239868164 length of segment : 191 time for calcul the mask position with numpy : 0.04004669189453125 nb_pixel_total : 17252 time to create 1 rle with old method : 0.024173259735107422 length of segment : 341 time for calcul the mask position with numpy : 0.2820258140563965 nb_pixel_total : 38284 time to create 1 rle with old method : 0.05063271522521973 length of segment : 213 time for calcul the mask position with numpy : 0.04157137870788574 nb_pixel_total : 6365 time to create 1 rle with old method : 0.013164281845092773 length of segment : 63 time for calcul the mask position with numpy : 0.12969064712524414 nb_pixel_total : 44841 time to create 1 rle with old method : 0.055863380432128906 length of segment : 406 time for calcul the mask position with numpy : 0.011140108108520508 nb_pixel_total : 6234 time to create 1 rle with old method : 0.009482145309448242 length of segment : 83 time for calcul the mask position with numpy : 0.037934303283691406 nb_pixel_total : 22907 time to create 1 rle with old method : 0.03664875030517578 length of segment : 191 time for calcul the mask position with numpy : 0.20631122589111328 nb_pixel_total : 17172 time to create 1 rle with old method : 0.024918556213378906 length of segment : 172 time for calcul the mask position with numpy : 0.028244733810424805 nb_pixel_total : 18424 time to create 1 rle with old method : 0.0278470516204834 length of segment : 182 time for calcul the mask position with numpy : 0.03742241859436035 nb_pixel_total : 18216 time to create 1 rle with old method : 0.023796796798706055 length of segment : 189 time for calcul the mask position with numpy : 0.17242074012756348 nb_pixel_total : 35905 time to create 1 rle with old method : 0.046883583068847656 length of segment : 236 time for calcul the mask position with numpy : 0.036769866943359375 nb_pixel_total : 18685 time to create 1 rle with old method : 0.024283170700073242 length of segment : 203 time for calcul the mask position with numpy : 0.04343366622924805 nb_pixel_total : 12912 time to create 1 rle with old method : 0.020690202713012695 length of segment : 160 time for calcul the mask position with numpy : 0.06467986106872559 nb_pixel_total : 23862 time to create 1 rle with old method : 0.03255581855773926 length of segment : 153 time for calcul the mask position with numpy : 0.009524106979370117 nb_pixel_total : 14432 time to create 1 rle with old method : 0.022062063217163086 length of segment : 143 time for calcul the mask position with numpy : 0.23552322387695312 nb_pixel_total : 29725 time to create 1 rle with old method : 0.05633354187011719 length of segment : 188 time for calcul the mask position with numpy : 0.047290802001953125 nb_pixel_total : 7328 time to create 1 rle with old method : 0.011709451675415039 length of segment : 102 time for calcul the mask position with numpy : 0.07470965385437012 nb_pixel_total : 71168 time to create 1 rle with old method : 0.1017765998840332 length of segment : 344 time for calcul the mask position with numpy : 0.026556730270385742 nb_pixel_total : 18769 time to create 1 rle with old method : 0.028940916061401367 length of segment : 216 time for calcul the mask position with numpy : 0.18107199668884277 nb_pixel_total : 41782 time to create 1 rle with old method : 0.05698084831237793 length of segment : 293 time for calcul the mask position with numpy : 0.0022907257080078125 nb_pixel_total : 19491 time to create 1 rle with old method : 0.025553464889526367 length of segment : 198 time for calcul the mask position with numpy : 0.17674803733825684 nb_pixel_total : 32325 time to create 1 rle with old method : 0.04083251953125 length of segment : 317 time for calcul the mask position with numpy : 0.16860294342041016 nb_pixel_total : 45184 time to create 1 rle with old method : 0.056320905685424805 length of segment : 508 time for calcul the mask position with numpy : 0.08730840682983398 nb_pixel_total : 28758 time to create 1 rle with old method : 0.0397183895111084 length of segment : 180 time for calcul the mask position with numpy : 0.05341744422912598 nb_pixel_total : 6908 time to create 1 rle with old method : 0.014018058776855469 length of segment : 130 time for calcul the mask position with numpy : 1.1145274639129639 nb_pixel_total : 58471 time to create 1 rle with old method : 0.07401514053344727 length of segment : 327 time for calcul the mask position with numpy : 0.3454725742340088 nb_pixel_total : 29436 time to create 1 rle with old method : 0.039948463439941406 length of segment : 249 time for calcul the mask position with numpy : 0.0926828384399414 nb_pixel_total : 17861 time to create 1 rle with old method : 0.04440927505493164 length of segment : 157 time for calcul the mask position with numpy : 0.06910204887390137 nb_pixel_total : 24972 time to create 1 rle with old method : 0.03386688232421875 length of segment : 145 time for calcul the mask position with numpy : 0.06559348106384277 nb_pixel_total : 19598 time to create 1 rle with old method : 0.02917194366455078 length of segment : 185 time for calcul the mask position with numpy : 0.09354400634765625 nb_pixel_total : 19221 time to create 1 rle with old method : 0.023637771606445312 length of segment : 489 time for calcul the mask position with numpy : 0.3731517791748047 nb_pixel_total : 243836 time to create 1 rle with new method : 0.01577591896057129 length of segment : 555 time for calcul the mask position with numpy : 0.012342214584350586 nb_pixel_total : 3183 time to create 1 rle with old method : 0.003972053527832031 length of segment : 60 time for calcul the mask position with numpy : 0.07341384887695312 nb_pixel_total : 39800 time to create 1 rle with old method : 0.05206155776977539 length of segment : 283 time for calcul the mask position with numpy : 0.026975393295288086 nb_pixel_total : 16008 time to create 1 rle with old method : 0.025902748107910156 length of segment : 117 time for calcul the mask position with numpy : 0.05617260932922363 nb_pixel_total : 16058 time to create 1 rle with old method : 0.025484323501586914 length of segment : 124 time for calcul the mask position with numpy : 0.08038949966430664 nb_pixel_total : 27986 time to create 1 rle with old method : 0.038649797439575195 length of segment : 173 time for calcul the mask position with numpy : 0.0916438102722168 nb_pixel_total : 25904 time to create 1 rle with old method : 0.035215139389038086 length of segment : 288 time for calcul the mask position with numpy : 0.13688063621520996 nb_pixel_total : 41970 time to create 1 rle with old method : 0.053128957748413086 length of segment : 281 time for calcul the mask position with numpy : 0.05350232124328613 nb_pixel_total : 15212 time to create 1 rle with old method : 0.022238492965698242 length of segment : 216 time for calcul the mask position with numpy : 0.0993661880493164 nb_pixel_total : 26876 time to create 1 rle with old method : 0.03632187843322754 length of segment : 225 time for calcul the mask position with numpy : 0.07013154029846191 nb_pixel_total : 20372 time to create 1 rle with old method : 0.025501728057861328 length of segment : 227 time for calcul the mask position with numpy : 0.06935334205627441 nb_pixel_total : 44525 time to create 1 rle with old method : 0.05591177940368652 length of segment : 261 time for calcul the mask position with numpy : 0.012959003448486328 nb_pixel_total : 8409 time to create 1 rle with old method : 0.014336824417114258 length of segment : 140 time for calcul the mask position with numpy : 0.0475924015045166 nb_pixel_total : 49582 time to create 1 rle with old method : 0.06179046630859375 length of segment : 299 time for calcul the mask position with numpy : 0.04416990280151367 nb_pixel_total : 12742 time to create 1 rle with old method : 0.021174192428588867 length of segment : 209 time for calcul the mask position with numpy : 0.046334028244018555 nb_pixel_total : 14660 time to create 1 rle with old method : 0.024274826049804688 length of segment : 156 time for calcul the mask position with numpy : 0.00564885139465332 nb_pixel_total : 10873 time to create 1 rle with old method : 0.015563488006591797 length of segment : 157 time for calcul the mask position with numpy : 0.03933978080749512 nb_pixel_total : 10941 time to create 1 rle with old method : 0.01667952537536621 length of segment : 141 time for calcul the mask position with numpy : 0.009403467178344727 nb_pixel_total : 6955 time to create 1 rle with old method : 0.009594440460205078 length of segment : 93 time for calcul the mask position with numpy : 0.0611119270324707 nb_pixel_total : 40254 time to create 1 rle with old method : 0.05167412757873535 length of segment : 200 time for calcul the mask position with numpy : 0.05925869941711426 nb_pixel_total : 14959 time to create 1 rle with old method : 0.0191800594329834 length of segment : 166 time for calcul the mask position with numpy : 0.02338576316833496 nb_pixel_total : 43526 time to create 1 rle with old method : 0.053101539611816406 length of segment : 324 time for calcul the mask position with numpy : 0.024283409118652344 nb_pixel_total : 18436 time to create 1 rle with old method : 0.0256500244140625 length of segment : 197 time for calcul the mask position with numpy : 0.005983829498291016 nb_pixel_total : 3211 time to create 1 rle with old method : 0.004891633987426758 length of segment : 60 time for calcul the mask position with numpy : 0.12740516662597656 nb_pixel_total : 54758 time to create 1 rle with old method : 0.06746268272399902 length of segment : 277 time for calcul the mask position with numpy : 0.05948328971862793 nb_pixel_total : 17606 time to create 1 rle with old method : 0.02652764320373535 length of segment : 230 time for calcul the mask position with numpy : 0.04253888130187988 nb_pixel_total : 12827 time to create 1 rle with old method : 0.02008795738220215 length of segment : 133 time for calcul the mask position with numpy : 0.10090446472167969 nb_pixel_total : 27845 time to create 1 rle with old method : 0.03617405891418457 length of segment : 410 time for calcul the mask position with numpy : 0.09190893173217773 nb_pixel_total : 33956 time to create 1 rle with old method : 0.04613232612609863 length of segment : 205 time for calcul the mask position with numpy : 0.06338882446289062 nb_pixel_total : 18759 time to create 1 rle with old method : 0.02639603614807129 length of segment : 192 time for calcul the mask position with numpy : 0.0668635368347168 nb_pixel_total : 18818 time to create 1 rle with old method : 0.02527451515197754 length of segment : 225 time for calcul the mask position with numpy : 0.11647391319274902 nb_pixel_total : 31358 time to create 1 rle with old method : 0.041185855865478516 length of segment : 310 time for calcul the mask position with numpy : 0.017809391021728516 nb_pixel_total : 27352 time to create 1 rle with old method : 0.03685903549194336 length of segment : 346 time for calcul the mask position with numpy : 0.15649938583374023 nb_pixel_total : 32869 time to create 1 rle with old method : 0.03923773765563965 length of segment : 214 time for calcul the mask position with numpy : 0.06372857093811035 nb_pixel_total : 13894 time to create 1 rle with old method : 0.01966238021850586 length of segment : 111 time for calcul the mask position with numpy : 0.08026289939880371 nb_pixel_total : 20817 time to create 1 rle with old method : 0.031171083450317383 length of segment : 186 time for calcul the mask position with numpy : 0.28720831871032715 nb_pixel_total : 94401 time to create 1 rle with old method : 0.11352729797363281 length of segment : 557 time for calcul the mask position with numpy : 0.1160576343536377 nb_pixel_total : 23411 time to create 1 rle with old method : 0.02998661994934082 length of segment : 272 time for calcul the mask position with numpy : 0.07517576217651367 nb_pixel_total : 15664 time to create 1 rle with old method : 0.020249605178833008 length of segment : 192 time for calcul the mask position with numpy : 0.042775869369506836 nb_pixel_total : 13466 time to create 1 rle with old method : 0.02245330810546875 length of segment : 187 time for calcul the mask position with numpy : 0.030995845794677734 nb_pixel_total : 10980 time to create 1 rle with old method : 0.01807880401611328 length of segment : 136 time for calcul the mask position with numpy : 0.2993009090423584 nb_pixel_total : 71171 time to create 1 rle with old method : 0.09304428100585938 length of segment : 783 time for calcul the mask position with numpy : 0.2810370922088623 nb_pixel_total : 68566 time to create 1 rle with old method : 0.08637881278991699 length of segment : 287 time for calcul the mask position with numpy : 0.26275634765625 nb_pixel_total : 150107 time to create 1 rle with new method : 0.008565425872802734 length of segment : 498 time for calcul the mask position with numpy : 0.05234479904174805 nb_pixel_total : 14334 time to create 1 rle with old method : 0.021079540252685547 length of segment : 134 time for calcul the mask position with numpy : 0.006849527359008789 nb_pixel_total : 21917 time to create 1 rle with old method : 0.030178308486938477 length of segment : 191 time for calcul the mask position with numpy : 0.04720711708068848 nb_pixel_total : 29694 time to create 1 rle with old method : 0.039130449295043945 length of segment : 217 time for calcul the mask position with numpy : 0.09867668151855469 nb_pixel_total : 34226 time to create 1 rle with old method : 0.04363083839416504 length of segment : 246 time for calcul the mask position with numpy : 0.18862318992614746 nb_pixel_total : 18549 time to create 1 rle with old method : 0.025916337966918945 length of segment : 159 time for calcul the mask position with numpy : 0.011270999908447266 nb_pixel_total : 34568 time to create 1 rle with old method : 0.04493904113769531 length of segment : 339 time for calcul the mask position with numpy : 0.0025005340576171875 nb_pixel_total : 7286 time to create 1 rle with old method : 0.010704994201660156 length of segment : 104 time for calcul the mask position with numpy : 0.3168909549713135 nb_pixel_total : 65112 time to create 1 rle with old method : 0.08270931243896484 length of segment : 458 time for calcul the mask position with numpy : 0.3926737308502197 nb_pixel_total : 38000 time to create 1 rle with old method : 0.048779964447021484 length of segment : 250 time for calcul the mask position with numpy : 1.804306983947754 nb_pixel_total : 256089 time to create 1 rle with new method : 0.03296327590942383 length of segment : 934 time for calcul the mask position with numpy : 0.08404207229614258 nb_pixel_total : 18759 time to create 1 rle with old method : 0.027668237686157227 length of segment : 197 time for calcul the mask position with numpy : 0.03328824043273926 nb_pixel_total : 14497 time to create 1 rle with old method : 0.022094011306762695 length of segment : 191 time for calcul the mask position with numpy : 0.08262944221496582 nb_pixel_total : 19652 time to create 1 rle with old method : 0.029501914978027344 length of segment : 185 time for calcul the mask position with numpy : 0.11264801025390625 nb_pixel_total : 19111 time to create 1 rle with old method : 0.032708168029785156 length of segment : 170 time for calcul the mask position with numpy : 0.05528616905212402 nb_pixel_total : 10462 time to create 1 rle with old method : 0.017976760864257812 length of segment : 93 time for calcul the mask position with numpy : 0.04263114929199219 nb_pixel_total : 7281 time to create 1 rle with old method : 0.011861324310302734 length of segment : 98 time for calcul the mask position with numpy : 0.057065486907958984 nb_pixel_total : 10185 time to create 1 rle with old method : 0.01730799674987793 length of segment : 109 time for calcul the mask position with numpy : 0.10830092430114746 nb_pixel_total : 20541 time to create 1 rle with old method : 0.027740478515625 length of segment : 193 time for calcul the mask position with numpy : 0.07268476486206055 nb_pixel_total : 16225 time to create 1 rle with old method : 0.028851747512817383 length of segment : 180 time for calcul the mask position with numpy : 0.12085819244384766 nb_pixel_total : 26230 time to create 1 rle with old method : 0.04241132736206055 length of segment : 183 time for calcul the mask position with numpy : 0.055307626724243164 nb_pixel_total : 8779 time to create 1 rle with old method : 0.01703810691833496 length of segment : 120 time for calcul the mask position with numpy : 0.39031410217285156 nb_pixel_total : 105366 time to create 1 rle with old method : 0.1461341381072998 length of segment : 397 time for calcul the mask position with numpy : 0.06365442276000977 nb_pixel_total : 11046 time to create 1 rle with old method : 0.01864171028137207 length of segment : 118 time for calcul the mask position with numpy : 0.13274240493774414 nb_pixel_total : 44846 time to create 1 rle with old method : 0.05355238914489746 length of segment : 319 time for calcul the mask position with numpy : 0.13996005058288574 nb_pixel_total : 40597 time to create 1 rle with old method : 0.05188751220703125 length of segment : 245 time for calcul the mask position with numpy : 0.005010128021240234 nb_pixel_total : 26782 time to create 1 rle with old method : 0.03322958946228027 length of segment : 143 time for calcul the mask position with numpy : 0.12822985649108887 nb_pixel_total : 26899 time to create 1 rle with old method : 0.03587841987609863 length of segment : 270 time for calcul the mask position with numpy : 0.08797669410705566 nb_pixel_total : 14616 time to create 1 rle with old method : 0.01984429359436035 length of segment : 160 time for calcul the mask position with numpy : 0.019915103912353516 nb_pixel_total : 21118 time to create 1 rle with old method : 0.029754638671875 length of segment : 300 time for calcul the mask position with numpy : 0.22728991508483887 nb_pixel_total : 43087 time to create 1 rle with old method : 0.05566000938415527 length of segment : 390 time for calcul the mask position with numpy : 0.008959293365478516 nb_pixel_total : 5335 time to create 1 rle with old method : 0.007412433624267578 length of segment : 73 time for calcul the mask position with numpy : 0.08693361282348633 nb_pixel_total : 27115 time to create 1 rle with old method : 0.03470039367675781 length of segment : 175 time for calcul the mask position with numpy : 0.027960538864135742 nb_pixel_total : 6507 time to create 1 rle with old method : 0.01364278793334961 length of segment : 124 time for calcul the mask position with numpy : 0.10467934608459473 nb_pixel_total : 44236 time to create 1 rle with old method : 0.060480594635009766 length of segment : 321 time for calcul the mask position with numpy : 0.03966379165649414 nb_pixel_total : 12595 time to create 1 rle with old method : 0.018195390701293945 length of segment : 193 time for calcul the mask position with numpy : 0.20081329345703125 nb_pixel_total : 33066 time to create 1 rle with old method : 0.047115325927734375 length of segment : 523 time for calcul the mask position with numpy : 0.07924056053161621 nb_pixel_total : 14113 time to create 1 rle with old method : 0.02326202392578125 length of segment : 217 time for calcul the mask position with numpy : 0.0696709156036377 nb_pixel_total : 14398 time to create 1 rle with old method : 0.023699045181274414 length of segment : 178 time for calcul the mask position with numpy : 0.03345131874084473 nb_pixel_total : 5074 time to create 1 rle with old method : 0.010173559188842773 length of segment : 106 time for calcul the mask position with numpy : 0.06396055221557617 nb_pixel_total : 12169 time to create 1 rle with old method : 0.02013373374938965 length of segment : 143 time for calcul the mask position with numpy : 0.1106259822845459 nb_pixel_total : 28032 time to create 1 rle with old method : 0.03810930252075195 length of segment : 302 time for calcul the mask position with numpy : 0.05926084518432617 nb_pixel_total : 21128 time to create 1 rle with old method : 0.029081344604492188 length of segment : 91 time for calcul the mask position with numpy : 0.030223608016967773 nb_pixel_total : 8998 time to create 1 rle with old method : 0.015108108520507812 length of segment : 66 time for calcul the mask position with numpy : 0.00028586387634277344 nb_pixel_total : 8865 time to create 1 rle with old method : 0.010538816452026367 length of segment : 74 time for calcul the mask position with numpy : 0.03954768180847168 nb_pixel_total : 13901 time to create 1 rle with old method : 0.021449565887451172 length of segment : 169 time for calcul the mask position with numpy : 0.024359941482543945 nb_pixel_total : 5126 time to create 1 rle with old method : 0.009229660034179688 length of segment : 95 time for calcul the mask position with numpy : 0.03189992904663086 nb_pixel_total : 13261 time to create 1 rle with old method : 0.02830028533935547 length of segment : 251 time for calcul the mask position with numpy : 0.0016448497772216797 nb_pixel_total : 49588 time to create 1 rle with old method : 0.058347225189208984 length of segment : 580 time for calcul the mask position with numpy : 0.12708640098571777 nb_pixel_total : 58435 time to create 1 rle with old method : 0.06926441192626953 length of segment : 368 time for calcul the mask position with numpy : 0.014502763748168945 nb_pixel_total : 6007 time to create 1 rle with old method : 0.01170492172241211 length of segment : 80 time for calcul the mask position with numpy : 0.13844919204711914 nb_pixel_total : 55511 time to create 1 rle with old method : 0.06725001335144043 length of segment : 365 time for calcul the mask position with numpy : 0.14613580703735352 nb_pixel_total : 78680 time to create 1 rle with old method : 0.0935516357421875 length of segment : 413 time for calcul the mask position with numpy : 0.046267032623291016 nb_pixel_total : 11743 time to create 1 rle with old method : 0.014552593231201172 length of segment : 228 time for calcul the mask position with numpy : 0.0543980598449707 nb_pixel_total : 14250 time to create 1 rle with old method : 0.021595239639282227 length of segment : 94 time for calcul the mask position with numpy : 0.11227607727050781 nb_pixel_total : 18704 time to create 1 rle with old method : 0.027377843856811523 length of segment : 192 time for calcul the mask position with numpy : 0.07989883422851562 nb_pixel_total : 18066 time to create 1 rle with old method : 0.029102325439453125 length of segment : 139 time for calcul the mask position with numpy : 0.059130191802978516 nb_pixel_total : 10430 time to create 1 rle with old method : 0.017597675323486328 length of segment : 152 time for calcul the mask position with numpy : 0.3705134391784668 nb_pixel_total : 73157 time to create 1 rle with old method : 0.08681249618530273 length of segment : 340 time for calcul the mask position with numpy : 0.1945955753326416 nb_pixel_total : 38849 time to create 1 rle with old method : 0.050740718841552734 length of segment : 246 time for calcul the mask position with numpy : 0.07968640327453613 nb_pixel_total : 15895 time to create 1 rle with old method : 0.03410649299621582 length of segment : 152 time for calcul the mask position with numpy : 0.10877203941345215 nb_pixel_total : 19927 time to create 1 rle with old method : 0.030054569244384766 length of segment : 198 time for calcul the mask position with numpy : 0.07598209381103516 nb_pixel_total : 13376 time to create 1 rle with old method : 0.019425392150878906 length of segment : 136 time for calcul the mask position with numpy : 0.04250359535217285 nb_pixel_total : 7330 time to create 1 rle with old method : 0.014060020446777344 length of segment : 87 time for calcul the mask position with numpy : 0.18212580680847168 nb_pixel_total : 52762 time to create 1 rle with old method : 0.06710481643676758 length of segment : 283 time for calcul the mask position with numpy : 0.11034607887268066 nb_pixel_total : 18101 time to create 1 rle with old method : 0.026328325271606445 length of segment : 235 time for calcul the mask position with numpy : 0.07254171371459961 nb_pixel_total : 23403 time to create 1 rle with old method : 0.04873085021972656 length of segment : 250 time for calcul the mask position with numpy : 0.27112460136413574 nb_pixel_total : 54453 time to create 1 rle with old method : 0.06842541694641113 length of segment : 256 time for calcul the mask position with numpy : 0.057724714279174805 nb_pixel_total : 10581 time to create 1 rle with old method : 0.017847537994384766 length of segment : 122 time for calcul the mask position with numpy : 0.0960085391998291 nb_pixel_total : 22845 time to create 1 rle with old method : 0.033733367919921875 length of segment : 112 time for calcul the mask position with numpy : 0.12395763397216797 nb_pixel_total : 24557 time to create 1 rle with old method : 0.03197646141052246 length of segment : 166 time for calcul the mask position with numpy : 0.06948566436767578 nb_pixel_total : 22084 time to create 1 rle with old method : 0.033922672271728516 length of segment : 217 time for calcul the mask position with numpy : 0.11915421485900879 nb_pixel_total : 21443 time to create 1 rle with old method : 0.029118061065673828 length of segment : 173 time for calcul the mask position with numpy : 0.1001744270324707 nb_pixel_total : 14610 time to create 1 rle with old method : 0.02270650863647461 length of segment : 226 time for calcul the mask position with numpy : 0.09188222885131836 nb_pixel_total : 17350 time to create 1 rle with old method : 0.0232698917388916 length of segment : 223 time for calcul the mask position with numpy : 0.2933049201965332 nb_pixel_total : 78219 time to create 1 rle with old method : 0.10545516014099121 length of segment : 396 time for calcul the mask position with numpy : 0.030481338500976562 nb_pixel_total : 10252 time to create 1 rle with old method : 0.01597309112548828 length of segment : 121 time for calcul the mask position with numpy : 0.01478719711303711 nb_pixel_total : 5947 time to create 1 rle with old method : 0.012133598327636719 length of segment : 69 time for calcul the mask position with numpy : 0.023711204528808594 nb_pixel_total : 9161 time to create 1 rle with old method : 0.016146421432495117 length of segment : 109 time for calcul the mask position with numpy : 0.0355682373046875 nb_pixel_total : 12282 time to create 1 rle with old method : 0.019202709197998047 length of segment : 175 time for calcul the mask position with numpy : 0.044141292572021484 nb_pixel_total : 12178 time to create 1 rle with old method : 0.020723581314086914 length of segment : 153 time for calcul the mask position with numpy : 0.24300599098205566 nb_pixel_total : 78247 time to create 1 rle with old method : 0.1118764877319336 length of segment : 443 time for calcul the mask position with numpy : 0.20068883895874023 nb_pixel_total : 22100 time to create 1 rle with old method : 0.030068397521972656 length of segment : 342 time for calcul the mask position with numpy : 0.05393099784851074 nb_pixel_total : 8921 time to create 1 rle with old method : 0.014846563339233398 length of segment : 104 time for calcul the mask position with numpy : 0.10483169555664062 nb_pixel_total : 36595 time to create 1 rle with old method : 0.04612159729003906 length of segment : 187 time for calcul the mask position with numpy : 0.0870201587677002 nb_pixel_total : 15022 time to create 1 rle with old method : 0.02112102508544922 length of segment : 181 time for calcul the mask position with numpy : 0.03483319282531738 nb_pixel_total : 14787 time to create 1 rle with old method : 0.02224111557006836 length of segment : 143 time for calcul the mask position with numpy : 0.023540973663330078 nb_pixel_total : 4687 time to create 1 rle with old method : 0.010508298873901367 length of segment : 63 time for calcul the mask position with numpy : 0.05341792106628418 nb_pixel_total : 13948 time to create 1 rle with old method : 0.02097010612487793 length of segment : 294 time for calcul the mask position with numpy : 0.07236146926879883 nb_pixel_total : 14529 time to create 1 rle with old method : 0.01990485191345215 length of segment : 171 time for calcul the mask position with numpy : 0.12654781341552734 nb_pixel_total : 40173 time to create 1 rle with old method : 0.05658698081970215 length of segment : 581 time for calcul the mask position with numpy : 0.05033230781555176 nb_pixel_total : 18412 time to create 1 rle with old method : 0.03594541549682617 length of segment : 185 time for calcul the mask position with numpy : 2.1310245990753174 nb_pixel_total : 944939 time to create 1 rle with new method : 0.1068718433380127 length of segment : 1174 time for calcul the mask position with numpy : 0.08455276489257812 nb_pixel_total : 10926 time to create 1 rle with old method : 