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 : 708613 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 : ['3234682'] with mtr_portfolio_ids : ['24581312'] and first list_photo_ids : [] new path : /proc/708613/ 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 , BFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 18 ; length of list_pids : 18 ; length of list_args : 18 time to download the photos : 3.2955105304718018 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 Fri Jul 4 09:00:31 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 : 5444 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-07-04 09:00:34.443299: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-07-04 09:00:34.471551: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493035000 Hz 2025-07-04 09:00:34.473513: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f3b5c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-07-04 09:00:34.473561: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-07-04 09:00:34.477141: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-07-04 09:00:34.607855: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x156966e0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-07-04 09:00:34.607924: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-07-04 09:00:34.609208: 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 2025-07-04 09:00:34.609675: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-07-04 09:00:34.613461: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-07-04 09:00:34.617121: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-07-04 09:00:34.617876: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-07-04 09:00:34.621676: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-07-04 09:00:34.623565: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-07-04 09:00:34.630258: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-07-04 09:00:34.631506: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-07-04 09:00:34.631617: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-07-04 09:00:34.632304: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-07-04 09:00:34.632326: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-07-04 09:00:34.632338: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-07-04 09:00:34.633471: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4831 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. 2025-07-04 09:00:35.007002: 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 2025-07-04 09:00:35.007094: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-07-04 09:00:35.007115: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-07-04 09:00:35.007133: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-07-04 09:00:35.007150: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-07-04 09:00:35.007184: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-07-04 09:00:35.007202: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-07-04 09:00:35.007220: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-07-04 09:00:35.008498: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-07-04 09:00:35.010085: 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 2025-07-04 09:00:35.010134: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-07-04 09:00:35.010153: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-07-04 09:00:35.010172: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-07-04 09:00:35.010192: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-07-04 09:00:35.010209: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-07-04 09:00:35.010227: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-07-04 09:00:35.010248: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-07-04 09:00:35.011506: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-07-04 09:00:35.011550: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-07-04 09:00:35.011563: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-07-04 09:00:35.011573: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-07-04 09:00:35.012744: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4831 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 : [] 2025-07-04 09:00:47.881193: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-07-04 09:00:48.113155: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-07-04 09:00:48.862815: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2025-07-04 09:00:48.864988: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2025-07-04 09:00:53.986329: 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 2025-07-04 09:00:53.995876: 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 2025-07-04 09:00:53.996729: 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 2025-07-04 09:00:54.824419: 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. 2025-07-04 09:00:54.893660: 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 2025-07-04 09:00:54.893754: 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. 2025-07-04 09:00:54.894535: 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 2025-07-04 09:00:54.894554: 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. 2025-07-04 09:00:54.901155: 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 2025-07-04 09:00:54.901183: 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. 2025-07-04 09:00:54.901879: 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 2025-07-04 09:00:54.901895: 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. 2025-07-04 09:00:54.934376: 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 2025-07-04 09:00:54.934486: 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. 2025-07-04 09:00:54.934514: 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. 2025-07-04 09:00:54.935930: 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 2025-07-04 09:00:54.935965: 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. 2025-07-04 09:00:54.937311: 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 2025-07-04 09:00:54.937342: 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. 2025-07-04 09:00:54.944417: 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 2025-07-04 09:00:54.944451: 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. 2025-07-04 09:00:54.945127: 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 2025-07-04 09:00:54.945143: 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. 2025-07-04 09:00:54.945848: 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 2025-07-04 09:00:54.945863: 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. 2025-07-04 09:00:54.946629: 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 2025-07-04 09:00:54.955330: 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 2025-07-04 09:00:54.956108: 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 2025-07-04 09:00:54.975442: 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 2025-07-04 09:00:54.976411: 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 2025-07-04 09:00:54.977135: 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 2025-07-04 09:00:54.977810: 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 2025-07-04 09:00:54.982014: 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 2025-07-04 09:00:54.982692: 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 2025-07-04 09:00:54.983500: 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 2025-07-04 09:00:54.984247: 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 2025-07-04 09:00:54.986017: 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 2025-07-04 09:00:54.995802: 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 2025-07-04 09:00:54.996535: 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 2025-07-04 09:00:55.005862: 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 2025-07-04 09:00:55.006578: 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 2025-07-04 09:00:55.007304: 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 2025-07-04 09:00:55.008036: 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 2025-07-04 09:00:55.008755: 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 2025-07-04 09:00:55.009425: 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 : 18 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 error in detect the image : temp/1751612427_708613_1370462805_92baa68020fe11e6d5850e303ae1500b_32504942.jpg 2 root error(s) found. (0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[node conv1/convolution (defined at /usr/local/lib/python3.8/dist-packages/keras/backend/tensorflow_backend.py:3007) ]] [[mrcnn_detection/map/while/body/_1/PadV2/paddings/_94]] (1) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[node conv1/convolution (defined at /usr/local/lib/python3.8/dist-packages/keras/backend/tensorflow_backend.py:3007) ]] 0 successful operations. 0 derived errors ignored. [Op:__inference_keras_scratch_graph_13584] Function call stack: keras_scratch_graph -> keras_scratch_graph NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 26 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 44 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 40 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 34 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 49 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 49 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 38 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 48 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 26 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 44 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 34 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 52 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 43 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 31 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 43 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 42 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3840.00000 nb d'objets trouves : 57 Detection mask done ! Trying to reset tf kernel 709269 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2546 tf kernel not reseted sub process len(results) : 17 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 17 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 : 5444 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 : 0.2569572925567627 nb_pixel_total : 44005 time to create 1 rle with old method : 0.05241680145263672 length of segment : 257 time for calcul the mask position with numpy : 0.13084959983825684 nb_pixel_total : 17545 time to create 1 rle with old method : 0.02342081069946289 length of segment : 214 time for calcul the mask position with numpy : 0.03930068016052246 nb_pixel_total : 16154 time to create 1 rle with old method : 0.02311253547668457 length of segment : 201 time for calcul the mask position with numpy : 0.12293171882629395 nb_pixel_total : 19740 time to create 1 rle with old method : 0.02614879608154297 length of segment : 180 time for calcul the mask position with numpy : 0.11617255210876465 nb_pixel_total : 10081 time to create 1 rle with old method : 0.01700735092163086 length of segment : 171 time for calcul the mask position with numpy : 0.35113954544067383 nb_pixel_total : 37441 time to create 1 rle with old method : 0.044805288314819336 length of segment : 350 time for calcul the mask position with numpy : 0.1951746940612793 nb_pixel_total : 44956 time to create 1 rle with old method : 0.054834842681884766 length of segment : 274 time for calcul the mask position with numpy : 0.08508539199829102 nb_pixel_total : 22508 time to create 1 rle with old method : 0.025350332260131836 length of segment : 194 time for calcul the mask position with numpy : 0.04045367240905762 nb_pixel_total : 7918 time to create 1 rle with old method : 0.012283802032470703 length of segment : 177 time for calcul the mask position with numpy : 0.09406685829162598 nb_pixel_total : 38278 time to create 1 rle with old method : 0.04609036445617676 length of segment : 296 time for calcul the mask position with numpy : 0.0543670654296875 nb_pixel_total : 29363 time to create 1 rle with old method : 0.05733132362365723 length of segment : 217 time for calcul the mask position with numpy : 0.11161375045776367 nb_pixel_total : 95721 time to create 1 rle with old method : 0.13917016983032227 length of segment : 479 time for calcul the mask position with numpy : 0.0873253345489502 nb_pixel_total : 56665 time to create 1 rle with old method : 0.06689643859863281 length of segment : 224 time for calcul the mask position with numpy : 0.0735776424407959 nb_pixel_total : 19551 time to create 1 rle with old method : 0.028228282928466797 length of segment : 235 time for calcul the mask position with numpy : 0.09760212898254395 nb_pixel_total : 24954 time to create 1 rle with old method : 0.03165102005004883 length of segment : 194 time for calcul the mask position with numpy : 0.06646728515625 nb_pixel_total : 13952 time to create 1 rle with old method : 0.022914409637451172 length of segment : 235 time for calcul the mask position with numpy : 0.10872483253479004 nb_pixel_total : 17739 time to create 1 rle with old method : 0.027174711227416992 length of segment : 331 time for calcul the mask position with numpy : 0.37302660942077637 nb_pixel_total : 259514 time to create 1 rle with new method : 0.0167238712310791 length of segment : 353 time for calcul the mask position with numpy : 0.1202852725982666 nb_pixel_total : 29335 time to create 1 rle with old method : 0.0435643196105957 length of segment : 301 time for calcul the mask position with numpy : 0.05010986328125 nb_pixel_total : 18232 time to create 1 rle with old method : 0.03201937675476074 length of segment : 135 time for calcul the mask position with numpy : 0.3962547779083252 nb_pixel_total : 162551 time to create 1 rle with new method : 0.01299142837524414 length of segment : 491 time for calcul the mask position with numpy : 0.012495756149291992 nb_pixel_total : 14649 time to create 1 rle with old method : 0.021581649780273438 length of segment : 133 time for calcul the mask position with numpy : 0.05257058143615723 nb_pixel_total : 17285 time to create 1 rle with old method : 0.02414727210998535 length of segment : 197 time for calcul the mask position with numpy : 0.16925334930419922 nb_pixel_total : 67219 time to create 1 rle with old method : 0.08427023887634277 length of segment : 393 time for calcul the mask position with numpy : 0.14362430572509766 nb_pixel_total : 104171 time to create 1 rle with old method : 0.1252269744873047 length of segment : 382 time for calcul the mask position with numpy : 0.0899817943572998 nb_pixel_total : 35412 time to create 1 rle with old method : 0.055275678634643555 length of segment : 433 time for calcul the mask position with numpy : 0.24152159690856934 nb_pixel_total : 104261 time to create 1 rle with old method : 0.1272132396697998 length of segment : 380 time for calcul the mask position with numpy : 0.07313394546508789 nb_pixel_total : 38539 time to create 1 rle with old method : 0.0476377010345459 length of segment : 551 time for calcul the mask position with numpy : 0.1493968963623047 nb_pixel_total : 61079 time to create 1 rle with old method : 0.07995390892028809 length of segment : 662 time for calcul the mask position with numpy : 0.029559612274169922 nb_pixel_total : 30347 time to create 1 rle with old method : 0.03522801399230957 length of segment : 328 time for calcul the mask position with numpy : 0.0195615291595459 nb_pixel_total : 8618 time to create 1 rle with old method : 0.015007495880126953 length of segment : 109 time for calcul the mask position with numpy : 0.00024437904357910156 nb_pixel_total : 5970 time to create 1 rle with old method : 0.007105588912963867 length of segment : 149 time for calcul the mask position with numpy : 0.5165514945983887 nb_pixel_total : 444465 time to create 1 rle with new method : 0.051888227462768555 length of segment : 1468 time for calcul the mask position with numpy : 0.09320998191833496 nb_pixel_total : 114831 time to create 1 rle with old method : 0.13267040252685547 length of segment : 516 time for calcul the mask position with numpy : 0.03994584083557129 nb_pixel_total : 31162 time to create 1 rle with old method : 0.03853344917297363 length of segment : 552 time for calcul the mask position with numpy : 0.06864643096923828 nb_pixel_total : 19715 time to create 1 rle with old method : 0.028011083602905273 length of segment : 313 time for calcul the mask position with numpy : 0.0015687942504882812 nb_pixel_total : 11150 time to create 1 rle with old method : 0.013192176818847656 length of segment : 218 time for calcul the mask position with numpy : 0.03347969055175781 nb_pixel_total : 11647 time to create 1 rle with old method : 0.01806783676147461 length of segment : 160 time for calcul the mask position with numpy : 0.026528358459472656 nb_pixel_total : 18709 time to create 1 rle with old method : 0.02767801284790039 length of segment : 171 time for calcul the mask position with numpy : 0.03795289993286133 nb_pixel_total : 31156 time to create 1 rle with old method : 0.03631925582885742 length of segment : 243 time for calcul the mask position with numpy : 0.10397100448608398 nb_pixel_total : 55751 time to create 1 rle with old method : 0.07490730285644531 length of segment : 271 time for calcul the mask position with numpy : 0.045345306396484375 nb_pixel_total : 19175 time to create 1 rle with old method : 0.0311739444732666 length of segment : 184 time for calcul the mask position with numpy : 0.008983850479125977 nb_pixel_total : 22194 time to create 1 rle with old method : 0.025516271591186523 length of segment : 170 time for calcul the mask position with numpy : 0.1969621181488037 nb_pixel_total : 134180 time to create 1 rle with old method : 0.16330766677856445 length of segment : 553 time for calcul the mask position with numpy : 0.14272594451904297 nb_pixel_total : 48443 time to create 1 rle with old method : 0.07370972633361816 length of segment : 290 time for calcul the mask position with numpy : 0.1240694522857666 nb_pixel_total : 56307 time to create 1 rle with old method : 0.08527374267578125 length of segment : 233 time for calcul the mask position with numpy : 0.15958905220031738 nb_pixel_total : 73978 time to create 1 rle with old method : 0.09571290016174316 length of segment : 406 time for calcul the mask position with numpy : 0.0809628963470459 nb_pixel_total : 30315 time to create 1 rle with old method : 0.041242122650146484 length of segment : 342 time for calcul the mask position with numpy : 0.08004307746887207 nb_pixel_total : 52123 time to create 1 rle with old method : 0.06327056884765625 length of segment : 221 time for calcul the mask position with numpy : 0.03134632110595703 nb_pixel_total : 7351 time to create 1 rle with old method : 0.013782739639282227 length of segment : 79 time for calcul the mask position with numpy : 0.16605305671691895 nb_pixel_total : 72532 time to create 1 rle with old method : 0.08564591407775879 length of segment : 410 time for calcul the mask position with numpy : 0.0934762954711914 nb_pixel_total : 15733 time to create 1 rle with old method : 0.021129131317138672 length of segment : 387 time for calcul the mask position with numpy : 0.08325004577636719 nb_pixel_total : 28696 time to create 1 rle with old method : 0.0351712703704834 length of segment : 144 time for calcul the mask position with numpy : 0.054215431213378906 nb_pixel_total : 18818 time to create 1 rle with old method : 0.02715277671813965 length of segment : 191 time for calcul the mask position with numpy : 0.011882543563842773 nb_pixel_total : 16075 time to create 1 rle with old method : 0.02452874183654785 length of segment : 166 time for calcul the mask position with numpy : 0.12676596641540527 nb_pixel_total : 58408 time to create 1 rle with old method : 0.08263754844665527 length of segment : 350 time for calcul the mask position with numpy : 0.05078387260437012 nb_pixel_total : 18935 time to create 1 rle with old method : 0.03516507148742676 length of segment : 350 time for calcul the mask position with numpy : 0.2346787452697754 nb_pixel_total : 188678 time to create 1 rle with new method : 0.014124155044555664 length of segment : 288 time for calcul the mask position with numpy : 0.10491299629211426 nb_pixel_total : 54205 time to create 1 rle with old method : 0.06365346908569336 length of segment : 288 time for calcul the mask position with numpy : 0.0002808570861816406 nb_pixel_total : 14896 time to create 1 rle with old method : 0.017729997634887695 length of segment : 106 time for calcul the mask position with numpy : 0.2685220241546631 nb_pixel_total : 103965 time to create 1 rle with old method : 0.1222989559173584 length of segment : 455 time for calcul the mask position with numpy : 0.10574698448181152 nb_pixel_total : 80951 time to create 1 rle with old method : 0.09365344047546387 length of segment : 265 time for calcul the mask position with numpy : 0.016546964645385742 nb_pixel_total : 38760 time to create 1 rle with old method : 0.046639204025268555 length of segment : 213 time for calcul the mask position with numpy : 0.06421041488647461 nb_pixel_total : 60810 time to create 1 rle with old method : 0.08939480781555176 length of segment : 277 time for calcul the mask position with numpy : 0.1080789566040039 nb_pixel_total : 121795 time to create 1 rle with old method : 0.1424562931060791 length of segment : 436 time for calcul the mask position with numpy : 0.023568391799926758 nb_pixel_total : 11357 time to create 1 rle with old method : 0.0157163143157959 length of segment : 130 time for calcul the mask position with numpy : 0.22339248657226562 nb_pixel_total : 155888 time to create 1 rle with new method : 0.014324426651000977 length of segment : 679 time for calcul the mask position with numpy : 0.48178577423095703 nb_pixel_total : 163599 time to create 1 rle with new method : 0.016057968139648438 length of segment : 675 time for calcul the mask position with numpy : 0.31410837173461914 nb_pixel_total : 93754 time to create 1 rle with old method : 0.10976099967956543 length of segment : 541 time for calcul the mask position with numpy : 0.11071014404296875 nb_pixel_total : 68051 time to create 1 rle with old method : 0.08549761772155762 length of segment : 255 time for calcul the mask position with numpy : 0.03947710990905762 nb_pixel_total : 20043 time to create 1 rle with old method : 0.030759572982788086 length of segment : 132 time for calcul the mask position with numpy : 0.0882411003112793 nb_pixel_total : 52043 time to create 1 rle with old method : 0.06354665756225586 length of segment : 387 time for calcul the mask position with numpy : 0.18318676948547363 nb_pixel_total : 82822 time to create 1 rle with old method : 0.09321093559265137 length of segment : 455 time for calcul the mask position with numpy : 0.1690077781677246 nb_pixel_total : 85442 time to create 1 rle with old method : 0.09635090827941895 length of segment : 449 time for calcul the mask position with numpy : 0.13895058631896973 nb_pixel_total : 69065 time to create 1 rle with old method : 0.07794404029846191 length of segment : 372 time for calcul the mask position with numpy : 0.08714652061462402 nb_pixel_total : 41709 time to create 1 rle with old method : 0.04909920692443848 length of segment : 280 time for calcul the mask position with numpy : 0.0829625129699707 nb_pixel_total : 70022 time to create 1 rle with old method : 0.07799625396728516 length of segment : 346 time for calcul the mask position with numpy : 0.02949833869934082 nb_pixel_total : 11282 time to create 1 rle with old method : 0.017702817916870117 length of segment : 119 time for calcul the mask position with numpy : 0.09615826606750488 nb_pixel_total : 35445 time to create 1 rle with old method : 0.042821407318115234 length of segment : 200 time for calcul the mask position with numpy : 0.09349536895751953 nb_pixel_total : 77078 time to create 1 rle with old method : 0.08315348625183105 length of segment : 335 time for calcul the mask position with numpy : 0.23206162452697754 nb_pixel_total : 277957 time to create 1 rle with new method : 0.016865253448486328 length of segment : 617 time for calcul the mask position with numpy : 0.07392549514770508 nb_pixel_total : 53567 time to create 1 rle with old method : 0.06351709365844727 length of segment : 354 time for calcul the mask position with numpy : 0.17211699485778809 nb_pixel_total : 131815 time to create 1 rle with old method : 0.13942408561706543 length of segment : 468 time for calcul the mask position with numpy : 0.3235805034637451 nb_pixel_total : 108507 time to create 1 rle with old method : 0.12091803550720215 length of segment : 487 time for calcul the mask position with numpy : 1.1536169052124023 nb_pixel_total : 323103 time to create 1 rle with new method : 0.04534173011779785 length of segment : 666 time for calcul the mask position with numpy : 0.07321310043334961 nb_pixel_total : 26033 time to create 1 rle with old method : 0.03545808792114258 length of segment : 168 time for calcul the mask position with numpy : 0.2706003189086914 nb_pixel_total : 90408 time to create 1 rle with old method : 0.12271809577941895 length of segment : 504 time for calcul the mask position with numpy : 0.013318061828613281 nb_pixel_total : 9864 time to create 1 rle with old method : 0.01652979850769043 length of segment : 108 time for calcul the mask position with numpy : 0.10663032531738281 nb_pixel_total : 28758 time to create 1 rle with old method : 0.04541325569152832 length of segment : 267 time for calcul the mask position with numpy : 0.4758479595184326 nb_pixel_total : 38239 time to create 1 rle with old method : 0.04635334014892578 length of segment : 271 time for calcul the mask position with numpy : 0.272446870803833 nb_pixel_total : 26517 time to create 1 rle with old method : 0.03594565391540527 length of segment : 126 time for calcul the mask position with numpy : 0.7314212322235107 nb_pixel_total : 44037 time to create 1 rle with old method : 0.05658102035522461 length of segment : 338 time for calcul the mask position with numpy : 0.9945883750915527 nb_pixel_total : 139053 time to create 1 rle with old method : 0.1676938533782959 length of segment : 303 time for calcul the mask position with numpy : 0.4870917797088623 nb_pixel_total : 123990 time to create 1 rle with old method : 0.14555597305297852 length of segment : 481 time for calcul the mask position with numpy : 0.7094576358795166 nb_pixel_total : 65716 time to create 1 rle with old method : 0.08191752433776855 length of segment : 311 time for calcul the mask position with numpy : 0.000156402587890625 nb_pixel_total : 4196 time to create 1 rle with old method : 0.005177497863769531 length of segment : 67 time for calcul the mask position with numpy : 0.9069488048553467 nb_pixel_total : 82955 time to create 1 rle with old method : 0.10076427459716797 length of segment : 512 time for calcul the mask position with numpy : 0.23681950569152832 nb_pixel_total : 8280 time to create 1 rle with old method : 0.014347553253173828 length of segment : 100 time for calcul the mask position with numpy : 0.3439207077026367 nb_pixel_total : 36327 time to create 1 rle with old method : 0.044896602630615234 length of segment : 238 time for calcul the mask position with numpy : 0.5587203502655029 nb_pixel_total : 56850 time to create 1 rle with old method : 0.06722164154052734 length of segment : 432 time for calcul the mask position with numpy : 0.01808929443359375 nb_pixel_total : 21669 time to create 1 rle with old method : 0.028776884078979492 length of segment : 184 time for calcul the mask position with numpy : 0.10257530212402344 nb_pixel_total : 22043 time to create 1 rle with old method : 0.03030109405517578 length of segment : 254 time for calcul the mask position with numpy : 0.34337306022644043 nb_pixel_total : 21852 time to create 1 rle with old method : 0.029284238815307617 length of segment : 221 time for calcul the mask position with numpy : 0.2522289752960205 nb_pixel_total : 21119 time to create 1 rle with old method : 0.029587268829345703 length of segment : 220 time for calcul the mask position with numpy : 0.5167768001556396 nb_pixel_total : 43942 time to create 1 rle with old method : 0.053299665451049805 length of segment : 197 time for calcul the mask position with numpy : 0.20491576194763184 nb_pixel_total : 31218 time to create 1 rle with old method : 0.039771080017089844 length of segment : 167 time for calcul the mask position with numpy : 0.2500286102294922 nb_pixel_total : 35110 time to create 1 rle with old method : 0.04438924789428711 length of segment : 434 time for calcul the mask position with numpy : 0.3616006374359131 nb_pixel_total : 24541 time to create 1 rle with old method : 0.04299569129943848 length of segment : 162 time for calcul the mask position with numpy : 0.29366302490234375 nb_pixel_total : 36734 time to create 1 rle with old method : 0.045183420181274414 length of segment : 207 time for calcul the mask position with numpy : 0.2851564884185791 nb_pixel_total : 81993 time to create 1 rle with old method : 0.10077810287475586 length of segment : 441 time for calcul the mask position with numpy : 0.29480481147766113 nb_pixel_total : 35544 time to create 1 rle with old method : 0.05752110481262207 length of segment : 280 time for calcul the mask position with numpy : 0.29810357093811035 nb_pixel_total : 24426 time to create 1 rle with old method : 0.026281356811523438 length of segment : 156 time for calcul the mask position with numpy : 0.3204641342163086 nb_pixel_total : 122274 time to create 1 rle with old method : 0.143843412399292 length of segment : 601 time for calcul the mask position with numpy : 0.12452030181884766 nb_pixel_total : 83665 time to create 1 rle with old method : 0.09949684143066406 length of segment : 476 time for calcul the mask position with numpy : 0.13170170783996582 nb_pixel_total : 39975 time to create 1 rle with old method : 0.05052590370178223 length of segment : 279 time for calcul the mask position with numpy : 0.01910996437072754 nb_pixel_total : 7282 time to create 1 rle with old method : 0.008536815643310547 length of segment : 65 time for calcul the mask position with numpy : 0.08312606811523438 nb_pixel_total : 34666 time to create 1 rle with old method : 0.04701662063598633 length of segment : 172 time for calcul the mask position with numpy : 0.0754690170288086 nb_pixel_total : 60281 time to create 1 rle with old method : 0.06896209716796875 length of segment : 291 time for calcul the mask position with numpy : 0.07762670516967773 nb_pixel_total : 58649 time to create 1 rle with old method : 0.07631778717041016 length of segment : 194 time for calcul the mask position with numpy : 0.03776955604553223 nb_pixel_total : 12404 