python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 10 -a ' -a 4234 -l 5 ' -s datou_current_4234 -M 0 -S 0 -U 95,95,80 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 : 3620078 load datou : 4234 # 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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 ? 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 ? 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 ? [ (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 ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl 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 ? 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)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 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 : 4234, datou_cur_ids : ['2551234'] with mtr_portfolio_ids : ['20255472'] and first list_photo_ids : [] new path : /proc/3620078/ 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 1 ; length of list_pids : 1 ; length of list_args : 1 time to download the photos : 0.22080159187316895 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 : 11 step1:mask_detect Wed Feb 5 12:20:28 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 : 4800 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-05 12:20:31.348334: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-05 12:20:31.375297: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-05 12:20:31.377469: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7ff0d4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-05 12:20:31.377524: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-05 12:20:31.381656: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-05 12:20:31.631533: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3dc38d60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-05 12:20:31.631583: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-05 12:20:31.632735: 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 2025-02-05 12:20:31.633149: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 12:20:31.636306: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 12:20:31.639508: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 12:20:31.640014: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 12:20:31.642828: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 12:20:31.644186: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 12:20:31.649747: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 12:20:31.651219: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 12:20:31.651317: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 12:20:31.652055: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-05 12:20:31.652073: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-05 12:20:31.652082: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-05 12:20:31.653039: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4348 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. 2025-02-05 12:20:31.900922: 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 2025-02-05 12:20:31.901064: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 12:20:31.901097: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 12:20:31.901126: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 12:20:31.901154: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 12:20:31.901182: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 12:20:31.901209: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 12:20:31.901236: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 12:20:31.902726: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 12:20:31.903937: 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 2025-02-05 12:20:31.903970: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 12:20:31.903986: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 12:20:31.904000: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 12:20:31.904014: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 12:20:31.904029: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 12:20:31.904043: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 12:20:31.904057: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 12:20:31.904898: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 12:20:31.904931: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-05 12:20:31.904939: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-05 12:20:31.904946: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-05 12:20:31.905835: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4348 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 : [] 2025-02-05 12:20:38.262726: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 12:20:38.432788: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 12:20:39.835140: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:39.835816: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.37G (3621873152 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:39.836449: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.04G (3259685632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:39.837038: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.73G (2933716992 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.577695: 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. 2025-02-05 12:20:40.638270: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.638342: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB 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. 2025-02-05 12:20:40.639467: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.639506: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB 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. 2025-02-05 12:20:40.647203: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.647243: 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. 2025-02-05 12:20:40.648012: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.648031: 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. 2025-02-05 12:20:40.654383: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.654443: 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. 2025-02-05 12:20:40.655094: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.655112: 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. 2025-02-05 12:20:40.680369: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.680442: 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. 2025-02-05 12:20:40.680461: 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. 2025-02-05 12:20:40.681572: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.681600: 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. 2025-02-05 12:20:40.682851: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.682880: 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. 2025-02-05 12:20:40.690809: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.690883: 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. 