0.018477439880371094 length of segment : 236 time for calcul the mask position with numpy : 0.1122896671295166 nb_pixel_total : 43819 time to create 1 rle with old method : 0.057595014572143555 length of segment : 183 time for calcul the mask position with numpy : 0.030080318450927734 nb_pixel_total : 4539 time to create 1 rle with old method : 0.010366201400756836 length of segment : 87 time for calcul the mask position with numpy : 0.07351016998291016 nb_pixel_total : 18933 time to create 1 rle with old method : 0.026772737503051758 length of segment : 165 time for calcul the mask position with numpy : 0.04334855079650879 nb_pixel_total : 10154 time to create 1 rle with old method : 0.01676321029663086 length of segment : 99 time for calcul the mask position with numpy : 0.0002453327178955078 nb_pixel_total : 8030 time to create 1 rle with old method : 0.009941339492797852 length of segment : 86 time for calcul the mask position with numpy : 0.22046923637390137 nb_pixel_total : 58264 time to create 1 rle with old method : 0.06955480575561523 length of segment : 442 time for calcul the mask position with numpy : 0.00754547119140625 nb_pixel_total : 1926 time to create 1 rle with old method : 0.0031404495239257812 length of segment : 57 time for calcul the mask position with numpy : 0.047141075134277344 nb_pixel_total : 31562 time to create 1 rle with old method : 0.03971529006958008 length of segment : 263 time for calcul the mask position with numpy : 0.029968738555908203 nb_pixel_total : 4098 time to create 1 rle with old method : 0.008283138275146484 length of segment : 85 time for calcul the mask position with numpy : 0.20934653282165527 nb_pixel_total : 49267 time to create 1 rle with old method : 0.06392383575439453 length of segment : 367 time for calcul the mask position with numpy : 0.04513430595397949 nb_pixel_total : 19543 time to create 1 rle with old method : 0.02925586700439453 length of segment : 187 time for calcul the mask position with numpy : 0.00019931793212890625 nb_pixel_total : 8130 time to create 1 rle with old method : 0.009432315826416016 length of segment : 127 time for calcul the mask position with numpy : 0.0009567737579345703 nb_pixel_total : 4608 time to create 1 rle with old method : 0.0056917667388916016 length of segment : 125 time for calcul the mask position with numpy : 0.001975536346435547 nb_pixel_total : 3771 time to create 1 rle with old method : 0.0046994686126708984 length of segment : 99 time for calcul the mask position with numpy : 0.06599211692810059 nb_pixel_total : 12241 time to create 1 rle with old method : 0.019687175750732422 length of segment : 132 time for calcul the mask position with numpy : 0.11475181579589844 nb_pixel_total : 31824 time to create 1 rle with old method : 0.042406320571899414 length of segment : 225 time for calcul the mask position with numpy : 0.0028159618377685547 nb_pixel_total : 2748 time to create 1 rle with old method : 0.003588438034057617 length of segment : 34 time for calcul the mask position with numpy : 0.035299062728881836 nb_pixel_total : 7775 time to create 1 rle with old method : 0.013769388198852539 length of segment : 110 time for calcul the mask position with numpy : 0.04066944122314453 nb_pixel_total : 6463 time to create 1 rle with old method : 0.010483503341674805 length of segment : 84 time for calcul the mask position with numpy : 0.03882193565368652 nb_pixel_total : 13652 time to create 1 rle with old method : 0.021693944931030273 length of segment : 151 time for calcul the mask position with numpy : 0.026549816131591797 nb_pixel_total : 5777 time to create 1 rle with old method : 0.011421680450439453 length of segment : 79 time for calcul the mask position with numpy : 0.09358525276184082 nb_pixel_total : 35424 time to create 1 rle with old method : 0.04317164421081543 length of segment : 308 time for calcul the mask position with numpy : 0.07946014404296875 nb_pixel_total : 21802 time to create 1 rle with old method : 0.03098464012145996 length of segment : 166 time for calcul the mask position with numpy : 0.03794121742248535 nb_pixel_total : 7502 time to create 1 rle with old method : 0.012993812561035156 length of segment : 84 time for calcul the mask position with numpy : 0.06830668449401855 nb_pixel_total : 10774 time to create 1 rle with old method : 0.016599416732788086 length of segment : 119 time for calcul the mask position with numpy : 0.13470935821533203 nb_pixel_total : 24308 time to create 1 rle with old method : 0.02745652198791504 length of segment : 266 time for calcul the mask position with numpy : 0.048084259033203125 nb_pixel_total : 9284 time to create 1 rle with old method : 0.017523765563964844 length of segment : 98 time for calcul the mask position with numpy : 0.05336880683898926 nb_pixel_total : 7674 time to create 1 rle with old method : 0.013326883316040039 length of segment : 101 time for calcul the mask position with numpy : 0.19353032112121582 nb_pixel_total : 44779 time to create 1 rle with old method : 0.05888009071350098 length of segment : 294 time for calcul the mask position with numpy : 0.13491082191467285 nb_pixel_total : 27182 time to create 1 rle with old method : 0.03675341606140137 length of segment : 269 time for calcul the mask position with numpy : 0.10320591926574707 nb_pixel_total : 24051 time to create 1 rle with old method : 0.03441762924194336 length of segment : 198 time for calcul the mask position with numpy : 0.0943295955657959 nb_pixel_total : 21167 time to create 1 rle with old method : 0.027448177337646484 length of segment : 147 time for calcul the mask position with numpy : 0.05600428581237793 nb_pixel_total : 10854 time to create 1 rle with old method : 0.017823219299316406 length of segment : 134 time for calcul the mask position with numpy : 0.09024691581726074 nb_pixel_total : 25475 time to create 1 rle with old method : 0.036115169525146484 length of segment : 190 time for calcul the mask position with numpy : 0.05128192901611328 nb_pixel_total : 13159 time to create 1 rle with old method : 0.02038264274597168 length of segment : 113 time for calcul the mask position with numpy : 0.04984092712402344 nb_pixel_total : 9407 time to create 1 rle with old method : 0.01659393310546875 length of segment : 120 time for calcul the mask position with numpy : 0.10541892051696777 nb_pixel_total : 18978 time to create 1 rle with old method : 0.028654098510742188 length of segment : 218 time for calcul the mask position with numpy : 0.011433124542236328 nb_pixel_total : 2635 time to create 1 rle with old method : 0.0060498714447021484 length of segment : 41 time for calcul the mask position with numpy : 0.10753178596496582 nb_pixel_total : 21331 time to create 1 rle with old method : 0.031615495681762695 length of segment : 172 time for calcul the mask position with numpy : 0.14908432960510254 nb_pixel_total : 16834 time to create 1 rle with old method : 0.025535106658935547 length of segment : 200 time for calcul the mask position with numpy : 0.1006004810333252 nb_pixel_total : 19760 time to create 1 rle with old method : 0.027612686157226562 length of segment : 265 time for calcul the mask position with numpy : 0.16489219665527344 nb_pixel_total : 39651 time to create 1 rle with old method : 0.050252676010131836 length of segment : 262 time for calcul the mask position with numpy : 0.10012698173522949 nb_pixel_total : 17088 time to create 1 rle with old method : 0.02488422393798828 length of segment : 260 time for calcul the mask position with numpy : 0.7016696929931641 nb_pixel_total : 145081 time to create 1 rle with old method : 0.17006516456604004 length of segment : 570 time for calcul the mask position with numpy : 0.12999725341796875 nb_pixel_total : 24234 time to create 1 rle with old method : 0.032434701919555664 length of segment : 173 time for calcul the mask position with numpy : 0.11262106895446777 nb_pixel_total : 28883 time to create 1 rle with old method : 0.039360761642456055 length of segment : 219 time for calcul the mask position with numpy : 0.10496926307678223 nb_pixel_total : 16523 time to create 1 rle with old method : 0.01885247230529785 length of segment : 164 time for calcul the mask position with numpy : 0.08971762657165527 nb_pixel_total : 22335 time to create 1 rle with old method : 0.025346040725708008 length of segment : 277 time for calcul the mask position with numpy : 0.04987478256225586 nb_pixel_total : 11979 time to create 1 rle with old method : 0.020198583602905273 length of segment : 114 time for calcul the mask position with numpy : 0.031145095825195312 nb_pixel_total : 4494 time to create 1 rle with old method : 0.010245084762573242 length of segment : 63 time for calcul the mask position with numpy : 0.08757925033569336 nb_pixel_total : 15089 time to create 1 rle with old method : 0.023949861526489258 length of segment : 185 time for calcul the mask position with numpy : 0.07952642440795898 nb_pixel_total : 30951 time to create 1 rle with old method : 0.03899049758911133 length of segment : 301 time for calcul the mask position with numpy : 0.011528253555297852 nb_pixel_total : 23152 time to create 1 rle with old method : 0.031128883361816406 length of segment : 199 time for calcul the mask position with numpy : 0.0189971923828125 nb_pixel_total : 13434 time to create 1 rle with old method : 0.0158998966217041 length of segment : 129 time for calcul the mask position with numpy : 0.12035036087036133 nb_pixel_total : 22820 time to create 1 rle with old method : 0.03262686729431152 length of segment : 195 time for calcul the mask position with numpy : 0.11719322204589844 nb_pixel_total : 22141 time to create 1 rle with old method : 0.029093027114868164 length of segment : 232 time for calcul the mask position with numpy : 0.03919625282287598 nb_pixel_total : 20881 time to create 1 rle with old method : 0.03329920768737793 length of segment : 153 time for calcul the mask position with numpy : 0.22722673416137695 nb_pixel_total : 101285 time to create 1 rle with old method : 0.1318356990814209 length of segment : 531 time for calcul the mask position with numpy : 0.18048810958862305 nb_pixel_total : 45389 time to create 1 rle with old method : 0.05862140655517578 length of segment : 475 time for calcul the mask position with numpy : 0.07468819618225098 nb_pixel_total : 24823 time to create 1 rle with old method : 0.03485298156738281 length of segment : 210 time for calcul the mask position with numpy : 0.04584217071533203 nb_pixel_total : 8710 time to create 1 rle with old method : 0.014122724533081055 length of segment : 94 time for calcul the mask position with numpy : 0.24317049980163574 nb_pixel_total : 122684 time to create 1 rle with old method : 0.14922451972961426 length of segment : 434 time for calcul the mask position with numpy : 0.06723141670227051 nb_pixel_total : 13181 time to create 1 rle with old method : 0.021666526794433594 length of segment : 115 time for calcul the mask position with numpy : 0.00020360946655273438 nb_pixel_total : 7170 time to create 1 rle with old method : 0.008931636810302734 length of segment : 85 time for calcul the mask position with numpy : 0.17936968803405762 nb_pixel_total : 107474 time to create 1 rle with old method : 0.13097238540649414 length of segment : 243 time for calcul the mask position with numpy : 0.05330514907836914 nb_pixel_total : 16910 time to create 1 rle with old method : 0.026610136032104492 length of segment : 122 time for calcul the mask position with numpy : 0.025142669677734375 nb_pixel_total : 3807 time to create 1 rle with old method : 0.0076367855072021484 length of segment : 56 time for calcul the mask position with numpy : 0.10086226463317871 nb_pixel_total : 25665 time to create 1 rle with old method : 0.03503918647766113 length of segment : 205 time for calcul the mask position with numpy : 0.1324465274810791 nb_pixel_total : 36204 time to create 1 rle with old method : 0.06288695335388184 length of segment : 289 time for calcul the mask position with numpy : 0.0473017692565918 nb_pixel_total : 19334 time to create 1 rle with old method : 0.032469749450683594 length of segment : 142 time for calcul the mask position with numpy : 0.062052011489868164 nb_pixel_total : 19243 time to create 1 rle with old method : 0.027830123901367188 length of segment : 202 time for calcul the mask position with numpy : 0.2480616569519043 nb_pixel_total : 58699 time to create 1 rle with old method : 0.07557344436645508 length of segment : 389 time for calcul the mask position with numpy : 0.006693363189697266 nb_pixel_total : 1810 time to create 1 rle with old method : 0.0023386478424072266 length of segment : 60 time for calcul the mask position with numpy : 0.07821798324584961 nb_pixel_total : 15042 time to create 1 rle with old method : 0.022660493850708008 length of segment : 181 time for calcul the mask position with numpy : 0.146209716796875 nb_pixel_total : 33372 time to create 1 rle with old method : 0.04391741752624512 length of segment : 248 time for calcul the mask position with numpy : 0.0033757686614990234 nb_pixel_total : 12878 time to create 1 rle with old method : 0.0177767276763916 length of segment : 190 time for calcul the mask position with numpy : 0.027378559112548828 nb_pixel_total : 25137 time to create 1 rle with old method : 0.0336308479309082 length of segment : 229 time for calcul the mask position with numpy : 0.17171025276184082 nb_pixel_total : 50706 time to create 1 rle with old method : 0.06192207336425781 length of segment : 304 time for calcul the mask position with numpy : 0.030617713928222656 nb_pixel_total : 11597 time to create 1 rle with old method : 0.017348766326904297 length of segment : 201 time for calcul the mask position with numpy : 0.5321145057678223 nb_pixel_total : 126306 time to create 1 rle with old method : 0.15247774124145508 length of segment : 667 time for calcul the mask position with numpy : 0.040132999420166016 nb_pixel_total : 13161 time to create 1 rle with old method : 0.02159428596496582 length of segment : 156 time for calcul the mask position with numpy : 0.03967642784118652 nb_pixel_total : 12426 time to create 1 rle with old method : 0.018382787704467773 length of segment : 135 time for calcul the mask position with numpy : 0.05885887145996094 nb_pixel_total : 16241 time to create 1 rle with old method : 0.024417400360107422 length of segment : 149 time for calcul the mask position with numpy : 0.00885629653930664 nb_pixel_total : 18 time to create 1 rle with old method : 0.00018310546875 length of segment : 9 time for calcul the mask position with numpy : 0.003849506378173828 nb_pixel_total : 19314 time to create 1 rle with old method : 0.02698040008544922 length of segment : 143 time for calcul the mask position with numpy : 0.062424659729003906 nb_pixel_total : 29634 time to create 1 rle with old method : 0.03835129737854004 length of segment : 251 time for calcul the mask position with numpy : 0.04927396774291992 nb_pixel_total : 17799 time to create 1 rle with old method : 0.02494049072265625 length of segment : 238 time for calcul the mask position with numpy : 0.013476133346557617 nb_pixel_total : 17528 time to create 1 rle with old method : 0.024748563766479492 length of segment : 166 time for calcul the mask position with numpy : 0.15837883949279785 nb_pixel_total : 154222 time to create 1 rle with new method : 0.013027191162109375 length of segment : 713 time for calcul the mask position with numpy : 0.07152748107910156 nb_pixel_total : 24603 time to create 1 rle with old method : 0.03284406661987305 length of segment : 238 time for calcul the mask position with numpy : 0.010725736618041992 nb_pixel_total : 3801 time to create 1 rle with old method : 0.008297204971313477 length of segment : 57 time for calcul the mask position with numpy : 0.023998022079467773 nb_pixel_total : 15695 time to create 1 rle with old method : 0.024527788162231445 length of segment : 184 time for calcul the mask position with numpy : 0.0014879703521728516 nb_pixel_total : 5427 time to create 1 rle with old method : 0.006998777389526367 length of segment : 100 time for calcul the mask position with numpy : 0.09923744201660156 nb_pixel_total : 49178 time to create 1 rle with old method : 0.060735464096069336 length of segment : 419 time for calcul the mask position with numpy : 0.03322029113769531 nb_pixel_total : 14138 time to create 1 rle with old method : 0.02290511131286621 length of segment : 180 time for calcul the mask position with numpy : 0.021641969680786133 nb_pixel_total : 29791 time to create 1 rle with old method : 0.040113210678100586 length of segment : 274 time for calcul the mask position with numpy : 0.0017390251159667969 nb_pixel_total : 6974 time to create 1 rle with old method : 0.008873701095581055 length of segment : 96 time for calcul the mask position with numpy : 0.04254627227783203 nb_pixel_total : 54797 time to create 1 rle with old method : 0.07136893272399902 length of segment : 247 time for calcul the mask position with numpy : 0.014881610870361328 nb_pixel_total : 19745 time to create 1 rle with old method : 0.028196096420288086 length of segment : 193 time for calcul the mask position with numpy : 0.02752685546875 nb_pixel_total : 25992 time to create 1 rle with old method : 0.034526824951171875 length of segment : 337 time for calcul the mask position with numpy : 0.04442119598388672 nb_pixel_total : 65525 time to create 1 rle with old method : 0.08521413803100586 length of segment : 299 time for calcul the mask position with numpy : 0.0011241436004638672 nb_pixel_total : 12542 time to create 1 rle with old method : 0.015724658966064453 length of segment : 81 time for calcul the mask position with numpy : 0.0822455883026123 nb_pixel_total : 51507 time to create 1 rle with old method : 0.07097721099853516 length of segment : 217 time for calcul the mask position with numpy : 0.0035114288330078125 nb_pixel_total : 4723 time to create 1 rle with old method : 0.008147954940795898 length of segment : 66 time for calcul the mask position with numpy : 0.009501457214355469 nb_pixel_total : 5563 time to create 1 rle with old method : 0.007338285446166992 length of segment : 92 time for calcul the mask position with numpy : 0.0022084712982177734 nb_pixel_total : 10703 time to create 1 rle with old method : 0.013437986373901367 length of segment : 112 time for calcul the mask position with numpy : 0.00022530555725097656 nb_pixel_total : 4568 time to create 1 rle with old method : 0.00574183464050293 length of segment : 227 time for calcul the mask position with numpy : 0.0008444786071777344 nb_pixel_total : 10368 time to create 1 rle with old method : 0.017224788665771484 length of segment : 107 time for calcul the mask position with numpy : 0.026822328567504883 nb_pixel_total : 108115 time to create 1 rle with old method : 0.12981295585632324 length of segment : 439 time for calcul the mask position with numpy : 0.003577709197998047 nb_pixel_total : 8216 time to create 1 rle with old method : 0.01099085807800293 length of segment : 86 time for calcul the mask position with numpy : 0.055635929107666016 nb_pixel_total : 27036 time to create 1 rle with old method : 0.03584456443786621 length of segment : 233 time for calcul the mask position with numpy : 0.018283367156982422 nb_pixel_total : 41707 time to create 1 rle with old method : 0.05181694030761719 length of segment : 260 time for calcul the mask position with numpy : 0.0030901432037353516 nb_pixel_total : 15624 time to create 1 rle with old method : 0.019470691680908203 length of segment : 177 time for calcul the mask position with numpy : 0.01294565200805664 nb_pixel_total : 44458 time to create 1 rle with old method : 0.0541074275970459 length of segment : 285 time for calcul the mask position with numpy : 0.03180980682373047 nb_pixel_total : 154367 time to create 1 rle with new method : 0.0051038265228271484 length of segment : 425 time for calcul the mask position with numpy : 0.0578460693359375 nb_pixel_total : 313090 time to create 1 rle with new method : 0.041673898696899414 length of segment : 1642 time for calcul the mask position with numpy : 0.03842425346374512 nb_pixel_total : 217964 time to create 1 rle with new method : 0.009491205215454102 length of segment : 514 time for calcul the mask position with numpy : 0.011811971664428711 nb_pixel_total : 108939 time to create 1 rle with old method : 0.13157010078430176 length of segment : 413 time for calcul the mask position with numpy : 0.006403684616088867 nb_pixel_total : 43515 time to create 1 rle with old method : 0.06076455116271973 length of segment : 215 time for calcul the mask position with numpy : 0.00441741943359375 nb_pixel_total : 15559 time to create 1 rle with old method : 0.023644208908081055 length of segment : 123 time for calcul the mask position with numpy : 0.006096839904785156 nb_pixel_total : 24695 time to create 1 rle with old method : 0.030274152755737305 length of segment : 209 time for calcul the mask position with numpy : 0.003865480422973633 nb_pixel_total : 19032 time to create 1 rle with old method : 0.026095151901245117 length of segment : 150 time for calcul the mask position with numpy : 0.0023260116577148438 nb_pixel_total : 18153 time to create 1 rle with old method : 0.0228424072265625 length of segment : 138 time spent for convertir_results : 85.1486303806305 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 445 chid ids of type : 3594 Number RLEs to save : 109969 save missing photos in datou_result : time spend for datou_step_exec : 327.72120428085327 time spend to save output : 8.868046522140503 total time spend for step 1 : 336.5892508029938 step2:crop_condition Mon Mar 17 20:26:07 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 ! 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 : 12 ! batch 1 Loaded 445 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 ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! 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 : 342 About to insert : list_path_to_insert length 342 new photo from crops ! About to upload 342 photos upload in portfolio : 3736932 init cache_photo without model_param we have 342 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1742239627_576165 we have uploaded 342 photos in the portfolio 3736932 time of upload the photos Elapsed time : 95.75714635848999 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 ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! 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 : 66 About to insert : list_path_to_insert length 66 new photo from crops ! About to upload 66 photos upload in portfolio : 3736932 init cache_photo without model_param we have 66 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1742239740_576165 we have uploaded 66 photos in the portfolio 3736932 time of upload the photos Elapsed time : 19.195069551467896 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 ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3736932 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1742239761_576165 we have uploaded 3 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.0973687171936035 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 ! map_result returned by crop_photo_return_map_crop : length : 27 About to insert : list_path_to_insert length 27 new photo from crops ! About to upload 27 photos upload in portfolio : 3736932 init cache_photo without model_param we have 27 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1742239778_576165 we have uploaded 27 photos in the portfolio 3736932 time of upload the photos Elapsed time : 7.21341872215271 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 ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 3736932 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1742239787_576165 we have uploaded 2 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.7931866645812988 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 ! 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 : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3736932 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1742239789_576165 we have uploaded 3 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.857945442199707 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 ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 3736932 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1742239792_576165 we have uploaded 2 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.7134191989898682 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 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1344944844, 1344944841, 1344944761, 1344944670, 1344944609, 1344944584, 1344941466, 1344941399, 1344940834, 1344940808, 1344940722, 1344940691] Looping around the photos to save general results len do output : 445 /1344958603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958656Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344958999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959136Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959291Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959295Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959297Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959298Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959300Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959305Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959307Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959309Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959311Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959317Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959320Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959321Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959401Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959405Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1344959406Didn'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, '2675453') ('3318', '21501459', '1344944844', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944841', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944761', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944670', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944609', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944584', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941466', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941399', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940834', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940808', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940722', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940691', None, None, None, None, None, '2675453') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1347 time used for this insertion : 0.15340113639831543 save_final save missing photos in datou_result : time spend for datou_step_exec : 225.62667846679688 time spend to save output : 0.16261887550354004 total time spend for step 2 : 225.78929734230042 step3:rle_unique_nms_with_priority Mon Mar 17 20:29:53 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 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 445 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 20 nb_hashtags : 3 time to prepare the origin masks : 5.15313458442688 time for calcul the mask position with numpy : 0.39043688774108887 nb_pixel_total : 5406746 time to create 1 rle with new method : 0.5414304733276367 time for calcul the mask position with numpy : 0.01999354362487793 nb_pixel_total : 15772 time to create 1 rle with old method : 0.017765522003173828 time for calcul the mask position with numpy : 0.020267248153686523 nb_pixel_total : 6935 time to create 1 rle with old method : 0.007574558258056641 time for calcul the mask position with numpy : 0.020437955856323242 nb_pixel_total : 63380 time to create 1 rle with old method : 0.06512451171875 time for calcul the mask position with numpy : 0.020232200622558594 nb_pixel_total : 3977 time to create 1 rle with old method : 0.0050008296966552734 time for calcul the mask position with numpy : 0.01984715461730957 nb_pixel_total : 18507 time to create 1 rle with old method : 0.019293785095214844 time for calcul the mask position with numpy : 0.020246267318725586 nb_pixel_total : 73427 time to create 1 rle with old method : 0.0805811882019043 time for calcul the mask position with numpy : 0.01928997039794922 nb_pixel_total : 78119 time to create 1 rle with old method : 0.08527660369873047 time for calcul the mask position with numpy : 0.02174091339111328 nb_pixel_total : 238888 time to create 1 rle with new method : 0.8262724876403809 time for calcul the mask position with numpy : 0.021748065948486328 nb_pixel_total : 17631 time to create 1 rle with old method : 0.02050495147705078 time for calcul