time to create 1 rle with old method : 0.019207000732421875 length of segment : 124 time for calcul the mask position with numpy : 0.0589599609375 nb_pixel_total : 25692 time to create 1 rle with old method : 0.09681820869445801 length of segment : 232 time for calcul the mask position with numpy : 0.049775123596191406 nb_pixel_total : 16919 time to create 1 rle with old method : 0.03376603126525879 length of segment : 183 time for calcul the mask position with numpy : 0.10822057723999023 nb_pixel_total : 28915 time to create 1 rle with old method : 0.05654287338256836 length of segment : 376 time for calcul the mask position with numpy : 0.16554546356201172 nb_pixel_total : 87694 time to create 1 rle with old method : 0.16271185874938965 length of segment : 342 time for calcul the mask position with numpy : 0.17299699783325195 nb_pixel_total : 57934 time to create 1 rle with old method : 0.08682799339294434 length of segment : 314 time for calcul the mask position with numpy : 0.10112786293029785 nb_pixel_total : 62602 time to create 1 rle with old method : 0.08201336860656738 length of segment : 451 time for calcul the mask position with numpy : 0.06766343116760254 nb_pixel_total : 32003 time to create 1 rle with old method : 0.04277157783508301 length of segment : 183 time for calcul the mask position with numpy : 0.08442378044128418 nb_pixel_total : 16332 time to create 1 rle with old method : 0.024263620376586914 length of segment : 370 time for calcul the mask position with numpy : 0.07311749458312988 nb_pixel_total : 33119 time to create 1 rle with old method : 0.06316828727722168 length of segment : 176 time for calcul the mask position with numpy : 0.11259222030639648 nb_pixel_total : 54406 time to create 1 rle with old method : 0.07670211791992188 length of segment : 398 time for calcul the mask position with numpy : 0.04367709159851074 nb_pixel_total : 13027 time to create 1 rle with old method : 0.019835948944091797 length of segment : 223 time for calcul the mask position with numpy : 0.05963015556335449 nb_pixel_total : 18326 time to create 1 rle with old method : 0.02500629425048828 length of segment : 238 time for calcul the mask position with numpy : 0.06848001480102539 nb_pixel_total : 27162 time to create 1 rle with old method : 0.0355684757232666 length of segment : 202 time for calcul the mask position with numpy : 0.14376258850097656 nb_pixel_total : 92422 time to create 1 rle with old method : 0.10970067977905273 length of segment : 551 time for calcul the mask position with numpy : 0.08997797966003418 nb_pixel_total : 51154 time to create 1 rle with old method : 0.062062978744506836 length of segment : 193 time for calcul the mask position with numpy : 0.07852697372436523 nb_pixel_total : 42274 time to create 1 rle with old method : 0.05107545852661133 length of segment : 275 time for calcul the mask position with numpy : 0.0493013858795166 nb_pixel_total : 30690 time to create 1 rle with old method : 0.039055824279785156 length of segment : 390 time for calcul the mask position with numpy : 0.23911237716674805 nb_pixel_total : 198200 time to create 1 rle with new method : 0.014236688613891602 length of segment : 311 time for calcul the mask position with numpy : 0.008922576904296875 nb_pixel_total : 19298 time to create 1 rle with old method : 0.025881528854370117 length of segment : 174 time for calcul the mask position with numpy : 0.15304112434387207 nb_pixel_total : 54815 time to create 1 rle with old method : 0.09560751914978027 length of segment : 639 time for calcul the mask position with numpy : 0.07057595252990723 nb_pixel_total : 34892 time to create 1 rle with old method : 0.040973663330078125 length of segment : 458 time for calcul the mask position with numpy : 0.16354775428771973 nb_pixel_total : 35054 time to create 1 rle with old method : 0.0451207160949707 length of segment : 378 time for calcul the mask position with numpy : 0.11558890342712402 nb_pixel_total : 26921 time to create 1 rle with old method : 0.03531026840209961 length of segment : 216 time for calcul the mask position with numpy : 0.1623079776763916 nb_pixel_total : 63750 time to create 1 rle with old method : 0.07743525505065918 length of segment : 348 time for calcul the mask position with numpy : 0.16974163055419922 nb_pixel_total : 271648 time to create 1 rle with new method : 0.016225814819335938 length of segment : 556 time for calcul the mask position with numpy : 0.10199284553527832 nb_pixel_total : 43263 time to create 1 rle with old method : 0.05394101142883301 length of segment : 335 time for calcul the mask position with numpy : 0.01587533950805664 nb_pixel_total : 34653 time to create 1 rle with old method : 0.04297590255737305 length of segment : 284 time for calcul the mask position with numpy : 0.07605743408203125 nb_pixel_total : 25901 time to create 1 rle with old method : 0.03357267379760742 length of segment : 195 time for calcul the mask position with numpy : 0.1390838623046875 nb_pixel_total : 49142 time to create 1 rle with old method : 0.057926177978515625 length of segment : 505 time for calcul the mask position with numpy : 0.03520321846008301 nb_pixel_total : 36361 time to create 1 rle with old method : 0.04649782180786133 length of segment : 288 time for calcul the mask position with numpy : 0.053346872329711914 nb_pixel_total : 46325 time to create 1 rle with old method : 0.05878257751464844 length of segment : 407 time for calcul the mask position with numpy : 0.023397207260131836 nb_pixel_total : 21296 time to create 1 rle with old method : 0.03879070281982422 length of segment : 126 time for calcul the mask position with numpy : 0.11001133918762207 nb_pixel_total : 63669 time to create 1 rle with old method : 0.07643771171569824 length of segment : 899 time for calcul the mask position with numpy : 0.05467534065246582 nb_pixel_total : 16491 time to create 1 rle with old method : 0.02235865592956543 length of segment : 190 time for calcul the mask position with numpy : 0.13555026054382324 nb_pixel_total : 46316 time to create 1 rle with old method : 0.056633710861206055 length of segment : 358 time for calcul the mask position with numpy : 0.34985876083374023 nb_pixel_total : 240650 time to create 1 rle with new method : 0.11192035675048828 length of segment : 853 time for calcul the mask position with numpy : 0.14339184761047363 nb_pixel_total : 215378 time to create 1 rle with new method : 0.03432822227478027 length of segment : 704 time for calcul the mask position with numpy : 0.05927228927612305 nb_pixel_total : 19463 time to create 1 rle with old method : 0.025569438934326172 length of segment : 234 time for calcul the mask position with numpy : 0.17756271362304688 nb_pixel_total : 67406 time to create 1 rle with old method : 0.07904791831970215 length of segment : 660 time for calcul the mask position with numpy : 0.13434624671936035 nb_pixel_total : 211148 time to create 1 rle with new method : 0.01285099983215332 length of segment : 434 time for calcul the mask position with numpy : 0.09662365913391113 nb_pixel_total : 55488 time to create 1 rle with old method : 0.06598877906799316 length of segment : 384 time for calcul the mask position with numpy : 0.11972451210021973 nb_pixel_total : 116968 time to create 1 rle with old method : 0.13472509384155273 length of segment : 355 time for calcul the mask position with numpy : 0.09096288681030273 nb_pixel_total : 46076 time to create 1 rle with old method : 0.05171942710876465 length of segment : 276 time for calcul the mask position with numpy : 0.2493903636932373 nb_pixel_total : 118060 time to create 1 rle with old method : 0.13212275505065918 length of segment : 406 time for calcul the mask position with numpy : 0.294722318649292 nb_pixel_total : 106177 time to create 1 rle with old method : 0.12359762191772461 length of segment : 532 time for calcul the mask position with numpy : 0.1797189712524414 nb_pixel_total : 63219 time to create 1 rle with old method : 0.07226872444152832 length of segment : 383 time for calcul the mask position with numpy : 0.342318058013916 nb_pixel_total : 321586 time to create 1 rle with new method : 0.06332039833068848 length of segment : 653 time for calcul the mask position with numpy : 0.11780571937561035 nb_pixel_total : 68623 time to create 1 rle with old method : 0.09053373336791992 length of segment : 657 time for calcul the mask position with numpy : 0.016672849655151367 nb_pixel_total : 47829 time to create 1 rle with old method : 0.0610804557800293 length of segment : 427 time for calcul the mask position with numpy : 0.03722953796386719 nb_pixel_total : 61373 time to create 1 rle with old method : 0.10002565383911133 length of segment : 150 time for calcul the mask position with numpy : 0.06893515586853027 nb_pixel_total : 80610 time to create 1 rle with old method : 0.0993337631225586 length of segment : 340 time for calcul the mask position with numpy : 0.12825512886047363 nb_pixel_total : 31908 time to create 1 rle with old method : 0.03970909118652344 length of segment : 346 time for calcul the mask position with numpy : 0.17902779579162598 nb_pixel_total : 61374 time to create 1 rle with old method : 0.07476806640625 length of segment : 407 time for calcul the mask position with numpy : 0.020260095596313477 nb_pixel_total : 20518 time to create 1 rle with old method : 0.029717445373535156 length of segment : 166 time for calcul the mask position with numpy : 0.14466094970703125 nb_pixel_total : 62509 time to create 1 rle with old method : 0.07417130470275879 length of segment : 349 time for calcul the mask position with numpy : 0.13029217720031738 nb_pixel_total : 44083 time to create 1 rle with old method : 0.05427074432373047 length of segment : 447 time for calcul the mask position with numpy : 0.17757391929626465 nb_pixel_total : 161114 time to create 1 rle with new method : 0.013144731521606445 length of segment : 472 time for calcul the mask position with numpy : 0.01105189323425293 nb_pixel_total : 17418 time to create 1 rle with old method : 0.022611141204833984 length of segment : 225 time for calcul the mask position with numpy : 0.11356401443481445 nb_pixel_total : 38532 time to create 1 rle with old method : 0.04812121391296387 length of segment : 652 time for calcul the mask position with numpy : 0.034279584884643555 nb_pixel_total : 69821 time to create 1 rle with old method : 0.08047676086425781 length of segment : 820 time for calcul the mask position with numpy : 0.02221536636352539 nb_pixel_total : 10018 time to create 1 rle with old method : 0.016382217407226562 length of segment : 135 time for calcul the mask position with numpy : 0.15011930465698242 nb_pixel_total : 99498 time to create 1 rle with old method : 0.11462569236755371 length of segment : 334 time for calcul the mask position with numpy : 0.15519380569458008 nb_pixel_total : 112852 time to create 1 rle with old method : 0.12972712516784668 length of segment : 293 time for calcul the mask position with numpy : 0.07102155685424805 nb_pixel_total : 21853 time to create 1 rle with old method : 0.030619144439697266 length of segment : 259 time for calcul the mask position with numpy : 0.04878807067871094 nb_pixel_total : 14992 time to create 1 rle with old method : 0.020484209060668945 length of segment : 181 time for calcul the mask position with numpy : 0.03876519203186035 nb_pixel_total : 18828 time to create 1 rle with old method : 0.026367902755737305 length of segment : 127 time for calcul the mask position with numpy : 0.15154528617858887 nb_pixel_total : 107957 time to create 1 rle with old method : 0.13689494132995605 length of segment : 415 time for calcul the mask position with numpy : 0.05045485496520996 nb_pixel_total : 26915 time to create 1 rle with old method : 0.03475236892700195 length of segment : 186 time for calcul the mask position with numpy : 0.032141923904418945 nb_pixel_total : 16611 time to create 1 rle with old method : 0.02377152442932129 length of segment : 128 time for calcul the mask position with numpy : 0.12610840797424316 nb_pixel_total : 91702 time to create 1 rle with old method : 0.10762691497802734 length of segment : 386 time for calcul the mask position with numpy : 0.08379173278808594 nb_pixel_total : 26871 time to create 1 rle with old method : 0.03780078887939453 length of segment : 517 time for calcul the mask position with numpy : 0.04848790168762207 nb_pixel_total : 28823 time to create 1 rle with old method : 0.03800177574157715 length of segment : 161 time for calcul the mask position with numpy : 0.022000551223754883 nb_pixel_total : 6142 time to create 1 rle with old method : 0.0072023868560791016 length of segment : 114 time for calcul the mask position with numpy : 0.19304704666137695 nb_pixel_total : 138416 time to create 1 rle with old method : 0.15918254852294922 length of segment : 697 time for calcul the mask position with numpy : 0.09025049209594727 nb_pixel_total : 54078 time to create 1 rle with old method : 0.06490254402160645 length of segment : 250 time for calcul the mask position with numpy : 0.06974363327026367 nb_pixel_total : 32787 time to create 1 rle with old method : 0.037767887115478516 length of segment : 344 time for calcul the mask position with numpy : 0.04498744010925293 nb_pixel_total : 48189 time to create 1 rle with old method : 0.06179237365722656 length of segment : 153 time for calcul the mask position with numpy : 0.07486414909362793 nb_pixel_total : 29505 time to create 1 rle with old method : 0.04216432571411133 length of segment : 410 time for calcul the mask position with numpy : 0.01353764533996582 nb_pixel_total : 16573 time to create 1 rle with old method : 0.02599167823791504 length of segment : 113 time for calcul the mask position with numpy : 0.014178752899169922 nb_pixel_total : 44758 time to create 1 rle with old method : 0.056728363037109375 length of segment : 438 time for calcul the mask position with numpy : 0.05673837661743164 nb_pixel_total : 131111 time to create 1 rle with old method : 0.1483004093170166 length of segment : 442 time for calcul the mask position with numpy : 0.0377805233001709 nb_pixel_total : 53019 time to create 1 rle with old method : 0.06354546546936035 length of segment : 376 time for calcul the mask position with numpy : 0.010133504867553711 nb_pixel_total : 58128 time to create 1 rle with old method : 0.06778216361999512 length of segment : 253 time for calcul the mask position with numpy : 0.07149410247802734 nb_pixel_total : 20089 time to create 1 rle with old method : 0.027133464813232422 length of segment : 336 time for calcul the mask position with numpy : 0.01911640167236328 nb_pixel_total : 83619 time to create 1 rle with old method : 0.09100461006164551 length of segment : 432 time for calcul the mask position with numpy : 0.02814316749572754 nb_pixel_total : 69725 time to create 1 rle with old method : 0.08471274375915527 length of segment : 515 time for calcul the mask position with numpy : 0.06565046310424805 nb_pixel_total : 47719 time to create 1 rle with old method : 0.061089515686035156 length of segment : 372 time for calcul the mask position with numpy : 0.03990364074707031 nb_pixel_total : 36403 time to create 1 rle with old method : 0.04457831382751465 length of segment : 277 time for calcul the mask position with numpy : 0.00213623046875 nb_pixel_total : 22090 time to create 1 rle with old method : 0.0257418155670166 length of segment : 144 time for calcul the mask position with numpy : 0.046042442321777344 nb_pixel_total : 29182 time to create 1 rle with old method : 0.03680610656738281 length of segment : 234 time for calcul the mask position with numpy : 0.0008513927459716797 nb_pixel_total : 18144 time to create 1 rle with old method : 0.022121429443359375 length of segment : 102 time for calcul the mask position with numpy : 0.00625300407409668 nb_pixel_total : 11138 time to create 1 rle with old method : 0.015698671340942383 length of segment : 87 time for calcul the mask position with numpy : 0.016150474548339844 nb_pixel_total : 12823 time to create 1 rle with old method : 0.02532052993774414 length of segment : 202 time for calcul the mask position with numpy : 0.0011920928955078125 nb_pixel_total : 11264 time to create 1 rle with old method : 0.01469111442565918 length of segment : 149 time for calcul the mask position with numpy : 0.015497446060180664 nb_pixel_total : 57505 time to create 1 rle with old method : 0.07990646362304688 length of segment : 271 time for calcul the mask position with numpy : 0.014964103698730469 nb_pixel_total : 58142 time to create 1 rle with old method : 0.06943058967590332 length of segment : 366 time for calcul the mask position with numpy : 0.05775308609008789 nb_pixel_total : 11714 time to create 1 rle with old method : 0.01907181739807129 length of segment : 333 time for calcul the mask position with numpy : 0.0004932880401611328 nb_pixel_total : 5838 time to create 1 rle with old method : 0.006754875183105469 length of segment : 191 time for calcul the mask position with numpy : 0.06755590438842773 nb_pixel_total : 54845 time to create 1 rle with old method : 0.06703734397888184 length of segment : 303 time for calcul the mask position with numpy : 0.07360577583312988 nb_pixel_total : 122160 time to create 1 rle with old method : 0.14996862411499023 length of segment : 646 time for calcul the mask position with numpy : 0.014470100402832031 nb_pixel_total : 32460 time to create 1 rle with old method : 0.037252187728881836 length of segment : 287 time for calcul the mask position with numpy : 0.010539054870605469 nb_pixel_total : 10062 time to create 1 rle with old method : 0.01172780990600586 length of segment : 321 time for calcul the mask position with numpy : 0.08473753929138184 nb_pixel_total : 54660 time to create 1 rle with old method : 0.06470656394958496 length of segment : 337 time for calcul the mask position with numpy : 0.058356285095214844 nb_pixel_total : 23114 time to create 1 rle with old method : 0.0302736759185791 length of segment : 322 time for calcul the mask position with numpy : 0.023421049118041992 nb_pixel_total : 71601 time to create 1 rle with old method : 0.08189010620117188 length of segment : 546 time for calcul the mask position with numpy : 0.016968727111816406 nb_pixel_total : 41851 time to create 1 rle with old method : 0.06853342056274414 length of segment : 612 time for calcul the mask position with numpy : 0.02030324935913086 nb_pixel_total : 76930 time to create 1 rle with old method : 0.08739614486694336 length of segment : 295 time for calcul the mask position with numpy : 0.014651775360107422 nb_pixel_total : 71167 time to create 1 rle with old method : 0.08456206321716309 length of segment : 238 time for calcul the mask position with numpy : 0.01306295394897461 nb_pixel_total : 31787 time to create 1 rle with old method : 0.04064369201660156 length of segment : 174 time for calcul the mask position with numpy : 0.0011029243469238281 nb_pixel_total : 10795 time to create 1 rle with old method : 0.012503385543823242 length of segment : 82 time for calcul the mask position with numpy : 0.04575753211975098 nb_pixel_total : 84767 time to create 1 rle with old method : 0.09656214714050293 length of segment : 345 time for calcul the mask position with numpy : 0.0016388893127441406 nb_pixel_total : 12425 time to create 1 rle with old method : 0.014255285263061523 length of segment : 204 time for calcul the mask position with numpy : 0.1559288501739502 nb_pixel_total : 197055 time to create 1 rle with new method : 0.045209407806396484 length of segment : 922 time for calcul the mask position with numpy : 0.024611234664916992 nb_pixel_total : 20506 time to create 1 rle with old method : 0.026047706604003906 length of segment : 210 time for calcul the mask position with numpy : 0.02220916748046875 nb_pixel_total : 39324 time to create 1 rle with old method : 0.04865837097167969 length of segment : 347 time for calcul the mask position with numpy : 0.018124103546142578 nb_pixel_total : 96395 time to create 1 rle with old method : 0.11103272438049316 length of segment : 374 time for calcul the mask position with numpy : 0.001262664794921875 nb_pixel_total : 21615 time to create 1 rle with old method : 0.03197526931762695 length of segment : 224 time for calcul the mask position with numpy : 0.005678653717041016 nb_pixel_total : 16414 time to create 1 rle with old method : 0.023550748825073242 length of segment : 202 time for calcul the mask position with numpy : 0.0035674571990966797 nb_pixel_total : 40012 time to create 1 rle with old method : 0.047402381896972656 length of segment : 211 time for calcul the mask position with numpy : 0.03630948066711426 nb_pixel_total : 28684 time to create 1 rle with old method : 0.03715777397155762 length of segment : 285 time for calcul the mask position with numpy : 0.005018949508666992 nb_pixel_total : 95551 time to create 1 rle with old method : 0.11233353614807129 length of segment : 414 time for calcul the mask position with numpy : 0.0011723041534423828 nb_pixel_total : 19704 time to create 1 rle with old method : 0.02289104461669922 length of segment : 176 time for calcul the mask position with numpy : 0.0045659542083740234 nb_pixel_total : 67826 time to create 1 rle with old method : 0.07545614242553711 length of segment : 383 time for calcul the mask position with numpy : 0.0036618709564208984 nb_pixel_total : 39473 time to create 1 rle with old method : 0.047124385833740234 length of segment : 341 time for calcul the mask position with numpy : 0.016390562057495117 nb_pixel_total : 314062 time to create 1 rle with new method : 0.13853049278259277 length of segment : 859 time for calcul the mask position with numpy : 0.006394386291503906 nb_pixel_total : 77740 time to create 1 rle with old method : 0.09200477600097656 length of segment : 461 time for calcul the mask position with numpy : 0.0022630691528320312 nb_pixel_total : 39522 time to create 1 rle with old method : 0.048250436782836914 length of segment : 185 time for calcul the mask position with numpy : 0.0016498565673828125 nb_pixel_total : 34731 time to create 1 rle with old method : 0.04032111167907715 length of segment : 187 time for calcul the mask position with numpy : 0.0011031627655029297 nb_pixel_total : 16662 time to create 1 rle with old method : 0.01903533935546875 length of segment : 140 time for calcul the mask position with numpy : 0.0019500255584716797 nb_pixel_total : 45470 time to create 1 rle with old method : 0.05336356163024902 length of segment : 261 time for calcul the mask position with numpy : 0.0009686946868896484 nb_pixel_total : 18042 time to create 1 rle with old method : 0.021184206008911133 length of segment : 148 time for calcul the mask position with numpy : 0.004208087921142578 nb_pixel_total : 68202 time to create 1 rle with old method : 0.07839107513427734 length of segment : 318 time for calcul the mask position with numpy : 0.0008525848388671875 nb_pixel_total : 15685 time to create 1 rle with old method : 0.01888728141784668 length of segment : 209 time for calcul the mask position with numpy : 0.001287221908569336 nb_pixel_total : 24768 time to create 1 rle with old method : 0.029608488082885742 length of segment : 178 time for calcul the mask position with numpy : 0.0035359859466552734 nb_pixel_total : 48335 time to create 1 rle with old method : 0.05434775352478027 length of segment : 293 time for calcul the mask position with numpy : 0.003397703170776367 nb_pixel_total : 68939 time to create 1 rle with old method : 0.07747936248779297 length of segment : 394 time for calcul the mask position with numpy : 0.011672496795654297 nb_pixel_total : 297610 time to create 1 rle with new method : 0.019858837127685547 length of segment : 899 time for calcul the mask position with numpy : 0.004240751266479492 nb_pixel_total : 78748 time to create 1 rle with old method : 0.08832907676696777 length of segment : 497 time for calcul the mask position with numpy : 0.03522658348083496 nb_pixel_total : 178820 time to create 1 rle with new method : 0.01766061782836914 length of segment : 799 time for calcul the mask position with numpy : 0.0024862289428710938 nb_pixel_total : 64811 time to create 1 rle with old method : 0.07440853118896484 length of segment : 342 time for calcul the mask position with numpy : 0.0027794837951660156 nb_pixel_total : 64666 time to create 1 rle with old method : 0.07488131523132324 length of segment : 248 time for calcul the mask position with numpy : 0.007325410842895508 nb_pixel_total : 125600 time to create 1 rle with old method : 0.14313411712646484 length of segment : 597 time for calcul the mask position with numpy : 0.006547451019287109 nb_pixel_total : 118763 time to create 1 rle with old method : 0.13458991050720215 length of segment : 376 time for calcul the mask position with numpy : 0.0002465248107910156 nb_pixel_total : 6356 time to create 1 rle with old method : 0.008233785629272461 length of segment : 88 time for calcul the mask position with numpy : 0.0007081031799316406 nb_pixel_total : 12007 time to create 1 rle with old method : 0.01425480842590332 length of segment : 201 time for calcul the mask position with numpy : 0.003733396530151367 nb_pixel_total : 74389 time to create 1 rle with old method : 0.08837366104125977 length of segment : 587 time for calcul the mask position with numpy : 0.0026216506958007812 nb_pixel_total : 76351 time to create 1 rle with old method : 0.08692121505737305 length of segment : 318 time for calcul the mask position with numpy : 0.008203506469726562 nb_pixel_total : 55597 time to create 1 rle with old method : 0.06751227378845215 length of segment : 322 time for calcul the mask position with numpy : 0.00638890266418457 nb_pixel_total : 93877 time to create 1 rle with old method : 0.10627388954162598 length of segment : 328 time for calcul the mask position with numpy : 0.0024385452270507812 nb_pixel_total : 28676 time to create 1 rle with old method : 0.03802895545959473 length of segment : 143 time for calcul the mask position with numpy : 0.005182981491088867 nb_pixel_total : 82879 time to create 1 rle with old method : 0.10186386108398438 length of segment : 523 time for calcul the mask position with numpy : 0.0051727294921875 nb_pixel_total : 27525 time to create 1 rle with old method : 0.033727169036865234 length of segment : 237 time for calcul the mask position with numpy : 0.0008757114410400391 nb_pixel_total : 10035 time to create 1 rle with old method : 0.011728525161743164 length of segment : 145 time for calcul the mask position with numpy : 0.0014605522155761719 nb_pixel_total : 14163 time to create 1 rle with old method : 0.016511917114257812 length of segment : 168 time for calcul the mask position with numpy : 0.0021224021911621094 nb_pixel_total : 31495 time to create 1 rle with old method : 0.0364382266998291 length of segment : 254 time for calcul the mask position with numpy : 0.0006616115570068359 nb_pixel_total : 10508 time to create 1 rle with old method : 0.012538433074951172 length of segment : 126 time for calcul the mask position with numpy : 0.001050710678100586 nb_pixel_total : 22918 time to create 1 rle with old method : 0.026221752166748047 length of segment : 219 time for calcul the mask position with numpy : 0.002008676528930664 nb_pixel_total : 21696 time to create 1 rle with old method : 0.02487778663635254 length of segment : 206 time for calcul the mask position with numpy : 0.0029087066650390625 nb_pixel_total : 53416 time to create 1 rle with old method : 0.06017255783081055 length of segment : 278 time for calcul the mask position with numpy : 0.003255605697631836 nb_pixel_total : 82640 time to create 1 rle with old method : 0.09234905242919922 length of segment : 296 time for calcul the mask position with numpy : 0.005570650100708008 nb_pixel_total : 146484 time to create 1 rle with old method : 0.16142487525939941 length of segment : 560 time for calcul the mask position with numpy : 0.006450176239013672 nb_pixel_total : 196699 time to create 1 rle with new method : 0.010022163391113281 length of segment : 415 time for calcul the mask position with numpy : 0.004537105560302734 nb_pixel_total : 127569 time to create 1 rle with old method : 0.14123177528381348 length of segment : 518 time for calcul the mask position with numpy : 0.0026192665100097656 nb_pixel_total : 34913 time to create 1 rle with old method : 0.03982067108154297 length of segment : 189 time for calcul the mask position with numpy : 0.002041339874267578 nb_pixel_total : 72705 time to create 1 rle with old method : 0.08209753036499023 length of segment : 403 time for calcul the mask position with numpy : 0.006616115570068359 nb_pixel_total : 60403 time to create 1 rle with old method : 0.0714261531829834 length of segment : 309 time for calcul the mask position with numpy : 0.00668644905090332 nb_pixel_total : 96086 time to create 1 rle with old method : 0.10911011695861816 length of segment : 277 time for calcul the mask position with numpy : 0.0014066696166992188 nb_pixel_total : 26914 time to create 1 rle with old method : 0.03131389617919922 length of segment : 148 time for calcul the mask position with numpy : 0.0025353431701660156 nb_pixel_total : 27962 time to create 1 rle with old method : 0.03217935562133789 length of segment : 244 time for calcul the mask position with numpy : 0.0017886161804199219 nb_pixel_total : 26290 time to create 1 rle with old method : 0.030473947525024414 length of segment : 317 time for calcul the mask position with numpy : 0.004653453826904297 nb_pixel_total : 110756 time to create 1 rle with old method : 0.12438392639160156 length of segment : 603 time for calcul the mask position with numpy : 0.011838436126708984 nb_pixel_total : 202512 time to create 1 rle with new method : 0.03960919380187988 length of segment : 506 time for calcul the mask position with numpy : 0.0024878978729248047 nb_pixel_total : 81539 time to create 1 rle with old method : 0.09495663642883301 length of segment : 444 time for calcul the mask position with numpy : 0.0010673999786376953 nb_pixel_total : 23342 time to create 1 rle with old method : 0.02742147445678711 length of segment : 353 time for calcul the mask position with numpy : 0.0015864372253417969 nb_pixel_total : 29303 time to create 1 rle with old method : 0.033987998962402344 length of segment : 295 time for calcul the mask position with numpy : 0.01054692268371582 nb_pixel_total : 282103 time to create 1 rle with new method : 0.030340909957885742 length of segment : 777 time for calcul the mask position with numpy : 0.005548715591430664 nb_pixel_total : 174865 time to create 1 rle with new method : 0.007002353668212891 length of segment : 402 time for calcul the mask position with numpy : 0.004346370697021484 