2025-02-05 12:20:40.691996: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.693131: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.694223: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.702563: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.703247: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.721440: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.722297: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.723128: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.723911: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.728526: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.729324: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.730039: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.730671: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.731860: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.742034: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.742680: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.751795: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.752446: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.753082: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.753704: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.754336: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 12:20:40.754980: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.75G (4024303616 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 : 1 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 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: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0005025863647460938 length of segment : 14 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 2697 time to create 1 rle with old method : 0.009170055389404297 length of segment : 118 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0010945796966552734 length of segment : 32 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 1654 time to create 1 rle with old method : 0.0019643306732177734 length of segment : 99 time for calcul the mask position with numpy : 0.0001251697540283203 nb_pixel_total : 2942 time to create 1 rle with old method : 0.003498554229736328 length of segment : 99 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 30 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 593 time to create 1 rle with old method : 0.0007262229919433594 length of segment : 41 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1167 time to create 1 rle with old method : 0.00147247314453125 length of segment : 61 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0004467964172363281 length of segment : 43 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 3689 time to create 1 rle with old method : 0.004345417022705078 length of segment : 61 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 3721 time to create 1 rle with old method : 0.00441431999206543 length of segment : 60 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.00028014183044433594 length of segment : 25 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 2553 time to create 1 rle with old method : 0.0030651092529296875 length of segment : 72 time for calcul the mask position with numpy : 0.00014710426330566406 nb_pixel_total : 4866 time to create 1 rle with old method : 0.005663871765136719 length of segment : 96 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.0005879402160644531 length of segment : 19 time for calcul the mask position with numpy : 0.00013327598571777344 nb_pixel_total : 4647 time to create 1 rle with old method : 0.005585432052612305 length of segment : 93 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.0005991458892822266 length of segment : 18 time for calcul the mask position with numpy : 0.00011134147644042969 nb_pixel_total : 2371 time to create 1 rle with old method : 0.002839326858520508 length of segment : 73 time for calcul the mask position with numpy : 0.00015401840209960938 nb_pixel_total : 3678 time to create 1 rle with old method : 0.0042912960052490234 length of segment : 128 Processing 1 images image shape: (400, 400, 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: 640.00000 nb d'objets trouves : 39 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.0005283355712890625 length of segment : 19 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 1609 time to create 1 rle with old method : 0.0021419525146484375 length of segment : 70 time for calcul the mask position with numpy : 0.00015354156494140625 nb_pixel_total : 3349 time to create 1 rle with old method : 0.003950357437133789 length of segment : 80 time for calcul the mask position with numpy : 0.00010514259338378906 nb_pixel_total : 2736 time to create 1 rle with old method : 0.0033109188079833984 length of segment : 48 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0004951953887939453 length of segment : 44 time for calcul the mask position with numpy : 0.00012350082397460938 nb_pixel_total : 4220 time to create 1 rle with old method : 0.0052225589752197266 length of segment : 95 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005590915679931641 length of segment : 25 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.00051116943359375 length of segment : 30 time for calcul the mask position with numpy : 0.00013589859008789062 nb_pixel_total : 4309 time to create 1 rle with old method : 0.0050506591796875 length of segment : 80 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006737709045410156 length of segment : 26 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 726 time to create 1 rle with old method : 0.0009255409240722656 length of segment : 67 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 2410 time to create 1 rle with old method : 0.0028586387634277344 length of segment : 73 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 2595 time to create 1 rle with old method : 0.0030825138092041016 length of segment : 74 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1002 time to create 1 rle with old method : 0.0012314319610595703 length of segment : 46 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 590 time to create 1 rle with old method : 0.0007617473602294922 length of segment : 34 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.00040793418884277344 length of segment : 36 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 4252 time to create 1 rle with old method : 0.005214214324951172 length of segment : 98 time for calcul the mask position with numpy : 0.0001285076141357422 nb_pixel_total : 2911 time to create 1 rle with old method : 0.0036144256591796875 length of segment : 109 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 971 time to create 1 rle with old method : 0.0013341903686523438 length of segment : 55 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 1734 time to create 1 rle with old method : 0.002078533172607422 length of segment : 65 time for calcul the mask position with numpy : 0.00011539459228515625 nb_pixel_total : 2236 time to create 1 rle with old method : 0.0027840137481689453 length of segment : 70 time for calcul the mask position with numpy : 0.00018358230590820312 nb_pixel_total : 4143 time to create 1 rle with old method : 0.005224466323852539 length of segment : 74 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 638 time to create 1 rle with old method : 0.0008809566497802734 length of segment : 19 time for calcul the mask position with numpy : 0.0002028942108154297 nb_pixel_total : 2940 time to create 1 rle with old method : 0.003544330596923828 length of segment : 104 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 