the mask position with numpy : 0.022915124893188477 nb_pixel_total : 39371 time to create 1 rle with old method : 0.04489016532897949 time for calcul the mask position with numpy : 0.021337032318115234 nb_pixel_total : 11363 time to create 1 rle with old method : 0.01261138916015625 time for calcul the mask position with numpy : 0.02272939682006836 nb_pixel_total : 26659 time to create 1 rle with old method : 0.04832935333251953 time for calcul the mask position with numpy : 0.027041196823120117 nb_pixel_total : 107481 time to create 1 rle with old method : 0.12105441093444824 time for calcul the mask position with numpy : 0.02211785316467285 nb_pixel_total : 246468 time to create 1 rle with new method : 0.8480644226074219 time for calcul the mask position with numpy : 0.03745865821838379 nb_pixel_total : 291657 time to create 1 rle with new method : 0.4653327465057373 time for calcul the mask position with numpy : 0.034157752990722656 nb_pixel_total : 147585 time to create 1 rle with old method : 0.17488360404968262 time for calcul the mask position with numpy : 0.03286862373352051 nb_pixel_total : 119149 time to create 1 rle with old method : 0.1363661289215088 time for calcul the mask position with numpy : 0.0321049690246582 nb_pixel_total : 85647 time to create 1 rle with old method : 0.10032033920288086 time for calcul the mask position with numpy : 0.031827449798583984 nb_pixel_total : 43415 time to create 1 rle with old method : 0.04881715774536133 time for calcul the mask position with numpy : 0.031128883361816406 nb_pixel_total : 8063 time to create 1 rle with old method : 0.009103775024414062 create new chi : 4.670978546142578 time to delete rle : 0.015175342559814453 batch 1 Loaded 41 chid ids of type : 3594 ++++++++++++++++++++++++Number RLEs to save : 14727 TO DO : save crop sub photo not yet done ! save time : 0.948131799697876 nb_obj : 33 nb_hashtags : 4 time to prepare the origin masks : 4.836021184921265 time for calcul the mask position with numpy : 0.8641448020935059 nb_pixel_total : 4211905 time to create 1 rle with new method : 0.6277074813842773 time for calcul the mask position with numpy : 0.028322935104370117 nb_pixel_total : 8382 time to create 1 rle with old method : 0.009433507919311523 time for calcul the mask position with numpy : 0.028078794479370117 nb_pixel_total : 20365 time to create 1 rle with old method : 0.023069381713867188 time for calcul the mask position with numpy : 0.0281982421875 nb_pixel_total : 71799 time to create 1 rle with old method : 0.07692670822143555 time for calcul the mask position with numpy : 0.02735304832458496 nb_pixel_total : 10377 time to create 1 rle with old method : 0.011415719985961914 time for calcul the mask position with numpy : 0.02769947052001953 nb_pixel_total : 4928 time to create 1 rle with old method : 0.005530118942260742 time for calcul the mask position with numpy : 0.027807950973510742 nb_pixel_total : 83732 time to create 1 rle with old method : 0.09579730033874512 time for calcul the mask position with numpy : 0.026436567306518555 nb_pixel_total : 35145 time to create 1 rle with old method : 0.04009389877319336 time for calcul the mask position with numpy : 0.02834010124206543 nb_pixel_total : 13307 time to create 1 rle with old method : 0.014487028121948242 time for calcul the mask position with numpy : 0.028649568557739258 nb_pixel_total : 61991 time to create 1 rle with old method : 0.06930232048034668 time for calcul the mask position with numpy : 0.028699398040771484 nb_pixel_total : 62082 time to create 1 rle with old method : 0.07449579238891602 time for calcul the mask position with numpy : 0.02794647216796875 nb_pixel_total : 24169 time to create 1 rle with old method : 0.027440547943115234 time for calcul the mask position with numpy : 0.028453826904296875 nb_pixel_total : 71110 time to create 1 rle with old method : 0.07688546180725098 time for calcul the mask position with numpy : 0.028172016143798828 nb_pixel_total : 33388 time to create 1 rle with old method : 0.03712773323059082 time for calcul the mask position with numpy : 0.02932143211364746 nb_pixel_total : 224391 time to create 1 rle with new method : 0.7086007595062256 time for calcul the mask position with numpy : 0.029567241668701172 nb_pixel_total : 400671 time to create 1 rle with new method : 0.5375809669494629 time for calcul the mask position with numpy : 0.028701305389404297 nb_pixel_total : 214391 time to create 1 rle with new method : 0.5090315341949463 time for calcul the mask position with numpy : 0.027630329132080078 nb_pixel_total : 11816 time to create 1 rle with old method : 0.013181447982788086 time for calcul the mask position with numpy : 0.028620243072509766 nb_pixel_total : 171037 time to create 1 rle with new method : 0.6629095077514648 time for calcul the mask position with numpy : 0.027011394500732422 nb_pixel_total : 11798 time to create 1 rle with old method : 0.013416290283203125 time for calcul the mask position with numpy : 0.02876877784729004 nb_pixel_total : 171407 time to create 1 rle with new method : 0.4453413486480713 time for calcul the mask position with numpy : 0.027857303619384766 nb_pixel_total : 15943 time to create 1 rle with old method : 0.01794290542602539 time for calcul the mask position with numpy : 0.028013229370117188 nb_pixel_total : 150681 time to create 1 rle with new method : 0.5164947509765625 time for calcul the mask position with numpy : 0.028502464294433594 nb_pixel_total : 63020 time to create 1 rle with old method : 0.07485604286193848 time for calcul the mask position with numpy : 0.029180526733398438 nb_pixel_total : 169530 time to create 1 rle with new method : 0.645035982131958 time for calcul the mask position with numpy : 0.02665257453918457 nb_pixel_total : 79420 time to create 1 rle with old method : 0.08677315711975098 time for calcul the mask position with numpy : 0.028655529022216797 nb_pixel_total : 374581 time to create 1 rle with new method : 0.41854143142700195 time for calcul the mask position with numpy : 0.02892899513244629 nb_pixel_total : 141761 time to create 1 rle with old method : 0.15240716934204102 time for calcul the mask position with numpy : 0.02753281593322754 nb_pixel_total : 48372 time to create 1 rle with old method : 0.05384516716003418 time for calcul the mask position with numpy : 0.02754831314086914 nb_pixel_total : 23123 time to create 1 rle with old method : 0.02468276023864746 time for calcul the mask position with numpy : 0.02766895294189453 nb_pixel_total : 8671 time to create 1 rle with old method : 0.009685993194580078 time for calcul the mask position with numpy : 0.028294086456298828 nb_pixel_total : 9858 time to create 1 rle with old method : 0.010645627975463867 time for calcul the mask position with numpy : 0.027225494384765625 nb_pixel_total : 36910 time to create 1 rle with old method : 0.03930020332336426 time for calcul the mask position with numpy : 0.026981115341186523 nb_pixel_total : 10179 time to create 1 rle with old method : 0.011477947235107422 create new chi : 8.14827561378479 time to delete rle : 0.0034868717193603516 batch 1 Loaded 67 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 25618 TO DO : save crop sub photo not yet done ! save time : 1.6937053203582764 nb_obj : 38 nb_hashtags : 3 time to prepare the origin masks : 3.8130886554718018 time for calcul the mask position with numpy : 0.478717565536499 nb_pixel_total : 5445297 time to create 1 rle with new method : 0.6512277126312256 time for calcul the mask position with numpy : 0.028690814971923828 nb_pixel_total : 62162 time to create 1 rle with old method : 0.07030749320983887 time for calcul the mask position with numpy : 0.02911067008972168 nb_pixel_total : 30767 time to create 1 rle with old method : 0.03529787063598633 time for calcul the mask position with numpy : 0.02846240997314453 nb_pixel_total : 32058 time to create 1 rle with old method : 0.03511667251586914 time for calcul the mask position with numpy : 0.028309345245361328 nb_pixel_total : 158231 time to create 1 rle with new method : 0.5510406494140625 time for calcul the mask position with numpy : 0.028996944427490234 nb_pixel_total : 26940 time to create 1 rle with old method : 0.04081082344055176 time for calcul the mask position with numpy : 0.032830238342285156 nb_pixel_total : 34953 time to create 1 rle with old method : 0.06789565086364746 time for calcul the mask position with numpy : 0.02874135971069336 nb_pixel_total : 23354 time to create 1 rle with old method : 0.027947187423706055 time for calcul the mask position with numpy : 0.029570817947387695 nb_pixel_total : 17974 time to create 1 rle with old method : 0.028404951095581055 time for calcul the mask position with numpy : 0.07555031776428223 nb_pixel_total : 117721 time to create 1 rle with old method : 0.3051156997680664 time for calcul the mask position with numpy : 0.05606341361999512 nb_pixel_total : 16303 time to create 1 rle with old method : 0.029682397842407227 time for calcul the mask position with numpy : 0.03799247741699219 nb_pixel_total : 13773 time to create 1 rle with old method : 0.02526569366455078 time for calcul the mask position with numpy : 0.038141727447509766 nb_pixel_total : 20283 time to create 1 rle with old method : 0.037871360778808594 time for calcul the mask position with numpy : 0.038605451583862305 nb_pixel_total : 32098 time to create 1 rle with old method : 0.058887481689453125 time for calcul the mask position with numpy : 0.039021968841552734 nb_pixel_total : 23739 time to create 1 rle with old method : 0.0444331169128418 time for calcul the mask position with numpy : 0.05082821846008301 nb_pixel_total : 40904 time to create 1 rle with old method : 0.07501029968261719 time for calcul the mask position with numpy : 0.03863883018493652 nb_pixel_total : 38820 time to create 1 rle with old method : 0.07283782958984375 time for calcul the mask position with numpy : 0.03796982765197754 nb_pixel_total : 16330 time to create 1 rle with old method : 0.03005242347717285 time for calcul the mask position with numpy : 0.036679744720458984 nb_pixel_total : 11931 time to create 1 rle with old method : 0.022150278091430664 time for calcul the mask position with numpy : 0.03647136688232422 nb_pixel_total : 1677 time to create 1 rle with old method : 0.0037946701049804688 time for calcul the mask position with numpy : 0.03747057914733887 nb_pixel_total : 105983 time to create 1 rle with old method : 0.19428038597106934 time for calcul the mask position with numpy : 0.03780364990234375 nb_pixel_total : 13970 time to create 1 rle with old method : 0.026308774948120117 time for calcul the mask position with numpy : 0.038214921951293945 nb_pixel_total : 58807 time to create 1 rle with old method : 0.06809234619140625 time for calcul the mask position with numpy : 0.02931976318359375 nb_pixel_total : 10892 time to create 1 rle with old method : 0.012657403945922852 time for calcul the mask position with numpy : 0.029294490814208984 nb_pixel_total : 21871 time to create 1 rle with old method : 0.02503657341003418 time for calcul the mask position with numpy : 0.03427720069885254 nb_pixel_total : 268509 time to create 1 rle with new method : 1.2910075187683105 time for calcul the mask position with numpy : 0.028836965560913086 nb_pixel_total : 7855 time to create 1 rle with old method : 0.009144067764282227 time for calcul the mask position with numpy : 0.02878117561340332 nb_pixel_total : 22879 time to create 1 rle with old method : 0.02704596519470215 time for calcul the mask position with numpy : 0.028849363327026367 nb_pixel_total : 46128 time to create 1 rle with old method : 0.05263710021972656 time for calcul the mask position with numpy : 0.029512643814086914 nb_pixel_total : 186489 time to create 1 rle with new method : 0.6691291332244873 time for calcul the mask position with numpy : 0.029088258743286133 nb_pixel_total : 6153 time to create 1 rle with old method : 0.007061958312988281 time for calcul the mask position with numpy : 0.028920888900756836 nb_pixel_total : 2957 time to create 1 rle with old method : 0.0038475990295410156 time for calcul the mask position with numpy : 0.028290510177612305 nb_pixel_total : 10258 time to create 1 rle with old method : 0.011307001113891602 time for calcul the mask position with numpy : 0.02817702293395996 nb_pixel_total : 6758 time to create 1 rle with old method : 0.0074045658111572266 time for calcul the mask position with numpy : 0.0278170108795166 nb_pixel_total : 9720 time to create 1 rle with old method : 0.010500907897949219 time for calcul the mask position with numpy : 0.027372360229492188 nb_pixel_total : 70651 time to create 1 rle with old method : 0.08022761344909668 time for calcul the mask position with numpy : 0.02922821044921875 nb_pixel_total : 15243 time to create 1 rle with old method : 0.018324613571166992 time for calcul the mask position with numpy : 0.032918691635131836 nb_pixel_total : 10435 time to create 1 rle with old method : 0.012126684188842773 time for calcul the mask position with numpy : 0.029101848602294922 nb_pixel_total : 9367 time to create 1 rle with old method : 0.01067352294921875 create new chi : 6.64108943939209 time to delete rle : 0.003520965576171875 batch 1 Loaded 78 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 22857 TO DO : save crop sub photo not yet done ! save time : 1.974400520324707 nb_obj : 25 nb_hashtags : 4 time to prepare the origin masks : 8.154691934585571 time for calcul the mask position with numpy : 0.4208815097808838 nb_pixel_total : 5591191 time to create 1 rle with new method : 0.5169003009796143 time for calcul the mask position with numpy : 0.03211665153503418 nb_pixel_total : 50015 time to create 1 rle with old method : 0.05901217460632324 time for calcul the mask position with numpy : 0.02747344970703125 nb_pixel_total : 9263 time to create 1 rle with old method : 0.0157928466796875 time for calcul the mask position with numpy : 0.022057294845581055 nb_pixel_total : 23396 time to create 1 rle with old method : 0.02703261375427246 time for calcul the mask position with numpy : 0.02514958381652832 nb_pixel_total : 55139 time to create 1 rle with old method : 0.06854844093322754 time for calcul the mask position with numpy : 0.02216196060180664 nb_pixel_total : 169673 time to create 1 rle with new method : 0.5389232635498047 time for calcul the mask position with numpy : 0.02104043960571289 nb_pixel_total : 3272 time to create 1 rle with old method : 0.0036225318908691406 time for calcul the mask position with numpy : 0.021483659744262695 nb_pixel_total : 19182 time to create 1 rle with old method : 0.022693157196044922 time for calcul the mask position with numpy : 0.02085733413696289 nb_pixel_total : 43744 time to create 1 rle with old method : 0.04908156394958496 time for calcul the mask position with numpy : 0.02188563346862793 nb_pixel_total : 76690 time to create 1 rle with old method : 0.09326767921447754 time for calcul the mask position with numpy : 0.022480010986328125 nb_pixel_total : 100619 time to create 1 rle with old method : 0.11312651634216309 time for calcul the mask position with numpy : 0.021750926971435547 nb_pixel_total : 12472 time to create 1 rle with old method : 0.01429295539855957 time for calcul the mask position with numpy : 0.02094554901123047 nb_pixel_total : 30782 time to create 1 rle with old method : 0.03574562072753906 time for calcul the mask position with numpy : 0.021451473236083984 nb_pixel_total : 29567 time to create 1 rle with old method : 0.035489559173583984 time for calcul the mask position with numpy : 0.0214996337890625 nb_pixel_total : 121215 time to create 1 rle with old method : 0.1454625129699707 time for calcul the mask position with numpy : 0.022914409637451172 nb_pixel_total : 11236 time to create 1 rle with old method : 0.013468027114868164 time for calcul the mask position with numpy : 0.022515296936035156 nb_pixel_total : 20911 time to create 1 rle with old method : 0.024613618850708008 time for calcul the mask position with numpy : 0.022725820541381836 nb_pixel_total : 17944 time to create 1 rle with old method : 0.020592689514160156 time for calcul the mask position with numpy : 0.02630472183227539 nb_pixel_total : 146819 time to create 1 rle with old method : 0.16916823387145996 time for calcul the mask position with numpy : 0.022273778915405273 nb_pixel_total : 29482 time to create 1 rle with old method : 0.035566091537475586 time for calcul the mask position with numpy : 0.022398948669433594 nb_pixel_total : 9807 time to create 1 rle with old method : 0.011567115783691406 time for calcul the mask position with numpy : 0.022818326950073242 nb_pixel_total : 178527 time to create 1 rle with new method : 0.3604621887207031 time for calcul the mask position with numpy : 0.02261495590209961 nb_pixel_total : 16533 time to create 1 rle with old method : 0.019220829010009766 time for calcul the mask position with numpy : 0.0220797061920166 nb_pixel_total : 177653 time to create 1 rle with new method : 0.39394164085388184 time for calcul the mask position with numpy : 0.021342992782592773 nb_pixel_total : 91099 time to create 1 rle with old method : 0.10247302055358887 time for calcul the mask position with numpy : 0.022411584854125977 nb_pixel_total : 14009 time to create 1 rle with old method : 0.016365766525268555 create new chi : 3.9974546432495117 time to delete rle : 0.002419710159301758 batch 1 Loaded 51 chid ids of type : 3594 +++++++++++++++++++++++++++++++Number RLEs to save : 15637 TO DO : save crop sub photo not yet done ! save time : 0.928391695022583 nb_obj : 62 nb_hashtags : 4 time to prepare the origin masks : 4.368598937988281 time for calcul the mask position with numpy : 0.6818373203277588 nb_pixel_total : 5360903 time to create 1 rle with new method : 1.4990088939666748 time for calcul the mask position with numpy : 0.02929091453552246 nb_pixel_total : 26318 time to create 1 rle with old method : 0.029813766479492188 time for calcul the mask position with numpy : 0.029225587844848633 nb_pixel_total : 6908 time to create 1 rle with old method : 0.009033918380737305 time for calcul the mask position with numpy : 0.03246927261352539 nb_pixel_total : 4975 time to create 1 rle with old method : 0.005957365036010742 time for calcul the mask position with numpy : 0.030511140823364258 nb_pixel_total : 128933 time to create 1 rle with old method : 0.15186429023742676 time for calcul the mask position with numpy : 0.029317140579223633 nb_pixel_total : 23645 time to create 1 rle with old method : 0.026896238327026367 time for calcul the mask position with numpy : 0.028888225555419922 nb_pixel_total : 15888 time to create 1 rle with old method : 0.019130945205688477 time for calcul the mask position with numpy : 0.028807878494262695 nb_pixel_total : 6477 time to create 1 rle with old method : 0.00755763053894043 time for calcul the mask position with numpy : 0.02906513214111328 nb_pixel_total : 6234 time to create 1 rle with old method : 0.0071985721588134766 time for calcul the mask position with numpy : 0.0290834903717041 nb_pixel_total : 16750 time to create 1 rle with old method : 0.02003335952758789 time for calcul the mask position with numpy : 0.029117345809936523 nb_pixel_total : 17172 time to create 1 rle with old method : 0.02068471908569336 time for calcul the mask position with numpy : 0.029071569442749023 nb_pixel_total : 32916 time to create 1 rle with old method : 0.038639068603515625 time for calcul the mask position with numpy : 0.02916693687438965 nb_pixel_total : 21691 time to create 1 rle with old method : 0.02506566047668457 time for calcul the mask position with numpy : 0.02901172637939453 nb_pixel_total : 18216 time to create 1 rle with old method : 0.02091526985168457 time for calcul the mask position with numpy : 0.029086589813232422 nb_pixel_total : 18397 time to create 1 rle with old method : 0.021411657333374023 time for calcul the mask position with numpy : 0.029026031494140625 nb_pixel_total : 18859 time to create 1 rle with old method : 0.022119760513305664 time for calcul the mask position with numpy : 0.029087543487548828 nb_pixel_total : 6250 time to create 1 rle with old method : 0.007466793060302734 time for calcul the mask position with numpy : 0.028982162475585938 nb_pixel_total : 22436 time to create 1 rle with old method : 0.02592182159423828 time for calcul the mask position with numpy : 0.028822898864746094 nb_pixel_total : 23862 time to create 1 rle with old method : 0.02787160873413086 time for calcul the mask position with numpy : 0.02930927276611328 nb_pixel_total : 8228 time to create 1 rle with old method : 0.009998083114624023 time for calcul the mask position with numpy : 0.029031991958618164 nb_pixel_total : 29725 time to create 1 rle with old method : 0.03490328788757324 time for calcul the mask position with numpy : 0.029140472412109375 nb_pixel_total : 32325 time to create 1 rle with old method : 0.038687705993652344 time for calcul the mask position with numpy : 0.029985427856445312 nb_pixel_total : 177457 time to create 1 rle with new method : 0.7488815784454346 time for calcul the mask position with numpy : 0.031340599060058594 nb_pixel_total : 10473 time to create 1 rle with old method : 0.012604713439941406 time for calcul the mask position with numpy : 0.02929234504699707 nb_pixel_total : 34411 time to create 1 rle with old method : 0.0413970947265625 time for calcul the mask position with numpy : 0.028997421264648438 nb_pixel_total : 45184 time to create 1 rle with old method : 0.052411556243896484 time for calcul the mask position with numpy : 0.029451847076416016 nb_pixel_total : 8754 time to create 1 rle with old method : 0.010694026947021484 time for calcul the mask position with numpy : 0.02908468246459961 nb_pixel_total : 27455 time to create 1 rle with old method : 0.032697200775146484 time for calcul the mask position with numpy : 0.02905130386352539 nb_pixel_total : 37421 time to create 1 rle with old method : 0.04223775863647461 time for calcul the mask position with numpy : 0.02905416488647461 nb_pixel_total : 18733 time to create 1 rle with old method : 0.022100210189819336 time for calcul the mask position with numpy : 0.0290679931640625 nb_pixel_total : 44841 time to create 1 rle with old method : 0.05333900451660156 time for calcul the mask position with numpy : 0.029097557067871094 nb_pixel_total : 12912 time to create 1 rle with old method : 0.015438079833984375 time for calcul the mask position with numpy : 0.0317838191986084 nb_pixel_total : 137218 time to create 1 rle with old method : 0.17351961135864258 time for calcul the mask position with numpy : 0.029623746871948242 nb_pixel_total : 11048 time to create 1 rle with old method : 0.017926931381225586 time for calcul the mask position with numpy : 0.03314638137817383 nb_pixel_total : 17315 time to create 1 rle with old method : 0.027664899826049805 time for calcul the mask position with numpy : 0.03070521354675293 nb_pixel_total : 41782 time to create 1 rle with old method : 0.04753565788269043 time for calcul the mask position with numpy : 0.02939009666442871 nb_pixel_total : 38833 time to create 1 rle with old method : 0.044397592544555664 time for calcul the mask position with numpy : 0.029100894927978516 nb_pixel_total : 14432 time to create 1 rle with old method : 0.016399383544921875 time for calcul the mask position with numpy : 0.029290437698364258 nb_pixel_total : 68420 time to create 1 rle with old method : 0.07795572280883789 time for calcul the mask position with numpy : 0.030806779861450195 nb_pixel_total : 22907 time to create 1 rle with old method : 0.027471065521240234 time for calcul the mask position with numpy : 0.02917170524597168 nb_pixel_total : 21733 time to create 1 rle with old method : 0.025367021560668945 time for calcul the mask position with numpy : 0.029074430465698242 nb_pixel_total : 6041 time to create 1 rle with old method : 0.007281780242919922 time for calcul the mask position with numpy : 0.029216527938842773 nb_pixel_total : 18424 time to create 1 rle with old method : 0.0211942195892334 time for calcul the mask position with numpy : 0.029255390167236328 nb_pixel_total : 18685 time to create 1 rle with old method : 0.021620512008666992 time for calcul the mask position with numpy : 0.029385089874267578 nb_pixel_total : 958 time to create 1 rle with old method : 0.0013844966888427734 time for calcul the mask position with numpy : 0.03081059455871582 nb_pixel_total : 36957 time to create 1 rle with old method : 0.05249929428100586 time for calcul the mask position with numpy : 0.034661054611206055 nb_pixel_total : 15259 time to create 1 rle with old method : 0.018372535705566406 time for calcul the mask position with numpy : 0.029270172119140625 nb_pixel_total : 14397 time to create 1 rle with old method : 0.016755342483520508 time for calcul the mask position with numpy : 0.02934432029724121 nb_pixel_total : 26704 time to create 1 rle with old method : 0.04250049591064453 time for calcul the mask position with numpy : 0.03598928451538086 nb_pixel_total : 60741 time to create 1 rle with old method : 0.08022689819335938 time for calcul the mask position with numpy : 0.029078245162963867 nb_pixel_total : 14038 time to create 1 rle with old method : 0.01781940460205078 time for calcul the mask position with numpy : 0.029213905334472656 nb_pixel_total : 20593 time to create 1 rle with old method : 0.024812698364257812 time for calcul the mask position with numpy : 0.032982587814331055 nb_pixel_total : 5086 time to create 1 rle with old method : 0.008222818374633789 time for calcul the mask position with numpy : 0.03402447700500488 nb_pixel_total : 28758 time to create 1 rle with old method : 0.033576011657714844 time for calcul the mask position with numpy : 0.029367446899414062 nb_pixel_total : 38284 time to create 1 rle with old method : 0.04348301887512207 time for calcul the mask position with numpy : 0.03358602523803711 nb_pixel_total : 6363 time to create 1 rle with old method : 0.009803295135498047 time for calcul the mask position with numpy : 0.03703022003173828 nb_pixel_total : 28751 time to create 1 rle with old method : 0.044873714447021484 time for calcul the mask position with numpy : 0.033193111419677734 nb_pixel_total : 35905 time to create 1 rle with old method : 0.04325294494628906 time for calcul the mask position with numpy : 0.029303789138793945 nb_pixel_total : 7328 time to create 1 rle with old method : 0.009495258331298828 time for calcul the mask position with numpy : 0.029500722885131836 nb_pixel_total : 5528 time to create 1 rle with old method : 0.0065157413482666016 time for calcul the mask position with numpy : 0.029171228408813477 nb_pixel_total : 12336 time to create 1 rle with old method : 0.01526498794555664 time for calcul the mask position with numpy : 0.029140472412109375 nb_pixel_total : 6365 time to create 1 rle with old method : 0.00784921646118164 time for calcul the mask position with numpy : 0.02925872802734375 nb_pixel_total : 4302 time to create 1 rle with old method : 0.005280733108520508 create new chi : 6.699845552444458 time to delete rle : 0.004507780075073242 batch 1 Loaded 125 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 27882 TO DO : save crop sub photo not yet done ! save time : 1.7999441623687744 nb_obj : 31 nb_hashtags : 3 time to prepare the origin masks : 3.5843825340270996 time for calcul the mask position with numpy : 0.8379385471343994 nb_pixel_total : 6079909 time to create 1 rle with new method : 0.8203175067901611 time for calcul the mask position with numpy : 0.029412508010864258 nb_pixel_total : 3183 time to create 1 rle with old method : 0.0035583972930908203 time for calcul the mask position with numpy : 0.028787851333618164 nb_pixel_total : 19598 time to create 1 rle with old method : 0.022314071655273438 time for calcul the mask position with numpy : 0.029506683349609375 nb_pixel_total : 58471 time to create 1 rle with old method : 0.06855416297912598 time for calcul the mask position with numpy : 0.028273582458496094 nb_pixel_total : 29436 time to create 1 rle with old method : 0.03368949890136719 time for calcul the mask position with numpy : 0.029652833938598633 nb_pixel_total : 49582 time to create 1 rle with old method : 0.05820775032043457 time for calcul the mask position with numpy : 0.029231548309326172 nb_pixel_total : 26876 time to create 1 rle with old method : 0.031083106994628906 time for calcul the mask position with numpy : 0.02889227867126465 nb_pixel_total : 14660 time to create 1 rle with old method : 0.016578197479248047 time for calcul the mask position with numpy : 0.029683351516723633 nb_pixel_total : 24972 time to create 1 rle with old method : 0.028486251831054688 time for calcul the mask position with numpy : 0.03360176086425781 nb_pixel_total : 39800 