nb_pixel_total : 152189 time to create 1 rle with new method : 0.005331516265869141 length of segment : 337 time for calcul the mask position with numpy : 0.004659891128540039 nb_pixel_total : 132789 time to create 1 rle with old method : 0.15070009231567383 length of segment : 765 time for calcul the mask position with numpy : 0.0016672611236572266 nb_pixel_total : 44515 time to create 1 rle with old method : 0.05052614212036133 length of segment : 279 time for calcul the mask position with numpy : 0.00060272216796875 nb_pixel_total : 9332 time to create 1 rle with old method : 0.010358810424804688 length of segment : 129 time for calcul the mask position with numpy : 0.0026383399963378906 nb_pixel_total : 76331 time to create 1 rle with old method : 0.08630180358886719 length of segment : 285 time for calcul the mask position with numpy : 0.0023148059844970703 nb_pixel_total : 48955 time to create 1 rle with old method : 0.062142372131347656 length of segment : 495 time for calcul the mask position with numpy : 0.0009720325469970703 nb_pixel_total : 56530 time to create 1 rle with old method : 0.06235241889953613 length of segment : 178 time for calcul the mask position with numpy : 0.0029103755950927734 nb_pixel_total : 80381 time to create 1 rle with old method : 0.08739089965820312 length of segment : 346 time for calcul the mask position with numpy : 0.011190652847290039 nb_pixel_total : 6325 time to create 1 rle with old method : 0.009112358093261719 length of segment : 91 time for calcul the mask position with numpy : 0.0026655197143554688 nb_pixel_total : 72716 time to create 1 rle with old method : 0.0828557014465332 length of segment : 314 time for calcul the mask position with numpy : 0.0014338493347167969 nb_pixel_total : 37563 time to create 1 rle with old method : 0.04298543930053711 length of segment : 234 time for calcul the mask position with numpy : 0.002305746078491211 nb_pixel_total : 45502 time to create 1 rle with old method : 0.05217576026916504 length of segment : 370 time for calcul the mask position with numpy : 0.0005190372467041016 nb_pixel_total : 14212 time to create 1 rle with old method : 0.01649761199951172 length of segment : 119 time for calcul the mask position with numpy : 0.0032308101654052734 nb_pixel_total : 73213 time to create 1 rle with old method : 0.09386014938354492 length of segment : 323 time for calcul the mask position with numpy : 0.0017998218536376953 nb_pixel_total : 31069 time to create 1 rle with old method : 0.03650975227355957 length of segment : 246 time for calcul the mask position with numpy : 0.0008916854858398438 nb_pixel_total : 15537 time to create 1 rle with old method : 0.017985105514526367 length of segment : 251 time for calcul the mask position with numpy : 0.0011320114135742188 nb_pixel_total : 21378 time to create 1 rle with old method : 0.02467179298400879 length of segment : 217 time for calcul the mask position with numpy : 0.004403114318847656 nb_pixel_total : 74864 time to create 1 rle with old method : 0.08491945266723633 length of segment : 460 time for calcul the mask position with numpy : 0.0050470829010009766 nb_pixel_total : 108394 time to create 1 rle with old method : 0.12127089500427246 length of segment : 621 time for calcul the mask position with numpy : 0.007475614547729492 nb_pixel_total : 197694 time to create 1 rle with new method : 0.0113677978515625 length of segment : 557 time for calcul the mask position with numpy : 0.0006861686706542969 nb_pixel_total : 17589 time to create 1 rle with old method : 0.020788908004760742 length of segment : 186 time for calcul the mask position with numpy : 0.0034363269805908203 nb_pixel_total : 93951 time to create 1 rle with old method : 0.10593867301940918 length of segment : 462 time for calcul the mask position with numpy : 0.0014121532440185547 nb_pixel_total : 30148 time to create 1 rle with old method : 0.03527951240539551 length of segment : 204 time for calcul the mask position with numpy : 0.001316070556640625 nb_pixel_total : 42734 time to create 1 rle with old method : 0.05340147018432617 length of segment : 432 time for calcul the mask position with numpy : 0.004572153091430664 nb_pixel_total : 58959 time to create 1 rle with old method : 0.0663444995880127 length of segment : 391 time for calcul the mask position with numpy : 0.001493215560913086 nb_pixel_total : 31771 time to create 1 rle with old method : 0.037283897399902344 length of segment : 178 time for calcul the mask position with numpy : 0.0071146488189697266 nb_pixel_total : 216219 time to create 1 rle with new method : 0.014628171920776367 length of segment : 553 time for calcul the mask position with numpy : 0.016012907028198242 nb_pixel_total : 442043 time to create 1 rle with new method : 0.0355229377746582 length of segment : 1072 time for calcul the mask position with numpy : 0.0016422271728515625 nb_pixel_total : 26093 time to create 1 rle with old method : 0.030142784118652344 length of segment : 312 time for calcul the mask position with numpy : 0.001922607421875 nb_pixel_total : 36435 time to create 1 rle with old method : 0.04185819625854492 length of segment : 453 time for calcul the mask position with numpy : 0.0004241466522216797 nb_pixel_total : 9572 time to create 1 rle with old method : 0.011008739471435547 length of segment : 185 time for calcul the mask position with numpy : 0.0008504390716552734 nb_pixel_total : 19706 time to create 1 rle with old method : 0.02262735366821289 length of segment : 179 time for calcul the mask position with numpy : 0.01651787757873535 nb_pixel_total : 346197 time to create 1 rle with new method : 0.04493403434753418 length of segment : 1271 time for calcul the mask position with numpy : 0.0005803108215332031 nb_pixel_total : 17071 time to create 1 rle with old method : 0.021093368530273438 length of segment : 182 time for calcul the mask position with numpy : 0.0020804405212402344 nb_pixel_total : 66695 time to create 1 rle with old method : 0.07429695129394531 length of segment : 717 time for calcul the mask position with numpy : 0.014864444732666016 nb_pixel_total : 306102 time to create 1 rle with new method : 0.06175947189331055 length of segment : 825 time for calcul the mask position with numpy : 0.0003638267517089844 nb_pixel_total : 9117 time to create 1 rle with old method : 0.010695934295654297 length of segment : 304 time for calcul the mask position with numpy : 0.00036406517028808594 nb_pixel_total : 15567 time to create 1 rle with old method : 0.01816105842590332 length of segment : 217 time for calcul the mask position with numpy : 0.00022220611572265625 nb_pixel_total : 8744 time to create 1 rle with old method : 0.010146379470825195 length of segment : 104 time for calcul the mask position with numpy : 0.0033740997314453125 nb_pixel_total : 37307 time to create 1 rle with old method : 0.0423738956451416 length of segment : 258 time for calcul the mask position with numpy : 0.0015883445739746094 nb_pixel_total : 35805 time to create 1 rle with old method : 0.044338226318359375 length of segment : 239 time for calcul the mask position with numpy : 0.0014286041259765625 nb_pixel_total : 25158 time to create 1 rle with old method : 0.03394341468811035 length of segment : 177 time for calcul the mask position with numpy : 0.0017497539520263672 nb_pixel_total : 41995 time to create 1 rle with old method : 0.048483848571777344 length of segment : 248 time for calcul the mask position with numpy : 0.002808094024658203 nb_pixel_total : 62090 time to create 1 rle with old method : 0.0721578598022461 length of segment : 345 time for calcul the mask position with numpy : 0.0008366107940673828 nb_pixel_total : 13626 time to create 1 rle with old method : 0.015708208084106445 length of segment : 186 time for calcul the mask position with numpy : 0.000812530517578125 nb_pixel_total : 21856 time to create 1 rle with old method : 0.02600693702697754 length of segment : 178 time for calcul the mask position with numpy : 0.0020554065704345703 nb_pixel_total : 43258 time to create 1 rle with old method : 0.05040740966796875 length of segment : 291 time for calcul the mask position with numpy : 0.0010523796081542969 nb_pixel_total : 22143 time to create 1 rle with old method : 0.026102542877197266 length of segment : 163 time for calcul the mask position with numpy : 0.006342649459838867 nb_pixel_total : 90978 time to create 1 rle with old method : 0.10277462005615234 length of segment : 354 time for calcul the mask position with numpy : 0.002938985824584961 nb_pixel_total : 57249 time to create 1 rle with old method : 0.06599807739257812 length of segment : 295 time for calcul the mask position with numpy : 0.0009446144104003906 nb_pixel_total : 21636 time to create 1 rle with old method : 0.025633573532104492 length of segment : 191 time for calcul the mask position with numpy : 0.0012047290802001953 nb_pixel_total : 21513 time to create 1 rle with old method : 0.024415016174316406 length of segment : 311 time for calcul the mask position with numpy : 0.0009312629699707031 nb_pixel_total : 33024 time to create 1 rle with old method : 0.03840303421020508 length of segment : 138 time for calcul the mask position with numpy : 0.0008568763732910156 nb_pixel_total : 6611 time to create 1 rle with old method : 0.008646488189697266 length of segment : 231 time for calcul the mask position with numpy : 0.003493070602416992 nb_pixel_total : 95868 time to create 1 rle with old method : 0.11029195785522461 length of segment : 337 time for calcul the mask position with numpy : 0.002172708511352539 nb_pixel_total : 58333 time to create 1 rle with old method : 0.06751155853271484 length of segment : 370 time for calcul the mask position with numpy : 0.0036296844482421875 nb_pixel_total : 88454 time to create 1 rle with old method : 0.10123562812805176 length of segment : 385 time for calcul the mask position with numpy : 0.0007605552673339844 nb_pixel_total : 18369 time to create 1 rle with old method : 0.02158975601196289 length of segment : 136 time for calcul the mask position with numpy : 0.0008344650268554688 nb_pixel_total : 14144 time to create 1 rle with old method : 0.016361236572265625 length of segment : 229 time for calcul the mask position with numpy : 0.006939411163330078 nb_pixel_total : 69403 time to create 1 rle with old method : 0.08270597457885742 length of segment : 663 time for calcul the mask position with numpy : 0.0007646083831787109 nb_pixel_total : 18196 time to create 1 rle with old method : 0.020978927612304688 length of segment : 152 time for calcul the mask position with numpy : 0.0009303092956542969 nb_pixel_total : 8826 time to create 1 rle with old method : 0.0103302001953125 length of segment : 293 time for calcul the mask position with numpy : 0.0015630722045898438 nb_pixel_total : 29112 time to create 1 rle with old method : 0.03379225730895996 length of segment : 334 time for calcul the mask position with numpy : 0.009277105331420898 nb_pixel_total : 225642 time to create 1 rle with new method : 0.015807628631591797 length of segment : 721 time for calcul the mask position with numpy : 0.001123189926147461 nb_pixel_total : 17106 time to create 1 rle with old method : 0.02010941505432129 length of segment : 238 time for calcul the mask position with numpy : 0.0010066032409667969 nb_pixel_total : 21627 time to create 1 rle with old method : 0.025153160095214844 length of segment : 160 time for calcul the mask position with numpy : 0.0046770572662353516 nb_pixel_total : 65327 time to create 1 rle with old method : 0.07569193840026855 length of segment : 427 time for calcul the mask position with numpy : 0.005966663360595703 nb_pixel_total : 91531 time to create 1 rle with old method : 0.11797165870666504 length of segment : 311 time for calcul the mask position with numpy : 0.002084970474243164 nb_pixel_total : 29557 time to create 1 rle with old method : 0.050310373306274414 length of segment : 185 time for calcul the mask position with numpy : 0.009220123291015625 nb_pixel_total : 125901 time to create 1 rle with old method : 0.19701910018920898 length of segment : 561 time for calcul the mask position with numpy : 0.0019822120666503906 nb_pixel_total : 22048 time to create 1 rle with old method : 0.027187824249267578 length of segment : 179 time for calcul the mask position with numpy : 0.006754875183105469 nb_pixel_total : 98836 time to create 1 rle with old method : 0.1276836395263672 length of segment : 408 time for calcul the mask position with numpy : 0.0019159317016601562 nb_pixel_total : 38015 time to create 1 rle with old method : 0.047693729400634766 length of segment : 190 time for calcul the mask position with numpy : 0.002729654312133789 nb_pixel_total : 55261 time to create 1 rle with old method : 0.10009551048278809 length of segment : 377 time for calcul the mask position with numpy : 0.0016472339630126953 nb_pixel_total : 26697 time to create 1 rle with old method : 0.030950546264648438 length of segment : 192 time for calcul the mask position with numpy : 0.0006554126739501953 nb_pixel_total : 19535 time to create 1 rle with old method : 0.022970199584960938 length of segment : 138 time for calcul the mask position with numpy : 0.006715059280395508 nb_pixel_total : 112823 time to create 1 rle with old method : 0.15409088134765625 length of segment : 475 time for calcul the mask position with numpy : 0.004525423049926758 nb_pixel_total : 79192 time to create 1 rle with old method : 0.0916905403137207 length of segment : 811 time for calcul the mask position with numpy : 0.006685495376586914 nb_pixel_total : 105546 time to create 1 rle with old method : 0.12331271171569824 length of segment : 469 time for calcul the mask position with numpy : 0.0020606517791748047 nb_pixel_total : 53836 time to create 1 rle with old method : 0.06115984916687012 length of segment : 218 time for calcul the mask position with numpy : 0.0014407634735107422 nb_pixel_total : 35496 time to create 1 rle with old method : 0.04046511650085449 length of segment : 188 time for calcul the mask position with numpy : 0.0024275779724121094 nb_pixel_total : 9850 time to create 1 rle with old method : 0.012096405029296875 length of segment : 277 time for calcul the mask position with numpy : 0.0005633831024169922 nb_pixel_total : 6786 time to create 1 rle with old method : 0.008272409439086914 length of segment : 262 time for calcul the mask position with numpy : 0.0009429454803466797 nb_pixel_total : 18271 time to create 1 rle with old method : 0.021225690841674805 length of segment : 188 time for calcul the mask position with numpy : 0.0008051395416259766 nb_pixel_total : 10945 time to create 1 rle with old method : 0.013277053833007812 length of segment : 245 time for calcul the mask position with numpy : 0.004261970520019531 nb_pixel_total : 39262 time to create 1 rle with old method : 0.044766902923583984 length of segment : 236 time for calcul the mask position with numpy : 0.0006108283996582031 nb_pixel_total : 13129 time to create 1 rle with old method : 0.015479087829589844 length of segment : 134 time for calcul the mask position with numpy : 0.003113985061645508 nb_pixel_total : 76587 time to create 1 rle with old method : 0.0864715576171875 length of segment : 252 time for calcul the mask position with numpy : 0.0036339759826660156 nb_pixel_total : 73662 time to create 1 rle with old method : 0.0860280990600586 length of segment : 472 time for calcul the mask position with numpy : 0.0002295970916748047 nb_pixel_total : 5662 time to create 1 rle with old method : 0.00667262077331543 length of segment : 94 time for calcul the mask position with numpy : 0.005973100662231445 nb_pixel_total : 100264 time to create 1 rle with old method : 0.1131591796875 length of segment : 414 time for calcul the mask position with numpy : 0.0020575523376464844 nb_pixel_total : 52465 time to create 1 rle with old method : 0.05940675735473633 length of segment : 602 time for calcul the mask position with numpy : 0.0028104782104492188 nb_pixel_total : 37520 time to create 1 rle with old method : 0.04137253761291504 length of segment : 355 time spent for convertir_results : 78.2082748413086 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 390 chid ids of type : 3594 Number RLEs to save : 129577 save missing photos in datou_result : time spend for datou_step_exec : 334.40607261657715 time spend to save output : 37.5241584777832 total time spend for step 1 : 371.93023109436035 step2:crop_condition Fri Jul 4 09:06:43 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 : 18 ! batch 1 Loaded 390 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 ! map_result returned by crop_photo_return_map_crop : length : 331 About to insert : list_path_to_insert length 331 new photo from crops ! About to upload 331 photos upload in portfolio : 3736932 init cache_photo without model_param we have 331 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1751612902_708613 we have uploaded 331 photos in the portfolio 3736932 time of upload the photos Elapsed time : 79.19908881187439 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 ! map_result returned by crop_photo_return_map_crop : length : 37 About to insert : list_path_to_insert length 37 new photo from crops ! About to upload 37 photos upload in portfolio : 3736932 init cache_photo without model_param we have 37 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1751612994_708613 we have uploaded 37 photos in the portfolio 3736932 time of upload the photos Elapsed time : 10.280113697052002 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 ! 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/1751613007_708613 we have uploaded 2 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.584399700164795 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 ! map_result returned by crop_photo_return_map_crop : length : 12 About to insert : list_path_to_insert length 12 new photo from crops ! About to upload 12 photos upload in portfolio : 3736932 init cache_photo without model_param we have 12 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1751613016_708613 we have uploaded 12 photos in the portfolio 3736932 time of upload the photos Elapsed time : 3.7021896839141846 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.7} filtre for class : autre hashtag_id of this class : 494826614 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 3736932 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1751613024_708613 we have uploaded 4 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.8157744407653809 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 begin to crop the class : pet_fonce param for this class : {'min_score': 0.7} filtre for class : pet_fonce hashtag_id of this class : 2107755900 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 3736932 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1751613031_708613 we have uploaded 4 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.1126372814178467 we have finished the crop for the class : pet_fonce delete rles from all chi we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1370462805, 1370462802, 1370462799, 1370462797, 1370462703, 1370462702, 1370462701, 1370462700, 1370462699, 1370462698, 1370462676, 1370462675, 1370462673, 1370462672, 1370462671, 1370462583, 1370462582, 1370462581] Looping around the photos to save general results len do output : 390 /1370510582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370510948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511223Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1370511225Didn'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, '3234682') ('3318', '24581312', '1370462805', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462802', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462799', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462797', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462703', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462702', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462701', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462700', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462699', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462698', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462676', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462675', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462673', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462672', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462671', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462583', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462582', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462581', None, None, None, None, None, '3234682') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1188 time used for this insertion : 0.6822702884674072 save_final save missing photos in datou_result : time spend for datou_step_exec : 228.87637615203857 time spend to save output : 0.6934645175933838 total time spend for step 2 : 229.56984066963196 step3:rle_unique_nms_with_priority Fri Jul 4 09:10:32 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 390 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ No data in photo_id : 1370462805 nb_obj : 13 nb_hashtags : 4 time to prepare the origin masks : 12.288999557495117 time for calcul the mask position with numpy : 0.8449172973632812 nb_pixel_total : 7854060 time to create 1 rle with new method : 0.9768719673156738 time for calcul the mask position with numpy : 0.0565035343170166 nb_pixel_total : 56665 time to create 1 rle with old method : 0.06416010856628418 time for calcul the mask position with numpy : 0.048554420471191406 nb_pixel_total : 95686 time to create 1 rle with old method : 0.11420035362243652 time for calcul the mask position with numpy : 0.04366755485534668 nb_pixel_total : 29363 time to create 1 rle with old method : 0.03305196762084961 time for calcul the mask position with numpy : 0.02879619598388672 nb_pixel_total : 38278 time to create 1 rle with old method : 0.04345083236694336 time for calcul the mask position with numpy : 0.02891254425048828 nb_pixel_total : 7918 time to create 1 rle with old method : 0.009275674819946289 time for calcul the mask position with numpy : 0.030046701431274414 nb_pixel_total : 22508 time to create 1 rle with old method : 0.02536749839782715 time for calcul the mask position with numpy : 0.04648733139038086 nb_pixel_total : 44956 time to create 1 rle with old method : 0.050527095794677734 time for calcul the mask position with numpy : 0.04431939125061035 nb_pixel_total : 37441 time to create 1 rle with old method : 0.04202747344970703 time for calcul the mask position with numpy : 0.04167938232421875 nb_pixel_total : 10081 time to create 1 rle with old method : 0.01154470443725586 time for calcul the mask position with numpy : 0.040222883224487305 nb_pixel_total : 19740 time to create 1 rle with old method : 0.022478580474853516 time for calcul the mask position with numpy : 0.04278230667114258 nb_pixel_total : 16154 time to create 1 rle with old method : 0.018699169158935547 time for calcul the mask position with numpy : 0.04037594795227051 nb_pixel_total : 17545 time to create 1 rle with old method : 0.01985788345336914 time for calcul the mask position with numpy : 0.035555362701416016 nb_pixel_total : 44005 time to create 1 rle with old method : 0.05162811279296875 create new chi : 2.9084134101867676 time to delete rle : 0.019749879837036133 batch 1 Loaded 27 chid ids of type : 3594 +++++++++++++++++++++++Number RLEs to save : 8628 TO DO : save crop sub photo not yet done ! save time : 3.3384807109832764 nb_obj : 30 nb_hashtags : 2 time to prepare the origin masks : 4.912249565124512 time for calcul the mask position with numpy : 0.4977571964263916 nb_pixel_total : 6494479 time to create 1 rle with new method : 0.918074369430542 time for calcul the mask position with numpy : 0.04040384292602539 nb_pixel_total : 19715 time to create 1 rle with old method : 0.03261923789978027 time for calcul the mask position with numpy : 0.035721540451049805 nb_pixel_total : 11647 time to create 1 rle with old method : 0.01373147964477539 time for calcul the mask position with numpy : 0.03610086441040039 nb_pixel_total : 38539 time to create 1 rle with old method : 0.04390978813171387 time for calcul the mask position with numpy : 0.0348050594329834 nb_pixel_total : 17739 time to create 1 rle with old method : 0.020282983779907227 time for calcul the mask position with numpy : 0.03591513633728027 nb_pixel_total : 35412 time to create 1 rle with old method : 0.04146432876586914 time for calcul the mask position with numpy : 0.03565406799316406 nb_pixel_total : 55751 time to create 1 rle with old method : 0.06256794929504395 time for calcul the mask position with numpy : 0.034655094146728516 nb_pixel_total : 18709 time to create 1 rle with old method : 0.021033048629760742 time for calcul the mask position with numpy : 0.034863948822021484 nb_pixel_total : 31156 time to create 1 rle with old method : 0.034819841384887695 time for calcul the mask position with numpy : 0.03605389595031738 nb_pixel_total : 104171 time to create 1 rle with old method : 0.1160588264465332 time for calcul the mask position with numpy : 0.04004859924316406 nb_pixel_total : 67219 time to create 1 rle with old method : 0.08476018905639648 time for calcul the mask position with numpy : 0.034449100494384766 nb_pixel_total : 31162 time to create 1 rle with old method : 0.0350649356842041 time for calcul the mask position with numpy : 0.035305023193359375 nb_pixel_total : 19551 time to create 1 rle with old method : 0.022000789642333984 time for calcul the mask position with numpy : 0.03760957717895508 nb_pixel_total : 162551 time to create 1 rle with new method : 0.9513444900512695 time for calcul the mask position with numpy : 0.1198575496673584 nb_pixel_total : 441538 time to create 1 rle with new method : 1.6206483840942383 time for calcul the mask position with numpy : 0.035028934478759766 nb_pixel_total : 22194 time to create 1 rle with old method : 0.02482891082763672 time for calcul the mask position with numpy : 0.03739190101623535 nb_pixel_total : 104261 time to create 1 rle with old method : 0.14449834823608398 time for calcul the mask position with numpy : 0.03591036796569824 nb_pixel_total : 107298 time to create 1 rle with old method : 0.12423086166381836 time for calcul the mask position with numpy : 0.0344235897064209 nb_pixel_total : 17285 time to create 1 rle with old method : 0.020653963088989258 time for calcul the mask position with numpy : 0.03450512886047363 nb_pixel_total : 30347 time to create 1 rle with old method : 0.03382587432861328 time for calcul the mask position with numpy : 0.03464365005493164 nb_pixel_total : 61079 time to create 1 rle with old method : 0.0689554214477539 time for calcul the mask position with numpy : 0.03444266319274902 nb_pixel_total : 29335 time to create 1 rle with old method : 0.03389906883239746 time for calcul the mask position with numpy : 0.03638291358947754 nb_pixel_total : 18686 time to create 1 rle with old method : 0.021104812622070312 time for calcul the mask position with numpy : 0.03746461868286133 nb_pixel_total : 13952 time to create 1 rle with old method : 0.022977828979492188 time for calcul the mask position with numpy : 0.03769803047180176 nb_pixel_total : 5970 time to create 1 rle with old method : 0.00675654411315918 time for calcul the mask position with numpy : 0.03458404541015625 nb_pixel_total : 8618 time to create 1 rle with old method : 0.009823322296142578 time for calcul the mask position with numpy : 0.035298824310302734 nb_pixel_total : 259514 time to create 1 rle with new method : 0.8553066253662109 time for calcul the mask position with numpy : 0.034893035888671875 nb_pixel_total : 14649 time to create 1 rle with old method : 0.01638627052307129 time for calcul the mask position with numpy : 0.03475141525268555 nb_pixel_total : 24954 time to create 1 rle with old method : 0.028345823287963867 time for calcul the mask position with numpy : 0.03467202186584473 nb_pixel_total : 8687 time to create 1 rle with old method : 0.009830236434936523 time for calcul the mask position with numpy : 0.03460550308227539 nb_pixel_total : 18232 time to create 1 rle with old method : 0.020394325256347656 create new chi : 7.247833728790283 time to delete rle : 0.005350589752197266 batch 1 Loaded 61 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 21948 TO DO : save crop sub photo not yet done ! save time : 7.68757700920105 nb_obj : 23 nb_hashtags : 4 time to prepare the origin masks : 9.456746339797974 time for calcul the mask position with numpy : 2.0738954544067383 nb_pixel_total : 7000665 time to create 1 rle with new method : 1.1045446395874023 time for calcul the mask position with numpy : 0.049616336822509766 nb_pixel_total : 11357 time to create 1 rle with old method : 0.012853860855102539 time for calcul the mask position with numpy : 0.05146360397338867 nb_pixel_total : 121795 time to create 1 rle with old method : 0.13619232177734375 time for calcul the mask position with numpy : 0.051093339920043945 nb_pixel_total : 60810 time to create 1 rle with old method : 0.06800341606140137 time for calcul the mask position with numpy : 0.04785299301147461 nb_pixel_total : 38760 time to create 1 rle with old method : 0.04341435432434082 time for calcul the mask position with numpy : 0.0428311824798584 nb_pixel_total : 80951 time to create 1 rle with old method : 0.0907127857208252 time for calcul the mask position with numpy : 0.04769539833068848 nb_pixel_total : 103965 time to create 1 rle with old method : 0.11590981483459473 time for calcul the mask position with numpy : 0.04209160804748535 nb_pixel_total : 1320 time to create 1 rle with old method : 0.0017414093017578125 time for calcul the mask position with numpy : 0.04880094528198242 nb_pixel_total : 54205 time to create 1 rle with old method : 0.060707807540893555 time for calcul the mask position with numpy : 0.04674029350280762 nb_pixel_total : 188678 time to create 1 rle with new method : 1.3624215126037598 time for calcul the mask position with numpy : 0.051915645599365234 nb_pixel_total : 18935 time to create 1 rle with old method : 0.021676063537597656 time for calcul the mask position with numpy : 0.05031251907348633 nb_pixel_total : 58408 time to create 1 rle with old method : 0.06465363502502441 time for calcul the mask position with numpy : 0.04971456527709961 nb_pixel_total : 16075 time to create 1 rle with old method : 0.018067598342895508 time for calcul the mask position with numpy : 0.04887890815734863 nb_pixel_total : 18818 time to create 1 rle with old method : 0.021143436431884766 time for