1236 time to create 1 rle with old method : 0.0014696121215820312 length of segment : 95 time for calcul the mask position with numpy : 0.00011944770812988281 nb_pixel_total : 2797 time to create 1 rle with old method : 0.003337860107421875 length of segment : 104 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 918 time to create 1 rle with old method : 0.0011126995086669922 length of segment : 53 time for calcul the mask position with numpy : 0.0004062652587890625 nb_pixel_total : 14670 time to create 1 rle with old method : 0.01676034927368164 length of segment : 337 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 813 time to create 1 rle with old method : 0.001032114028930664 length of segment : 38 time for calcul the mask position with numpy : 0.0002033710479736328 nb_pixel_total : 4518 time to create 1 rle with old method : 0.005674839019775391 length of segment : 206 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005652904510498047 length of segment : 39 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 919 time to create 1 rle with old method : 0.0011963844299316406 length of segment : 50 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0012204647064208984 length of segment : 71 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 886 time to create 1 rle with old method : 0.0010650157928466797 length of segment : 52 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 855 time to create 1 rle with old method : 0.0010418891906738281 length of segment : 43 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 924 time to create 1 rle with old method : 0.0010859966278076172 length of segment : 59 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1380 time to create 1 rle with old method : 0.0016353130340576172 length of segment : 60 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1433 time to create 1 rle with old method : 0.0017108917236328125 length of segment : 65 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 871 time to create 1 rle with old method : 0.001081228256225586 length of segment : 51 Processing 1 images image shape: (400, 400, 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: 640.00000 nb d'objets trouves : 27 time for calcul the mask position with numpy : 0.00014638900756835938 nb_pixel_total : 5113 time to create 1 rle with old method : 0.0060083866119384766 length of segment : 88 time for calcul the mask position with numpy : 0.00013947486877441406 nb_pixel_total : 3752 time to create 1 rle with old method : 0.004276752471923828 length of segment : 123 time for calcul the mask position with numpy : 0.00019693374633789062 nb_pixel_total : 4952 time to create 1 rle with old method : 0.007421970367431641 length of segment : 120 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 1766 time to create 1 rle with old method : 0.0030364990234375 length of segment : 75 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0007331371307373047 length of segment : 27 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0006964206695556641 length of segment : 41 time for calcul the mask position with numpy : 0.00018334388732910156 nb_pixel_total : 6209 time to create 1 rle with old method : 0.01097559928894043 length of segment : 92 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 557 time to create 1 rle with old method : 0.0010409355163574219 length of segment : 52 time for calcul the mask position with numpy : 0.0006620883941650391 nb_pixel_total : 31882 time to create 1 rle with old method : 0.03669238090515137 length of segment : 257 time for calcul the mask position with numpy : 0.0001327991485595703 nb_pixel_total : 3217 time to create 1 rle with old method : 0.003953218460083008 length of segment : 90 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00029659271240234375 length of segment : 29 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1285 time to create 1 rle with old method : 0.0016245841979980469 length of segment : 37 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2619 time to create 1 rle with old method : 0.003304004669189453 length of segment : 44 time for calcul the mask position with numpy : 0.0002541542053222656 nb_pixel_total : 14730 time to create 1 rle with old method : 0.01648569107055664 length of segment : 124 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1628 time to create 1 rle with old method : 0.002118825912475586 length of segment : 51 time for calcul the mask position with numpy : 0.00032210350036621094 nb_pixel_total : 14005 time to create 1 rle with old method : 0.021463871002197266 length of segment : 116 time for calcul the mask position with numpy : 0.0004017353057861328 nb_pixel_total : 3150 time to create 1 rle with old method : 0.005513668060302734 length of segment : 217 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0007781982421875 length of segment : 37 time for calcul the mask position with numpy : 0.0001068115234375 nb_pixel_total : 2959 time to create 1 rle with old method : 0.005075693130493164 length of segment : 82 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 2392 time to create 1 rle with old method : 0.00301361083984375 length of segment : 51 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.00022482872009277344 length of segment : 20 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1030 time to create 1 rle with old method : 0.0013091564178466797 length of segment : 58 time for calcul the mask position with numpy : 0.00014638900756835938 nb_pixel_total : 171 time to create 1 rle with old method : 0.00033974647521972656 length of segment : 35 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.0005664825439453125 length of segment : 39 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 2666 time to create 1 rle with old method : 0.003289937973022461 length of segment : 44 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 2082 time to create 1 rle with old method : 0.0025348663330078125 length of segment : 57 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 2155 time to create 1 rle with old method : 0.0024271011352539062 length of segment : 59 Processing 1 images image shape: (400, 400, 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: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0007481575012207031 length of segment : 19 time for calcul the mask position with numpy : 0.00023436546325683594 nb_pixel_total : 2700 time to create 1 rle with old method : 0.003398895263671875 length of segment : 100 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 1874 time to create 1 rle with old method : 0.0023965835571289062 length of segment : 39 time for calcul the mask position with numpy : 0.00017023086547851562 nb_pixel_total : 5940 time to create 1 rle with old method : 0.006760597229003906 length of segment : 127 time for calcul the mask position with numpy : 0.00015592575073242188 nb_pixel_total : 6016 time to create 1 rle with old method : 0.007227182388305664 length of segment : 93 time for calcul the mask position with numpy : 0.0002818107604980469 nb_pixel_total : 13859 time to create 1 rle with old method : 0.015796184539794922 length of segment : 100 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004565715789794922 length of segment : 29 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 70 time to create 1 rle with old method : 0.0001392364501953125 length of segment : 9 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.00041174888610839844 length of segment : 15 time for calcul the mask position with numpy : 0.0001742839813232422 nb_pixel_total : 9763 time to create 1 rle with old method : 0.011433601379394531 length of segment : 93 time for calcul the mask position with numpy : 0.00013256072998046875 nb_pixel_total : 277 time to create 1 rle with old method : 0.0004940032958984375 length of segment : 51 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0006067752838134766 length of segment : 31 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 541 time to create 1 rle with old method : 0.00069427490234375 length of segment : 52 time for calcul the mask position with numpy : 0.0001277923583984375 nb_pixel_total : 5917 time to create 1 rle with old method : 0.006809234619140625 length of segment : 113 time for calcul the mask position with numpy : 0.0001850128173828125 nb_pixel_total : 11818 time to create 1 rle with old method : 0.013416767120361328 length of segment : 80 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 2092 time to create 1 rle with old method : 0.0026030540466308594 length of segment : 48 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1542 time to create 1 rle with old method : 0.001987457275390625 length of segment : 40 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 932 time to create 1 rle with old method : 0.0012013912200927734 length of segment : 45 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 2118 time to create 1 rle with old method : 0.0026938915252685547 length of segment : 48 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 2031 time to create 1 rle with old method : 0.002618551254272461 length of segment : 51 time for calcul the mask position with numpy : 0.0001895427703857422 nb_pixel_total : 10240 time to create 1 rle with old method : 0.011652469635009766 length of segment : 102 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 1173 time to create 1 rle with old method : 0.0014286041259765625 length of segment : 52 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1031 time to create 1 rle with old method : 0.0014181137084960938 length of segment : 50 Processing 1 images image shape: (400, 400, 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: 640.00000 nb d'objets trouves : 38 time for calcul the mask position with numpy : 0.00010895729064941406 nb_pixel_total : 3224 time to create 1 rle with old method : 0.003851175308227539 length of segment : 62 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 2556 time to create 1 rle with old method : 0.003836393356323242 length of segment : 118 time for calcul the mask position with numpy : 0.00016260147094726562 nb_pixel_total : 3536 time to create 1 rle with old method : 0.004329204559326172 length of segment : 113 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004317760467529297 length of segment : 51 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003809928894042969 length of segment : 70 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 905 time to create 1 rle with old method : 0.0013759136199951172 length of segment : 50 time for calcul the mask position with numpy : 0.00015473365783691406 nb_pixel_total : 2732 time to create 1 rle with old method : 0.003408670425415039 length of segment : 84 time for calcul the mask position with numpy : 0.00012373924255371094 nb_pixel_total : 2104 time to create 1 rle with old method : 0.0025682449340820312 length of segment : 102 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 599 time to create 1 rle with old method : 0.0007536411285400391 length of segment : 31 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.0001888275146484375 length of segment : 23 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0005915164947509766 length of segment : 93 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.00040793418884277344 length of segment : 45 time for calcul the mask position with numpy : 0.00012087821960449219 nb_pixel_total : 4635 time to create 1 rle with old method : 0.005641937255859375 length of segment : 56 time for calcul the mask position with numpy : 0.00013875961303710938 nb_pixel_total : 3292 time to create 1 rle with old method : 0.004250049591064453 length of segment : 69 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005660057067871094 length of segment : 37 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.00046443939208984375 length of segment : 22 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 987 time to create 1 rle with old method : 0.0014188289642333984 length of segment : 96 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0003190040588378906 length of segment : 16 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0007100105285644531 length of segment : 20 time for calcul the mask position with numpy : 0.0004851818084716797 nb_pixel_total : 19175 time to create 1 rle with old method : 0.02157115936279297 length of segment : 255 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.0003688335418701172 length of segment : 32 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0005176067352294922 length of segment : 48 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002918243408203125 length of segment : 17 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.00012254714965820312 length of segment : 11 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 3405 time to create 1 rle with old method : 0.004053354263305664 length of segment : 57 time for calcul the mask position with numpy : 0.00017595291137695312 nb_pixel_total : 4396 time to create 1 rle with old method : 0.005309104919433594 length of segment : 131 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.00042724609375 length of segment : 19 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 57 time to create 1 rle with old method : 0.00021529197692871094 length of segment : 19 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 369 time to create 1 rle with old method : 0.0004937648773193359 length of segment : 58 time for calcul the mask position with numpy : 0.00012373924255371094 nb_pixel_total : 2597 time to create 1 rle with old method : 0.0032677650451660156 length of segment : 70 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 889 time to create 1 rle with old method : 0.0011599063873291016 length of segment : 46 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0008802413940429688 length of segment : 58 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 997 time to create 1 rle with old method : 0.001379251480102539 length of segment : 54 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003237724304199219 length of segment : 15 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 768 time to create 1 rle with old method : 0.0010762214660644531 length of segment : 37 time for calcul the mask position with numpy : 0.0001595020294189453 nb_pixel_total : 3735 time to create 1 rle with old method : 0.004629611968994141 length of segment : 111 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 729 time to create 1 rle with