time to create 1 rle with old method : 0.06031942367553711 time for calcul the mask position with numpy : 0.03127264976501465 nb_pixel_total : 239476 time to create 1 rle with new method : 1.179175853729248 time for calcul the mask position with numpy : 0.029324769973754883 nb_pixel_total : 54758 time to create 1 rle with old method : 0.0650792121887207 time for calcul the mask position with numpy : 0.030333995819091797 nb_pixel_total : 19221 time to create 1 rle with old method : 0.023633956909179688 time for calcul the mask position with numpy : 0.029932260513305664 nb_pixel_total : 41970 time to create 1 rle with old method : 0.049482107162475586 time for calcul the mask position with numpy : 0.02946758270263672 nb_pixel_total : 25904 time to create 1 rle with old method : 0.03072500228881836 time for calcul the mask position with numpy : 0.029689788818359375 nb_pixel_total : 43526 time to create 1 rle with old method : 0.04956316947937012 time for calcul the mask position with numpy : 0.030308246612548828 nb_pixel_total : 15212 time to create 1 rle with old method : 0.018146038055419922 time for calcul the mask position with numpy : 0.03046870231628418 nb_pixel_total : 8409 time to create 1 rle with old method : 0.010343074798583984 time for calcul the mask position with numpy : 0.029142141342163086 nb_pixel_total : 17861 time to create 1 rle with old method : 0.02023029327392578 time for calcul the mask position with numpy : 0.0291440486907959 nb_pixel_total : 3211 time to create 1 rle with old method : 0.003723621368408203 time for calcul the mask position with numpy : 0.028522729873657227 nb_pixel_total : 16008 time to create 1 rle with old method : 0.018619775772094727 time for calcul the mask position with numpy : 0.02850484848022461 nb_pixel_total : 44525 time to create 1 rle with old method : 0.05144071578979492 time for calcul the mask position with numpy : 0.028804540634155273 nb_pixel_total : 10941 time to create 1 rle with old method : 0.012151002883911133 time for calcul the mask position with numpy : 0.02879476547241211 nb_pixel_total : 5718 time to create 1 rle with old method : 0.0065326690673828125 time for calcul the mask position with numpy : 0.028688907623291016 nb_pixel_total : 20372 time to create 1 rle with old method : 0.02280902862548828 time for calcul the mask position with numpy : 0.028769969940185547 nb_pixel_total : 12742 time to create 1 rle with old method : 0.014802217483520508 time for calcul the mask position with numpy : 0.028903961181640625 nb_pixel_total : 14959 time to create 1 rle with old method : 0.01733851432800293 time for calcul the mask position with numpy : 0.028433799743652344 nb_pixel_total : 40254 time to create 1 rle with old method : 0.046877145767211914 time for calcul the mask position with numpy : 0.033321380615234375 nb_pixel_total : 18436 time to create 1 rle with old method : 0.029804229736328125 time for calcul the mask position with numpy : 0.03138017654418945 nb_pixel_total : 27986 time to create 1 rle with old method : 0.030941486358642578 time for calcul the mask position with numpy : 0.027804851531982422 nb_pixel_total : 16058 time to create 1 rle with old method : 0.017992019653320312 time for calcul the mask position with numpy : 0.02779364585876465 nb_pixel_total : 6206 time to create 1 rle with old method : 0.007066488265991211 create new chi : 4.690655708312988 time to delete rle : 0.0036325454711914062 batch 1 Loaded 63 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 15572 TO DO : save crop sub photo not yet done ! save time : 0.9355192184448242 nb_obj : 26 nb_hashtags : 3 time to prepare the origin masks : 3.6211330890655518 time for calcul the mask position with numpy : 0.6453320980072021 nb_pixel_total : 6194942 time to create 1 rle with new method : 0.517390251159668 time for calcul the mask position with numpy : 0.03167867660522461 nb_pixel_total : 18549 time to create 1 rle with old method : 0.0208437442779541 time for calcul the mask position with numpy : 0.028330087661743164 nb_pixel_total : 31358 time to create 1 rle with old method : 0.03497314453125 time for calcul the mask position with numpy : 0.028893470764160156 nb_pixel_total : 13466 time to create 1 rle with old method : 0.015114784240722656 time for calcul the mask position with numpy : 0.02888011932373047 nb_pixel_total : 68566 time to create 1 rle with old method : 0.07959365844726562 time for calcul the mask position with numpy : 0.02981281280517578 nb_pixel_total : 14635 time to create 1 rle with old method : 0.017756223678588867 time for calcul the mask position with numpy : 0.03170061111450195 nb_pixel_total : 71171 time to create 1 rle with old method : 0.08080315589904785 time for calcul the mask position with numpy : 0.03202700614929199 nb_pixel_total : 15664 time to create 1 rle with old method : 0.018564224243164062 time for calcul the mask position with numpy : 0.02840423583984375 nb_pixel_total : 23411 time to create 1 rle with old method : 0.027904033660888672 time for calcul the mask position with numpy : 0.030397891998291016 nb_pixel_total : 150107 time to create 1 rle with new method : 0.33356189727783203 time for calcul the mask position with numpy : 0.029802322387695312 nb_pixel_total : 34226 time to create 1 rle with old method : 0.039849042892456055 time for calcul the mask position with numpy : 0.028775930404663086 nb_pixel_total : 28439 time to create 1 rle with old method : 0.032497406005859375 time for calcul the mask position with numpy : 0.0286099910736084 nb_pixel_total : 32869 time to create 1 rle with old method : 0.037120819091796875 time for calcul the mask position with numpy : 0.028568506240844727 nb_pixel_total : 14334 time to create 1 rle with old method : 0.016059398651123047 time for calcul the mask position with numpy : 0.028584003448486328 nb_pixel_total : 20817 time to create 1 rle with old method : 0.023698091506958008 time for calcul the mask position with numpy : 0.028702497482299805 nb_pixel_total : 18818 time to create 1 rle with old method : 0.02087092399597168 time for calcul the mask position with numpy : 0.027990102767944336 nb_pixel_total : 93795 time to create 1 rle with old method : 0.10624575614929199 time for calcul the mask position with numpy : 0.03100752830505371 nb_pixel_total : 33956 time to create 1 rle with old method : 0.03973078727722168 time for calcul the mask position with numpy : 0.029411792755126953 nb_pixel_total : 18759 time to create 1 rle with old method : 0.022675752639770508 time for calcul the mask position with numpy : 0.028835535049438477 nb_pixel_total : 27352 time to create 1 rle with old method : 0.03164529800415039 time for calcul the mask position with numpy : 0.028695106506347656 nb_pixel_total : 34568 time to create 1 rle with old method : 0.03856611251831055 time for calcul the mask position with numpy : 0.027959823608398438 nb_pixel_total : 17606 time to create 1 rle with old method : 0.01983642578125 time for calcul the mask position with numpy : 0.02849102020263672 nb_pixel_total : 27845 time to create 1 rle with old method : 0.03360414505004883 time for calcul the mask position with numpy : 0.02898120880126953 nb_pixel_total : 7286 time to create 1 rle with old method : 0.0086517333984375 time for calcul the mask position with numpy : 0.030375242233276367 nb_pixel_total : 13894 time to create 1 rle with old method : 0.016238689422607422 time for calcul the mask position with numpy : 0.028644084930419922 nb_pixel_total : 12827 time to create 1 rle with old method : 0.014322042465209961 time for calcul the mask position with numpy : 0.029038667678833008 nb_pixel_total : 10980 time to create 1 rle with old method : 0.013005256652832031 create new chi : 3.1302390098571777 time to delete rle : 0.0024003982543945312 batch 1 Loaded 53 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 15589 TO DO : save crop sub photo not yet done ! save time : 1.0690796375274658 nb_obj : 46 nb_hashtags : 4 time to prepare the origin masks : 4.013475179672241 time for calcul the mask position with numpy : 0.351809024810791 nb_pixel_total : 5699854 time to create 1 rle with new method : 0.43738627433776855 time for calcul the mask position with numpy : 0.029473543167114258 nb_pixel_total : 8779 time to create 1 rle with old method : 0.010676860809326172 time for calcul the mask position with numpy : 0.029413223266601562 nb_pixel_total : 65112 time to create 1 rle with old method : 0.07547187805175781 time for calcul the mask position with numpy : 0.029576539993286133 nb_pixel_total : 26899 time to create 1 rle with old method : 0.03128480911254883 time for calcul the mask position with numpy : 0.03025221824645996 nb_pixel_total : 33066 time to create 1 rle with old method : 0.03956198692321777 time for calcul the mask position with numpy : 0.030460119247436523 nb_pixel_total : 13261 time to create 1 rle with old method : 0.01538228988647461 time for calcul the mask position with numpy : 0.030015230178833008 nb_pixel_total : 40597 time to create 1 rle with old method : 0.045710086822509766 time for calcul the mask position with numpy : 0.029009342193603516 nb_pixel_total : 10462 time to create 1 rle with old method : 0.012004613876342773 time for calcul the mask position with numpy : 0.028639554977416992 nb_pixel_total : 8725 time to create 1 rle with old method : 0.010556697845458984 time for calcul the mask position with numpy : 0.028699398040771484 nb_pixel_total : 6007 time to create 1 rle with old method : 0.007909774780273438 time for calcul the mask position with numpy : 0.02845168113708496 nb_pixel_total : 5074 time to create 1 rle with old method : 0.0059816837310791016 time for calcul the mask position with numpy : 0.029823780059814453 nb_pixel_total : 105366 time to create 1 rle with old method : 0.1220555305480957 time for calcul the mask position with numpy : 0.029321670532226562 nb_pixel_total : 20541 time to create 1 rle with old method : 0.02427506446838379 time for calcul the mask position with numpy : 0.029767274856567383 nb_pixel_total : 28032 time to create 1 rle with old method : 0.034705162048339844 time for calcul the mask position with numpy : 0.029814958572387695 nb_pixel_total : 7281 time to create 1 rle with old method : 0.008973360061645508 time for calcul the mask position with numpy : 0.029636859893798828 nb_pixel_total : 14398 time to create 1 rle with old method : 0.018105506896972656 time for calcul the mask position with numpy : 0.029967308044433594 nb_pixel_total : 19652 time to create 1 rle with old method : 0.024197101593017578 time for calcul the mask position with numpy : 0.030013084411621094 nb_pixel_total : 8998 time to create 1 rle with old method : 0.011677026748657227 time for calcul the mask position with numpy : 0.0316314697265625 nb_pixel_total : 256089 time to create 1 rle with new method : 0.7154722213745117 time for calcul the mask position with numpy : 0.03342795372009277 nb_pixel_total : 10185 time to create 1 rle with old method : 0.011738777160644531 time for calcul the mask position with numpy : 0.02989363670349121 nb_pixel_total : 44236 time to create 1 rle with old method : 0.05124711990356445 time for calcul the mask position with numpy : 0.029870271682739258 nb_pixel_total : 1326 time to create 1 rle with old method : 0.0017490386962890625 time for calcul the mask position with numpy : 0.029979467391967773 nb_pixel_total : 21118 time to create 1 rle with old method : 0.026229381561279297 time for calcul the mask position with numpy : 0.030417680740356445 nb_pixel_total : 27115 time to create 1 rle with old method : 0.033354759216308594 time for calcul the mask position with numpy : 0.030968666076660156 nb_pixel_total : 26230 time to create 1 rle with old method : 0.031242847442626953 time for calcul the mask position with numpy : 0.03178071975708008 nb_pixel_total : 11046 time to create 1 rle with old method : 0.013905048370361328 time for calcul the mask position with numpy : 0.030849933624267578 nb_pixel_total : 58435 time to create 1 rle with old method : 0.06697249412536621 time for calcul the mask position with numpy : 0.02950429916381836 nb_pixel_total : 14497 time to create 1 rle with old method : 0.017429351806640625 time for calcul the mask position with numpy : 0.029907703399658203 nb_pixel_total : 43087 time to create 1 rle with old method : 0.04961395263671875 time for calcul the mask position with numpy : 0.029623985290527344 nb_pixel_total : 78680 time to create 1 rle with old method : 0.09093832969665527 time for calcul the mask position with numpy : 0.030918121337890625 nb_pixel_total : 12595 time to create 1 rle with old method : 0.015866994857788086 time for calcul the mask position with numpy : 0.03089165687561035 nb_pixel_total : 16225 time to create 1 rle with old method : 0.02001333236694336 time for calcul the mask position with numpy : 0.031180858612060547 nb_pixel_total : 38000 time to create 1 rle with old method : 0.04711794853210449 time for calcul the mask position with numpy : 0.031241655349731445 nb_pixel_total : 18759 time to create 1 rle with old method : 0.0308077335357666 time for calcul the mask position with numpy : 0.03405618667602539 nb_pixel_total : 12169 time to create 1 rle with old method : 0.020560741424560547 time for calcul the mask position with numpy : 0.03155231475830078 nb_pixel_total : 5126 time to create 1 rle with old method : 0.0062983036041259766 time for calcul the mask position with numpy : 0.030017375946044922 nb_pixel_total : 26407 time to create 1 rle with old method : 0.031142711639404297 time for calcul the mask position with numpy : 0.02985382080078125 nb_pixel_total : 44846 time to create 1 rle with old method : 0.053008317947387695 time for calcul the mask position with numpy : 0.031126022338867188 nb_pixel_total : 55511 time to create 1 rle with old method : 0.06685137748718262 time for calcul the mask position with numpy : 0.03160977363586426 nb_pixel_total : 13901 time to create 1 rle with old method : 0.01663351058959961 time for calcul the mask position with numpy : 0.030608415603637695 nb_pixel_total : 6507 time to create 1 rle with old method : 0.007953166961669922 time for calcul the mask position with numpy : 0.030226945877075195 nb_pixel_total : 14113 time to create 1 rle with old method : 0.01750040054321289 time for calcul the mask position with numpy : 0.02954721450805664 nb_pixel_total : 5335 time to create 1 rle with old method : 0.006453037261962891 time for calcul the mask position with numpy : 0.03131532669067383 nb_pixel_total : 11743 time to create 1 rle with old method : 0.01460409164428711 time for calcul the mask position with numpy : 0.030223369598388672 nb_pixel_total : 14616 time to create 1 rle with old method : 0.01816582679748535 time for calcul the mask position with numpy : 0.029842376708984375 nb_pixel_total : 19111 time to create 1 rle with old method : 0.023426532745361328 time for calcul the mask position with numpy : 0.03049492835998535 nb_pixel_total : 21128 time to create 1 rle with old method : 0.025155067443847656 create new chi : 4.280242681503296 time to delete rle : 0.0041849613189697266 batch 1 Loaded 93 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 22774 TO DO : save crop sub photo not yet done ! save time : 2.685944080352783 nb_obj : 64 nb_hashtags : 4 time to prepare the origin masks : 4.972167730331421 time for calcul the mask position with numpy : 0.5825028419494629 nb_pixel_total : 4792383 time to create 1 rle with new method : 0.33860206604003906 time for calcul the mask position with numpy : 0.029972553253173828 nb_pixel_total : 12241 time to create 1 rle with old method : 0.014235973358154297 time for calcul the mask position with numpy : 0.04096078872680664 nb_pixel_total : 944939 time to create 1 rle with new method : 0.431882381439209 time for calcul the mask position with numpy : 0.03312993049621582 nb_pixel_total : 4098 time to create 1 rle with old method : 0.0069828033447265625 time for calcul the mask position with numpy : 0.03018665313720703 nb_pixel_total : 15022 time to create 1 rle with old method : 0.017939090728759766 time for calcul the mask position with numpy : 0.029596328735351562 nb_pixel_total : 31252 time to create 1 rle with old method : 0.03626704216003418 time for calcul the mask position with numpy : 0.029352664947509766 nb_pixel_total : 52762 time to create 1 rle with old method : 0.05952119827270508 time for calcul the mask position with numpy : 0.029481887817382812 nb_pixel_total : 49267 time to create 1 rle with old method : 0.05804133415222168 time for calcul the mask position with numpy : 0.029091835021972656 nb_pixel_total : 18933 time to create 1 rle with old method : 0.02327108383178711 time for calcul the mask position with numpy : 0.029169321060180664 nb_pixel_total : 8130 time to create 1 rle with old method : 0.009912490844726562 time for calcul the mask position with numpy : 0.029048681259155273 nb_pixel_total : 4539 time to create 1 rle with old method : 0.005472660064697266 time for calcul the mask position with numpy : 0.03252005577087402 nb_pixel_total : 19543 time to create 1 rle with old method : 0.02225947380065918 time for calcul the mask position with numpy : 0.030629873275756836 nb_pixel_total : 13948 time to create 1 rle with old method : 0.022364377975463867 time for calcul the mask position with numpy : 0.0293729305267334 nb_pixel_total : 18704 time to create 1 rle with old method : 0.022444963455200195 time for calcul the mask position with numpy : 0.032294511795043945 nb_pixel_total : 10926 time to create 1 rle with old method : 0.017815351486206055 time for calcul the mask position with numpy : 0.03139519691467285 nb_pixel_total : 13376 time to create 1 rle with old method : 0.015964269638061523 time for calcul the mask position with numpy : 0.02916240692138672 nb_pixel_total : 22100 time to create 1 rle with old method : 0.02934408187866211 time for calcul the mask position with numpy : 0.041219234466552734 nb_pixel_total : 8921 time to create 1 rle with old method : 0.010911703109741211 time for calcul the mask position with numpy : 0.0314176082611084 nb_pixel_total : 15895 time to create 1 rle with old method : 0.018952369689941406 time for calcul the mask position with numpy : 0.0323636531829834 nb_pixel_total : 5947 time to create 1 rle with old method : 0.0071027278900146484 time for calcul the mask position with numpy : 0.02924633026123047 nb_pixel_total : 17350 time to create 1 rle with old method : 0.02113962173461914 time for calcul the mask position with numpy : 0.03214573860168457 nb_pixel_total : 24557 time to create 1 rle with old method : 0.03192257881164551 time for calcul the mask position with numpy : 0.029432058334350586 nb_pixel_total : 21443 time to create 1 rle with old method : 0.030449867248535156 time for calcul the mask position with numpy : 0.03213047981262207 nb_pixel_total : 21802 time to create 1 rle with old method : 0.032253265380859375 time for calcul the mask position with numpy : 0.0295407772064209 nb_pixel_total : 10252 time to create 1 rle with old method : 0.013002634048461914 time for calcul the mask position with numpy : 0.029361486434936523 nb_pixel_total : 14610 time to create 1 rle with old method : 0.020209074020385742 time for calcul the mask position with numpy : 0.03310537338256836 nb_pixel_total : 12178 time to create 1 rle with old method : 0.01968979835510254 time for calcul the mask position with numpy : 0.03258657455444336 nb_pixel_total : 18066 time to create 1 rle with old method : 0.020641803741455078 time for calcul the mask position with numpy : 0.02942514419555664 nb_pixel_total : 18412 time to create 1 rle with old method : 0.021806001663208008 time for calcul the mask position with numpy : 0.03185772895812988 nb_pixel_total : 38849 time to create 1 rle with old method : 0.04600834846496582 time for calcul the mask position with numpy : 0.030086278915405273 nb_pixel_total : 23403 time to create 1 rle with old method : 0.028304100036621094 time for calcul the mask position with numpy : 0.03058481216430664 nb_pixel_total : 22084 time to create 1 rle with old method : 0.027779340744018555 time for calcul the mask position with numpy : 0.03393077850341797 nb_pixel_total : 12282 time to create 1 rle with old method : 0.014844417572021484 time for calcul the mask position with numpy : 0.029542922973632812 nb_pixel_total : 58264 time to create 1 rle with old method : 0.07239699363708496 time for calcul the mask position with numpy : 0.030136823654174805 nb_pixel_total : 13652 time to create 1 rle with old method : 0.01635909080505371 time for calcul the mask position with numpy : 0.0300137996673584 nb_pixel_total : 31562 time to create 1 rle with old method : 0.03770160675048828 time for calcul the mask position with numpy : 0.030365705490112305 nb_pixel_total : 78219 time to create 1 rle with old method : 0.09253883361816406 time for calcul the mask position with numpy : 0.030486583709716797 nb_pixel_total : 54453 time to create 1 rle with old method : 0.06248140335083008 time for calcul the mask position with numpy : 0.03224682807922363 nb_pixel_total : 2879 time to create 1 rle with old method : 0.0036792755126953125 time for calcul the mask position with numpy : 0.030073881149291992 nb_pixel_total : 18101 time to create 1 rle with old method : 0.02248668670654297 time for calcul the mask position with numpy : 0.030104875564575195 nb_pixel_total : 9161 time to create 1 rle with old method : 0.011022806167602539 time for calcul the mask position with numpy : 0.03119206428527832 nb_pixel_total : 78247 time to create 1 rle with old method : 0.08838367462158203 time for calcul the mask position with numpy : 0.0321195125579834 nb_pixel_total : 73157 time to create 1 rle with old method : 0.08568835258483887 time for calcul the mask position with numpy : 0.03030562400817871 nb_pixel_total : 32917 time to create 1 rle with old method : 0.039725542068481445 time for calcul the mask position with numpy : 0.030423879623413086 nb_pixel_total : 19927 time to create 1 rle with old method : 0.025384187698364258 time for calcul the mask position with numpy : 0.03067612648010254 nb_pixel_total : 31824 time to create 1 rle with old method : 0.03659200668334961 time for calcul the mask position with numpy : 0.030342578887939453 nb_pixel_total : 10581 time to create 1 rle with old method : 0.012622833251953125 time for calcul the mask position with numpy : 0.032724857330322266 nb_pixel_total : 7502 time to create 1 rle with old method : 0.011262893676757812 time for calcul the mask position with numpy : 0.030085086822509766 nb_pixel_total : 14250 time to create 1 rle with old method : 0.01665186882019043 time for calcul the mask position with numpy : 0.029997825622558594 nb_pixel_total : 14563 time to create 1 rle with old method : 0.018442630767822266 time for calcul the mask position with numpy : 0.0310823917388916 nb_pixel_total : 43819 time to create 1 rle with old method : 0.05114865303039551 time for calcul the mask position with numpy : 0.0299832820892334 nb_pixel_total : 36595 time to create 1 rle with old method : 0.04199695587158203 time for calcul the mask position with numpy : 0.029783248901367188 nb_pixel_total : 7775 time to create 1 rle with old method : 0.009096622467041016 time for calcul the mask position with numpy : 0.029661893844604492 nb_pixel_total : 10430 time to create 1 rle with old method : 0.012531280517578125 time for calcul the mask position with numpy : 0.02979731559753418 nb_pixel_total : 5777 time to create 1 rle with old method : 0.006863117218017578 time for calcul the mask position with numpy : 0.029681921005249023 nb_pixel_total : 4601 time to create 1 rle with old method : 0.005705833435058594 time for calcul the mask position with numpy : 0.030803203582763672 nb_pixel_total : 4687 time to create 1 rle with old method : 0.00580906867980957 time for calcul the mask position with numpy : 0.029776573181152344 nb_pixel_total : 14529 time to create 1 rle with old method : 0.017333030700683594 time for calcul the mask position with numpy : 0.029692411422729492 nb_pixel_total : 7330 time to create 1 rle with old method : 0.008548259735107422 time for calcul the mask position with numpy : 0.02973628044128418 nb_pixel_total : 6463 time to create 1 rle with old method : 0.007849931716918945 time for calcul the mask position with numpy : 0.02965569496154785 nb_pixel_total : 3088 time to create 1 rle with old method : 0.003935813903808594 time for calcul the mask position with numpy : 0.029752731323242188 nb_pixel_total : 1926 time to create 1 rle with old method : 0.0023429393768310547 time for calcul the mask position with numpy : 0.029787302017211914 nb_pixel_total : 22845 time to create 1 rle with old method : 0.02787613868713379 time for calcul the mask position with numpy : 0.02970743179321289 nb_pixel_total : 10154 time to create 1 rle with old method : 0.012049436569213867 time for calcul the mask position with numpy : 0.029062509536743164 nb_pixel_total : 2748 time to create 1 rle with old method : 0.0034418106079101562 create new chi : 4.990529298782349 time to delete rle : 0.004385709762573242 batch 1 Loaded 129 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 27524 TO DO : save crop sub photo not yet done ! save time : 2.578200578689575 nb_obj : 60 nb_hashtags : 3 time to prepare the origin masks : 4.468486070632935 time for calcul the mask position with numpy : 0.2165365219116211 nb_pixel_total : 5362096 time to create 1 rle with new method : 0.6510417461395264 time for calcul the mask position with numpy : 0.029659271240234375 nb_pixel_total : 107474 time to create 1 rle with old method : 0.1230471134185791 time for calcul the mask position with numpy : 0.03191947937011719 nb_pixel_total : 24823 time to create 1 rle with old method : 0.03875231742858887 time for calcul the mask position with numpy : 0.03325462341308594 nb_pixel_total : 16523 time to create 1 rle with old method : 0.025397539138793945 time for calcul the mask position with numpy : 0.028924226760864258 nb_pixel_total : 22141 time to create 1 rle with old method : 0.02655768394470215 time for calcul the mask position with numpy : 0.029280424118041992 nb_pixel_total : 25137 time to create 1 rle with old method : 0.029900074005126953 time for calcul the mask position with numpy : 0.030941009521484375 nb_pixel_total : 22820 time to create 1 rle with old method : 0.02818584442138672 time for calcul the mask position with numpy : 0.03191351890563965 nb_pixel_total : 20881 time to create 1 rle with old method : 0.028760194778442383 time for calcul the mask position with numpy : 0.02924036979675293 nb_pixel_total : 16910 time to create 1 rle with old method : 0.020844221115112305 time for calcul the mask position with numpy : 0.0315854549407959 nb_pixel_total : 13161 time to create 1 rle with old method : 0.015972614288330078 time for calcul the mask position with numpy : 0.02998185157775879 nb_pixel_total : 44779 time to create 1 rle with old method : 0.058110952377319336 time for calcul the mask position with numpy : 0.030230283737182617 nb_pixel_total : 15042 time to create 1 rle with old method : 0.01815032958984375 time for calcul the mask position with numpy : 0.028905630111694336 nb_pixel_total : 39651 time to create 1 rle with old method : 0.04657483100891113 time for calcul the mask position with numpy : 0.028847932815551758 nb_pixel_total : 21167 time to create 1 rle with old method : 0.024825572967529297 time for calcul the mask position with numpy : 0.028485536575317383 nb_pixel_total : 24234 time to create 1 rle with old method : 0.027826786041259766 time for calcul the mask position with numpy : 0.0292665958404541 nb_pixel_total : 126306 time to create 1 rle with old method : 0.14687561988830566 time for calcul the mask position with numpy : 0.02952289581298828 nb_pixel_total : 101285 time to create 1 rle with old method : 0.1157996654510498 time for calcul the mask position with numpy : 0.029748916625976562 nb_pixel_total : 24308 time to create 1 rle with old method : 0.030934810638427734 time for calcul the mask position with numpy : 0.03251075744628906 nb_pixel_total : 10774 time to create 1 rle with old method : 0.013155937194824219 time for calcul the mask position with numpy : 0.030121803283691406 nb_pixel_total : 122684 time to create 1 rle with old method : 0.1464853286743164 time for calcul the mask position with numpy : 0.030179262161254883 nb_pixel_total : 13159 time to create 1 rle with old method : 0.015192270278930664 time for calcul the mask position with numpy : 0.029833555221557617 nb_pixel_total : 24051 time to create 1 rle with old method : 0.02863454818725586 time for calcul the mask position with numpy : 0.029518842697143555 nb_pixel_total : 7674 time to create 1 rle with old method : 0.009119510650634766 time for calcul the mask position with numpy : 