calcul the mask position with numpy : 0.056182861328125 nb_pixel_total : 28696 time to create 1 rle with old method : 0.032550811767578125 time for calcul the mask position with numpy : 0.04642057418823242 nb_pixel_total : 15733 time to create 1 rle with old method : 0.017971515655517578 time for calcul the mask position with numpy : 0.050873517990112305 nb_pixel_total : 72532 time to create 1 rle with old method : 0.0843505859375 time for calcul the mask position with numpy : 0.040268898010253906 nb_pixel_total : 7351 time to create 1 rle with old method : 0.00849771499633789 time for calcul the mask position with numpy : 0.047830820083618164 nb_pixel_total : 52123 time to create 1 rle with old method : 0.07460975646972656 time for calcul the mask position with numpy : 0.05135631561279297 nb_pixel_total : 30315 time to create 1 rle with old method : 0.03381848335266113 time for calcul the mask position with numpy : 0.05157184600830078 nb_pixel_total : 73978 time to create 1 rle with old method : 0.08229422569274902 time for calcul the mask position with numpy : 0.05083322525024414 nb_pixel_total : 56307 time to create 1 rle with old method : 0.06986498832702637 time for calcul the mask position with numpy : 0.05019354820251465 nb_pixel_total : 48443 time to create 1 rle with old method : 0.05913376808166504 time for calcul the mask position with numpy : 0.05183124542236328 nb_pixel_total : 134180 time to create 1 rle with old method : 0.1493973731994629 create new chi : 7.01564621925354 time to delete rle : 0.0042514801025390625 batch 1 Loaded 47 chid ids of type : 3594 ++++++++++++++++++++++++++++++Number RLEs to save : 15243 TO DO : save crop sub photo not yet done ! save time : 4.016467809677124 nb_obj : 17 nb_hashtags : 2 time to prepare the origin masks : 9.110451936721802 time for calcul the mask position with numpy : 0.9060864448547363 nb_pixel_total : 6805028 time to create 1 rle with new method : 1.2557101249694824 time for calcul the mask position with numpy : 0.05208849906921387 nb_pixel_total : 131815 time to create 1 rle with old method : 0.14673995971679688 time for calcul the mask position with numpy : 0.05501270294189453 nb_pixel_total : 53567 time to create 1 rle with old method : 0.0597538948059082 time for calcul the mask position with numpy : 0.052541255950927734 nb_pixel_total : 277762 time to create 1 rle with new method : 0.6337246894836426 time for calcul the mask position with numpy : 0.0521240234375 nb_pixel_total : 77070 time to create 1 rle with old method : 0.08561372756958008 time for calcul the mask position with numpy : 0.04372453689575195 nb_pixel_total : 35445 time to create 1 rle with old method : 0.04014778137207031 time for calcul the mask position with numpy : 0.04949164390563965 nb_pixel_total : 11282 time to create 1 rle with old method : 0.01277780532836914 time for calcul the mask position with numpy : 0.05058646202087402 nb_pixel_total : 70022 time to create 1 rle with old method : 0.09211325645446777 time for calcul the mask position with numpy : 0.04969525337219238 nb_pixel_total : 41709 time to create 1 rle with old method : 0.046956777572631836 time for calcul the mask position with numpy : 0.04616665840148926 nb_pixel_total : 69065 time to create 1 rle with old method : 0.1783607006072998 time for calcul the mask position with numpy : 0.05084705352783203 nb_pixel_total : 85442 time to create 1 rle with old method : 0.09809255599975586 time for calcul the mask position with numpy : 0.05607271194458008 nb_pixel_total : 82822 time to create 1 rle with old method : 0.09251976013183594 time for calcul the mask position with numpy : 0.04420971870422363 nb_pixel_total : 52043 time to create 1 rle with old method : 0.058145761489868164 time for calcul the mask position with numpy : 0.0508730411529541 nb_pixel_total : 20043 time to create 1 rle with old method : 0.022728443145751953 time for calcul the mask position with numpy : 0.05073285102844238 nb_pixel_total : 68044 time to create 1 rle with old method : 0.07619285583496094 time for calcul the mask position with numpy : 0.05114293098449707 nb_pixel_total : 93754 time to create 1 rle with old method : 0.10468125343322754 time for calcul the mask position with numpy : 0.04942750930786133 nb_pixel_total : 163599 time to create 1 rle with new method : 1.501920461654663 time for calcul the mask position with numpy : 0.04543638229370117 nb_pixel_total : 155888 time to create 1 rle with new method : 0.9156672954559326 create new chi : 7.324362277984619 time to delete rle : 0.003912448883056641 batch 1 Loaded 35 chid ids of type : 3594 +++++++++++++++++++++Number RLEs to save : 15368 TO DO : save crop sub photo not yet done ! save time : 5.391620635986328 nb_obj : 25 nb_hashtags : 4 time to prepare the origin masks : 13.612950563430786 time for calcul the mask position with numpy : 0.5871462821960449 nb_pixel_total : 6866765 time to create 1 rle with new method : 0.9651644229888916 time for calcul the mask position with numpy : 0.05024242401123047 nb_pixel_total : 24541 time to create 1 rle with old method : 0.02738165855407715 time for calcul the mask position with numpy : 0.05016064643859863 nb_pixel_total : 34420 time to create 1 rle with old method : 0.03901100158691406 time for calcul the mask position with numpy : 0.04994606971740723 nb_pixel_total : 31218 time to create 1 rle with old method : 0.03549623489379883 time for calcul the mask position with numpy : 0.04955172538757324 nb_pixel_total : 43942 time to create 1 rle with old method : 0.049692630767822266 time for calcul the mask position with numpy : 0.04905986785888672 nb_pixel_total : 21119 time to create 1 rle with old method : 0.023860692977905273 time for calcul the mask position with numpy : 0.04993414878845215 nb_pixel_total : 21852 time to create 1 rle with old method : 0.024688720703125 time for calcul the mask position with numpy : 0.04915356636047363 nb_pixel_total : 22043 time to create 1 rle with old method : 0.02479243278503418 time for calcul the mask position with numpy : 0.0413966178894043 nb_pixel_total : 16777 time to create 1 rle with old method : 0.018823623657226562 time for calcul the mask position with numpy : 0.03194570541381836 nb_pixel_total : 56850 time to create 1 rle with old method : 0.06423592567443848 time for calcul the mask position with numpy : 0.03165745735168457 nb_pixel_total : 36327 time to create 1 rle with old method : 0.04074692726135254 time for calcul the mask position with numpy : 0.03425097465515137 nb_pixel_total : 8280 time to create 1 rle with old method : 0.009487152099609375 time for calcul the mask position with numpy : 0.033860206604003906 nb_pixel_total : 82955 time to create 1 rle with old method : 0.09245920181274414 time for calcul the mask position with numpy : 0.030284404754638672 nb_pixel_total : 4196 time to create 1 rle with old method : 0.0048370361328125 time for calcul the mask position with numpy : 0.03366684913635254 nb_pixel_total : 65716 time to create 1 rle with old method : 0.08135819435119629 time for calcul the mask position with numpy : 0.03679180145263672 nb_pixel_total : 122880 time to create 1 rle with old method : 0.1375281810760498 time for calcul the mask position with numpy : 0.035402774810791016 nb_pixel_total : 139053 time to create 1 rle with old method : 0.1535651683807373 time for calcul the mask position with numpy : 0.03810310363769531 nb_pixel_total : 44037 time to create 1 rle with old method : 0.04935431480407715 time for calcul the mask position with numpy : 0.052805423736572266 nb_pixel_total : 26517 time to create 1 rle with old method : 0.029653549194335938 time for calcul the mask position with numpy : 0.05016732215881348 nb_pixel_total : 38239 time to create 1 rle with old method : 0.042493343353271484 time for calcul the mask position with numpy : 0.04991412162780762 nb_pixel_total : 28758 time to create 1 rle with old method : 0.03235602378845215 time for calcul the mask position with numpy : 0.050606727600097656 nb_pixel_total : 9864 time to create 1 rle with old method : 0.011363744735717773 time for calcul the mask position with numpy : 0.05004262924194336 nb_pixel_total : 90408 time to create 1 rle with old method : 0.10044384002685547 time for calcul the mask position with numpy : 0.0506596565246582 nb_pixel_total : 26033 time to create 1 rle with old method : 0.02914595603942871 time for calcul the mask position with numpy : 0.05007600784301758 nb_pixel_total : 323103 time to create 1 rle with new method : 0.7922701835632324 time for calcul the mask position with numpy : 0.033170223236083984 nb_pixel_total : 108507 time to create 1 rle with old method : 0.12272429466247559 create new chi : 4.756579637527466 time to delete rle : 0.004096508026123047 batch 1 Loaded 51 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++Number RLEs to save : 16411 TO DO : save crop sub photo not yet done ! save time : 5.48945951461792 nb_obj : 31 nb_hashtags : 3 time to prepare the origin masks : 4.65968918800354 time for calcul the mask position with numpy : 0.323300838470459 nb_pixel_total : 6870040 time to create 1 rle with new method : 0.658888578414917 time for calcul the mask position with numpy : 0.03590679168701172 nb_pixel_total : 83665 time to create 1 rle with old method : 0.0964357852935791 time for calcul the mask position with numpy : 0.03731799125671387 nb_pixel_total : 198200 time to create 1 rle with new method : 0.8294174671173096 time for calcul the mask position with numpy : 0.03457784652709961 nb_pixel_total : 16919 time to create 1 rle with old method : 0.018993616104125977 time for calcul the mask position with numpy : 0.0361933708190918 nb_pixel_total : 58649 time to create 1 rle with old method : 0.07280349731445312 time for calcul the mask position with numpy : 0.03480219841003418 nb_pixel_total : 18326 time to create 1 rle with old method : 0.020547151565551758 time for calcul the mask position with numpy : 0.03660464286804199 nb_pixel_total : 33119 time to create 1 rle with old method : 0.03723406791687012 time for calcul the mask position with numpy : 0.034677982330322266 nb_pixel_total : 36734 time to create 1 rle with old method : 0.04124116897583008 time for calcul the mask position with numpy : 0.03566408157348633 nb_pixel_total : 122274 time to create 1 rle with old method : 0.21640586853027344 time for calcul the mask position with numpy : 0.10661959648132324 nb_pixel_total : 25692 time to create 1 rle with old method : 0.04271078109741211 time for calcul the mask position with numpy : 0.04599618911743164 nb_pixel_total : 19298 time to create 1 rle with old method : 0.040220022201538086 time for calcul the mask position with numpy : 0.047553062438964844 nb_pixel_total : 13027 time to create 1 rle with old method : 0.02350592613220215 time for calcul the mask position with numpy : 0.04589104652404785 nb_pixel_total : 12404 time to create 1 rle with old method : 0.02158832550048828 time for calcul the mask position with numpy : 0.038956642150878906 nb_pixel_total : 51154 time to create 1 rle with old method : 0.057634592056274414 time for calcul the mask position with numpy : 0.04129338264465332 nb_pixel_total : 81993 time to create 1 rle with old method : 0.09601068496704102 time for calcul the mask position with numpy : 0.03595232963562012 nb_pixel_total : 10720 time to create 1 rle with old method : 0.012873649597167969 time for calcul the mask position with numpy : 0.037441253662109375 nb_pixel_total : 27162 time to create 1 rle with old method : 0.0630943775177002 time for calcul the mask position with numpy : 0.04006361961364746 nb_pixel_total : 42274 time to create 1 rle with old method : 0.04756951332092285 time for calcul the mask position with numpy : 0.03621101379394531 nb_pixel_total : 87694 time to create 1 rle with old method : 0.1216268539428711 time for calcul the mask position with numpy : 0.03639841079711914 nb_pixel_total : 62602 time to create 1 rle with old method : 0.07456517219543457 time for calcul the mask position with numpy : 0.03914189338684082 nb_pixel_total : 60281 time to create 1 rle with old method : 0.0739736557006836 time for calcul the mask position with numpy : 0.03686976432800293 nb_pixel_total : 32003 time to create 1 rle with old method : 0.03792428970336914 time for calcul the mask position with numpy : 0.03787851333618164 nb_pixel_total : 35544 time to create 1 rle with old method : 0.04224228858947754 time for calcul the mask position with numpy : 0.03856778144836426 nb_pixel_total : 57934 time to create 1 rle with old method : 0.06807923316955566 time for calcul the mask position with numpy : 0.03631949424743652 nb_pixel_total : 54406 time to create 1 rle with old method : 0.06252145767211914 time for calcul the mask position with numpy : 0.03637433052062988 nb_pixel_total : 30690 time to create 1 rle with old method : 0.035212039947509766 time for calcul the mask position with numpy : 0.03644275665283203 nb_pixel_total : 39975 time to create 1 rle with old method : 0.05398273468017578 time for calcul the mask position with numpy : 0.08503079414367676 nb_pixel_total : 7282 time to create 1 rle with old method : 0.028291940689086914 time for calcul the mask position with numpy : 0.09107327461242676 nb_pixel_total : 16332 time to create 1 rle with old method : 0.04219961166381836 time for calcul the mask position with numpy : 0.04426717758178711 nb_pixel_total : 28915 time to create 1 rle with old method : 0.03282809257507324 time for calcul the mask position with numpy : 0.03641676902770996 nb_pixel_total : 24426 time to create 1 rle with old method : 0.02825021743774414 time for calcul the mask position with numpy : 0.07028841972351074 nb_pixel_total : 34666 time to create 1 rle with old method : 0.041208744049072266 create new chi : 4.923615217208862 time to delete rle : 0.0057108402252197266 batch 1 Loaded 63 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 19173 TO DO : save crop sub photo not yet done ! save time : 8.016268491744995 nb_obj : 21 nb_hashtags : 4 time to prepare the origin masks : 6.180201530456543 time for calcul the mask position with numpy : 0.3634054660797119 nb_pixel_total : 6674314 time to create 1 rle with new method : 1.5509724617004395 time for calcul the mask position with numpy : 0.0492403507232666 nb_pixel_total : 211148 time to create 1 rle with new method : 0.8005461692810059 time for calcul the mask position with numpy : 0.04348182678222656 nb_pixel_total : 67406 time to create 1 rle with old method : 0.07767796516418457 time for calcul the mask position with numpy : 0.045792579650878906 nb_pixel_total : 19463 time to create 1 rle with old method : 0.0208280086517334 time for calcul the mask position with numpy : 0.033892154693603516 nb_pixel_total : 215378 time to create 1 rle with new method : 0.6688549518585205 time for calcul the mask position with numpy : 0.034868717193603516 nb_pixel_total : 240650 time to create 1 rle with new method : 0.9122087955474854 time for calcul the mask position with numpy : 0.04262709617614746 nb_pixel_total : 46316 time to create 1 rle with old method : 0.052082061767578125 time for calcul the mask position with numpy : 0.04111194610595703 nb_pixel_total : 16491 time to create 1 rle with old method : 0.018718719482421875 time for calcul the mask position with numpy : 0.04243063926696777 nb_pixel_total : 63669 time to create 1 rle with old method : 0.07174253463745117 time for calcul the mask position with numpy : 0.04106307029724121 nb_pixel_total : 21296 time to create 1 rle with old method : 0.023862123489379883 time for calcul the mask position with numpy : 0.04068875312805176 nb_pixel_total : 44340 time to create 1 rle with old method : 0.05027127265930176 time for calcul the mask position with numpy : 0.043868064880371094 nb_pixel_total : 36295 time to create 1 rle with old method : 0.040749311447143555 time for calcul the mask position with numpy : 0.03868556022644043 nb_pixel_total : 49142 time to create 1 rle with old method : 0.05499744415283203 time for calcul the mask position with numpy : 0.041433095932006836 nb_pixel_total : 25901 time to create 1 rle with old method : 0.02909255027770996 time for calcul the mask position with numpy : 0.041257619857788086 nb_pixel_total : 32248 time to create 1 rle with old method : 0.03618049621582031 time for calcul the mask position with numpy : 0.04346632957458496 nb_pixel_total : 43263 time to create 1 rle with old method : 0.0483698844909668 time for calcul the mask position with numpy : 0.04559469223022461 nb_pixel_total : 271648 time to create 1 rle with new method : 1.0221977233886719 time for calcul the mask position with numpy : 0.05383563041687012 nb_pixel_total : 63750 time to create 1 rle with old method : 0.07176542282104492 time for calcul the mask position with numpy : 0.04334521293640137 nb_pixel_total : 26921 time to create 1 rle with old method : 0.03046393394470215 time for calcul the mask position with numpy : 0.056596994400024414 nb_pixel_total : 35054 time to create 1 rle with old method : 0.040221214294433594 time for calcul the mask position with numpy : 0.05005455017089844 nb_pixel_total : 34892 time to create 1 rle with old method : 0.039510250091552734 time for calcul the mask position with numpy : 0.04552936553955078 nb_pixel_total : 54815 time to create 1 rle with old method : 0.06301116943359375 create new chi : 7.164093971252441 time to delete rle : 0.007812738418579102 batch 1 Loaded 43 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 20006 TO DO : save crop sub photo not yet done ! save time : 9.619608640670776 nb_obj : 24 nb_hashtags : 2 time to prepare the origin masks : 8.710690021514893 time for calcul the mask position with numpy : 0.7242705821990967 nb_pixel_total : 6458683 time to create 1 rle with new method : 0.8811933994293213 time for calcul the mask position with numpy : 0.05535125732421875 nb_pixel_total : 21853 time to create 1 rle with old method : 0.03884601593017578 time for calcul the mask position with numpy : 0.048107147216796875 nb_pixel_total : 112852 time to create 1 rle with old method : 0.13791251182556152 time for calcul the mask position with numpy : 0.04674959182739258 nb_pixel_total : 99498 time to create 1 rle with old method : 0.1376197338104248 time for calcul the mask position with numpy : 0.05467414855957031 nb_pixel_total : 10018 time to create 1 rle with old method : 0.013006448745727539 time for calcul the mask position with numpy : 0.04956984519958496 nb_pixel_total : 69821 time to create 1 rle with old method : 0.08590555191040039 time for calcul the mask position with numpy : 0.04471778869628906 nb_pixel_total : 38532 time to create 1 rle with old method : 0.05275845527648926 time for calcul the mask position with numpy : 0.04804635047912598 nb_pixel_total : 17418 time to create 1 rle with old method : 0.02161097526550293 time for calcul the mask position with numpy : 0.04790997505187988 nb_pixel_total : 161114 time to create 1 rle with new method : 0.6592867374420166 time for calcul the mask position with numpy : 0.04151272773742676 nb_pixel_total : 44083 time to create 1 rle with old method : 0.05057096481323242 time for calcul the mask position with numpy : 0.026996374130249023 nb_pixel_total : 62509 time to create 1 rle with old method : 0.07069087028503418 time for calcul the mask position with numpy : 0.02875065803527832 nb_pixel_total : 20518 time to create 1 rle with old method : 0.023161649703979492 time for calcul the mask position with numpy : 0.03621673583984375 nb_pixel_total : 61374 time to create 1 rle with old method : 0.0684664249420166 time for calcul the mask position with numpy : 0.03326296806335449 nb_pixel_total : 31908 time to create 1 rle with old method : 0.03731131553649902 time for calcul the mask position with numpy : 0.038062095642089844 nb_pixel_total : 80610 time to create 1 rle with old method : 0.0897974967956543 time for calcul the mask position with numpy : 0.03248238563537598 nb_pixel_total : 59980 time to create 1 rle with old method : 0.06770133972167969 time for calcul the mask position with numpy : 0.032355546951293945 nb_pixel_total : 47814 time to create 1 rle with old method : 0.053836822509765625 time for calcul the mask position with numpy : 0.033016204833984375 nb_pixel_total : 68623 time to create 1 rle with old method : 0.07738494873046875 time for calcul the mask position with numpy : 0.036484718322753906 nb_pixel_total : 321204 time to create 1 rle with new method : 1.2487826347351074 time for calcul the mask position with numpy : 0.05060839653015137 nb_pixel_total : 63219 time to create 1 rle with old method : 0.07371091842651367 time for calcul the mask position with numpy : 0.05142331123352051 nb_pixel_total : 106177 time to create 1 rle with old method : 0.12248516082763672 time for calcul the mask position with numpy : 0.052282094955444336 nb_pixel_total : 118060 time to create 1 rle with old method : 0.13817119598388672 time for calcul the mask position with numpy : 0.05534696578979492 nb_pixel_total : 46076 time to create 1 rle with old method : 0.05209970474243164 time for calcul the mask position with numpy : 0.04155921936035156 nb_pixel_total : 116968 time to create 1 rle with old method : 0.14409852027893066 time for calcul the mask position with numpy : 0.04201459884643555 nb_pixel_total : 55488 time to create 1 rle with old method : 0.06204843521118164 create new chi : 6.5261616706848145 time to delete rle : 0.0034492015838623047 batch 1 Loaded 49 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 20995 TO DO : save crop sub photo not yet done ! save time : 10.565173387527466 nb_obj : 14 nb_hashtags : 2 time to prepare the origin masks : 7.813958644866943 time for calcul the mask position with numpy : 0.43862056732177734 nb_pixel_total : 7652584 time to create 1 rle with new method : 0.9214491844177246 time for calcul the mask position with numpy : 0.027161359786987305 nb_pixel_total : 29505 time to create 1 rle with old method : 0.03306126594543457 time for calcul the mask position with numpy : 0.044599294662475586 nb_pixel_total : 48189 time to create 1 rle with old method : 0.05396556854248047 time for calcul the mask position with numpy : 0.05396389961242676 nb_pixel_total : 32787 time to create 1 rle with old method : 0.03720211982727051 time for calcul the mask position with numpy : 0.05442929267883301 nb_pixel_total : 54078 time to create 1 rle with old method : 0.06049799919128418 time for calcul the mask position with numpy : 0.05312752723693848 nb_pixel_total : 138416 time to create 1 rle with old method : 0.15549969673156738 time for calcul the mask position with numpy : 0.05331110954284668 nb_pixel_total : 6142 time to create 1 rle with old method : 0.007047891616821289 time for calcul the mask position with numpy : 0.05456233024597168 nb_pixel_total : 28823 time to create 1 rle with old method : 0.03279280662536621 time for calcul the mask position with numpy : 0.049883365631103516 nb_pixel_total : 26871 time to create 1 rle with old method : 0.030518054962158203 time for calcul the mask position with numpy : 0.05023646354675293 nb_pixel_total : 91702 time to create 1 rle with old method : 0.1031503677368164 time for calcul the mask position with numpy : 0.0469660758972168 nb_pixel_total : 16611 time to create 1 rle with old method : 0.018788576126098633 time for calcul the mask position with numpy : 0.0356752872467041 nb_pixel_total : 26915 time to create 1 rle with old method : 0.03032660484313965 time for calcul the mask position with numpy : 0.0346531867980957 nb_pixel_total : 107957 time to create 1 rle with old method : 0.12035536766052246 time for calcul the mask position with numpy : 0.03247523307800293 nb_pixel_total : 18828 time to create 1 rle with old method : 0.021228551864624023 time for calcul the mask position with numpy : 0.03191518783569336 nb_pixel_total : 14992 time to create 1 rle with old method : 0.016915321350097656 create new chi : 2.753391981124878 time to delete rle : 0.0029802322387695312 batch 1 Loaded 29 chid ids of type : 3594 ++++++++++++++++++++Number RLEs to save : 10298 TO DO : save crop sub photo not yet done ! save time : 1.409515619277954 nb_obj : 26 nb_hashtags : 3 time to prepare the origin masks : 4.32083797454834 time for calcul the mask position with numpy : 0.7839314937591553 nb_pixel_total : 7257485 time to create 1 rle with new method : 1.1577229499816895 time for calcul the mask position with numpy : 0.03473258018493652 nb_pixel_total : 32460 time to create 1 rle with old method : 0.03636765480041504 time for calcul the mask position with numpy : 0.03527688980102539 nb_pixel_total : 131111 time to create 1 rle with old method : 0.1464214324951172 time for calcul the mask position with numpy : 0.03514885902404785 nb_pixel_total : 12823 time to create 1 rle with old method : 0.014539718627929688 time for calcul the mask position with numpy : 0.03427433967590332 nb_pixel_total : 10062 time to create 1 rle with old method : 0.013415336608886719 time for calcul the mask position with numpy : 0.034924983978271484 nb_pixel_total : 58142 time to create 1 rle with old method : 0.06514787673950195 time for calcul the mask position with numpy : 0.034305572509765625 nb_pixel_total : 57505 time to create 1 rle with old method : 0.06420326232910156 time for calcul the mask position with numpy : 0.034543752670288086 nb_pixel_total : 58128 time to create 1 rle with old method : 0.06497979164123535 time for calcul the mask position with numpy : 0.03495597839355469 nb_pixel_total : 44758 time to create 1 rle with old method : 0.050328731536865234 time for calcul the mask position with numpy : 0.03544902801513672 nb_pixel_total : 83619 time to create 1 rle with old method : 0.0935673713684082 time for calcul the mask position with numpy : 0.03493094444274902 nb_pixel_total : 69725 time to create 1 rle with old method : 0.0786285400390625 time for calcul the mask position with numpy : 0.03519392013549805 nb_pixel_total : 53019 time to create 1 rle with old method : 0.05973649024963379 time for calcul the mask position with numpy : 0.035288095474243164 nb_pixel_total : 54660 time to create 1 rle with old method : 0.06180715560913086 time for calcul the mask position with numpy : 0.03499341011047363 nb_pixel_total : 22949 time to create 1 rle with old method : 0.026084184646606445 time for calcul the mask position with numpy : 0.0348052978515625 nb_pixel_total : 29182 time to create 1 rle with old method : 0.03266787528991699 time for calcul the mask position with numpy : 0.03466176986694336 nb_pixel_total : 11714 time to create 1 rle with old method : 0.013680696487426758 time for calcul the mask position with numpy : 0.034990549087524414 nb_pixel_total : 66152 time to create 1 rle with old method : 0.07506990432739258 time for calcul the mask position with numpy : 0.03487730026245117 nb_pixel_total : 54845 time to create 1 rle with old method : 0.06188225746154785 time for calcul the mask position with numpy : 0.034841060638427734 nb_pixel_total : 20089 time to create 1 rle with old method : 0.022986650466918945 time for calcul the mask position with numpy : 0.03469419479370117 nb_pixel_total : 3001 time to create 1 rle with old method : 0.0035266876220703125 time for calcul the mask position with numpy : 0.03479504585266113 nb_pixel_total : 47719 time to create 1 rle with old method : 0.05371212959289551 time for calcul the mask position with numpy : 0.03487110137939453 nb_pixel_total : 36403 time to create 1 rle with old method : 0.04047346115112305 time for calcul the mask position with numpy : 0.03477144241333008 nb_pixel_total : 22090 time to create 1 rle with old method : 0.024890899658203125 time for calcul the mask position with numpy : 0.03567790985107422 nb_pixel_total : 10904 time to create 1 rle with old method : 0.01230001449584961 time for calcul the mask position with numpy : 0.03462362289428711 nb_pixel_total : 16573 time to create 1 rle with old method : 0.01880335807800293 time for calcul the mask position with numpy : 0.03459572792053223 nb_pixel_total : 18144 time to create 1 rle with old method : 0.02064061164855957 time for calcul the mask position with numpy : 0.03451824188232422 nb_pixel_total : 11138 time to create 1 rle with old method : 0.012636661529541016 create new chi : 4.059997081756592 time to delete rle : 0.004329681396484375 batch 1 Loaded 53 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 17619 TO DO : save crop sub photo not yet done ! save time : 2.30006742477417 nb_obj : 16 nb_hashtags : 3 time to prepare the origin masks : 6.550925970077515 time for calcul the mask position with numpy : 0.35140156745910645 nb_pixel_total : 7433072 time to create 1 rle with new method : 0.45233964920043945 time for calcul the mask position with numpy : 0.044974327087402344 nb_pixel_total : 28684 time to create 1 rle with old method : 0.03190970420837402 time for calcul the mask position with numpy : 0.04147219657897949 nb_pixel_total : 40012 time to create 1 rle with old method : 0.04653644561767578 time for calcul the mask position with numpy : 0.03345990180969238 nb_pixel_total : 16414 time to create 1 rle with old method : 0.018378019332885742 time for calcul the mask position with numpy : 0.025355815887451172 nb_pixel_total : 21615 time to create 1 rle with old method : 0.024277448654174805 time for calcul the mask position with numpy : 0.02577805519104004 nb_pixel_total : 96395 time to create 1 rle with old method : 0.10774993896484375 time for calcul the mask position with numpy : 0.026738643646240234 nb_pixel_total : 39324 time to create 1 rle with old method : 0.04430866241455078 time for calcul the mask position with numpy : 0.02574324607849121 nb_pixel_total : 20506 time to create 1 rle with old method : 0.023128747940063477 time for calcul the mask position with numpy : 0.02659893035888672 nb_pixel_total : 197055 time to create 1 rle with new method : 0.8255224227905273 time for calcul the mask position with numpy : 0.026492595672607422 nb_pixel_total : 12425 time to create 1 rle with old method : 0.01438283920288086 time for calcul the mask position with numpy : 0.028412342071533203 nb_pixel_total : 84767 time to create 1 rle with old method : 0.09481430053710938 time for calcul the mask position with numpy : 0.026460886001586914 nb_pixel_total : 10795 time to create 1 rle with old method : 0.012190103530883789 time for calcul the mask position with numpy : 0.026629924774169922 nb_pixel_total : 31787 time to create 1 rle with old method : 0.035564422607421875 time for calcul the mask position with numpy : 0.025997161865234375 nb_pixel_total : 71167 time to create 1 rle with old method : 0.08009886741638184 time for calcul the mask position with numpy : 0.026886701583862305 nb_pixel_total : 76930 time to create 1 rle with old method : 0.08620977401733398 time for calcul the