old method : 0.0011005401611328125 length of segment : 49 time for calcul the mask position with numpy : 0.00014281272888183594 nb_pixel_total : 3055 time to create 1 rle with old method : 0.003572225570678711 length of segment : 77 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.13750 max: 139.79922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 744 time to create 1 rle with old method : 0.0009963512420654297 length of segment : 26 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0006794929504394531 length of segment : 43 time for calcul the mask position with numpy : 0.0001888275146484375 nb_pixel_total : 8611 time to create 1 rle with old method : 0.010275602340698242 length of segment : 166 time for calcul the mask position with numpy : 0.00011730194091796875 nb_pixel_total : 2426 time to create 1 rle with old method : 0.0029408931732177734 length of segment : 106 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0012309551239013672 length of segment : 39 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0007271766662597656 length of segment : 69 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002849102020263672 length of segment : 36 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006260871887207031 length of segment : 28 time for calcul the mask position with numpy : 0.0002713203430175781 nb_pixel_total : 13175 time to create 1 rle with old method : 0.014907121658325195 length of segment : 311 time for calcul the mask position with numpy : 0.013517141342163086 nb_pixel_total : 4887 time to create 1 rle with old method : 0.03930497169494629 length of segment : 137 time for calcul the mask position with numpy : 0.00011944770812988281 nb_pixel_total : 2700 time to create 1 rle with old method : 0.004927158355712891 length of segment : 84 time for calcul the mask position with numpy : 0.00012421607971191406 nb_pixel_total : 811 time to create 1 rle with old method : 0.0016412734985351562 length of segment : 101 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00020313262939453125 length of segment : 17 time for calcul the mask position with numpy : 9.894371032714844e-05 nb_pixel_total : 1173 time to create 1 rle with old method : 0.001527547836303711 length of segment : 118 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1267 time to create 1 rle with old method : 0.0015943050384521484 length of segment : 78 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 157.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 43.43984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 845 time to create 1 rle with old method : 0.0010402202606201172 length of segment : 49 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.000392913818359375 length of segment : 38 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006699562072753906 length of segment : 37 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 850 time to create 1 rle with old method : 0.0010404586791992188 length of segment : 41 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003910064697265625 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.59063 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 0.0004024505615234375 nb_pixel_total : 16629 time to create 1 rle with old method : 0.019751548767089844 length of segment : 330 time for calcul the mask position with numpy : 0.00035071372985839844 nb_pixel_total : 15729 time to create 1 rle with old method : 0.019812583923339844 length of segment : 178 time for calcul the mask position with numpy : 0.0005261898040771484 nb_pixel_total : 38217 time to create 1 rle with old method : 0.04334211349487305 length of segment : 259 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 1649 time to create 1 rle with old method : 0.001964092254638672 length of segment : 97 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.0013115406036376953 length of segment : 25 time for calcul the mask position with numpy : 0.00031113624572753906 nb_pixel_total : 17274 time to create 1 rle with old method : 0.021507978439331055 length of segment : 141 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002675056457519531 length of segment : 24 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.0006811618804931641 length of segment : 35 time for calcul the mask position with numpy : 0.0002887248992919922 nb_pixel_total : 17873 time to create 1 rle with old method : 0.019753217697143555 length of segment : 155 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.00025916099548339844 length of segment : 20 Processing 1 images image shape: (400, 400, 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: 640.00000 nb d'objets trouves : 32 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 784 time to create 1 rle with old method : 0.0010385513305664062 length of segment : 33 time for calcul the mask position with numpy : 0.00010776519775390625 nb_pixel_total : 4556 time to create 1 rle with old method : 0.0051991939544677734 length of segment : 92 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.0007357597351074219 length of segment : 17 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 953 time to create 1 rle with old method : 0.001180887222290039 length of segment : 47 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1240 time to create 1 rle with old method : 0.0014622211456298828 length of segment : 72 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1363 time to create 1 rle with old method : 0.0017173290252685547 length of segment : 35 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.0008826255798339844 length of segment : 26 time for calcul the mask position with numpy : 0.00012230873107910156 nb_pixel_total : 4445 time to create 1 rle with old method : 0.005380392074584961 length of segment : 92 time for calcul the mask position with numpy : 0.00012159347534179688 nb_pixel_total : 4450 time to create 1 rle with old method : 0.005140066146850586 length of segment : 99 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 37 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0004017353057861328 length of segment : 48 time for calcul the mask position with numpy : 0.00019097328186035156 nb_pixel_total : 2818 time to create 1 rle with old method : 0.003465890884399414 length of segment : 204 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 1706 time to create 1 rle with old method : 0.002287626266479492 length of segment : 51 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0005939006805419922 length of segment : 46 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0006749629974365234 length of segment : 44 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 3886 time to create 1 rle with old method : 0.004876375198364258 length of segment : 49 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0007812976837158203 length of segment : 26 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0011088848114013672 length of segment : 34 time for calcul the mask position with numpy : 0.000148773193359375 nb_pixel_total : 824 time to create 1 rle with old method : 0.001150369644165039 length of segment : 108 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.0001876354217529297 length of segment : 10 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0008168220520019531 