0.0295257568359375 nb_pixel_total : 25475 time to create 1 rle with old method : 0.03189992904663086 time for calcul the mask position with numpy : 0.03181290626525879 nb_pixel_total : 145081 time to create 1 rle with old method : 0.16396117210388184 time for calcul the mask position with numpy : 0.033742427825927734 nb_pixel_total : 13434 time to create 1 rle with old method : 0.016061782836914062 time for calcul the mask position with numpy : 0.02945709228515625 nb_pixel_total : 17088 time to create 1 rle with old method : 0.023346900939941406 time for calcul the mask position with numpy : 0.030071020126342773 nb_pixel_total : 11979 time to create 1 rle with old method : 0.014069557189941406 time for calcul the mask position with numpy : 0.03026890754699707 nb_pixel_total : 9407 time to create 1 rle with old method : 0.015451431274414062 time for calcul the mask position with numpy : 0.034446001052856445 nb_pixel_total : 28883 time to create 1 rle with old method : 0.03791165351867676 time for calcul the mask position with numpy : 0.028516530990600586 nb_pixel_total : 5412 time to create 1 rle with old method : 0.006418704986572266 time for calcul the mask position with numpy : 0.02937626838684082 nb_pixel_total : 10854 time to create 1 rle with old method : 0.012841224670410156 time for calcul the mask position with numpy : 0.02901434898376465 nb_pixel_total : 12422 time to create 1 rle with old method : 0.014711618423461914 time for calcul the mask position with numpy : 0.028605937957763672 nb_pixel_total : 30951 time to create 1 rle with old method : 0.0345768928527832 time for calcul the mask position with numpy : 0.02984905242919922 nb_pixel_total : 19760 time to create 1 rle with old method : 0.024050474166870117 time for calcul the mask position with numpy : 0.029569387435913086 nb_pixel_total : 25665 time to create 1 rle with old method : 0.03061532974243164 time for calcul the mask position with numpy : 0.029298782348632812 nb_pixel_total : 21331 time to create 1 rle with old method : 0.026013851165771484 time for calcul the mask position with numpy : 0.02941298484802246 nb_pixel_total : 23152 time to create 1 rle with old method : 0.02923417091369629 time for calcul the mask position with numpy : 0.028333663940429688 nb_pixel_total : 16834 time to create 1 rle with old method : 0.02087092399597168 time for calcul the mask position with numpy : 0.03036189079284668 nb_pixel_total : 45389 time to create 1 rle with old method : 0.05359482765197754 time for calcul the mask position with numpy : 0.02942800521850586 nb_pixel_total : 16241 time to create 1 rle with old method : 0.01960277557373047 time for calcul the mask position with numpy : 0.029500961303710938 nb_pixel_total : 18978 time to create 1 rle with old method : 0.021823406219482422 time for calcul the mask position with numpy : 0.029335737228393555 nb_pixel_total : 19334 time to create 1 rle with old method : 0.02198934555053711 time for calcul the mask position with numpy : 0.029341936111450195 nb_pixel_total : 1810 time to create 1 rle with old method : 0.0021784305572509766 time for calcul the mask position with numpy : 0.02883768081665039 nb_pixel_total : 50706 time to create 1 rle with old method : 0.05806708335876465 time for calcul the mask position with numpy : 0.029633522033691406 nb_pixel_total : 53397 time to create 1 rle with old method : 0.05893445014953613 time for calcul the mask position with numpy : 0.028366804122924805 nb_pixel_total : 19243 time to create 1 rle with old method : 0.022402524948120117 time for calcul the mask position with numpy : 0.02904057502746582 nb_pixel_total : 27182 time to create 1 rle with old method : 0.03323221206665039 time for calcul the mask position with numpy : 0.02906942367553711 nb_pixel_total : 33372 time to create 1 rle with old method : 0.039255380630493164 time for calcul the mask position with numpy : 0.029842615127563477 nb_pixel_total : 15089 time to create 1 rle with old method : 0.01820063591003418 time for calcul the mask position with numpy : 0.02981400489807129 nb_pixel_total : 13181 time to create 1 rle with old method : 0.0176544189453125 time for calcul the mask position with numpy : 0.03332924842834473 nb_pixel_total : 11597 time to create 1 rle with old method : 0.018990039825439453 time for calcul the mask position with numpy : 0.03313159942626953 nb_pixel_total : 12426 time to create 1 rle with old method : 0.014568090438842773 time for calcul the mask position with numpy : 0.029196500778198242 nb_pixel_total : 36204 time to create 1 rle with old method : 0.04271531105041504 time for calcul the mask position with numpy : 0.027811765670776367 nb_pixel_total : 22335 time to create 1 rle with old method : 0.025217533111572266 time for calcul the mask position with numpy : 0.0287015438079834 nb_pixel_total : 9284 time to create 1 rle with old method : 0.010999679565429688 time for calcul the mask position with numpy : 0.02856159210205078 nb_pixel_total : 4494 time to create 1 rle with old method : 0.005168914794921875 time for calcul the mask position with numpy : 0.028262615203857422 nb_pixel_total : 2635 time to create 1 rle with old method : 0.0029668807983398438 time for calcul the mask position with numpy : 0.028613805770874023 nb_pixel_total : 18 time to create 1 rle with old method : 8.20159912109375e-05 time for calcul the mask position with numpy : 0.028336286544799805 nb_pixel_total : 3807 time to create 1 rle with old method : 0.004654884338378906 time for calcul the mask position with numpy : 0.028542757034301758 nb_pixel_total : 8710 time to create 1 rle with old method : 0.01046133041381836 create new chi : 4.72170090675354 time to delete rle : 0.004620075225830078 batch 1 Loaded 121 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 27144 TO DO : save crop sub photo not yet done ! save time : 2.7295398712158203 nb_obj : 29 nb_hashtags : 4 time to prepare the origin masks : 3.6856162548065186 time for calcul the mask position with numpy : 0.3851127624511719 nb_pixel_total : 6195858 time to create 1 rle with new method : 0.37319397926330566 time for calcul the mask position with numpy : 0.029484272003173828 nb_pixel_total : 8216 time to create 1 rle with old method : 0.009833574295043945 time for calcul the mask position with numpy : 0.029277563095092773 nb_pixel_total : 29634 time to create 1 rle with old method : 0.033727407455444336 time for calcul the mask position with numpy : 0.02935051918029785 nb_pixel_total : 4115 time to create 1 rle with old method : 0.005063533782958984 time for calcul the mask position with numpy : 0.033121347427368164 nb_pixel_total : 49178 time to create 1 rle with old method : 0.059516191482543945 time for calcul the mask position with numpy : 0.029331445693969727 nb_pixel_total : 24603 time to create 1 rle with old method : 0.029640913009643555 time for calcul the mask position with numpy : 0.02945709228515625 nb_pixel_total : 14138 time to create 1 rle with old method : 0.01668834686279297 time for calcul the mask position with numpy : 0.030155420303344727 nb_pixel_total : 17799 time to create 1 rle with old method : 0.02097797393798828 time for calcul the mask position with numpy : 0.02950906753540039 nb_pixel_total : 15695 time to create 1 rle with old method : 0.018970251083374023 time for calcul the mask position with numpy : 0.029766559600830078 nb_pixel_total : 27036 time to create 1 rle with old method : 0.0304868221282959 time for calcul the mask position with numpy : 0.029868602752685547 nb_pixel_total : 51507 time to create 1 rle with old method : 0.05917477607727051 time for calcul the mask position with numpy : 0.029367446899414062 nb_pixel_total : 4723 time to create 1 rle with old method : 0.005629777908325195 time for calcul the mask position with numpy : 0.029375791549682617 nb_pixel_total : 19745 time to create 1 rle with old method : 0.023534536361694336 time for calcul the mask position with numpy : 0.02952289581298828 nb_pixel_total : 65525 time to create 1 rle with old method : 0.07513809204101562 time for calcul the mask position with numpy : 0.029500246047973633 nb_pixel_total : 29791 time to create 1 rle with old method : 0.03466367721557617 time for calcul the mask position with numpy : 0.028939008712768555 nb_pixel_total : 17528 time to create 1 rle with old method : 0.021047592163085938 time for calcul the mask position with numpy : 0.029004812240600586 nb_pixel_total : 19314 time to create 1 rle with old method : 0.022937536239624023 time for calcul the mask position with numpy : 0.029378414154052734 nb_pixel_total : 6974 time to create 1 rle with old method : 0.007965087890625 time for calcul the mask position with numpy : 0.028989553451538086 nb_pixel_total : 10368 time to create 1 rle with old method : 0.01234126091003418 time for calcul the mask position with numpy : 0.02933979034423828 nb_pixel_total : 108115 time to create 1 rle with old method : 0.12168145179748535 time for calcul the mask position with numpy : 0.029881000518798828 nb_pixel_total : 12542 time to create 1 rle with old method : 0.015924453735351562 time for calcul the mask position with numpy : 0.029836654663085938 nb_pixel_total : 15624 time to create 1 rle with old method : 0.01915717124938965 time for calcul the mask position with numpy : 0.02951788902282715 nb_pixel_total : 154222 time to create 1 rle with new method : 0.5194783210754395 time for calcul the mask position with numpy : 0.03310513496398926 nb_pixel_total : 41707 time to create 1 rle with old method : 0.06841731071472168 time for calcul the mask position with numpy : 0.03489208221435547 nb_pixel_total : 54797 time to create 1 rle with old method : 0.062436580657958984 time for calcul the mask position with numpy : 0.029525041580200195 nb_pixel_total : 25992 time to create 1 rle with old method : 0.031215429306030273 time for calcul the mask position with numpy : 0.0290219783782959 nb_pixel_total : 5563 time to create 1 rle with old method : 0.006620645523071289 time for calcul the mask position with numpy : 0.029256582260131836 nb_pixel_total : 3801 time to create 1 rle with old method : 0.00464940071105957 time for calcul the mask position with numpy : 0.029393911361694336 nb_pixel_total : 5427 time to create 1 rle with old method : 0.006668567657470703 time for calcul the mask position with numpy : 0.029114961624145508 nb_pixel_total : 10703 time to create 1 rle with old method : 0.013229608535766602 create new chi : 3.041987419128418 time to delete rle : 0.0033273696899414062 batch 1 Loaded 59 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++Number RLEs to save : 14513 TO DO : save crop sub photo not yet done ! save time : 0.8905916213989258 nb_obj : 10 nb_hashtags : 4 time to prepare the origin masks : 2.16062593460083 time for calcul the mask position with numpy : 0.20863604545593262 nb_pixel_total : 6090468 time to create 1 rle with new method : 0.34003543853759766 time for calcul the mask position with numpy : 0.0259244441986084 nb_pixel_total : 18153 time to create 1 rle with old method : 0.023853063583374023 time for calcul the mask position with numpy : 0.02386760711669922 nb_pixel_total : 19032 time to create 1 rle with old method : 0.027142763137817383 time for calcul the mask position with numpy : 0.02565169334411621 nb_pixel_total : 24695 time to create 1 rle with old method : 0.030400514602661133 time for calcul the mask position with numpy : 0.021505355834960938 nb_pixel_total : 15559 time to create 1 rle with old method : 0.01902174949645996 time for calcul the mask position with numpy : 0.021088123321533203 nb_pixel_total : 43515 time to create 1 rle with old method : 0.047905683517456055 time for calcul the mask position with numpy : 0.021733760833740234 nb_pixel_total : 108939 time to create 1 rle with old method : 0.11964702606201172 time for calcul the mask position with numpy : 0.022873401641845703 nb_pixel_total : 217964 time to create 1 rle with new method : 0.3103775978088379 time for calcul the mask position with numpy : 0.023668527603149414 nb_pixel_total : 313090 time to create 1 rle with new method : 0.3166313171386719 time for calcul the mask position with numpy : 0.02827763557434082 nb_pixel_total : 154367 time to create 1 rle with new method : 0.34667015075683594 time for calcul the mask position with numpy : 0.032115936279296875 nb_pixel_total : 44458 time to create 1 rle with old method : 0.0488438606262207 create new chi : 2.1861562728881836 time to delete rle : 0.002570629119873047 batch 1 Loaded 21 chid ids of type : 3594 +++++++++++++Number RLEs to save : 10388 TO DO : save crop sub photo not yet done ! save time : 0.755561351776123 map_output_result : {1344944844: (0.0, 'Should be the crop_list due to order', 0), 1344944841: (0.0, 'Should be the crop_list due to order', 0), 1344944761: (0.0, 'Should be the crop_list due to order', 0), 1344944670: (0.0, 'Should be the crop_list due to order', 0), 1344944609: (0.0, 'Should be the crop_list due to order', 0), 1344944584: (0.0, 'Should be the crop_list due to order', 0), 1344941466: (0.0, 'Should be the crop_list due to order', 0), 1344941399: (0.0, 'Should be the crop_list due to order', 0), 1344940834: (0.0, 'Should be the crop_list due to order', 0), 1344940808: (0.0, 'Should be the crop_list due to order', 0), 1344940722: (0.0, 'Should be the crop_list due to order', 0), 1344940691: (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 [1344944844, 1344944841, 1344944761, 1344944670, 1344944609, 1344944584, 1344941466, 1344941399, 1344940834, 1344940808, 1344940722, 1344940691] Looping around the photos to save general results len do output : 12 /1344944844.Didn't retrieve data . /1344944841.Didn't retrieve data . /1344944761.Didn't retrieve data . /1344944670.Didn't retrieve data . /1344944609.Didn't retrieve data . /1344944584.Didn't retrieve data . /1344941466.Didn't retrieve data . /1344941399.Didn't retrieve data . /1344940834.Didn't retrieve data . /1344940808.Didn't retrieve data . /1344940722.Didn't retrieve data . /1344940691.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, '2675453') ('3318', '21501459', '1344944844', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944841', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944761', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944670', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944609', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944584', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941466', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941399', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940834', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940808', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940722', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940691', None, None, None, None, None, '2675453') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 36 time used for this insertion : 0.014163494110107422 save_final save missing photos in datou_result : time spend for datou_step_exec : 130.63339471817017 time spend to save output : 0.01502227783203125 total time spend for step 3 : 130.6484169960022 step4:ventilate_hashtags_in_portfolio Mon Mar 17 20:32:04 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 : 21501459 get user id for portfolio 21501459 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`=21501459 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','pehd','carton','metal','papier','pet_fonce','mal_croppe','background','environnement','autre','pet_clair')) 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`=21501459 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','pehd','carton','metal','papier','pet_fonce','mal_croppe','background','environnement','autre','pet_clair')) AND mptpi.`min_score`=0.5 To do Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") 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`=21501459 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','pehd','carton','metal','papier','pet_fonce','mal_croppe','background','environnement','autre','pet_clair')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://www.fotonower.com/velours/21501677,21501678,21501679,21501680,21501681,21501682,21501683,21501684,21501685,21501686,21501687?tags=flou,pehd,carton,metal,papier,pet_fonce,mal_croppe,background,environnement,autre,pet_clair Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1344944844, 1344944841, 1344944761, 1344944670, 1344944609, 1344944584, 1344941466, 1344941399, 1344940834, 1344940808, 1344940722, 1344940691] Looping around the photos to save general results len do output : 1 /21501459. 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, '2675453') ('3318', '21501459', '1344944844', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944841', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944761', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944670', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944609', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944584', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941466', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941399', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940834', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940808', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940722', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940691', None, None, None, None, None, '2675453') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 13 time used for this insertion : 0.014510393142700195 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.6492187976837158 time spend to save output : 0.01500844955444336 total time spend for step 4 : 1.6642272472381592 step5:final Mon Mar 17 20:32:05 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 : {1344944844: ('0.2147837993221981',), 1344944841: ('0.2147837993221981',), 1344944761: ('0.2147837993221981',), 1344944670: ('0.2147837993221981',), 1344944609: ('0.2147837993221981',), 1344944584: ('0.2147837993221981',), 1344941466: ('0.2147837993221981',), 1344941399: ('0.2147837993221981',), 1344940834: ('0.2147837993221981',), 1344940808: ('0.2147837993221981',), 1344940722: ('0.2147837993221981',), 1344940691: ('0.2147837993221981',)} new output for save of step final : {1344944844: ('0.2147837993221981',), 1344944841: ('0.2147837993221981',), 1344944761: ('0.2147837993221981',), 1344944670: ('0.2147837993221981',), 1344944609: ('0.2147837993221981',), 1344944584: ('0.2147837993221981',), 1344941466: ('0.2147837993221981',), 1344941399: ('0.2147837993221981',), 1344940834: ('0.2147837993221981',), 1344940808: ('0.2147837993221981',), 1344940722: ('0.2147837993221981',), 1344940691: ('0.2147837993221981',)} [1344944844, 1344944841, 1344944761, 1344944670, 1344944609, 1344944584, 1344941466, 1344941399, 1344940834, 1344940808, 1344940722, 1344940691] Looping around the photos to save general results len do output : 12 /1344944844.Didn't retrieve data . /1344944841.Didn't retrieve data . /1344944761.Didn't retrieve data . /1344944670.Didn't retrieve data . /1344944609.Didn't retrieve data . /1344944584.Didn't retrieve data . /1344941466.Didn't retrieve data . /1344941399.Didn't retrieve data . /1344940834.Didn't retrieve data . /1344940808.Didn't retrieve data . /1344940722.Didn't retrieve data . /1344940691.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, '2675453') ('3318', '21501459', '1344944844', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944841', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944761', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944670', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944609', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944584', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941466', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941399', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940834', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940808', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940722', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940691', None, None, None, None, None, '2675453') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 36 time used for this insertion : 0.014415264129638672 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11390805244445801 time spend to save output : 0.01505899429321289 total time spend for step 5 : 0.1289670467376709 step6:blur_detection Mon Mar 17 20:32:05 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/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6.jpg resize: (2160, 3264) 1344944844 -0.7797608471700513 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589.jpg resize: (2160, 3264) 1344944841 -3.3921694729204983 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc.jpg resize: (2160, 3264) 1344944761 -4.791298796530102 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07.jpg resize: (2160, 3264) 1344944670 -2.005585781186239 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e.jpg resize: (2160, 3264) 1344944609 -3.758482784676107 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095.jpg resize: (2160, 3264) 1344944584 -4.020153804614197 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56.jpg resize: (2160, 3264) 1344941466 -3.583759073980087 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008.jpg resize: (2160, 3264) 1344941399 -5.171135879829996 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a.jpg resize: (2160, 3264) 1344940834 -5.207228871339992 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78.jpg resize: (2160, 3264) 1344940808 -5.26293212030625 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65.jpg resize: (2160, 3264) 1344940722 -4.139935398347291 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c.jpg resize: (2160, 3264) 1344940691 -1.7863308962890765 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479625_0.png resize: (571, 225) 1344958603 0.09061703162570263 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479636_0.png resize: (313, 318) 1344958605 0.411511099569568 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479633_0.png resize: (148, 347) 1344958608 -1.7632285134683816 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479623_0.png resize: (105, 128) 1344958609 -3.185638312665064 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479639_0.png resize: (497, 648) 1344958610 -0.8920087771790105 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479634_0.png resize: (164, 171) 1344958613 0.46947270129150703 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479629_0.png resize: (731, 506) 1344958614 -0.5297441430885412 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479638_0.png resize: (135, 173) 1344958615 -1.1759398929765528 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479632_0.png resize: (148, 118) 1344958616 -1.5268018301185393 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479656_0.png resize: (317, 267) 1344958619 -1.6959832982815344 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479649_0.png resize: (858, 944) 1344958620 -2.277011670488248 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479668_0.png resize: (175, 295) 1344958621 -2.702741381371069 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479665_0.png resize: (122, 106) 1344958624 -2.318389179970598 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479654_0.png resize: (432, 563) 1344958625 0.029779252334105923 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479651_0.png resize: (368, 227) 1344958626 -1.1103416643749884 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479646_0.png resize: (503, 539) 1344958628 -2.503480051524155 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479667_0.png resize: (122, 123) 1344958630 -0.6876724526165973 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479675_0.png resize: (393, 643) 1344958631 -3.5879083952002477 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479663_0.png resize: (184, 189) 1344958632 -1.8803368439079229 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479645_0.png resize: (417, 409) 1344958635 -1.4802016019875113 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479669_0.png resize: (123, 127) 1344958636 -2.937720927226259 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479655_0.png resize: (642, 737) 1344958637 -2.146221888956004 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479660_0.png resize: (621, 381) 1344958640 -2.5967011750613493 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479653_0.png resize: (230, 212) 1344958641 -2.1723607751544587 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479650_0.png resize: (281, 357) 1344958642 -3.1180765095197884 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479647_0.png resize: (154, 215) 1344958644 -2.0776810437535023 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479691_0.png resize: (141, 99) 1344958646 -1.5510549591134088 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479692_0.png resize: (289, 115) 1344958647 -2.518322146778691 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479685_0.png resize: (254, 279) 1344958648 -2.7124094337641083 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479700_0.png resize: (83, 94) 1344958651 -2.109959837688346 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479711_0.png resize: (135, 121) 1344958652 -2.7313317706420692 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479679_0.png resize: (106, 138) 1344958653 -1.794648645806615 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479696_0.png resize: (201, 212) 1344958656 -2.310826682992747 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479683_0.png resize: (150, 210) 1344958657 -4.7086742817736456 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479706_0.png resize: (189, 128) 1344958658 -5.488866716570103 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479702_0.png resize: (147, 59) 1344958660 -0.20827093777026842 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479695_0.png resize: (93, 85) 1344958662 -1.1061491787190376 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479704_0.png resize: (163, 147) 1344958663 -2.7164108937723515 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479694_0.png resize: (106, 105) 1344958665 -1.683452629763627 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479705_0.png resize: (541, 428) 1344958667 -1.7420521081413816 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479677_0.png resize: (359, 486) 1344958668 -4.128678084369075 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479699_0.png resize: (225, 211) 1344958671 -3.010322609950072 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479714_0.png resize: (319, 203) 1344958672 -3.306362717731728 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479697_0.png resize: (411, 224) 1344958673 -2.70744621510788 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479686_0.png resize: (427, 348) 1344958676 -2.4390307423651993 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479708_0.png resize: (268, 202) 1344958677 -1.57129826611017 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479689_0.png resize: (251, 229) 1344958681 -3.8642519510162368 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479688_0.png resize: (205, 281) 1344958682 -1.546547697414414 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479703_0.png resize: (198, 183) 1344958685 -3.67751189967248 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479676_0.png resize: (665, 556) 1344958686 -2.8051349272966317 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479707_0.png resize: (152, 90) 1344958687 -1.718814533062248 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479693_0.png resize: (441, 196) 1344958690 -2.767452297541206 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479720_0.png resize: (115, 118) 1344958691 -2.201210821145525 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479731_0.png resize: (433, 294) 1344958692 -2.1077281064505873 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479728_0.png resize: (175, 227) 1344958695 -2.1361343245509476 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479734_0.png resize: (84, 70) 1344958696 -3.541727772989344 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479725_0.png resize: (119, 155) 1344958697 2.9884476103904123 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479718_0.png resize: (138, 151) 1344958698 -1.41868371733346 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479737_0.png resize: (175, 196) 1344958701 -3.1180090378457077 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479729_0.png resize: (136, 127) 1344958702 -1.118236336922496 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479733_0.png resize: (172, 181) 1344958703 -1.8688386102957506 