mask position with numpy : 0.02596116065979004 nb_pixel_total : 41851 time to create 1 rle with old method : 0.05219745635986328 time for calcul the mask position with numpy : 0.028850555419921875 nb_pixel_total : 71601 time to create 1 rle with old method : 0.0809175968170166 create new chi : 2.9102365970611572 time to delete rle : 0.0028645992279052734 batch 1 Loaded 33 chid ids of type : 3594 ++++++++++++++++++++Number RLEs to save : 12702 TO DO : save crop sub photo not yet done ! save time : 7.635769367218018 nb_obj : 27 nb_hashtags : 3 time to prepare the origin masks : 5.233006715774536 time for calcul the mask position with numpy : 0.28229212760925293 nb_pixel_total : 6208148 time to create 1 rle with new method : 0.43985557556152344 time for calcul the mask position with numpy : 0.03464674949645996 nb_pixel_total : 19704 time to create 1 rle with old method : 0.022045373916625977 time for calcul the mask position with numpy : 0.03466653823852539 nb_pixel_total : 45470 time to create 1 rle with old method : 0.05097699165344238 time for calcul the mask position with numpy : 0.03558778762817383 nb_pixel_total : 178820 time to create 1 rle with new method : 0.38706040382385254 time for calcul the mask position with numpy : 0.03578805923461914 nb_pixel_total : 297610 time to create 1 rle with new method : 0.3912830352783203 time for calcul the mask position with numpy : 0.03456735610961914 nb_pixel_total : 34731 time to create 1 rle with old method : 0.03867506980895996 time for calcul the mask position with numpy : 0.03451728820800781 nb_pixel_total : 48335 time to create 1 rle with old method : 0.054230451583862305 time for calcul the mask position with numpy : 0.03464055061340332 nb_pixel_total : 67826 time to create 1 rle with old method : 0.07506990432739258 time for calcul the mask position with numpy : 0.034897565841674805 nb_pixel_total : 68939 time to create 1 rle with old method : 0.07784652709960938 time for calcul the mask position with numpy : 0.03566265106201172 nb_pixel_total : 74389 time to create 1 rle with old method : 0.0869147777557373 time for calcul the mask position with numpy : 0.03522849082946777 nb_pixel_total : 125600 time to create 1 rle with old method : 0.14092707633972168 time for calcul the mask position with numpy : 0.035111427307128906 nb_pixel_total : 95551 time to create 1 rle with old method : 0.10648131370544434 time for calcul the mask position with numpy : 0.035964250564575195 nb_pixel_total : 314062 time to create 1 rle with new method : 0.7905793190002441 time for calcul the mask position with numpy : 0.0343780517578125 nb_pixel_total : 64666 time to create 1 rle with old method : 0.07166028022766113 time for calcul the mask position with numpy : 0.03496575355529785 nb_pixel_total : 76351 time to create 1 rle with old method : 0.08533287048339844 time for calcul the mask position with numpy : 0.034667015075683594 nb_pixel_total : 39522 time to create 1 rle with old method : 0.044428110122680664 time for calcul the mask position with numpy : 0.034996747970581055 nb_pixel_total : 77740 time to create 1 rle with old method : 0.08746767044067383 time for calcul the mask position with numpy : 0.03438305854797363 nb_pixel_total : 24768 time to create 1 rle with old method : 0.027849674224853516 time for calcul the mask position with numpy : 0.03447270393371582 nb_pixel_total : 78748 time to create 1 rle with old method : 0.0887753963470459 time for calcul the mask position with numpy : 0.03760933876037598 nb_pixel_total : 18042 time to create 1 rle with old method : 0.0202944278717041 time for calcul the mask position with numpy : 0.03476238250732422 nb_pixel_total : 118763 time to create 1 rle with old method : 0.13347291946411133 time for calcul the mask position with numpy : 0.034554481506347656 nb_pixel_total : 39473 time to create 1 rle with old method : 0.04442286491394043 time for calcul the mask position with numpy : 0.034633636474609375 nb_pixel_total : 68202 time to create 1 rle with old method : 0.07638335227966309 time for calcul the mask position with numpy : 0.03471183776855469 nb_pixel_total : 6266 time to create 1 rle with old method : 0.007107973098754883 time for calcul the mask position with numpy : 0.03477311134338379 nb_pixel_total : 58320 time to create 1 rle with old method : 0.06487083435058594 time for calcul the mask position with numpy : 0.03455686569213867 nb_pixel_total : 15685 time to create 1 rle with old method : 0.017847061157226562 time for calcul the mask position with numpy : 0.034650325775146484 nb_pixel_total : 12007 time to create 1 rle with old method : 0.013692855834960938 time for calcul the mask position with numpy : 0.03488802909851074 nb_pixel_total : 16662 time to create 1 rle with old method : 0.01863551139831543 create new chi : 4.80745792388916 time to delete rle : 0.004590511322021484 batch 1 Loaded 55 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++Number RLEs to save : 21771 TO DO : save crop sub photo not yet done ! save time : 3.546505928039551 nb_obj : 28 nb_hashtags : 3 time to prepare the origin masks : 4.826322078704834 time for calcul the mask position with numpy : 1.273230791091919 nb_pixel_total : 6537589 time to create 1 rle with new method : 1.9285969734191895 time for calcul the mask position with numpy : 0.03531336784362793 nb_pixel_total : 60403 time to create 1 rle with old method : 0.06820797920227051 time for calcul the mask position with numpy : 0.03454232215881348 nb_pixel_total : 27525 time to create 1 rle with old method : 0.03171062469482422 time for calcul the mask position with numpy : 0.03485894203186035 nb_pixel_total : 34913 time to create 1 rle with old method : 0.03873848915100098 time for calcul the mask position with numpy : 0.03471207618713379 nb_pixel_total : 21696 time to create 1 rle with old method : 0.0247957706451416 time for calcul the mask position with numpy : 0.03449082374572754 nb_pixel_total : 27962 time to create 1 rle with old method : 0.03141975402832031 time for calcul the mask position with numpy : 0.03481340408325195 nb_pixel_total : 55597 time to create 1 rle with old method : 0.061820030212402344 time for calcul the mask position with numpy : 0.03435635566711426 nb_pixel_total : 14163 time to create 1 rle with old method : 0.015942811965942383 time for calcul the mask position with numpy : 0.03450918197631836 nb_pixel_total : 93877 time to create 1 rle with old method : 0.1106712818145752 time for calcul the mask position with numpy : 0.03464984893798828 nb_pixel_total : 22918 time to create 1 rle with old method : 0.025867223739624023 time for calcul the mask position with numpy : 0.035155296325683594 nb_pixel_total : 72691 time to create 1 rle with old method : 0.08111286163330078 time for calcul the mask position with numpy : 0.03470158576965332 nb_pixel_total : 10035 time to create 1 rle with old method : 0.011345386505126953 time for calcul the mask position with numpy : 0.034881591796875 nb_pixel_total : 26914 time to create 1 rle with old method : 0.030173063278198242 time for calcul the mask position with numpy : 0.03484702110290527 nb_pixel_total : 53416 time to create 1 rle with old method : 0.059311628341674805 time for calcul the mask position with numpy : 0.03457999229431152 nb_pixel_total : 82879 time to create 1 rle with old method : 0.09412240982055664 time for calcul the mask position with numpy : 0.037026405334472656 nb_pixel_total : 96086 time to create 1 rle with old method : 0.10634899139404297 time for calcul the mask position with numpy : 0.036821603775024414 nb_pixel_total : 202502 time to create 1 rle with new method : 0.5059781074523926 time for calcul the mask position with numpy : 0.034749746322631836 nb_pixel_total : 81539 time to create 1 rle with old method : 0.09128379821777344 time for calcul the mask position with numpy : 0.03420615196228027 nb_pixel_total : 13443 time to create 1 rle with old method : 0.015343666076660156 time for calcul the mask position with numpy : 0.03418874740600586 nb_pixel_total : 29303 time to create 1 rle with old method : 0.03301405906677246 time for calcul the mask position with numpy : 0.03444504737854004 nb_pixel_total : 82640 time to create 1 rle with old method : 0.09252619743347168 time for calcul the mask position with numpy : 0.03508877754211426 nb_pixel_total : 146484 time to create 1 rle with old method : 0.16350483894348145 time for calcul the mask position with numpy : 0.03469133377075195 nb_pixel_total : 127569 time to create 1 rle with old method : 0.14145326614379883 time for calcul the mask position with numpy : 0.03517007827758789 nb_pixel_total : 78588 time to create 1 rle with old method : 0.08819150924682617 time for calcul the mask position with numpy : 0.03458356857299805 nb_pixel_total : 26290 time to create 1 rle with old method : 0.02983570098876953 time for calcul the mask position with numpy : 0.03625774383544922 nb_pixel_total : 196699 time to create 1 rle with new method : 0.4889261722564697 time for calcul the mask position with numpy : 0.03490710258483887 nb_pixel_total : 31495 time to create 1 rle with old method : 0.0430448055267334 time for calcul the mask position with numpy : 0.03605198860168457 nb_pixel_total : 28676 time to create 1 rle with old method : 0.033940792083740234 time for calcul the mask position with numpy : 0.03896737098693848 nb_pixel_total : 10508 time to create 1 rle with old method : 0.01379084587097168 create new chi : 6.816116571426392 time to delete rle : 0.004518270492553711 batch 1 Loaded 57 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 19320 TO DO : save crop sub photo not yet done ! save time : 1.9202563762664795 nb_obj : 15 nb_hashtags : 3 time to prepare the origin masks : 7.524763107299805 time for calcul the mask position with numpy : 0.7803659439086914 nb_pixel_total : 7061445 time to create 1 rle with new method : 2.1047282218933105 time for calcul the mask position with numpy : 0.027640581130981445 nb_pixel_total : 14212 time to create 1 rle with old method : 0.01643991470336914 time for calcul the mask position with numpy : 0.028992414474487305 nb_pixel_total : 45502 time to create 1 rle with old method : 0.0522463321685791 time for calcul the mask position with numpy : 0.027570724487304688 nb_pixel_total : 37563 time to create 1 rle with old method : 0.043375492095947266 time for calcul the mask position with numpy : 0.03542184829711914 nb_pixel_total : 72716 time to create 1 rle with old method : 0.08492255210876465 time for calcul the mask position with numpy : 0.04923701286315918 nb_pixel_total : 6325 time to create 1 rle with old method : 0.007413148880004883 time for calcul the mask position with numpy : 0.047823190689086914 nb_pixel_total : 80381 time to create 1 rle with old method : 0.09059309959411621 time for calcul the mask position with numpy : 0.043669939041137695 nb_pixel_total : 55177 time to create 1 rle with old method : 0.0616912841796875 time for calcul the mask position with numpy : 0.043515682220458984 nb_pixel_total : 48955 time to create 1 rle with old method : 0.06849503517150879 time for calcul the mask position with numpy : 0.03960084915161133 nb_pixel_total : 76331 time to create 1 rle with old method : 0.10141158103942871 time for calcul the mask position with numpy : 0.04601430892944336 nb_pixel_total : 9332 time to create 1 rle with old method : 0.010529756546020508 time for calcul the mask position with numpy : 0.0398101806640625 nb_pixel_total : 44515 time to create 1 rle with old method : 0.04935288429260254 time for calcul the mask position with numpy : 0.040735483169555664 nb_pixel_total : 132789 time to create 1 rle with old method : 0.14900803565979004 time for calcul the mask position with numpy : 0.03708314895629883 nb_pixel_total : 152189 time to create 1 rle with new method : 0.5108141899108887 time for calcul the mask position with numpy : 0.026096105575561523 nb_pixel_total : 174865 time to create 1 rle with new method : 0.6685075759887695 time for calcul the mask position with numpy : 0.02640843391418457 nb_pixel_total : 282103 time to create 1 rle with new method : 0.5241947174072266 create new chi : 6.014646053314209 time to delete rle : 0.002126455307006836 batch 1 Loaded 31 chid ids of type : 3594 ++++++++++++++++++Number RLEs to save : 12345 TO DO : save crop sub photo not yet done ! save time : 2.871673107147217 nb_obj : 27 nb_hashtags : 2 time to prepare the origin masks : 5.085648059844971 time for calcul the mask position with numpy : 0.40633702278137207 nb_pixel_total : 5980681 time to create 1 rle with new method : 0.425555944442749 time for calcul the mask position with numpy : 0.034333229064941406 nb_pixel_total : 36435 time to create 1 rle with old method : 0.04024457931518555 time for calcul the mask position with numpy : 0.0341191291809082 nb_pixel_total : 457 time to create 1 rle with old method : 0.0006115436553955078 time for calcul the mask position with numpy : 0.04143810272216797 nb_pixel_total : 417328 time to create 1 rle with new method : 0.3893163204193115 time for calcul the mask position with numpy : 0.0345454216003418 nb_pixel_total : 30148 time to create 1 rle with old method : 0.033722877502441406 time for calcul the mask position with numpy : 0.03477764129638672 nb_pixel_total : 93951 time to create 1 rle with old method : 0.10543608665466309 time for calcul the mask position with numpy : 0.034305572509765625 nb_pixel_total : 66695 time to create 1 rle with old method : 0.07417488098144531 time for calcul the mask position with numpy : 0.034453630447387695 nb_pixel_total : 74864 time to create 1 rle with old method : 0.08342456817626953 time for calcul the mask position with numpy : 0.0341801643371582 nb_pixel_total : 21378 time to create 1 rle with old method : 0.023996353149414062 time for calcul the mask position with numpy : 0.03523135185241699 nb_pixel_total : 305477 time to create 1 rle with new method : 0.4480304718017578 time for calcul the mask position with numpy : 0.034529924392700195 nb_pixel_total : 42734 time to create 1 rle with old method : 0.04799342155456543 time for calcul the mask position with numpy : 0.03507423400878906 nb_pixel_total : 197694 time to create 1 rle with new method : 0.40563488006591797 time for calcul the mask position with numpy : 0.034598588943481445 nb_pixel_total : 31069 time to create 1 rle with old method : 0.03522324562072754 time for calcul the mask position with numpy : 0.035607337951660156 nb_pixel_total : 346197 time to create 1 rle with new method : 0.9610469341278076 time for calcul the mask position with numpy : 0.035204172134399414 nb_pixel_total : 216219 time to create 1 rle with new method : 0.7629706859588623 time for calcul the mask position with numpy : 0.03477025032043457 nb_pixel_total : 8744 time to create 1 rle with old method : 0.009942770004272461 time for calcul the mask position with numpy : 0.03775167465209961 nb_pixel_total : 17589 time to create 1 rle with old method : 0.0196688175201416 time for calcul the mask position with numpy : 0.034891366958618164 nb_pixel_total : 73213 time to create 1 rle with old method : 0.08223605155944824 time for calcul the mask position with numpy : 0.03454399108886719 nb_pixel_total : 17071 time to create 1 rle with old method : 0.019155502319335938 time for calcul the mask position with numpy : 0.03531312942504883 nb_pixel_total : 108394 time to create 1 rle with old method : 0.1205744743347168 time for calcul the mask position with numpy : 0.03457045555114746 nb_pixel_total : 19706 time to create 1 rle with old method : 0.022080659866333008 time for calcul the mask position with numpy : 0.034287452697753906 nb_pixel_total : 9572 time to create 1 rle with old method : 0.010796308517456055 time for calcul the mask position with numpy : 0.03456854820251465 nb_pixel_total : 9117 time to create 1 rle with old method : 0.010713577270507812 time for calcul the mask position with numpy : 0.03466153144836426 nb_pixel_total : 26093 time to create 1 rle with old method : 0.031046390533447266 time for calcul the mask position with numpy : 0.036832332611083984 nb_pixel_total : 31771 time to create 1 rle with old method : 0.03615069389343262 time for calcul the mask position with numpy : 0.03547096252441406 nb_pixel_total : 15537 time to create 1 rle with old method : 0.017809629440307617 time for calcul the mask position with numpy : 0.03682279586791992 nb_pixel_total : 58959 time to create 1 rle with old method : 0.06495928764343262 time for calcul the mask position with numpy : 0.03615093231201172 nb_pixel_total : 37307 time to create 1 rle with old method : 0.04354405403137207 create new chi : 6.0036256313323975 time to delete rle : 0.003925800323486328 batch 1 Loaded 55 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++Number RLEs to save : 23805 TO DO : save crop sub photo not yet done ! save time : 6.400266647338867 nb_obj : 26 nb_hashtags : 3 time to prepare the origin masks : 4.2182228565216064 time for calcul the mask position with numpy : 0.6274011135101318 nb_pixel_total : 7160911 time to create 1 rle with new method : 1.014204502105713 time for calcul the mask position with numpy : 0.03439044952392578 nb_pixel_total : 18196 time to create 1 rle with old method : 0.020349979400634766 time for calcul the mask position with numpy : 0.034245967864990234 nb_pixel_total : 8826 time to create 1 rle with old method : 0.010003805160522461 time for calcul the mask position with numpy : 0.03453469276428223 nb_pixel_total : 43258 time to create 1 rle with old method : 0.04833865165710449 time for calcul the mask position with numpy : 0.03444552421569824 nb_pixel_total : 21513 time to create 1 rle with old method : 0.02416515350341797 time for calcul the mask position with numpy : 0.03422379493713379 nb_pixel_total : 5521 time to create 1 rle with old method : 0.006471872329711914 time for calcul the mask position with numpy : 0.03508710861206055 nb_pixel_total : 95868 time to create 1 rle with old method : 0.10849380493164062 time for calcul the mask position with numpy : 0.0348665714263916 nb_pixel_total : 88454 time to create 1 rle with old method : 0.10057377815246582 time for calcul the mask position with numpy : 0.03440237045288086 nb_pixel_total : 21515 time to create 1 rle with old method : 0.024306058883666992 time for calcul the mask position with numpy : 0.03614616394042969 nb_pixel_total : 13626 time to create 1 rle with old method : 0.015365839004516602 time for calcul the mask position with numpy : 0.034996986389160156 nb_pixel_total : 225642 time to create 1 rle with new method : 0.6218650341033936 time for calcul the mask position with numpy : 0.0344080924987793 nb_pixel_total : 35805 time to create 1 rle with old method : 0.03997468948364258 time for calcul the mask position with numpy : 0.03442263603210449 nb_pixel_total : 62090 time to create 1 rle with old method : 0.06853985786437988 time for calcul the mask position with numpy : 0.03431963920593262 nb_pixel_total : 29112 time to create 1 rle with old method : 0.03239250183105469 time for calcul the mask position with numpy : 0.05422496795654297 nb_pixel_total : 57249 time to create 1 rle with old method : 0.0637044906616211 time for calcul the mask position with numpy : 0.041878461837768555 nb_pixel_total : 90978 time to create 1 rle with old method : 0.1022958755493164 time for calcul the mask position with numpy : 0.04124331474304199 nb_pixel_total : 32991 time to create 1 rle with old method : 0.036865234375 time for calcul the mask position with numpy : 0.03790783882141113 nb_pixel_total : 41995 time to create 1 rle with old method : 0.04714155197143555 time for calcul the mask position with numpy : 0.03445005416870117 nb_pixel_total : 18369 time to create 1 rle with old method : 0.020847082138061523 time for calcul the mask position with numpy : 0.034256696701049805 nb_pixel_total : 14144 time to create 1 rle with old method : 0.015838623046875 time for calcul the mask position with numpy : 0.03431558609008789 nb_pixel_total : 59874 time to create 1 rle with old method : 0.06754207611083984 time for calcul the mask position with numpy : 0.03448033332824707 nb_pixel_total : 40564 time to create 1 rle with old method : 0.045912981033325195 time for calcul the mask position with numpy : 0.03427696228027344 nb_pixel_total : 22143 time to create 1 rle with old method : 0.02489638328552246 time for calcul the mask position with numpy : 0.03428363800048828 nb_pixel_total : 17106 time to create 1 rle with old method : 0.019243240356445312 time for calcul the mask position with numpy : 0.03438210487365723 nb_pixel_total : 25158 time to create 1 rle with old method : 0.028174400329589844 time for calcul the mask position with numpy : 0.03443312644958496 nb_pixel_total : 21856 time to create 1 rle with old method : 0.024651288986206055 time for calcul the mask position with numpy : 0.03445124626159668 nb_pixel_total : 21636 time to create 1 rle with old method : 0.024196386337280273 create new chi : 4.286164045333862 time to delete rle : 0.16057729721069336 batch 1 Loaded 53 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 16339 TO DO : save crop sub photo not yet done ! save time : 3.7848739624023438 nb_obj : 27 nb_hashtags : 3 time to prepare the origin masks : 4.579419851303101 time for calcul the mask position with numpy : 0.6165764331817627 nb_pixel_total : 6890396 time to create 1 rle with new method : 0.5564937591552734 time for calcul the mask position with numpy : 0.034447431564331055 nb_pixel_total : 9850 time to create 1 rle with old method : 0.012588977813720703 time for calcul the mask position with numpy : 0.03577995300292969 nb_pixel_total : 22048 time to create 1 rle with old method : 0.027141809463500977 time for calcul the mask position with numpy : 0.03652238845825195 nb_pixel_total : 112823 time to create 1 rle with old method : 0.1352393627166748 time for calcul the mask position with numpy : 0.03619527816772461 nb_pixel_total : 55261 time to create 1 rle with old method : 0.06939244270324707 time for calcul the mask position with numpy : 0.036535024642944336 nb_pixel_total : 76587 time to create 1 rle with old method : 0.08751583099365234 time for calcul the mask position with numpy : 0.03439950942993164 nb_pixel_total : 73662 time to create 1 rle with old method : 0.08149266242980957 time for calcul the mask position with numpy : 0.03456377983093262 nb_pixel_total : 91531 time to create 1 rle with old method : 0.10716605186462402 time for calcul the mask position with numpy : 0.03411078453063965 nb_pixel_total : 98836 time to create 1 rle with old method : 0.11904788017272949 time for calcul the mask position with numpy : 0.03569364547729492 nb_pixel_total : 37520 time to create 1 rle with old method : 0.0462803840637207 time for calcul the mask position with numpy : 0.03534817695617676 nb_pixel_total : 79192 time to create 1 rle with old method : 0.10103774070739746 time for calcul the mask position with numpy : 0.03966116905212402 nb_pixel_total : 10945 time to create 1 rle with old method : 0.017735719680786133 time for calcul the mask position with numpy : 0.037507057189941406 nb_pixel_total : 35496 time to create 1 rle with old method : 0.046180009841918945 time for calcul the mask position with numpy : 0.03780078887939453 nb_pixel_total : 52465 time to create 1 rle with old method : 0.06684017181396484 time for calcul the mask position with numpy : 0.036795616149902344 nb_pixel_total : 18271 time to create 1 rle with old method : 0.030060768127441406 time for calcul the mask position with numpy : 0.0410304069519043 nb_pixel_total : 105546 time to create 1 rle with old method : 0.1322932243347168 time for calcul the mask position with numpy : 0.03907132148742676 nb_pixel_total : 19535 time to create 1 rle with old method : 0.026531457901000977 time for calcul the mask position with numpy : 0.03789806365966797 nb_pixel_total : 39262 time to create 1 rle with old method : 0.04850625991821289 time for calcul the mask position with numpy : 0.039301395416259766 nb_pixel_total : 125901 time to create 1 rle with old method : 0.16011977195739746 time for calcul the mask position with numpy : 0.03524613380432129 nb_pixel_total : 65327 time to create 1 rle with old method : 0.07912063598632812 time for calcul the mask position with numpy : 0.03695178031921387 nb_pixel_total : 38015 time to create 1 rle with old method : 0.044400691986083984 time for calcul the mask position with numpy : 0.037287235260009766 nb_pixel_total : 13129 time to create 1 rle with old method : 0.01574540138244629 time for calcul the mask position with numpy : 0.03718304634094238 nb_pixel_total : 26697 time to create 1 rle with old method : 0.03406214714050293 time for calcul the mask position with numpy : 0.03605151176452637 nb_pixel_total : 100264 time to create 1 rle with old method : 0.12023043632507324 time for calcul the mask position with numpy : 0.03623604774475098 nb_pixel_total : 6786 time to create 1 rle with old method : 0.008760690689086914 time for calcul the mask position with numpy : 0.03633880615234375 nb_pixel_total : 53836 time to create 1 rle with old method : 0.0645132064819336 time for calcul the mask position with numpy : 0.03471207618713379 nb_pixel_total : 29557 time to create 1 rle with old method : 0.0327908992767334 time for calcul the mask position with numpy : 0.03436589241027832 nb_pixel_total : 5662 time to create 1 rle with old method : 0.006367921829223633 create new chi : 3.9234917163848877 time to delete rle : 0.0031905174255371094 batch 1 Loaded 55 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 19478 TO DO : save crop sub photo not yet done ! save time : 6.575790166854858 map_output_result : {1370462805: (0.0, 'Should be the crop_list due to order', 0.0), 1370462802: (0.0, 'Should be the crop_list due to order', 0), 1370462799: (0.0, 'Should be the crop_list due to order', 0), 1370462797: (0.0, 'Should be the crop_list due to order', 0), 1370462703: (0.0, 'Should be the crop_list due to order', 0), 1370462702: (0.0, 'Should be the crop_list due to order', 0), 1370462701: (0.0, 'Should be the crop_list due to order', 0), 1370462700: (0.0, 'Should be the crop_list due to order', 0), 1370462699: (0.0, 'Should be the crop_list due to order', 0), 1370462698: (0.0, 'Should be the crop_list due to order', 0), 1370462676: (0.0, 'Should be the crop_list due to order', 0), 1370462675: (0.0, 'Should be the crop_list due to order', 0), 1370462673: (0.0, 'Should be the crop_list due to order', 0), 1370462672: (0.0, 'Should be the crop_list due to order', 0), 1370462671: (0.0, 'Should be the crop_list due to order', 0), 1370462583: (0.0, 'Should be the crop_list due to order', 0), 1370462582: (0.0, 'Should be the crop_list due to order', 0), 1370462581: (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 [1370462805, 1370462802, 1370462799, 1370462797, 1370462703, 1370462702, 1370462701, 1370462700, 1370462699, 1370462698, 1370462676, 1370462675, 1370462673, 1370462672, 1370462671, 1370462583, 1370462582, 1370462581] Looping around the photos to save general results len do output : 18 /1370462805.Didn't retrieve data . /1370462802.Didn't retrieve data . /1370462799.Didn't retrieve data . /1370462797.Didn't retrieve data . /1370462703.Didn't retrieve data . /1370462702.Didn't retrieve data . /1370462701.Didn't retrieve data . /1370462700.Didn't retrieve data . /1370462699.Didn't retrieve data . /1370462698.Didn't retrieve data . /1370462676.Didn't retrieve data . /1370462675.Didn't retrieve data . /1370462673.Didn't retrieve data . /1370462672.Didn't retrieve data . /1370462671.Didn't retrieve data . /1370462583.Didn't retrieve data . /1370462582.Didn't retrieve data . /1370462581.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, '3234682') ('3318', '24581312', '1370462805', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462802', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462799', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462797', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462703', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462702', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462701', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462700', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462699', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462698', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462676', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462675', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462673', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462672', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462671', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462583', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462582', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462581', None, None, None, None, None, '3234682') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 54 time used for this insertion : 0.01578521728515625 save_final save missing photos in datou_result : time spend for datou_step_exec : 302.0922758579254 time spend to save output : 0.0533137321472168 total time spend for step 3 : 302.14558959007263 step4:ventilate_hashtags_in_portfolio Fri Jul 4 09:15:34 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 : 24581312 get user id for portfolio 24581312 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`=24581312 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pehd','pet_clair','environnement','papier','autre','metal','mal_croppe','background','pet_fonce','carton','flou')) 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`=24581312 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pehd','pet_clair','environnement','papier','autre','metal','mal_croppe','background','pet_fonce','carton','flou')) AND mptpi.`min_score`=0.5 To do To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=24581312 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pehd','pet_clair','environnement','papier','autre','metal','mal_croppe','background','pet_fonce','carton','flou')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://www.fotonower.com/velours/24583719,24583720,24583721,24583722,24583723,24583724,24583725,24583726,24583727,24583728,24583729?tags=pehd,pet_clair,environnement,papier,autre,metal,mal_croppe,background,pet_fonce,carton,flou Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1370462805, 1370462802, 1370462799, 1370462797, 1370462703, 1370462702, 1370462701, 1370462700, 1370462699, 1370462698, 1370462676, 1370462675, 1370462673, 1370462672, 1370462671, 1370462583, 1370462582, 1370462581] Looping around the photos to save general results len do output : 1 /24581312. 