length of segment : 29 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1096 time to create 1 rle with old method : 0.0015151500701904297 length of segment : 28 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.00074005126953125 length of segment : 26 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 2907 time to create 1 rle with old method : 0.0035212039947509766 length of segment : 54 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 1529 time to create 1 rle with old method : 0.0020618438720703125 length of segment : 40 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1036 time to create 1 rle with old method : 0.0013277530670166016 length of segment : 53 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0013365745544433594 length of segment : 36 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 2594 time to create 1 rle with old method : 0.0031311511993408203 length of segment : 74 time for calcul the mask position with numpy : 0.00016498565673828125 nb_pixel_total : 3412 time to create 1 rle with old method : 0.005849599838256836 length of segment : 68 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1085 time to create 1 rle with old method : 0.0018887519836425781 length of segment : 44 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 711 time to create 1 rle with old method : 0.0012493133544921875 length of segment : 36 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0012753009796142578 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.51250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 687 time to create 1 rle with old method : 0.0008528232574462891 length of segment : 54 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.0010457038879394531 length of segment : 49 time for calcul the mask position with numpy : 0.0001766681671142578 nb_pixel_total : 10111 time to create 1 rle with old method : 0.011514663696289062 length of segment : 122 time for calcul the mask position with numpy : 0.0002512931823730469 nb_pixel_total : 8025 time to create 1 rle with old method : 0.009249687194824219 length of segment : 139 time for calcul the mask position with numpy : 0.0001068115234375 nb_pixel_total : 3047 time to create 1 rle with old method : 0.003744840621948242 length of segment : 52 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1079 time to create 1 rle with old method : 0.0014259815216064453 length of segment : 37 time for calcul the mask position with numpy : 0.0002799034118652344 nb_pixel_total : 13998 time to create 1 rle with old method : 0.015557289123535156 length of segment : 208 time for calcul the mask position with numpy : 0.0001919269561767578 nb_pixel_total : 8601 time to create 1 rle with old method : 0.00993967056274414 length of segment : 120 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1505 time to create 1 rle with old method : 0.0019004344940185547 length of segment : 48 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 2598 time to create 1 rle with old method : 0.0033957958221435547 length of segment : 39 time for calcul the mask position with numpy : 0.00023651123046875 nb_pixel_total : 9231 time to create 1 rle with old method : 0.010786056518554688 length of segment : 159 time for calcul the mask position with numpy : 0.00020694732666015625 nb_pixel_total : 8347 time to create 1 rle with old method : 0.009595155715942383 length of segment : 148 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004162788391113281 length of segment : 30 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0006010532379150391 length of segment : 66 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 1566 time to create 1 rle with old method : 0.0018930435180664062 length of segment : 53 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1690 time to create 1 rle with old method : 0.002184629440307617 length of segment : 59 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004062652587890625 length of segment : 34 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0007178783416748047 length of segment : 37 time for calcul the mask position with numpy : 0.0001049041748046875 nb_pixel_total : 3705 time to create 1 rle with old method : 0.004350900650024414 length of segment : 57 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 957 time to create 1 rle with old method : 0.001252889633178711 length of segment : 56 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00029015541076660156 length of segment : 18 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1650 time to create 1 rle with old method : 0.002110719680786133 length of segment : 45 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1850 time to create 1 rle with old method : 0.0023584365844726562 length of segment : 38 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 2021 time to create 1 rle with old method : 0.0025708675384521484 length of segment : 80 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1045 time to create 1 rle with old method : 0.0013277530670166016 length of segment : 48 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1758 time to create 1 rle with old method : 0.002185344696044922 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.88750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 0.0001633167266845703 nb_pixel_total : 4791 time to create 1 rle with old method : 0.00916910171508789 length of segment : 101 time for calcul the mask position with numpy : 0.00034809112548828125 nb_pixel_total : 14345 time to create 1 rle with old method : 0.017323970794677734 length of segment : 272 time for calcul the mask position with numpy : 0.0002295970916748047 nb_pixel_total : 7809 time to create 1 rle with old method : 0.009575843811035156 length of segment : 189 time for calcul the mask position with numpy : 0.0002129077911376953 nb_pixel_total : 509 time to create 1 rle with old method : 0.0011165142059326172 length of segment : 55 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002841949462890625 length of segment : 16 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003390312194824219 length of segment : 17 length of segment : 0 time for calcul the mask position with numpy : 0.00014019012451171875 nb_pixel_total : 5701 time to create 1 rle with old method : 0.006638288497924805 length of segment : 146 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1995 time to create 1 rle with old method : 0.0023851394653320312 length of segment : 48 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 947 time to create 1 rle with old method : 0.0012471675872802734 length of segment : 41 time for calcul the mask position with numpy : 0.00015020370483398438 nb_pixel_total : 5891 time to create 1 rle with old method : 0.009456872940063477 length of segment : 217 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1195 time to create 1 rle with old method : 0.001499176025390625 length of segment : 44 time for calcul the mask position with numpy : 0.000202178955078125 nb_pixel_total : 8159 time to create 1 rle with old method : 0.009169816970825195 length of segment : 223 time for calcul the mask position with numpy : 0.00010704994201660156 nb_pixel_total : 2881 time to create 1 rle with old method : 0.003508329391479492 length