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479723_0.png resize: (131, 231) 1344958706 -2.0511343805656996 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479715_0.png resize: (153, 150) 1344958707 -1.282904224656801 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479719_0.png resize: (398, 505) 1344958708 3.3195051094403456 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479732_0.png resize: (220, 290) 1344958709 -1.7151295444916403 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479721_0.png resize: (163, 203) 1344958712 -1.343924279331996 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479727_0.png resize: (252, 214) 1344958713 -2.3763057146671533 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479789_0.png resize: (151, 160) 1344958714 -3.1107822352855865 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479748_0.png resize: (167, 139) 1344958717 -1.8389748943212605 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479800_0.png resize: (180, 191) 1344958718 -0.9015884203431113 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479741_0.png resize: (345, 296) 1344958719 -1.5579757806213428 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479768_0.png resize: (289, 331) 1344958722 -1.8586270137670833 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479791_0.png resize: (141, 136) 1344958723 -2.060203210394523 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479765_0.png resize: (86, 100) 1344958724 -2.0431597755295616 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479761_0.png resize: (237, 95) 1344958725 -2.4778340710869893 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479783_0.png resize: (190, 167) 1344958728 -1.6765076879098568 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479758_0.png resize: (190, 208) 1344958729 -1.6202000128549519 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479742_0.png resize: (216, 160) 1344958730 -2.138442653396397 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479798_0.png resize: (254, 244) 1344958733 -2.471611090177547 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479752_0.png resize: (38, 135) 1344958734 5.19205447017114 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479795_0.png resize: (209, 151) 1344958735 -1.5332483324604842 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479766_0.png resize: (168, 128) 1344958738 -2.3018175744015266 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479773_0.png resize: (95, 214) 1344958739 -3.062285645417888 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479746_0.png resize: (103, 145) 1344958740 -2.385368697032771 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479759_0.png resize: (303, 189) 1344958743 -2.410529300049415 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479788_0.png resize: (202, 170) 1344958744 -2.1029165078306855 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479794_0.png resize: (318, 411) 1344958745 -2.7033580315196533 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479762_0.png resize: (163, 159) 1344958746 -2.4464555556187384 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479801_0.png resize: (129, 75) 1344958749 -2.5975650871642797 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479781_0.png resize: (187, 470) 1344958750 -3.8415011529548697 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479777_0.png resize: (190, 247) 1344958751 -1.538462142330664 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479756_0.png resize: (157, 144) 1344958754 -2.6527473699311153 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479743_0.png resize: (249, 278) 1344958755 -3.5136167235280826 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479760_0.png resize: (171, 227) 1344958756 -4.002461910932548 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479771_0.png resize: (71, 105) 1344958757 -2.4946377567573537 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479749_0.png resize: (153, 167) 1344958760 -1.2449665189284997 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479778_0.png resize: (218, 160) 1344958761 -2.6535870510940844 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479745_0.png resize: (74, 125) 1344958762 -2.3635383309949547 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479764_0.png resize: (273, 149) 1344958765 -2.42389465267252 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479796_0.png resize: (267, 251) 1344958766 -2.2759058493115423 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479755_0.png resize: (82, 102) 1344958767 -1.7567927975908197 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479763_0.png resize: (239, 201) 1344958769 -1.2693821480532537 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479782_0.png resize: (80, 100) 1344958771 -2.66243410493214 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479750_0.png resize: (71, 103) 1344958772 -2.869533633033859 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479784_0.png resize: (150, 155) 1344958773 -0.24598834037071682 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479747_0.png resize: (103, 176) 1344958776 -2.9820362671912006 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479785_0.png resize: (171, 185) 1344958777 -2.469702523335649 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479767_0.png resize: (84, 186) 1344958778 -2.675707877493678 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479753_0.png resize: (78, 100) 1344958781 4.261276781438071 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479775_0.png resize: (603, 364) 1344958782 -2.33783389917238 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479772_0.png resize: (94, 170) 1344958784 -3.188064048401217 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479793_0.png resize: (102, 121) 1344958786 -2.7968567377415625 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479740_0.png resize: (81, 80) 1344958788 -2.1912670403209544 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479769_0.png resize: (207, 116) 1344958789 -3.3514583948934002 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479757_0.png resize: (526, 400) 1344958791 -1.3114231149986384 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479780_0.png resize: (61, 134) 1344958794 -1.740147269727598 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479792_0.png resize: (188, 206) 1344958795 -0.19290300141164535 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479754_0.png resize: (649, 363) 1344958796 -1.5840371321377313 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479816_0.png resize: (199, 105) 1344958799 -2.132729765739248 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479808_0.png resize: (555, 608) 1344958800 -2.3136689353310884 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479809_0.png resize: (60, 66) 1344958801 -0.07112894781243558 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479825_0.png resize: (140, 113) 1344958803 -1.8677537034801932 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479807_0.png resize: (232, 166) 1344958805 -2.0183110814399168 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479829_0.png resize: (211, 279) 1344958807 -3.6197900751194227 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479814_0.png resize: (287, 145) 1344958809 -2.778373969996554 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479803_0.png resize: (249, 188) 1344958811 -3.467674171918009 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479805_0.png resize: (141, 268) 1344958813 -3.733453866600577 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479806_0.png resize: (182, 160) 1344958815 -4.503979201119694 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479823_0.png resize: (156, 106) 1344958817 1.530639570954393 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479832_0.png resize: (262, 288) 1344958819 -3.1452273796813266 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479830_0.png resize: (189, 131) 1344958821 -1.225044896216026 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479826_0.png resize: (93, 138) 1344958823 -1.6668220290663855 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479827_0.png resize: (200, 311) 1344958825 -2.351279491878839 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479804_0.png resize: (157, 184) 1344958827 -3.2101355569978742 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479815_0.png resize: (256, 302) 1344958829 -4.347141824088607 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479811_0.png resize: (111, 197) 1344958831 -2.8393903370427056 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479812_0.png resize: (116, 215) 1344958832 -2.227772178287228 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479820_0.png resize: (140, 89) 1344958834 -2.5251919914949084 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479817_0.png resize: (223, 217) 1344958837 -2.988794602233462 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479818_0.png resize: (227, 131) 1344958838 -2.2506389003512357 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479831_0.png resize: (59, 71) 1344958840 -0.006324683164683091 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479819_0.png resize: (222, 351) 1344958842 -2.590897876860239 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479802_0.png resize: (319, 231) 1344958844 -2.783494670800766 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479847_0.png resize: (187, 98) 1344958846 -1.8931840028084077 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479836_0.png resize: (196, 207) 1344958848 -1.0987046128051907 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479839_0.png resize: (258, 227) 1344958849 -2.651475112835438 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479848_0.png resize: (103, 158) 1344958850 -2.201492624969617 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479857_0.png resize: (250, 192) 1344958852 -3.1109112637251397 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479835_0.png resize: (249, 186) 1344958854 -3.0538130778060557 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479840_0.png resize: (312, 194) 1344958855 -2.357307121430534 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479855_0.png resize: (176, 282) 1344958857 -1.9845428696957141 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479834_0.png resize: (133, 145) 1344958859 -1.7300716181797073 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479833_0.png resize: (121, 195) 1344958860 -1.6789877054119173 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479845_0.png resize: (272, 118) 1344958862 -1.1682949669432725 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479838_0.png resize: (225, 141) 1344958864 -2.758005757156949 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479837_0.png resize: (191, 145) 1344958865 -2.4843702373508934 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479849_0.png resize: (511, 235) 1344958867 -2.628966508229147 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479851_0.png resize: (368, 603) 1344958868 -3.62174548043393 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479843_0.png resize: (186, 133) 1344958870 -3.9947301475209036 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479850_0.png resize: (226, 423) 1344958872 -2.8011291070223177 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479844_0.png resize: (401, 395) 1344958873 -2.8531297420780275 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479842_0.png resize: (111, 145) 1344958875 1.2412913603099476 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479853_0.png resize: (190, 168) 1344958876 -1.7099795464816223 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479858_0.png resize: (98, 88) 1344958878 0.3322901003539039 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479846_0.png resize: (186, 156) 1344958879 -3.4680240689690107 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479871_0.png resize: (183, 181) 1344958881 -2.7528449156707344 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479868_0.png resize: (109, 108) 1344958883 -0.2166315935194818 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479881_0.png resize: (282, 259) 1344958884 -2.8640186635526867 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479890_0.png resize: (106, 73) 1344958886 -2.456646571820084 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479889_0.png resize: (176, 108) 1344958888 -1.7688836762557067 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479892_0.png resize: (203, 331) 1344958889 -3.7275243123269584 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479874_0.png resize: (115, 138) 1344958891 -1.5977618467594328 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479878_0.png resize: (256, 159) 1344958892 -3.354611671611598 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479865_0.png resize: (168, 171) 1344958894 -3.382074845311988 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479901_0.png resize: (69, 150) 1344958897 -3.524730954386959 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479866_0.png resize: (86, 154) 1344958898 -1.6643511977135161 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479903_0.png resize: (356, 295) 1344958900 -3.5204251061361442 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479898_0.png resize: (157, 126) 1344958901 -2.7183003873868117 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479900_0.png resize: (241, 335) 1344958903 -4.621281158226307 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479904_0.png resize: (196, 83) 1344958905 -3.2625395140106774 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479876_0.png resize: (237, 280) 1344958906 -3.01671143921038 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479859_0.png resize: (350, 359) 1344958908 -3.970267737461556 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479884_0.png resize: (123, 66) 1344958910 0.10944268129764613 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479861_0.png resize: (855, 498) 1344958911 -4.126400156583036 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479867_0.png resize: (98, 111) 1344958913 -3.536833461932205 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479899_0.png resize: (411, 235) 1344958914 -3.6862476820210714 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479880_0.png resize: (246, 131) 1344958917 -4.081311550645596 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479863_0.png resize: (191, 141) 1344958919 -1.3816964930891886 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479887_0.png resize: (354, 154) 1344958922 -4.166081388190074 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479864_0.png resize: (180, 165) 1344958923 -2.0279806821823008 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479897_0.png resize: (95, 99) 1344958926 -3.90200850258333 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479888_0.png resize: (173, 172) 1344958927 -3.809092430966818 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479873_0.png resize: (397, 450) 1344958928 -1.966684365904251 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479879_0.png resize: (145, 195) 1344958930 -2.5786482061155915 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479895_0.png resize: (73, 164) 1344958932 -4.62655917629249 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479896_0.png resize: (148, 143) 1344958933 -3.651197824170321 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479883_0.png resize: (175, 173) 1344958935 1.1184295022989321 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479885_0.png resize: (319, 194) 1344958937 -3.6121457140110023 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479862_0.png resize: (197, 184) 1344958938 -3.638931098825876 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479870_0.png resize: (180, 157) 1344958939 -3.1105258698227782 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479886_0.png resize: (158, 126) 1344958941 -2.7863737177033236 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479872_0.png resize: (117, 131) 1344958943 -4.038620895030361 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479902_0.png resize: (342, 211) 1344958944 -2.821569658859836 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479891_0.png resize: (139, 173) 1344958946 -1.7838534147005203 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479950_0.png resize: (441, 168) 1344958948 -3.0787107952098363 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479966_0.png resize: (293, 153) 1344958949 -3.0304781596400825 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479946_0.png resize: (86, 66) 1344958951 -0.30793252977964747 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479908_0.png resize: (152, 91) 1344958952 -1.9134831385757265 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479906_0.png resize: (189, 155) 1344958954 -3.2034718843389163 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479957_0.png resize: (123, 60) 1344958955 -2.0951018480820207 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479926_0.png resize: (395, 347) 1344958957 -3.9987277814570934 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479935_0.png resize: (178, 242) 1344958959 -2.293242940940502 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479968_0.png resize: (83, 122) 1344958960 -1.9726706013752797 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479911_0.png resize: (148, 156) 1344958962 -1.136311007401527 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479967_0.png resize: (165, 182) 1344958964 -1.902816429832341 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479912_0.png resize: (198, 137) 1344958965 -3.902095950036411 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479948_0.png resize: (99, 121) 1344958967 0.13015337128211127 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479939_0.png resize: (198, 141) 1344958968 -3.788575144088698 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479915_0.png resize: (270, 306) 1344958970 -2.717893594448592 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479914_0.png resize: (87, 115) 1344958971 -1.368821721349442 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479918_0.png resize: (255, 316) 1344958973 -3.082377965273702 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479923_0.png resize: (173, 153) 1344958975 -1.2728944283758366 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479962_0.png resize: (109, 105) 1344958976 -4.51265823267211 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479913_0.png resize: (135, 118) 1344958978 -0.629018628120897 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479928_0.png resize: (66, 116) 1344958980 -0.6199821064561908 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479941_0.png resize: (289, 288) 1344958981 -4.535811571285645 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479942_0.png resize: (156, 166) 1344958983 -3.2840859681398435 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479944_0.png resize: (192, 197) 1344958984 -2.2197066110577723 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479927_0.png resize: (121, 100) 1344958986 -1.4538680582747479 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479955_0.png resize: (146, 182) 1344958987 -3.3754155384931646 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479919_0.png resize: (118, 127) 1344958989 -2.5318929314374485 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479921_0.png resize: (140, 237) 1344958991 -3.953784941675674 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479938_0.png resize: (62, 94) 1344958992 2.637095684470931 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479964_0.png resize: (151, 120) 1344958994 -3.1900413971309183 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479924_0.png resize: (226, 93) 1344958996 -1.731137516685149 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479905_0.png resize: (94, 208) 1344958997 -2.0275346741273848 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479965_0.png resize: (69, 121) 1344958999 -2.091231411077303 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479920_0.png resize: (107, 321) 1344959001 -2.8919996270126243 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479947_0.png resize: (163, 153) 1344959002 -2.8326843467591867 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479940_0.png resize: (161, 142) 1344959003 -4.691132375888251 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479958_0.png resize: (70, 81) 1344959005 -4.304545753932775 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479961_0.png resize: (34, 104) 1344959006 -1.0013266837070953 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479951_0.png resize: (56, 54) 1344959007 -3.431512088358738 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479952_0.png resize: (185, 301) 1344959009 -4.186075823932199 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479960_0.png resize: (210, 248) 1344959010 -3.1269314827301464 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479922_0.png resize: (217, 173) 1344959011 -4.937402520861564 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479936_0.png resize: (180, 138) 1344959013 -2.0195604107416014 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479907_0.png resize: (139, 177) 1344959014 -2.361239351083668 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479949_0.png resize: (82, 140) 1344959015 -0.7402857813512205 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479917_0.png resize: (246, 164) 1344959017 -2.7450664035959345 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479931_0.png resize: (153, 133) 1344959018 -2.7236702328039826 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479916_0.png resize: (204, 136) 1344959019 -4.10716557268478 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479910_0.png resize: (246, 189) 1344959021 -3.716581552914461 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479933_0.png resize: (340, 160) 1344959022 -2.3596820976620645 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479929_0.png resize: (108, 98) 1344959024 -2.5681237187829575 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479930_0.png resize: (175, 83) 1344959026 -3.5762391841425685 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479954_0.png resize: (350, 200) 1344959027 -1.3435833237736483 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479973_0.png resize: (290, 171) 1344959028 -1.1254202519455883 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479988_0.png resize: (501, 519) 1344959029 -2.040843824365005 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479979_0.png resize: (103, 161) 1344959031 -1.783380219809152 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479995_0.png resize: (161, 151) 1344959032 -2.9647886775277428 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480016_0.png resize: (369, 360) 1344959033 -2.6179203633225425 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479972_0.png resize: (101, 107) 1344959035 -1.4734680011469896 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479997_0.png resize: (182, 226) 1344959036 -3.122965276673407 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479982_0.png resize: (41, 80) 1344959037 -0.551882839657325 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480005_0.png resize: (88, 148) 1344959038 -2.5656838236415944 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479971_0.png resize: (97, 125) 1344959040 -2.906902300947084 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479996_0.png resize: (257, 244) 1344959041 -3.2323081371404765 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480008_0.png resize: (85, 117) 1344959042 -2.4187603907996587 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480011_0.png resize: (53, 96) 1344959044 -1.530089224474809 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480028_0.png resize: (23, 41) 1344959045 20.0 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480020_0.png resize: (137, 176) 1344959046 -3.8393001532019135 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479987_0.png resize: (195, 187) 1344959047 -2.372005257693583 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479983_0.png resize: (168, 210) 1344959049 -2.874718707840709 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479986_0.png resize: (259, 180) 1344959050 -3.7385260237023274 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479981_0.png resize: (150, 176) 1344959051 -3.954678566529399 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479969_0.png resize: (119, 188) 1344959054 -2.176609580343769 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479980_0.png resize: (120, 108) 1344959055 -3.619422417000291 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480022_0.png resize: (292, 257) 1344959057 -2.598355216207421 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479998_0.png resize: (129, 146) 1344959061 -4.057113795282164 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480024_0.png resize: (325, 824) 1344959062 -3.8431669655340417 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479975_0.png resize: (187, 185) 1344959064 -1.9016393481213245 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480009_0.png resize: (241, 587) 1344959065 -4.489333830673449 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479994_0.png resize: (63, 83) 1344959066 8.416533963938367 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480012_0.png resize: (190, 204) 1344959068 -2.4543752232192944 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479999_0.png resize: (194, 191) 1344959069 -4.3341208061855925 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480001_0.png resize: (152, 178) 1344959070 -3.3498624329949465 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479976_0.png resize: (146, 239) 1344959072 -1.6021190316736857 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480027_0.png resize: (130, 243) 1344959073 -2.80825966298728 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480026_0.png resize: (131, 204) 1344959074 -3.934875439079093 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480015_0.png resize: (195, 127) 1344959076 -2.605486695139443 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480007_0.png resize: (105, 229) 1344959077 -3.695882579424417 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480003_0.png resize: (310, 279) 1344959078 -3.1317145294803224 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479992_0.png resize: (170, 203) 1344959080 -3.270013366130748 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480021_0.png resize: (215, 205) 1344959081 -3.6842797741583095 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479984_0.png resize: (200, 225) 1344959082 -2.2707007026042043 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480019_0.png resize: (221, 285) 1344959084 -3.2751426200420455 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479990_0.png resize: (188, 235) 1344959085 -2.6071856364383295 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479989_0.png resize: (158, 194) 1344959086 -2.272949011487467 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479991_0.png resize: (164, 158) 1344959088 -1.1420558205196505 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479978_0.png resize: (162, 219) 1344959089 -3.132428215741255 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480010_0.png resize: (122, 203) 1344959090 -2.2353550936060382 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480004_0.png resize: (210, 237) 1344959091 -2.6663324512107676 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479993_0.png resize: (108, 147) 1344959093 -3.179291786428222 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480018_0.png resize: (123, 201) 1344959094 -3.5473021573612176 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480023_0.png resize: (126, 174) 1344959095 -3.6336663557346336 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480014_0.png resize: (142, 166) 1344959097 -3.1232623865585882 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479970_0.png resize: (205, 186) 1344959098 -2.9872247715755456 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479974_0.png resize: (252, 162) 1344959099 -2.598656900092607 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479977_0.png resize: (130, 113) 1344959101 -3.1557537349949474 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479985_0.png resize: (235, 127) 1344959102 -3.46932173855156 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480017_0.png resize: (60, 37) 1344959103 4.117176313632051 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480033_0.png