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, '3234682') ('3318', '24581312', '1370462805', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462802', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462799', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462797', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462703', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462702', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462701', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462700', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462699', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462698', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462676', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462675', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462673', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462672', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462671', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462583', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462582', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462581', None, None, None, None, None, '3234682') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 19 time used for this insertion : 0.018696069717407227 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.8409767150878906 time spend to save output : 0.024103164672851562 total time spend for step 4 : 1.8650798797607422 step5:final Fri Jul 4 09:15:36 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 : {1370462805: ('0.15940108855238333',), 1370462802: ('0.15940108855238333',), 1370462799: ('0.15940108855238333',), 1370462797: ('0.15940108855238333',), 1370462703: ('0.15940108855238333',), 1370462702: ('0.15940108855238333',), 1370462701: ('0.15940108855238333',), 1370462700: ('0.15940108855238333',), 1370462699: ('0.15940108855238333',), 1370462698: ('0.15940108855238333',), 1370462676: ('0.15940108855238333',), 1370462675: ('0.15940108855238333',), 1370462673: ('0.15940108855238333',), 1370462672: ('0.15940108855238333',), 1370462671: ('0.15940108855238333',), 1370462583: ('0.15940108855238333',), 1370462582: ('0.15940108855238333',), 1370462581: ('0.15940108855238333',)} new output for save of step final : {1370462805: ('0.15940108855238333',), 1370462802: ('0.15940108855238333',), 1370462799: ('0.15940108855238333',), 1370462797: ('0.15940108855238333',), 1370462703: ('0.15940108855238333',), 1370462702: ('0.15940108855238333',), 1370462701: ('0.15940108855238333',), 1370462700: ('0.15940108855238333',), 1370462699: ('0.15940108855238333',), 1370462698: ('0.15940108855238333',), 1370462676: ('0.15940108855238333',), 1370462675: ('0.15940108855238333',), 1370462673: ('0.15940108855238333',), 1370462672: ('0.15940108855238333',), 1370462671: ('0.15940108855238333',), 1370462583: ('0.15940108855238333',), 1370462582: ('0.15940108855238333',), 1370462581: ('0.15940108855238333',)} [1370462805, 1370462802, 1370462799, 1370462797, 1370462703, 1370462702, 1370462701, 1370462700, 1370462699, 1370462698, 1370462676, 1370462675, 1370462673, 1370462672, 1370462671, 1370462583, 1370462582, 1370462581] Looping around the photos to save general results len do output : 18 /1370462805.Didn't retrieve data . /1370462802.Didn't retrieve data . /1370462799.Didn't retrieve data . /1370462797.Didn't retrieve data . /1370462703.Didn't retrieve data . /1370462702.Didn't retrieve data . /1370462701.Didn't retrieve data . /1370462700.Didn't retrieve data . /1370462699.Didn't retrieve data . /1370462698.Didn't retrieve data . /1370462676.Didn't retrieve data . /1370462675.Didn't retrieve data . /1370462673.Didn't retrieve data . /1370462672.Didn't retrieve data . /1370462671.Didn't retrieve data . /1370462583.Didn't retrieve data . /1370462582.Didn't retrieve data . /1370462581.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, '3234682') ('3318', '24581312', '1370462805', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462802', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462799', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462797', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462703', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462702', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462701', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462700', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462699', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462698', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462676', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462675', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462673', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462672', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462671', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462583', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462582', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462581', None, None, None, None, None, '3234682') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 54 time used for this insertion : 0.018140554428100586 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.3906571865081787 time spend to save output : 0.021337032318115234 total time spend for step 5 : 0.41199421882629395 step6:blur_detection Fri Jul 4 09:15:37 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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/1751612427_708613_1370462805_92baa68020fe11e6d5850e303ae1500b_32504942.jpg resize: (2160, 3840) 1370462805 -6.53074096576479 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708.jpg resize: (2160, 3840) 1370462802 -6.830635050193761 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047.jpg resize: (2160, 3840) 1370462799 -7.120642533700665 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850.jpg resize: (2160, 3840) 1370462797 -7.121749218598173 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881.jpg resize: (2160, 3840) 1370462703 -7.304475533392903 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556.jpg resize: (2160, 3840) 1370462702 -7.158017882525462 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882.jpg resize: (2160, 3840) 1370462701 -7.103082801927135 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584.jpg resize: (2160, 3840) 1370462700 -7.076696675962365 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432.jpg resize: (2160, 3840) 1370462699 -7.3918239638307215 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484.jpg resize: (2160, 3840) 1370462698 -7.282015724582517 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304.jpg resize: (2160, 3840) 1370462676 -7.268429981977539 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497.jpg resize: (2160, 3840) 1370462675 -7.2303132294297665 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813.jpg resize: (2160, 3840) 1370462673 -7.326071268790546 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791.jpg resize: (2160, 3840) 1370462672 -7.122897407798106 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350.jpg resize: (2160, 3840) 1370462671 -7.123164742489054 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737.jpg resize: (2160, 3840) 1370462583 -7.234960959084353 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746.jpg resize: (2160, 3840) 1370462582 -7.234587788309596 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435.jpg resize: (2160, 3840) 1370462581 -7.096545403946157 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563689_0.png resize: (180, 139) 1370510582 -2.6089076377685743 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563698_0.png resize: (217, 363) 1370510583 -4.736018211986017 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563686_0.png resize: (254, 290) 1370510584 -3.858907433543374 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563697_0.png resize: (369, 371) 1370510585 -1.9216918404107224 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563690_0.png resize: (104, 219) 1370510586 -5.09905440528434 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563691_0.png resize: (345, 236) 1370510587 -3.7528880096014134 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563688_0.png resize: (200, 106) 1370510588 -3.3505817567066325 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563693_0.png resize: (194, 167) 1370510589 0.5977549575745423 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563687_0.png resize: (212, 116) 1370510590 -4.429581976620396 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563699_0.png resize: (234, 137) 1370510591 1.6644900716745 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563718_0.png resize: (941, 674) 1370510592 -4.1809379973140635 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563704_0.png resize: (293, 151) 1370510593 -3.189191205788317 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563721_0.png resize: (313, 84) 1370510594 -3.0701759366070167 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563714_0.png resize: (459, 202) 1370510595 -4.005002279212452 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563715_0.png resize: (323, 177) 1370510596 -3.3301093684929013 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563705_0.png resize: (151, 204) 1370510597 -3.58599845085388 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563722_0.png resize: (147, 121) 1370510598 -4.634944371401261 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563701_0.png resize: (225, 97) 1370510599 -4.4347149172716565 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563707_0.png resize: (123, 203) 1370510600 -1.126016853805773 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563717_0.png resize: (116, 68) 1370510601 -2.780468031333778 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563727_0.png resize: (188, 266) 1370510602 -3.4961592393770142 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563716_0.png resize: (90, 149) 1370510604 -3.2923770762253484 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563700_0.png resize: (192, 173) 1370510606 -3.536129315841677 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563710_0.png resize: (320, 535) 1370510607 -3.3397305730317637 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563703_0.png resize: (319, 1006) 1370510608 -2.4216549871640893 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563706_0.png resize: (461, 499) 1370510609 -2.4496515938209966 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563726_0.png resize: (268, 281) 1370510610 -3.4085516708351697 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563728_0.png resize: (170, 246) 1370510611 -3.9616508553754493 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563719_0.png resize: (373, 449) 1370510612 -3.961363334846378 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563720_0.png resize: (331, 182) 1370510613 -3.6840463977451456 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563712_0.png resize: (370, 400) 1370510614 -4.535206775012049 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563709_0.png resize: (350, 295) 1370510615 -0.9677883316640812 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563713_0.png resize: (451, 127) 1370510616 -2.755019633272537 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563711_0.png resize: (346, 143) 1370510617 -4.400017147066179 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563725_0.png resize: (220, 202) 1370510618 -1.7747487106583677 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563708_0.png resize: (141, 213) 1370510619 -3.248978693836067 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563702_0.png resize: (274, 115) 1370510620 4.785953373605917 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563724_0.png resize: (160, 180) 1370510621 -4.026597348773167 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563736_0.png resize: (384, 271) 1370510622 -3.7933491028874253 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563731_0.png resize: (186, 520) 1370510623 -1.4960381098765048 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563745_0.png resize: (95, 227) 1370510624 -1.5820505882723759 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563732_0.png resize: (392, 263) 1370510625 -3.8138270852129885 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563740_0.png resize: (166, 150) 1370510626 -1.9892075601587813 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563741_0.png resize: (350, 279) 1370510627 -4.39108791124153 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563751_0.png resize: (113, 160) 1370510628 0.02878139832838685 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563739_0.png resize: (160, 172) 1370510629 -2.806122219449755 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563730_0.png resize: (290, 394) 1370510630 1.8939568920605503 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563735_0.png resize: (79, 126) 1370510631 -2.540976504719531 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563738_0.png resize: (143, 340) 1370510633 -3.278915104303947 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563749_0.png resize: (258, 301) 1370510634 -0.45091637826254244 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563742_0.png resize: (286, 112) 1370510635 -1.3246607530240067 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563733_0.png resize: (269, 184) 1370510636 -3.1555859401633906 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563729_0.png resize: (454, 454) 1370510637 -3.1380405935927955 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563737_0.png resize: (268, 164) 1370510638 -3.2484289842533784 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563746_0.png resize: (455, 384) 1370510639 -3.670199922302746 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563750_0.png resize: (436, 424) 1370510640 -4.941704886785757 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563754_0.png resize: (541, 223) 1370510641 -1.8815505773016081 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563758_0.png resize: (382, 387) 1370510643 -0.30645536920102145 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563752_0.png resize: (603, 442) 1370510644 -3.678539233934519 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563755_0.png resize: (242, 396) 1370510645 -0.4123364957056599 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563765_0.png resize: (325, 365) 1370510646 -4.506583300085398 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563766_0.png resize: (602, 664) 1370510648 -3.655857778474132 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563757_0.png resize: (382, 215) 1370510649 -0.8329107259332281 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563762_0.png resize: (334, 341) 1370510650 1.104284120220781 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563753_0.png resize: (675, 526) 1370510652 -5.074636422595153 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563767_0.png resize: (351, 289) 1370510653 -3.5970956664307763 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563768_0.png resize: (467, 420) 1370510654 0.14621138269370157 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563763_0.png resize: (118, 123) 1370510655 -2.8468687842433464 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563761_0.png resize: (271, 220) 1370510657 -1.698708695913627 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563756_0.png resize: (132, 229) 1370510658 -3.259489462790199 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563785_0.png resize: (432, 173) 1370510659 -3.1772710793060566 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563777_0.png resize: (330, 176) 1370510661 -5.266256444380314 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563769_0.png resize: (375, 444) 1370510662 -0.07979298796708485 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563782_0.png resize: (499, 266) 1370510663 0.521271747131184 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563783_0.png resize: (76, 210) 1370510664 -2.8263052865909652 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563773_0.png resize: (96, 140) 1370510666 0.11155866086032201 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563791_0.png resize: (164, 289) 1370510667 0.19909703679622798 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563774_0.png resize: (192, 276) 1370510668 -0.16748549597354592 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563792_0.png resize: (283, 341) 1370510669 0.33333009886654164 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563793_0.png resize: (145, 275) 1370510670 -4.5159479307811035 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563780_0.png resize: (279, 324) 1370510671 -3.5324244574275827 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563787_0.png resize: (223, 190) 1370510672 -3.793989432937906 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563784_0.png resize: (237, 200) 1370510673 -4.488159731956424 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563786_0.png resize: (187, 164) 1370510674 -2.8551570132151114 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563779_0.png resize: (404, 533) 1370510675 -2.224377361603201 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563781_0.png resize: (63, 118) 1370510676 -4.2319569424543015 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563770_0.png resize: (655, 880) 1370510677 -3.874084726342853 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563776_0.png resize: (125, 341) 1370510678 -1.9769256217088444 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563772_0.png resize: (503, 272) 1370510679 -2.6065433256443447 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563789_0.png resize: (220, 160) 1370510680 -3.5960014630252846 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563788_0.png resize: (210, 156) 1370510681 -4.932138360348204 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563775_0.png resize: (257, 213) 1370510682 -4.5140665587654265 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563799_0.png resize: (299, 526) 1370510683 -2.1655458805647694 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563796_0.png resize: (260, 252) 1370510684 -2.6360176690809514 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563818_0.png resize: (202, 202) 1370510685 -3.0991557440295767 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563802_0.png resize: (166, 277) 1370510686 -2.6409317535278483 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563803_0.png resize: (290, 337) 1370510687 -3.560546539908387 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563819_0.png resize: (573, 598) 1370510688 -1.9533121546350305 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563801_0.png resize: (65, 148) 1370510689 -2.2405915134812258 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563795_0.png resize: (441, 386) 1370510690 -2.364173841064909 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563797_0.png resize: (151, 263) 1370510691 -3.4647517739482154 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563794_0.png resize: (206, 223) 1370510692 -2.6831967782745734 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563817_0.png resize: (237, 158) 1370510693 -2.684086190875915 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563800_0.png resize: (279, 252) 1370510694 -1.930476633532447 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563812_0.png resize: (183, 227) 1370510695 -0.7614690812339528 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563807_0.png resize: (183, 172) 1370510696 -2.950341330516441 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563798_0.png resize: (393, 389) 1370510697 -4.7978712991263075 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563815_0.png resize: (328, 253) 1370510698 -4.476336352624536 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563811_0.png resize: (379, 276) 1370510699 -4.3827195341957115 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563806_0.png resize: (232, 174) 1370510700 -4.58622364463479 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563809_0.png resize: (341, 324) 1370510701 -3.9108026876570765 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563822_0.png resize: (336, 211) 1370510702 -2.664187692204066 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563824_0.png resize: (174, 175) 1370510703 -3.7596253991205106 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563808_0.png resize: (276, 188) 1370510704 -3.8154247063683484 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563813_0.png resize: (209, 259) 1370510705 -4.061999072316582 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563821_0.png resize: (275, 237) 1370510706 -3.8232217819356724 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563825_0.png resize: (513, 136) 1370510707 5.623947219728224 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563835_0.png resize: (233, 273) 1370510708 -2.860898320762478 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563826_0.png resize: (458, 117) 1370510709 -4.9331282806922285 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563830_0.png resize: (555, 674) 1370510710 1.2002852279565217 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563827_0.png resize: (349, 288) 1370510711 -3.508738840835229 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563832_0.png resize: (196, 263) 1370510712 -3.8779763643599194 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563828_0.png resize: (216, 234) 1370510714 -3.6937591073543734 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563841_0.png resize: (829, 481) 1370510715 -5.4798133885157005 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563837_0.png resize: (122, 217) 1370510716 -0.41802662183737443 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563840_0.png resize: (330, 320) 1370510717 -3.1382963090734712 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563833_0.png resize: (171, 232) 1370510718 -1.7962661395838289 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563838_0.png resize: (515, 260) 1370510719 -0.7085697645472868 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563843_0.png resize: (192, 164) 1370510721 -1.3498306703933844 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563845_0.png resize: (433, 695) 1370510722 -3.5759348112882776 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563834_0.png resize: (392, 220) 1370510724 -2.9161548189354085 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563844_0.png resize: (411, 440) 1370510725 -4.48883607666053 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563851_0.png resize: (379, 201) 1370510726 -0.20157421518217977 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563869_0.png resize: (244, 157) 1370510727 -2.7540587479120586 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563847_0.png resize: (320, 476) 1370510728 -4.440812653270572 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563852_0.png resize: (641, 899) 1370510729 -4.471957767478828 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563855_0.png resize: (148, 576) 1370510731 -1.241220096845472 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563848_0.png resize: (256, 231) 1370510733 -3.460191095976612 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563864_0.png resize: (443, 291) 1370510734 -3.5750203510631042 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563846_0.png resize: (315, 274) 1370510735 -3.14167278960578 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563862_0.png resize: (371, 612) 1370510736 -4.317037267452944 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563853_0.png resize: (431, 251) 1370510738 -5.00534346632151 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563859_0.png resize: (154, 206) 1370510739 -3.2214092341084575 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563854_0.png resize: (323, 235) 1370510740 -4.470405502732419 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563850_0.png resize: (514, 486) 1370510741 -3.9013003339350654 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563856_0.png resize: (323, 405) 1370510742 -5.016543376986538 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563860_0.png resize: (312, 323) 1370510743 -4.870254850469305 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563861_0.png resize: (421, 353) 1370510744 -4.41000274019024 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563849_0.png resize: (400, 431) 1370510745 -4.604051312777991 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563868_0.png resize: (267, 533) 1370510746 -3.9238950601515583 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563865_0.png resize: (432, 350) 1370510747 -3.952627757000618 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563858_0.png resize: (367, 437) 1370510748 -2.8115139940113485 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563857_0.png resize: (250, 185) 1370510749 -2.292381994208827 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563866_0.png resize: (135, 108) 1370510750 -3.336571245316996 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563863_0.png resize: (169, 183) 1370510751 -1.457438495483804 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563883_0.png resize: (403, 130) 1370510752 -4.296832141221843 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563878_0.png resize: (114, 69) 1370510753 7.926241206822912 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563882_0.png resize: (139, 453) 1370510754 -1.4895262591317773 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563872_0.png resize: (333, 510) 1370510755 -2.38674134917689 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563873_0.png resize: (184, 274) 1370510756 -1.6848429032820678 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563877_0.png resize: (152, 289) 1370510757 -4.230075055121837 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563874_0.png resize: (113, 227) 1370510758 -4.845102124540976 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563879_0.png resize: (574, 466) 1370510759 -4.852662116290386 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563876_0.png resize: (457, 76) 1370510760 -2.6811918161591057 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563870_0.png resize: (173, 133) 1370510761 -4.487001802398317 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563900_0.png resize: (268, 312) 1370510762 -3.59048792837979 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563886_0.png resize: (366, 512) 1370510763 0.6045215291548542 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563889_0.png resize: (269, 248) 1370510764 -0.9842135706636915 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563891_0.png resize: (490, 186) 1370510765 -3.6688412866182896 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563899_0.png resize: (147, 114) 1370510766 -4.398342784411678 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563890_0.png resize: (428, 282) 1370510767 -4.5266419010045675 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563894_0.png resize: (144, 179) 1370510768 2.577506515072943 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563892_0.png resize: (288, 413) 1370510769 -2.8236871206593745 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563888_0.png resize: (253, 365) 1370510770 -2.7495482709703403 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563909_0.png resize: (296, 219) 1370510771 -3.864679389029128 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563896_0.png resize: (99, 269) 1370510772 -1.3902860178040712 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563903_0.png resize: (146, 74) 1370510774 -4.789977514113317 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563902_0.png resize: (226, 98) 1370510775 -4.219989549452292 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563885_0.png resize: (378, 208) 1370510776 -1.8804036565282394 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563905_0.png resize: (353, 710) 1370510777 -5.081671133211294 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563895_0.png resize: (234, 167) 1370510779 -4.4235208932172485 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563897_0.png resize: (84, 189) 1370510780 -1.0702741554164044 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563906_0.png resize: (287, 177) 1370510781 -1.0545593792584624 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563898_0.png resize: (184, 152) 1370510782 -3.8241363288631303 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563884_0.png resize: (112, 170) 1370510783 -0.5224788872571594 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563904_0.png resize: (263, 267) 1370510784 -5.465806708793556 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563918_0.png resize: (812, 538) 1370510785 -3.6520518049080923 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563912_0.png resize: (295, 374) 1370510786 0.7454494316004535 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563922_0.png resize: (189, 172) 1370510787 -4.608895769371458 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563917_0.png resize: (204, 131) 1370510788 -2.037067682262192 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563913_0.png resize: (231, 397) 1370510789 0.04955953846322446 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563915_0.png resize: (82, 166) 1370510790 -4.295431598707463 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563919_0.png resize: (203, 186) 1370510791 -0.42957279407084575 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563910_0.png resize: (531, 230) 1370510792 -0.6886178894363686 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563916_0.png resize: (310, 413) 1370510793 -3.2672986106040325 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563914_0.png resize: (173, 285) 1370510794 -4.463918559744631 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563923_0.png resize: (201, 116) 1370510795 -2.9977273930411865 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563920_0.png resize: (301, 206) 1370510796 -3.1501715577457667 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563911_0.png resize: (410, 199) 1370510797 -3.7208042989128396 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563942_0.png resize: (800, 556) 1370510798 -2.352482970563363 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563948_0.png resize: (359, 408) 1370510799 -2.6670760914466336 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563927_0.png resize: (176, 152) 1370510800 3.8016362836155264 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563939_0.png resize: (172, 203) 1370510801 -1.5986901071672117 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563940_0.png resize: (293, 282) 1370510802 -4.391586078292216 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563950_0.png resize: (146, 135) 1370510803 -3.455534522092395 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563944_0.png resize: (678, 466) 1370510804 -4.107460957623989 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563929_0.png resize: (270, 233) 1370510805 -3.2204129751006243 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563946_0.png resize: (243, 354) 1370510806 -3.7929587521726567 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563932_0.png resize: (182, 315) 1370510807 -4.66451124000012 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563931_0.png resize: (461, 271) 1370510808 -3.6391483672103 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563934_0.png resize: (140, 157) 1370510809 -3.628825631860159 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563945_0.png resize: (315, 428) 1370510810 -3.2169202406745643 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563938_0.png resize: (181, 136) 1370510811 -4.7127625480503355 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563943_0.png resize: (434, 283) 1370510812 -4.665032367642349 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563941_0.png resize: (377, 256) 1370510813 -4.220855729652964 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563952_0.png resize: (313, 356) 1370510815 -4.908144262328614 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563928_0.png resize: (378, 272) 1370510816 -1.9818255333451988 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563930_0.png resize: (839, 613) 1370510817 -4.0936150405772365 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563926_0.png resize: (401, 359) 1370510818 2.2104425409647805 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563933_0.png resize: (181, 258) 1370510819 -4.867782527573725 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563937_0.png resize: (317, 377) 1370510820 -3.758982291115623 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563949_0.png resize: (87, 116) 1370510821 -3.964419396439231 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563947_0.png resize: (502, 448) 1370510822 -4.290680218204318 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563936_0.png resize: (148, 184) 1370510823 -3.2325802368764984 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563979_0.png resize: (341, 208) 1370510824 3.6199076928410463 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563953_0.png resize: (322, 299) 1370510825 -1.8162211019260668 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563977_0.png resize: (525, 625) 1370510826 -1.2721967400224465 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563967_0.png resize: (399, 608) 1370510827 -1.844206258465723 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563956_0.png resize: (450, 382) 1370510828 -2.79604399240399 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563969_0.png resize: (184, 228) 1370510829 -0.7103254098814745 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563962_0.png resize: (213, 134) 1370510830 0.01752411936466547 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563959_0.png resize: (176, 175) 1370510831 1.5714165430818405 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563978_0.png resize: (398, 485) 1370510833 -4.087448853661604 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563968_0.png resize: (474, 318) 1370510834 -5.226253482943541 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563957_0.png resize: (237, 190) 1370510835 -3.379403597875676 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563958_0.png resize: (133, 119) 1370510838 -2.644686840741224 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563955_0.png resize: (143, 235) 1370510839 2.416069279340463 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563973_0.png resize: (142, 211) 1370510840 -0.692142621658894 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563976_0.png resize: (418, 530) 1370510842 -4.085752813501298 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563965_0.png resize: (269, 375) 1370510843 -1.5699192383044636 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563960_0.png resize: (184, 282) 1370510844 -3.375267932528582 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563964_0.png resize: (245, 382) 1370510845 -3.7901035534682936 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563954_0.png resize: (328, 505) 1370510846 -4.0160802558412625 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563975_0.png resize: (289, 212) 1370510847 1.0705571251662218 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563972_0.png resize: (263, 545) 1370510848 -4.399559674819149 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563961_0.png resize: (126, 167) 1370510849 -2.3768534134329116 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563974_0.png resize: (205, 213) 1370510850 -3.5029755021255498 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563971_0.png resize: (285, 318) 1370510851 -1.3824816347214068 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563980_0.png resize: (291, 185) 1370510852 -3.8161597464755213 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563982_0.png resize: (396, 509) 1370510853 -4.933020132258276 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563989_0.png resize: (160, 391) 1370510854 -4.681845449412771 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563988_0.png resize: (319, 330) 1370510855 -3.0928767253678884 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563993_0.png resize: (230, 279) 1370510856 -3.677380450242178 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563985_0.png resize: (271, 255) 1370510857 -1.4199054705801852 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563981_0.png resize: (759, 590) 1370510858 0.04888821687797252 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563992_0.png resize: (291, 337) 1370510859 -1.7322687619228652 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563983_0.png resize: (317, 741) 1370510860 -2.952469323420434 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563987_0.png resize: (285, 398) 1370510862 -0.06278323066041203 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563991_0.png resize: (78, 117) 1370510863 -4.655156076520208 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563986_0.png resize: (128, 139) 1370510865 -0.4467287810082626 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563994_0.png resize: (370, 238) 1370510866 -3.3357905774337455 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563984_0.png resize: (763, 258) 1370510867 -1.5435350867349602 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564010_0.png resize: (1031, 518) 1370510868 -4.076802542961309 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564005_0.png resize: (195, 257) 1370510869 -2.2265207229358785 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564015_0.png resize: (869, 851) 1370510870 -2.956547163587673 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564012_0.png resize: (370, 217) 1370510871 -2.6636019292601887 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564020_0.png resize: (217, 97) 1370510872 -3.548279791528755 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564017_0.png resize: (599, 154) 1370510873 -3.3379598104288943 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564008_0.png resize: (176, 270) 1370510874 -2.1516959847486516 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564007_0.png resize: (320, 460) 1370510875 -1.2623281080336337 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564002_0.png resize: (557, 572) 1370510876 -1.5874491865232832 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564022_0.png resize: (254, 201) 1370510877 -1.8053277028417616 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871563997_0.png resize: (243, 194) 1370510878 -2.570941577698978 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564004_0.png resize: (461, 290) 1370510879 -2.39326882745483 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564003_0.png resize: (186, 138) 1370510880 -2.871190924447266 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564011_0.png resize: (281, 160) 1370510881 -4.525888385876544 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564006_0.png resize: (361, 240) 1370510882 -4.333564637549077 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564009_0.png resize: (553, 500) 1370510883 -4.2610482626410455 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871563996_0.png resize: (323, 331) 1370510884 -2.4346313065021317 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564019_0.png resize: (169, 91) 1370510885 -2.397203214010609 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564000_0.png resize: (372, 423) 1370510886 -3.188512292201456 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564013_0.png resize: (180, 85) 1370510887 -5.01385646707337 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564018_0.png resize: (761, 745) 1370510888 -3.1477137328191067 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871563998_0.png resize: (251, 105) 1370510890 -4.043069778682834 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564016_0.png resize: (182, 117) 1370510891 -1.3742277537328842 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564021_0.png resize: (103, 117) 1370510892 -1.7302675073091829 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564001_0.png resize: (615, 299) 1370510894 -3.8300320195545905 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564034_0.png resize: (264, 124) 1370510895 -3.454248654231918 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564036_0.png resize: (173, 102) 1370510896 -2.302060779579195 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564040_0.png resize: (117, 231) 1370510897 -2.85428157778129 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564033_0.png resize: (168, 176) 1370510898 -4.906317009824757 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564038_0.png resize: (261, 464) 1370510899 -4.505834459965966 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564032_0.png resize: (284, 322) 1370510900 -4.885674776044354 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564030_0.png resize: (142, 262) 1370510901 -3.115513259105463 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564042_0.png resize: (369, 1039) 1370510902 -3.2265490682433353 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564028_0.png resize: (176, 155) 1370510904 -1.4097222962405538 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564048_0.png resize: (159, 272) 1370510906 -2.983337031015109 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564037_0.png resize: (330, 369) 1370510907 -4.792075109364851 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564045_0.png resize: (203, 220) 1370510908 -4.326235129516773 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564025_0.png resize: (248, 264) 1370510910 0.7199557988944504 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564031_0.png resize: (326, 483) 1370510912 -3.148408328104747 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564046_0.png resize: (497, 769) 1370510913 -2.860279742610738 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564047_0.png resize: (201, 194) 1370510914 -3.4395529248614687 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564044_0.png resize: (291, 121) 1370510916 -3.4522204786039525 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564024_0.png resize: (177, 250) 1370510917 -1.783239731485263 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564041_0.png resize: (227, 106) 1370510918 -4.0998648437806775 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564035_0.png resize: (138, 323) 1370510920 -3.9705888991766325 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564074_0.png resize: (517, 147) 1370510921 -2.336941803544035 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564053_0.png resize: (176, 217) 1370510922 -3.2976902211510737 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564066_0.png resize: (187, 131) 1370510923 3.4686729368868607 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564049_0.png resize: (421, 313) 1370510925 -2.1228539411193355 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564063_0.png resize: (184, 228) 1370510926 -0.48830833599009893 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564071_0.png resize: (468, 271) 1370510927 -4.069081209534695 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564058_0.png resize: (137, 198) 1370510929 -3.300369311329902 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564052_0.png resize: (450, 399) 1370510930 -5.20581707420496 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564050_0.png resize: (283, 578) 1370510931 -0.8238873634578711 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564051_0.png resize: (180, 286) 1370510932 -2.1456049836957063 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564060_0.png resize: (481, 391) 1370510934 -3.6885362059498035 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564065_0.png resize: (127, 140) 1370510936 -0.9844776037610684 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564072_0.png resize: (94, 79) 1370510937 -2.458905219946785 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564064_0.png resize: (252, 257) 1370510938 -1.735326816107723 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564073_0.png resize: (281, 511) 1370510939 -2.9122731915894438 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564061_0.png resize: (458, 374) 1370510940 -4.511721831483534 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564054_0.png resize: (403, 477) 1370510941 -2.922770866345792 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564059_0.png resize: (394, 509) 1370510942 -0.9437269487988931 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564056_0.png resize: (323, 281) 1370510943 -2.6611716189510712 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564075_0.png resize: (335, 212) 1370510944 -2.69581295086812 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564062_0.png resize: (200, 363) 1370510945 -1.4492710225813972 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564055_0.png resize: (184, 303) 1370510946 3.238344764708857 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564057_0.png resize: (176, 254) 1370510947 -0.6352612961879247 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564067_0.png resize: (237, 68) 1370510948 -2.3818059408367493 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563695_0.png resize: (288, 250) 1370511037 -4.396935877706079 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563694_0.png resize: (155, 106) 1370511038 -4.2090391935264 treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563723_0.png resize: (160, 127) 1370511039 -2.5595758221058453 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563734_0.png resize: (205, 357) 1370511040 -4.584124572538009 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563747_0.png resize: (233, 482) 1370511041 -4.589908405044672 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563760_0.png resize: (284, 357) 1370511042 -4.763084099811706 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563764_0.png resize: (200, 262) 1370511043 -4.444399628872265 treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563759_0.png resize: (434, 290) 1370511044 -3.8345575703996637 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563771_0.png resize: (168, 215) 1370511045 -3.5852753769358494 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563805_0.png resize: (124, 135) 1370511046 -4.119050900141559 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563804_0.png resize: (191, 401) 1370511047 -3.2223600728541304 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563810_0.png resize: (310, 287) 1370511048 -5.381882484149124 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563814_0.png resize: (176, 273) 1370511049 -3.494033971213856 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563820_0.png resize: (170, 398) 1370511050 -4.302358189382981 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563816_0.png resize: (218, 86) 1370511051 -2.9716806723751907 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563842_0.png resize: (596, 741) 1370511052 -2.954679015289127 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563829_0.png resize: (346, 257) 1370511053 -2.568146798306442 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563831_0.png resize: (301, 267) 1370511054 -4.105415368255206 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563875_0.png resize: (386, 332) 1370511055 -5.22326795367523 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563880_0.png resize: (231, 345) 1370511056 -2.94299583390451 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563871_0.png resize: (124, 284) 1370511057 -3.0686216789287815 treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563881_0.png resize: (227, 186) 1370511058 -3.411337549092775 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563907_0.png resize: (204, 105) 1370511059 -3.271692163504803 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563887_0.png resize: (376, 277) 1370511060 -4.240460823442974 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563901_0.png resize: (357, 216) 1370511061 -4.359818675503087 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563921_0.png resize: (374, 404) 1370511062 -4.431873227494113 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563935_0.png resize: (258, 234) 1370511063 -4.435623592581865 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563970_0.png resize: (398, 251) 1370511064 -3.2492807250189824 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563963_0.png resize: (206, 152) 1370511065 -3.0816598160227473 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563990_0.png resize: (335, 375) 1370511066 -2.7280275988024183 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564014_0.png resize: (173, 147) 1370511068 -4.31190681568681 treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871563999_0.png resize: (217, 186) 1370511069 -4.124208538231206 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564039_0.png resize: (376, 385) 1370511070 -4.476492512553978 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564027_0.png resize: (186, 96) 1370511071 -3.4558633597065818 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564029_0.png resize: (289, 231) 1370511072 -4.384971235741843 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564026_0.png resize: (334, 343) 1370511074 -3.524304564117278 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564023_0.png resize: (234, 222) 1370511075 -3.8504108204207395 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563692_0.png resize: (274, 202) 1370511161 -5.0478894479467264 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563839_0.png resize: (145, 147) 1370511163 -4.148248476227726 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563743_0.png resize: (270, 1040) 1370511194 -4.203936250193369 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563744_0.png resize: (277, 285) 1370511195 -4.544717255466293 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563778_0.png resize: (295, 637) 1370511196 -3.2985226676162664 treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563836_0.png resize: (340, 205) 1370511197 -2.9747001603514502 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563908_0.png resize: (306, 305) 1370511198 -4.294315567686425 treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563893_0.png resize: (277, 202) 1370511199 -3.817874225499469 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563925_0.png resize: (259, 217) 1370511200 -4.127203655676424 treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563924_0.png resize: (192, 243) 1370511201 -4.7513598343742505 treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563951_0.png resize: (399, 326) 1370511202 -5.141575225113487 treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563966_0.png resize: (517, 355) 1370511203 -4.686152470060003 treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564043_0.png resize: (147, 167) 1370511204 -3.7116027361351183 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564070_0.png resize: (251, 416) 1370511205 -4.76821626508039 treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563748_0.png resize: (209, 213) 1370511209 -4.656493538102854 treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563823_0.png resize: (311, 1163) 1370511210 -4.043606338863188 treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563867_0.png resize: (334, 398) 1370511211 -4.368351434160803 treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563995_0.png resize: (119, 136) 1370511212 -3.385597787052669 treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563696_0.png resize: (216, 184) 1370511222 -4.4209815361921665 treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563790_0.png resize: (173, 408) 1370511223 -3.6528535201640477 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564068_0.png resize: (232, 302) 1370511224 -4.4813734854035845 treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564069_0.png resize: (118, 152) 1370511225 -4.246534688615001 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 : 408 time used for this insertion : 0.047600746154785156 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 408 time used for this insertion : 0.13576006889343262 save missing photos in datou_result : time spend for datou_step_exec : 85.57779264450073 time spend to save output : 0.19184541702270508 total time spend for step 6 : 85.76963806152344 step7:brightness Fri Jul 4 09:17:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1751612427_708613_1370462805_92baa68020fe11e6d5850e303ae1500b_32504942.jpg treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708.jpg treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047.jpg treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850.jpg treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881.jpg treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556.jpg treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882.jpg treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584.jpg treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432.jpg treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484.jpg treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304.jpg treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497.jpg treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813.jpg treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791.jpg treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350.jpg treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737.jpg treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746.jpg treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435.jpg treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563689_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563698_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563686_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563697_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563690_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563691_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563688_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563693_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563687_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563699_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563718_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563704_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563721_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563714_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563715_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563705_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563722_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563701_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563707_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563717_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563727_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563716_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563700_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563710_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563703_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563706_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563726_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563728_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563719_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563720_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563712_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563709_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563713_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563711_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563725_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563708_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563702_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563724_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563736_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563731_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563745_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563732_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563740_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563741_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563751_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563739_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563730_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563735_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563738_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563749_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563742_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563733_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563729_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563737_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563746_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563750_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563754_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563758_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563752_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563755_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563765_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563766_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563757_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563762_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563753_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563767_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563768_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563763_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563761_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563756_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563785_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563777_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563769_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563782_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563783_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563773_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563791_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563774_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563792_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563793_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563780_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563787_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563784_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563786_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563779_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563781_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563770_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563776_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563772_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563789_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563788_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563775_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563799_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563796_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563818_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563802_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563803_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563819_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563801_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563795_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563797_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563794_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563817_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563800_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563812_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563807_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563798_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563815_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563811_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563806_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563809_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563822_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563824_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563808_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563813_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563821_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563825_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563835_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563826_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563830_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563827_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563832_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563828_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563841_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563837_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563840_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563833_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563838_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563843_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563845_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