of segment : 99 time for calcul the mask position with numpy : 0.00015687942504882812 nb_pixel_total : 3095 time to create 1 rle with old method : 0.0039768218994140625 length of segment : 160 time for calcul the mask position with numpy : 0.0002791881561279297 nb_pixel_total : 13500 time to create 1 rle with old method : 0.015039205551147461 length of segment : 292 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.64141 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006797313690185547 length of segment : 30 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 1191 time to create 1 rle with old method : 0.0014867782592773438 length of segment : 64 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1600 time to create 1 rle with old method : 0.0020532608032226562 length of segment : 48 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.001302957534790039 length of segment : 23 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.0010111331939697266 length of segment : 63 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.0008611679077148438 length of segment : 22 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.0006606578826904297 length of segment : 74 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0005543231964111328 length of segment : 25 time for calcul the mask position with numpy : 0.00032520294189453125 nb_pixel_total : 12358 time to create 1 rle with old method : 0.01630377769470215 length of segment : 140 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 773 time to create 1 rle with old method : 0.0010352134704589844 length of segment : 41 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 2128 time to create 1 rle with old method : 0.002565622329711914 length of segment : 55 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0011494159698486328 length of segment : 60 time for calcul the mask position with numpy : 0.0002830028533935547 nb_pixel_total : 14909 time to create 1 rle with old method : 0.01694178581237793 length of segment : 256 time for calcul the mask position with numpy : 0.00011229515075683594 nb_pixel_total : 1280 time to create 1 rle with old method : 0.001874685287475586 length of segment : 63 time for calcul the mask position with numpy : 0.0005927085876464844 nb_pixel_total : 8807 time to create 1 rle with old method : 0.012512922286987305 length of segment : 305 time for calcul the mask position with numpy : 0.0001220703125 nb_pixel_total : 907 time to create 1 rle with old method : 0.0020928382873535156 length of segment : 26 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 1418 time to create 1 rle with old method : 0.0026369094848632812 length of segment : 63 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1115 time to create 1 rle with old method : 0.0014941692352294922 length of segment : 39 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 737 time to create 1 rle with old method : 0.0008823871612548828 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.64531 max: 149.57266 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 0.00026535987854003906 nb_pixel_total : 8998 time to create 1 rle with old method : 0.010562658309936523 length of segment : 278 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 1853 time to create 1 rle with old method : 0.0023856163024902344 length of segment : 97 time for calcul the mask position with numpy : 0.00026035308837890625 nb_pixel_total : 12114 time to create 1 rle with old method : 0.01394796371459961 length of segment : 119 time for calcul the mask position with numpy : 0.00011801719665527344 nb_pixel_total : 2623 time to create 1 rle with old method : 0.003114461898803711 length of segment : 76 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 3431 time to create 1 rle with old method : 0.00443577766418457 length of segment : 70 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1115 time to create 1 rle with old method : 0.0014290809631347656 length of segment : 35 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0003447532653808594 length of segment : 25 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.000301361083984375 length of segment : 9 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1821 time to create 1 rle with old method : 0.002245187759399414 length of segment : 46 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1763 time to create 1 rle with old method : 0.0020546913146972656 length of segment : 57 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 3030 time to create 1 rle with old method : 0.003859281539916992 length of segment : 56 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 934 time to create 1 rle with old method : 0.0017926692962646484 length of segment : 60 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 2680 time to create 1 rle with old method : 0.0033092498779296875 length of segment : 57 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1520 time to create 1 rle with old method : 0.0019729137420654297 length of segment : 48 time for calcul the mask position with numpy : 0.00018358230590820312 nb_pixel_total : 5958 time to create 1 rle with old method : 0.007070064544677734 length of segment : 83 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 734 time to create 1 rle with old method : 0.0010042190551757812 length of segment : 40 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1358 time to create 1 rle with old method : 0.001893758773803711 length of segment : 65 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 2682 time to create 1 rle with old method : 0.0032317638397216797 length of segment : 46 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 193.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 83.40859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00022339820861816406 length of segment : 35 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002765655517578125 length of segment : 16 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005288124084472656 length of segment : 44 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00032067298889160156 length of segment : 24 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0008995532989501953 length of segment : 29 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0006048679351806641 length of segment : 79 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 1157 time to create 1 rle with old method : 0.0018436908721923828 length of segment : 58 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.000553131103515625 length of segment : 32 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003714561462402344 length of segment : 42 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.000640869140625 length of segment : 56 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.00038623809814453125 length of segment : 35 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.00072479248046875 length of segment : 35 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0005950927734375 length of segment : 43 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 413 time to create 1 rle with old method : 0.0009560585021972656 length of segment : 37 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0013928413391113281 length of segment : 43 