resize: (530, 551) 1344959104 -2.151874096412986 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480041_0.png resize: (95, 94) 1344959106 -2.3020507403227506 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480049_0.png resize: (92, 91) 1344959107 -1.280592668086213 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480056_0.png resize: (259, 239) 1344959108 -2.860803808513067 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480037_0.png resize: (100, 89) 1344959111 -2.0296113181081994 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480030_0.png resize: (248, 217) 1344959112 -2.748646964850229 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480042_0.png resize: (238, 365) 1344959113 -2.5958050735227487 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480036_0.png resize: (182, 144) 1344959117 -2.4464898053129134 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480046_0.png resize: (81, 191) 1344959118 -0.4331001917763805 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480055_0.png resize: (216, 189) 1344959119 -0.8997470005769964 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480053_0.png resize: (396, 496) 1344959121 -2.1620479475740195 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480032_0.png resize: (132, 177) 1344959122 -1.0608481572744946 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480048_0.png resize: (65, 88) 1344959123 3.262095281244512 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480047_0.png resize: (199, 386) 1344959125 -2.5789438472448727 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480035_0.png resize: (54, 94) 1344959126 -1.8706790480714255 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480039_0.png resize: (148, 154) 1344959127 -2.009211977147313 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480052_0.png resize: (105, 121) 1344959129 -1.810242048065729 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480040_0.png resize: (231, 192) 1344959130 -2.8048305448588358 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480034_0.png resize: (215, 166) 1344959131 -3.699085824575923 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480045_0.png resize: (286, 334) 1344959133 -2.911599794357579 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480043_0.png resize: (193, 170) 1344959134 -2.590522548468604 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480031_0.png resize: (238, 131) 1344959135 -2.511152041077554 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480029_0.png resize: (137, 202) 1344959136 -2.5424803181151945 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480038_0.png resize: (386, 210) 1344959138 -3.664329255664262 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480051_0.png resize: (135, 71) 1344959139 -2.362339325090492 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480060_0.png resize: (885, 922) 1344959140 -0.9255949605734317 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480059_0.png resize: (425, 464) 1344959142 -1.8367047625673478 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480061_0.png resize: (514, 619) 1344959144 -0.8869583461608495 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480066_0.png resize: (149, 244) 1344959146 -2.7852469947237344 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480058_0.png resize: (270, 273) 1344959148 -2.258597965865782 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479630_0.png resize: (383, 418) 1344959252 -1.4367564239725898 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479624_0.png resize: (176, 435) 1344959254 -2.801766328338855 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479631_0.png resize: (212, 177) 1344959256 -1.8341938352908003 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479642_0.png resize: (122, 216) 1344959257 -1.0741144455286715 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479641_0.png resize: (79, 129) 1344959258 -2.151881265935798 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479635_0.png resize: (512, 653) 1344959260 -1.0890345890928281 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479657_0.png resize: (367, 386) 1344959261 -2.6703437873079334 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479664_0.png resize: (107, 127) 1344959262 -1.7839046503603386 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479671_0.png resize: (306, 237) 1344959264 -2.664017946368359 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479673_0.png resize: (159, 192) 1344959265 -1.7810182572659865 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479674_0.png resize: (340, 214) 1344959266 -1.8653644317225295 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479670_0.png resize: (92, 185) 1344959267 -2.3340825817125457 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479666_0.png resize: (651, 820) 1344959269 -3.6554492659653057 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479643_0.png resize: (716, 544) 1344959270 -1.575693122028779 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479652_0.png resize: (175, 319) 1344959271 -1.5704923801929493 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479658_0.png resize: (149, 101) 1344959272 -3.3003091396169513 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479644_0.png resize: (413, 525) 1344959273 -1.9553579636512164 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479678_0.png resize: (162, 144) 1344959274 -1.8954408233455569 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479701_0.png resize: (527, 448) 1344959275 -1.6721516220346704 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479713_0.png resize: (470, 519) 1344959276 -2.1278662218005424 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479681_0.png resize: (174, 288) 1344959278 -2.9283111802524195 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479712_0.png resize: (88, 151) 1344959279 -1.754920999131365 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479709_0.png resize: (130, 213) 1344959280 -1.9364601846719434 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479684_0.png resize: (144, 135) 1344959281 -2.848636177289303 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479682_0.png resize: (185, 187) 1344959282 -3.069853518164602 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479690_0.png resize: (200, 474) 1344959283 -1.7915932316693164 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479698_0.png resize: (190, 152) 1344959284 -2.4229881273315006 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479687_0.png resize: (154, 134) 1344959285 -3.2650290735256124 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479717_0.png resize: (411, 516) 1344959286 -1.151600277211573 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479724_0.png resize: (153, 210) 1344959287 -2.5600756552837347 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479735_0.png resize: (517, 472) 1344959288 -0.5838243736812756 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479726_0.png resize: (449, 364) 1344959289 -3.1875208261887216 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479716_0.png resize: (465, 330) 1344959290 -2.753708340739707 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479751_0.png resize: (147, 221) 1344959291 -2.175910997335858 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479787_0.png resize: (237, 259) 1344959292 -2.565205278627406 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479797_0.png resize: (198, 185) 1344959293 -2.179416491928318 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479774_0.png resize: (265, 275) 1344959294 -4.229783659377091 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479779_0.png resize: (207, 290) 1344959295 -2.716798194057717 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479776_0.png resize: (164, 187) 1344959296 -1.523094788691361 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479744_0.png resize: (217, 326) 1344959297 -3.333249166083615 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479799_0.png resize: (328, 425) 1344959298 -2.9801251107178537 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479828_0.png resize: (164, 119) 1344959299 -2.9791633903315033 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479813_0.png resize: (173, 246) 1344959300 -2.4129827640313626 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479822_0.png resize: (138, 144) 1344959301 -3.2370230445776724 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479824_0.png resize: (89, 192) 1344959302 -3.0419360646691955 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479852_0.png resize: (125, 157) 1344959303 -2.0907160645308025 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479894_0.png resize: (65, 192) 1344959304 -1.863290804427225 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479875_0.png resize: (288, 377) 1344959305 -2.3776556047408097 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479860_0.png resize: (234, 258) 1344959306 -3.635991222890474 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479882_0.png resize: (69, 109) 1344959307 -3.0864459663219592 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479869_0.png resize: (189, 196) 1344959308 -2.8435875287625523 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479953_0.png resize: (85, 64) 1344959309 -1.2108268877725483 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479925_0.png resize: (223, 166) 1344959310 -2.6648904766784 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479909_0.png resize: (323, 361) 1344959311 -4.6092566454180215 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479937_0.png resize: (136, 187) 1344959312 -3.257051144641001 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479956_0.png resize: (127, 83) 1344959313 -1.7329435208282375 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479934_0.png resize: (103, 138) 1344959314 -2.1450509590969893 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480002_0.png resize: (492, 262) 1344959316 -2.3872473182258753 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480025_0.png resize: (154, 167) 1344959317 -1.9885155861251498 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480013_0.png resize: (283, 185) 1344959318 -3.7209469437687956 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480000_0.png resize: (232, 139) 1344959319 -4.376445275497303 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480057_0.png resize: (135, 176) 1344959320 -2.81906001662965 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480044_0.png resize: (332, 228) 1344959321 -2.006531725484177 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480063_0.png resize: (214, 309) 1344959322 -1.2984551183819522 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480067_0.png resize: (138, 157) 1344959323 -1.4375331401867442 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480064_0.png resize: (123, 169) 1344959324 -1.1227273648155336 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479738_0.png resize: (161, 80) 1344959326 -1.8361467119959947 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479877_0.png resize: (140, 245) 1344959327 -2.536680961087667 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480054_0.png resize: (83, 133) 1344959328 -3.263193803095163 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479626_0.png resize: (216, 738) 1344959366 -0.8236179097730093 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479628_0.png resize: (628, 643) 1344959367 -1.6142314611811839 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479627_0.png resize: (314, 690) 1344959368 -2.0615745736130675 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479640_0.png resize: (275, 318) 1344959369 -1.5417113498942774 treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479637_0.png resize: (480, 343) 1344959370 -0.9578705551031383 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479648_0.png resize: (404, 453) 1344959371 -2.244768386266138 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479659_0.png resize: (574, 515) 1344959372 -3.786420823409293 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479662_0.png resize: (113, 160) 1344959373 -4.611420299474413 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479661_0.png resize: (296, 295) 1344959374 -3.712592877511055 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479710_0.png resize: (602, 657) 1344959375 -3.0389749744095904 treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479680_0.png resize: (245, 335) 1344959376 -3.9020774637998263 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479739_0.png resize: (174, 386) 1344959377 -2.7696348611128463 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479722_0.png resize: (458, 521) 1344959378 -3.480540851858104 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479736_0.png resize: (415, 257) 1344959379 -2.233268020027971 treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479730_0.png resize: (352, 416) 1344959380 -1.8422265687506867 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479810_0.png resize: (283, 195) 1344959381 -3.3305070573481337 treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479821_0.png resize: (292, 265) 1344959382 -3.5060541379200276 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479856_0.png resize: (159, 149) 1344959383 -3.1163050510723864 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479841_0.png resize: (197, 221) 1344959384 -2.483703650325938 treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479854_0.png resize: (197, 200) 1344959385 -3.1870753953672786 treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479893_0.png resize: (91, 300) 1344959386 -2.565966417691837 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479943_0.png resize: (1169, 974) 1344959387 -2.1252942148923903 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479945_0.png resize: (183, 316) 1344959388 -3.829841436954696 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479932_0.png resize: (342, 442) 1344959389 -3.5864467532199393 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479959_0.png resize: (132, 124) 1344959390 -1.75300830441381 treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480006_0.png resize: (434, 392) 1344959391 -2.0710347604461297 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480062_0.png resize: (413, 421) 1344959393 -2.815445662537091 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479770_0.png resize: (138, 228) 1344959395 -3.454940052846337 treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480050_0.png resize: (110, 115) 1344959397 0.6149361911078678 treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479672_0.png resize: (160, 128) 1344959400 -2.1849743281210605 treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479963_0.png resize: (83, 103) 1344959401 -2.1105484126639604 treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480065_0.png resize: (209, 158) 1344959402 -1.062212702976278 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479786_0.png resize: (189, 140) 1344959405 -2.5779159774962928 treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479790_0.png resize: (133, 245) 1344959406 -1.1621067924006085 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 : 457 time used for this insertion : 0.03258872032165527 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 457 time used for this insertion : 0.10825562477111816 save missing photos in datou_result : time spend for datou_step_exec : 51.68922233581543 time spend to save output : 0.1592874526977539 total time spend for step 6 : 51.848509788513184 step7:brightness Mon Mar 17 20:32:57 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/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6.jpg treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589.jpg treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc.jpg treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07.jpg treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e.jpg treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095.jpg treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56.jpg treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008.jpg treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a.jpg treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78.jpg treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65.jpg treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c.jpg treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479625_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479636_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479633_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479623_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479639_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479634_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479629_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479638_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479632_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479656_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479649_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479668_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479665_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479654_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479651_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479646_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479667_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479675_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479663_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479645_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479669_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479655_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479660_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479653_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479650_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479647_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479691_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479692_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479685_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479700_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479711_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479679_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479696_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479683_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479706_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479702_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479695_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479704_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479694_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479705_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479677_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479699_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479714_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479697_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479686_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479708_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479689_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479688_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479703_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479676_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479707_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479693_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479720_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479731_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479728_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479734_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479725_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479718_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479737_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479729_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479733_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479723_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479715_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479719_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479732_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479721_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479727_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479789_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479748_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479800_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479741_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479768_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479791_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479765_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479761_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479783_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479758_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479742_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479798_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479752_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479795_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479766_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479773_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479746_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479759_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479788_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479794_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479762_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479801_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479781_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479777_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479756_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479743_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479760_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479771_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479749_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479778_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479745_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479764_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479796_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479755_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479763_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479782_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479750_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479784_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479747_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479785_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479767_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479753_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479775_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479772_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479793_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479740_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479769_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479757_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479780_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479792_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479754_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479816_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479808_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479809_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479825_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479807_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479829_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479814_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479803_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479805_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479806_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479823_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479832_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479830_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479826_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479827_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479804_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479815_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479811_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479812_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479820_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479817_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479818_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479831_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479819_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479802_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479847_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479836_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479839_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479848_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479857_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479835_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479840_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479855_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479834_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479833_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479845_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479838_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479837_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479849_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479851_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479843_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479850_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479844_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479842_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479853_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479858_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479846_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479871_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479868_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479881_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479890_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479889_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479892_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479874_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479878_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479865_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479901_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479866_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479903_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479898_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479900_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479904_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479876_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479859_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479884_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479861_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479867_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479899_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479880_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479863_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479887_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479864_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479897_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479888_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479873_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479879_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479895_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479896_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479883_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479885_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479862_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479870_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479886_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479872_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479902_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479891_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479950_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