563834_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563844_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563851_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563869_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563847_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563852_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563855_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563848_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563864_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563846_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563862_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563853_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563859_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563854_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563850_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563856_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563860_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563861_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563849_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563868_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563865_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563858_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563857_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563866_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563863_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563883_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563878_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563882_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563872_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563873_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563877_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563874_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563879_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563876_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563870_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563900_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563886_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563889_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563891_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563899_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563890_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563894_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563892_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563888_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563909_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563896_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563903_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563902_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563885_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563905_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563895_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563897_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563906_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563898_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563884_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563904_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563918_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563912_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563922_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563917_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563913_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563915_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563919_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563910_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563916_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563914_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563923_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563920_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563911_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563942_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563948_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563927_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563939_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563940_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563950_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563944_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563929_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563946_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563932_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563931_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563934_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563945_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563938_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563943_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563941_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563952_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563928_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563930_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563926_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563933_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563937_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563949_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563947_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563936_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563979_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563953_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563977_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563967_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563956_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563969_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563962_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563959_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563978_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563968_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563957_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563958_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563955_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563973_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563976_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563965_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563960_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563964_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563954_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563975_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563972_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563961_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563974_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563971_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563980_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563982_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563989_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563988_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563993_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563985_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563981_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563992_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563983_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563987_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563991_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563986_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563994_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563984_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564010_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564005_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564015_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564012_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564020_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564017_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564008_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564007_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564002_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564022_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871563997_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564004_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564003_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564011_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564006_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564009_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871563996_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564019_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564000_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564013_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564018_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871563998_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564016_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564021_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564001_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564034_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564036_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564040_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564033_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564038_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564032_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564030_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564042_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564028_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564048_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564037_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564045_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564025_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564031_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564046_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564047_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564044_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564024_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564041_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564035_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564074_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564053_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564066_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564049_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564063_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564071_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564058_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564052_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564050_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564051_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564060_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564065_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564072_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564064_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564073_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564061_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564054_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564059_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564056_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564075_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564062_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564055_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564057_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564067_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563695_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563694_0.png treat image : temp/1751612427_708613_1370462799_1e21364dd411ec68f82a403dd4aae39e_88204047_rle_crop_3871563723_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563734_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563747_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563760_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563764_0.png treat image : temp/1751612427_708613_1370462703_1351c5a0161cb0fa1e678af4a3ae6da0_54053881_rle_crop_3871563759_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563771_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563805_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563804_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563810_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563814_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563820_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563816_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563842_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563829_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563831_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563875_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563880_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563871_0.png treat image : temp/1751612427_708613_1370462698_37d03cd3bd3c7287ffe8275ff1d88887_5236484_rle_crop_3871563881_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563907_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563887_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563901_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563921_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563935_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563970_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563963_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563990_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871564014_0.png treat image : temp/1751612427_708613_1370462583_5bc3c5d0d19f74f53b5269bf4c26f110_78667737_rle_crop_3871563999_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564039_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564027_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564029_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564026_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564023_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563692_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563839_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563743_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563744_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563778_0.png treat image : temp/1751612427_708613_1370462700_b7ca8b3a90bf558de62418bb9a108531_55726584_rle_crop_3871563836_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563908_0.png treat image : temp/1751612427_708613_1370462676_c8c7de616b3672cd03580bc193018086_60072304_rle_crop_3871563893_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563925_0.png treat image : temp/1751612427_708613_1370462675_533c478f7eea34c4aaec119f9d118b7e_13286497_rle_crop_3871563924_0.png treat image : temp/1751612427_708613_1370462673_11823d0f63aa705545168231aa4acfc3_63766813_rle_crop_3871563951_0.png treat image : temp/1751612427_708613_1370462672_dbf09a378f41a63c35b6f1c92a0d4f2b_6432791_rle_crop_3871563966_0.png treat image : temp/1751612427_708613_1370462582_c2acae2d6196bed9ec4dc77b5ed6b4a3_88845746_rle_crop_3871564043_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564070_0.png treat image : temp/1751612427_708613_1370462797_23865ad7c7402db5b3a1f9f0d113a4f8_12508850_rle_crop_3871563748_0.png treat image : temp/1751612427_708613_1370462701_f4eefc9a19c821d49602a79f354feb90_6444882_rle_crop_3871563823_0.png treat image : temp/1751612427_708613_1370462699_0be17f6088b91637bf2bec1968ad8d70_87174432_rle_crop_3871563867_0.png treat image : temp/1751612427_708613_1370462671_287bdd763ab308821dd088d092b44400_15011350_rle_crop_3871563995_0.png treat image : temp/1751612427_708613_1370462802_e963d7c113fdb9b231f176bc7d16966b_99993708_rle_crop_3871563696_0.png treat image : temp/1751612427_708613_1370462702_5edd903ac8efb51a52ea7f54dbea2767_34293556_rle_crop_3871563790_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564068_0.png treat image : temp/1751612427_708613_1370462581_9d5cbc2382e074da2eeba778ee039eb3_7869435_rle_crop_3871564069_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 : 408 time used for this insertion : 0.03505063056945801 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 408 time used for this insertion : 0.7689197063446045 save missing photos in datou_result : time spend for datou_step_exec : 19.684226989746094 time spend to save output : 0.8108484745025635 total time spend for step 7 : 20.495075464248657 step8:velours_tree Fri Jul 4 09:17:23 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure can't find the photo_desc_type Inside saveOutput : final : False verbose : 0 ouput is None No outpout to save, returning out of save general time spend for datou_step_exec : 2.113696575164795 time spend to save output : 5.626678466796875e-05 total time spend for step 8 : 2.113752841949463 step9:send_mail_cod Fri Jul 4 09:17:25 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_P24581312_04-07-2025_09_17_25.pdf 24583719 imagette245837191751613445 24583720 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 .imagette245837201751613445 24583722 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 .imagette245837221751613446 24583723 change filename to text .change filename to text .change filename to text .change filename to text .imagette245837231751613447 24583724 change filename to text .change filename to text .imagette245837241751613448 24583725 imagette245837251751613448 24583726 imagette245837261751613448 24583727 change filename to text .change filename to text .change filename to text .change filename to text .imagette245837271751613448 24583728 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 .imagette245837281751613448 24583729 imagette245837291751613450 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=24581312 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/24583719,24583720,24583721,24583722,24583723,24583724,24583725,24583726,24583727,24583728,24583729?tags=pehd,pet_clair,environnement,papier,autre,metal,mal_croppe,background,pet_fonce,carton,flou args[1370462805] : ((1370462805, -6.53074096576479, 492609224), (1370462805, 0.2800795083508671, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462802] : ((1370462802, -6.830635050193761, 492609224), (1370462802, 0.34348639554230537, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462799] : ((1370462799, -7.120642533700665, 492609224), (1370462799, 1.3240134121398055, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462797] : ((1370462797, -7.121749218598173, 492609224), (1370462797, 0.9862986315076663, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462703] : ((1370462703, -7.304475533392903, 492609224), (1370462703, 1.6758765090348486, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462702] : ((1370462702, -7.158017882525462, 492609224), (1370462702, 1.924001327009083, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462701] : ((1370462701, -7.103082801927135, 492609224), (1370462701, 0.6621231570337281, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462700] : ((1370462700, -7.076696675962365, 492609224), (1370462700, 1.6769428313774712, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462699] : ((1370462699, -7.3918239638307215, 492609224), (1370462699, 1.6441970740240268, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462698] : ((1370462698, -7.282015724582517, 492609224), (1370462698, 1.235149849443769, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462676] : ((1370462676, -7.268429981977539, 492609224), (1370462676, 1.1020600959357807, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462675] : ((1370462675, -7.2303132294297665, 492609224), (1370462675, 1.651059601788772, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462673] : ((1370462673, -7.326071268790546, 492609224), (1370462673, 1.3893088732253787, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462672] : ((1370462672, -7.122897407798106, 492609224), (1370462672, 1.246132506518139, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462671] : ((1370462671, -7.123164742489054, 492609224), (1370462671, 1.3375780259973948, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462583] : ((1370462583, -7.234960959084353, 492609224), (1370462583, 1.3327632406216057, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462582] : ((1370462582, -7.234587788309596, 492609224), (1370462582, 1.1443829510975305, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com args[1370462581] : ((1370462581, -7.096545403946157, 492609224), (1370462581, 1.6829663226914267, 2107752395), '0.15940108855238333') We are sending mail with results at report@fotonower.com refus_total : 0.15940108855238333 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=24581312 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581312_04-07-2025_09_17_25.pdf results_Auto_P24581312_04-07-2025_09_17_25.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581312_04-07-2025_09_17_25.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','24581312','results_Auto_P24581312_04-07-2025_09_17_25.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581312_04-07-2025_09_17_25.pdf','pdf','','1.01','0.15940108855238333') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/24581312

https://www.fotonower.com/image?json=false&list_photos_id=1370462805
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462802
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462799
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462797
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462703
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462702
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462701
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462700
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462699
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462698
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462676
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462675
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462673
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462672
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462671
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462583
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462582
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1370462581
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 15.94%
Veuillez trouver les photos des contaminants.

exemples de contaminants: pet_clair: https://www.fotonower.com/view/24583720?limit=200
exemples de contaminants: papier: https://www.fotonower.com/view/24583722?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/24583723?limit=200
exemples de contaminants: metal: https://www.fotonower.com/view/24583724?limit=200
exemples de contaminants: pet_fonce: https://www.fotonower.com/view/24583727?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/24583728?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581312_04-07-2025_09_17_25.pdf.

Lien vers velours :https://www.fotonower.com/velours/24583719,24583720,24583721,24583722,24583723,24583724,24583725,24583726,24583727,24583728,24583729?tags=pehd,pet_clair,environnement,papier,autre,metal,mal_croppe,background,pet_fonce,carton,flou.


L'équipe Fotonower 202 b'' Server: nginx Date: Fri, 04 Jul 2025 07:17:34 GMT Content-Length: 0 Connection: close X-Message-Id: 9cZmkl43Qw29qWe7tQC3kA 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 [1370462805, 1370462802, 1370462799, 1370462797, 1370462703, 1370462702, 1370462701, 1370462700, 1370462699, 1370462698, 1370462676, 1370462675, 1370462673, 1370462672, 1370462671, 1370462583, 1370462582, 1370462581] 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, '3234682') ('3318', '24581312', '1370462805', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462802', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462799', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462797', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462703', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462702', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462701', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462700', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462699', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462698', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462676', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462675', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462673', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462672', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462671', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462583', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462582', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462581', None, None, None, None, None, '3234682') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 18 time used for this insertion : 0.01404261589050293 save_final save missing photos in datou_result : time spend for datou_step_exec : 8.797406196594238 time spend to save output : 0.014343500137329102 total time spend for step 9 : 8.811749696731567 step10:split_time_score Fri Jul 4 09:17:34 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'}] (('16', 18),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 03072025 24581312 Nombre de photos uploadées : 18 / 23040 (0%) 03072025 24581312 Nombre de photos taguées (types de déchets): 0 / 18 (0%) 03072025 24581312 Nombre de photos taguées (volume) : 0 / 18 (0%) elapsed_time : load_data_split_time_score 1.1920928955078125e-06 elapsed_time : order_list_meta_photo_and_scores 4.76837158203125e-06 ?????????????????? elapsed_time : fill_and_build_computed_from_old_data 0.0008444786071777344 elapsed_time : insert_dashboard_record_day_entry 0.0242464542388916 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 : 0.07112368741734716 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581025_04-07-2025_09_02_50.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24581025 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`=24581025 AND mptpi.`type`=3726 To do Qualite : 0.029696513136184908 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24569263_03-07-2025_11_43_31.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24569263 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`=24569263 AND mptpi.`type`=3726 To do Qualite : 0.03129936084068947 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24569302_03-07-2025_11_44_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24569302 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`=24569302 AND mptpi.`type`=3726 To do Qualite : 0.04215979239896914 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24571191_03-07-2025_12_26_14.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24571191 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`=24571191 AND mptpi.`type`=3726 To do Qualite : 0.015375019127491259 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581039_04-07-2025_08_59_09.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24581039 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`=24581039 AND mptpi.`type`=3726 To do Qualite : 0.1078739631558642 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581228_04-07-2025_09_14_11.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24581228 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`=24581228 AND mptpi.`type`=3594 To do Qualite : 0.15940108855238333 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581312_04-07-2025_09_17_25.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24581312 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`=24581312 AND mptpi.`type`=3594 To do Qualite : 0.16029692322530867 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581421_04-07-2025_08_54_59.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24581421 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`=24581421 AND mptpi.`type`=3594 To do Qualite : 0.032759106967075576 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P24581424_04-07-2025_08_51_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 24581424 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`=24581424 AND mptpi.`type`=3726 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'03072025': {'nb_upload': 18, '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 [1370462805, 1370462802, 1370462799, 1370462797, 1370462703, 1370462702, 1370462701, 1370462700, 1370462699, 1370462698, 1370462676, 1370462675, 1370462673, 1370462672, 1370462671, 1370462583, 1370462582, 1370462581] Looping around the photos to save general results len do output : 1 /24581312Didn'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, '3234682') ('3318', '24581312', '1370462805', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462802', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462799', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462797', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462703', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462702', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462701', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462700', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462699', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462698', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462676', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462675', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462673', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462672', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462671', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462583', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462582', None, None, None, None, None, '3234682') ('3318', None, None, None, None, None, None, None, '3234682') ('3318', '24581312', '1370462581', None, None, None, None, None, '3234682') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 19 time used for this insertion : 0.027643203735351562 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.8533201217651367 time spend to save output : 0.027974367141723633 total time spend for step 10 : 0.8812944889068604 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 18 set_done_treatment 401.99user 304.20system 17:10.48elapsed 68%CPU (0avgtext+0avgdata 5007748maxresident)k 19481920inputs+296824outputs (683921major+34629442minor)pagefaults 0swaps