479966_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479946_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479908_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479906_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479957_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479926_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479935_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479968_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479911_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479967_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479912_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479948_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479939_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479915_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479914_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479918_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479923_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479962_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479913_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479928_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479941_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479942_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479944_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479927_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479955_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479919_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479921_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479938_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479964_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479924_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479905_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479965_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479920_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479947_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479940_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479958_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479961_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479951_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479952_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479960_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479922_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479936_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479907_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479949_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479917_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479931_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479916_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479910_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479933_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479929_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479930_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479954_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479973_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479988_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479979_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479995_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480016_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479972_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479997_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479982_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480005_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479971_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479996_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480008_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480011_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480028_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480020_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479987_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479983_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479986_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479981_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479969_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479980_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480022_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479998_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480024_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479975_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480009_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479994_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480012_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479999_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480001_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479976_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480027_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480026_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480015_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480007_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480003_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479992_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480021_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479984_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480019_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479990_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479989_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479991_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479978_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480010_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480004_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479993_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480018_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480023_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480014_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479970_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479974_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479977_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716479985_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480017_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480033_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480041_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480049_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480056_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480037_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480030_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480042_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480036_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480046_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480055_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480053_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480032_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480048_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480047_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480035_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480039_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480052_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480040_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480034_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480045_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480043_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480031_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480029_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480038_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480051_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480060_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480059_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480061_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480066_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480058_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479630_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479624_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479631_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479642_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479641_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479635_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479657_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479664_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479671_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479673_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479674_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479670_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479666_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479643_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479652_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479658_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479644_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479678_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479701_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479713_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479681_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479712_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479709_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479684_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479682_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479690_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479698_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479687_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479717_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479724_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479735_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479726_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479716_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479751_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479787_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479797_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479774_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479779_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479776_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479744_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479799_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479828_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479813_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479822_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479824_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479852_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479894_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479875_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479860_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479882_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479869_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479953_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479925_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479909_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479937_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479956_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479934_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480002_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480025_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480013_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480000_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480057_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480044_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480063_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480067_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480064_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479738_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479877_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480054_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479626_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479628_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479627_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479640_0.png treat image : temp/1742239229_576165_1344944844_df8bfd28109eb226f1f25fed9f0cbae6_rle_crop_3716479637_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479648_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479659_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479662_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479661_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479710_0.png treat image : temp/1742239229_576165_1344944761_f0bcff9dd34bca11e8d52432e9a6c6fc_rle_crop_3716479680_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479739_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479722_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479736_0.png treat image : temp/1742239229_576165_1344944670_1eaa4bacb365014cc2d9be4f0f459d07_rle_crop_3716479730_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479810_0.png treat image : temp/1742239229_576165_1344944584_de073f12bf5de40c5cc34688f5e7a095_rle_crop_3716479821_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479856_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479841_0.png treat image : temp/1742239229_576165_1344941466_b958db9a7a21eb67ccc4a988c1c3cb56_rle_crop_3716479854_0.png treat image : temp/1742239229_576165_1344941399_3ef54d12d51bacbe10294dcb1fe6c008_rle_crop_3716479893_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479943_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479945_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479932_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479959_0.png treat image : temp/1742239229_576165_1344940808_da78e2a40d3440f1f4127ad4a2b99d78_rle_crop_3716480006_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480062_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479770_0.png treat image : temp/1742239229_576165_1344940722_514ebb20e7e5bae9186b085f321e5c65_rle_crop_3716480050_0.png treat image : temp/1742239229_576165_1344944841_6eecab0482cdea45ff2a85fe06233589_rle_crop_3716479672_0.png treat image : temp/1742239229_576165_1344940834_cea13776af52de63b33938a1cd85337a_rle_crop_3716479963_0.png treat image : temp/1742239229_576165_1344940691_2c3cc6f79fdc67b9bf878f55ffc4462c_rle_crop_3716480065_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479786_0.png treat image : temp/1742239229_576165_1344944609_a7b4d67c38c448c9cb85cac3ff50ea0e_rle_crop_3716479790_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 : 457 time used for this insertion : 1.3799211978912354 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 457 time used for this insertion : 0.1116628646850586 save missing photos in datou_result : time spend for datou_step_exec : 13.288839101791382 time spend to save output : 1.5098483562469482 total time spend for step 7 : 14.79868745803833 step8:velours_tree Mon Mar 17 20:33:12 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 : 1.641404151916504 time spend to save output : 5.91278076171875e-05 total time spend for step 8 : 1.641463279724121 step9:send_mail_cod Mon Mar 17 20:33:14 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_P21501459_17-03-2025_20_33_14.pdf 21501677 imagette215016771742239994 21501678 change filename to text .change filename to text .change filename to text .imagette215016781742239994 21501679 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 .imagette215016791742239994 21501680 change filename to text .change filename to text .change filename to text .imagette215016801742239995 21501681 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 .imagette215016811742239995 21501682 change filename to text .change filename to text .imagette215016821742239997 21501683 imagette215016831742239997 21501684 imagette215016841742239997 21501686 change filename to text .change filename to text .imagette215016861742239997 21501687 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 .imagette215016871742239997 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21501459 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21501677,21501678,21501679,21501680,21501681,21501682,21501683,21501684,21501685,21501686,21501687?tags=flou,pehd,carton,metal,papier,pet_fonce,mal_croppe,background,environnement,autre,pet_clair args[1344944844] : ((1344944844, -0.7797608471700513, 492688767), (1344944844, 0.20720841822300737, 2107752395), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344944841] : ((1344944841, -3.3921694729204983, 492609224), (1344944841, -0.20009761585612376, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344944761] : ((1344944761, -4.791298796530102, 492609224), (1344944761, -0.30677681950372604, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344944670] : ((1344944670, -2.005585781186239, 492609224), (1344944670, -0.35831181893585484, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344944609] : ((1344944609, -3.758482784676107, 492609224), (1344944609, -0.15536143088224666, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344944584] : ((1344944584, -4.020153804614197, 492609224), (1344944584, -0.476353587364772, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344941466] : ((1344941466, -3.583759073980087, 492609224), (1344941466, -0.2437122662094503, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344941399] : ((1344941399, -5.171135879829996, 492609224), (1344941399, -0.1158708349793395, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344940834] : ((1344940834, -5.207228871339992, 492609224), (1344940834, -0.05785492304800675, 2107752395), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344940808] : ((1344940808, -5.26293212030625, 492609224), (1344940808, -0.2075530167783632, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344940722] : ((1344940722, -4.139935398347291, 492609224), (1344940722, -0.219592553583184, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com args[1344940691] : ((1344940691, -1.7863308962890765, 492688767), (1344940691, -0.416547170217176, 496442774), '0.2147837993221981') We are sending mail with results at report@fotonower.com refus_total : 0.2147837993221981 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=21501459 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 SELECT photo_id, url FROM MTRBack.photos ph WHERE photo_id IN (1344944761,1344944841,1344944844,1344940834,1344940691,1344940722,1344940808,1344941399,1344941466,1344944584,1344944609,1344944670) Found this number of photos: 12 begin to download photo : 1344944761 begin to download photo : 1344940834 begin to download photo : 1344940808 begin to download photo : 1344944584 download finish for photo 1344940834 begin to download photo : 1344940691 download finish for photo 1344940808 begin to download photo : 1344941399 download finish for photo 1344944584 begin to download photo : 1344944609 download finish for photo 1344944761 begin to download photo : 1344944841 download finish for photo 1344940691 begin to download photo : 1344940722 download finish for photo 1344941399 begin to download photo : 1344941466 download finish for photo 1344944841 begin to download photo : 1344944844 download finish for photo 1344944609 begin to download photo : 1344944670 download finish for photo 1344940722 download finish for photo 1344944844 download finish for photo 1344944670 download finish for photo 1344941466 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21501459_17-03-2025_20_33_14.pdf results_Auto_P21501459_17-03-2025_20_33_14.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21501459_17-03-2025_20_33_14.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','21501459','results_Auto_P21501459_17-03-2025_20_33_14.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21501459_17-03-2025_20_33_14.pdf','pdf','','0.99','0.2147837993221981') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/21501459

https://www.fotonower.com/image?json=false&list_photos_id=1344944844
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344944841
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344944761
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344944670
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344944609
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344944584
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344941466
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344941399
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344940834
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344940808
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344940722
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1344940691
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 21.48%
Veuillez trouver les photos des contaminants.

exemples de contaminants: pehd: https://www.fotonower.com/view/21501678?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/21501679?limit=200
exemples de contaminants: metal: https://www.fotonower.com/view/21501680?limit=200
exemples de contaminants: papier: https://www.fotonower.com/view/21501681?limit=200
exemples de contaminants: pet_fonce: https://www.fotonower.com/view/21501682?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/21501686?limit=200
exemples de contaminants: pet_clair: https://www.fotonower.com/view/21501687?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21501459_17-03-2025_20_33_14.pdf.

Lien vers velours :https://www.fotonower.com/velours/21501677,21501678,21501679,21501680,21501681,21501682,21501683,21501684,21501685,21501686,21501687?tags=flou,pehd,carton,metal,papier,pet_fonce,mal_croppe,background,environnement,autre,pet_clair.


L'équipe Fotonower 202 b'' Server: nginx Date: Mon, 17 Mar 2025 19:33:22 GMT Content-Length: 0 Connection: close X-Message-Id: OLbbqer1TlqhmWa6IOPyEA 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 [1344944844, 1344944841, 1344944761, 1344944670, 1344944609, 1344944584, 1344941466, 1344941399, 1344940834, 1344940808, 1344940722, 1344940691] 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, '2675453') ('3318', '21501459', '1344944844', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944841', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944761', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944670', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944609', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944584', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941466', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941399', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940834', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940808', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940722', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940691', None, None, None, None, None, '2675453') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.01405191421508789 save_final save missing photos in datou_result : time spend for datou_step_exec : 8.393519163131714 time spend to save output : 0.014351844787597656 total time spend for step 9 : 8.407871007919312 step10:split_time_score Mon Mar 17 20:33:22 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'}] (('19', 12),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 17032025 21501459 Nombre de photos uploadées : 12 / 23040 (0%) 17032025 21501459 Nombre de photos taguées (types de déchets): 0 / 12 (0%) 17032025 21501459 Nombre de photos taguées (volume) : 0 / 12 (0%) elapsed_time : load_data_split_time_score 3.337860107421875e-06 elapsed_time : order_list_meta_photo_and_scores 8.106231689453125e-06 ???????????? elapsed_time : fill_and_build_computed_from_old_data 0.0006749629974365234 elapsed_time : insert_dashboard_record_day_entry 0.02619171142578125 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.2100151268068956 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21487447_17-03-2025_11_11_31.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21487447 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`=21487447 AND mptpi.`type`=3594 To do Qualite : 0.11901509511795412 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21489006_17-03-2025_12_20_47.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21489006 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 ! 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=21489006 AND mptpi.`type`=3726 To do Qualite : 0.0614624131463237 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21489027_17-03-2025_12_25_04.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21489027 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 ! 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=21489027 AND mptpi.`type`=3726 To do Qualite : 0.25338279264251995 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21491643_17-03-2025_14_02_24.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21491643 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`=21491643 AND mptpi.`type`=3594 To do Qualite : 0.23104907066993471 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21491644_17-03-2025_14_01_16.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21491644 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`=21491644 AND mptpi.`type`=3594 To do Qualite : 0.23672240629791017 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21493940_17-03-2025_16_38_51.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21493940 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`=21493940 AND mptpi.`type`=3594 To do Qualite : 0.0 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21493942_17-03-2025_15_21_58.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21493942 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`=21493942 AND mptpi.`type`=3594 To do Qualite : 0.07818962663281916 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21498709_17-03-2025_19_00_47.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21498709 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 ! 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=21498709 AND mptpi.`type`=3726 To do Qualite : 0.08741344217039969 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21498714_17-03-2025_18_51_09.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21498714 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 ! 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=21498714 AND mptpi.`type`=3726 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21501457 order by id desc limit 1 Qualite : 0.2147837993221981 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21501459_17-03-2025_20_33_14.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21501459 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`=21501459 AND mptpi.`type`=3594 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'17032025': {'nb_upload': 12, '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 [1344944844, 1344944841, 1344944761, 1344944670, 1344944609, 1344944584, 1344941466, 1344941399, 1344940834, 1344940808, 1344940722, 1344940691] Looping around the photos to save general results len do output : 1 /21501459Didn'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, '2675453') ('3318', '21501459', '1344944844', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944841', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944761', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944670', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944609', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344944584', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941466', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344941399', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940834', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940808', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940722', None, None, None, None, None, '2675453') ('3318', None, None, None, None, None, None, None, '2675453') ('3318', '21501459', '1344940691', None, None, None, None, None, '2675453') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 13 time used for this insertion : 0.015299558639526367 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.6752753257751465 time spend to save output : 0.015583992004394531 total time spend for step 10 : 1.690859317779541 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 12 set_done_treatment 341.78user 185.49system 12:59.46elapsed 67%CPU (0avgtext+0avgdata 5371060maxresident)k 21894384inputs+237392outputs (678601major+30943855minor)pagefaults 0swaps