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0006577968597412109 length of segment : 38 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00024247169494628906 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.61406 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0008664131164550781 length of segment : 24 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 636 time to create 1 rle with old method : 0.001207113265991211 length of segment : 39 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1019 time to create 1 rle with old method : 0.0018513202667236328 length of segment : 52 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0022814273834228516 length of segment : 62 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 1270 time to create 1 rle with old method : 0.0025010108947753906 length of segment : 56 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 1799 time to create 1 rle with old method : 0.0022249221801757812 length of segment : 74 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0004489421844482422 length of segment : 26 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005204677581787109 length of segment : 36 time for calcul the mask position with numpy : 0.00025582313537597656 nb_pixel_total : 6475 time to create 1 rle with old method : 0.010860919952392578 length of segment : 183 time for calcul the mask position with numpy : 0.00014543533325195312 nb_pixel_total : 3100 time to create 1 rle with old method : 0.005414724349975586 length of segment : 104 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 1285 time to create 1 rle with old method : 0.00240325927734375 length of segment : 77 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 1809 time to create 1 rle with old method : 0.003247976303100586 length of segment : 73 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1326 time to create 1 rle with old method : 0.0016596317291259766 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.60625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 34 time for calcul the mask position with numpy : 0.00013518333435058594 nb_pixel_total : 1725 time to create 1 rle with old method : 0.0031969547271728516 length of segment : 83 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 926 time to create 1 rle with old method : 0.0016913414001464844 length of segment : 33 time for calcul the mask position with numpy : 0.00018095970153808594 nb_pixel_total : 5764 time to create 1 rle with old method : 0.009816408157348633 length of segment : 74 time for calcul the mask position with numpy : 0.00016307830810546875 nb_pixel_total : 3765 time to create 1 rle with old method : 0.006556272506713867 length of segment : 81 time for calcul the mask position with numpy : 0.0006394386291503906 nb_pixel_total : 27081 time to create 1 rle with old method : 0.0352778434753418 length of segment : 187 time for calcul the mask position with numpy : 0.00023865699768066406 nb_pixel_total : 7152 time to create 1 rle with old method : 0.011934041976928711 length of segment : 156 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 1384 time to create 1 rle with old method : 0.0024061203002929688 length of segment : 62 time for calcul the mask position with numpy : 0.00040221214294433594 nb_pixel_total : 15448 time to create 1 rle with old method : 0.02538585662841797 length of segment : 365 time for calcul the mask position with numpy : 0.00019311904907226562 nb_pixel_total : 3223 time to create 1 rle with old method : 0.0046367645263671875 length of segment : 73 time for calcul the mask position with numpy : 0.0003745555877685547 nb_pixel_total : 11496 time to create 1 rle with old method : 0.013407707214355469 length of segment : 203 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 611 time to create 1 rle with old method : 0.0009000301361083984 length of segment : 26 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 1309 time to create 1 rle with old method : 0.0017399787902832031 length of segment : 61 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 1370 time to create 1 rle with old method : 0.001661062240600586 length of segment : 74 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0016875267028808594 length of segment : 95 time for calcul the mask position with numpy : 0.00012874603271484375 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0017511844635009766 length of segment : 67 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1195 time to create 1 rle with old method : 0.0014870166778564453 length of segment : 59 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006341934204101562 length of segment : 34 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 1116 time to create 1 rle with old method : 0.0015349388122558594 length of segment : 54 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 996 time to create 1 rle with old method : 0.0012788772583007812 length of segment : 39 time for calcul the mask position with numpy : 0.0002040863037109375 nb_pixel_total : 4870 time to create 1 rle with old method : 0.005756378173828125 length of segment : 84 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0005133152008056641 length of segment : 45 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 1006 time to create 1 rle with old method : 0.0013039112091064453 length of segment : 33 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1197 time to create 1 rle with old method : 0.0015630722045898438 length of segment : 46 time for calcul the mask position with numpy : 0.00020503997802734375 nb_pixel_total : 3195 time to create 1 rle with old method : 0.004653215408325195 length of segment : 103 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1190 time to create 1 rle with old method : 0.0014388561248779297 length of segment : 56 time for calcul the mask position with numpy : 0.00018596649169921875 nb_pixel_total : 3574 time to create 1 rle with old method : 0.004263877868652344 length of segment : 64 time for calcul the mask position with numpy : 0.00013399124145507812 nb_pixel_total : 1550 time to create 1 rle with old method : 0.002150297164916992 length of segment : 40 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00030803680419921875 length of segment : 11 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0007982254028320312 length of segment : 34 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 366 time to create 1 rle with old method : 0.0005321502685546875 length of segment : 36 time for calcul the mask position with numpy : 0.00012993812561035156 nb_pixel_total : 3674 time to create 1 rle with old method : 0.00456690788269043 length of segment : 67 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.000316619873046875 length of segment : 18 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.000675201416015625 length of segment : 27 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1257 time to create 1 rle with old method : 0.0015528202056884766 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.87969 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 0.0001926422119140625 nb_pixel_total : 9362 time to create 1 rle with old method : 0.010436773300170898 length of segment : 198 time for calcul the mask position with numpy : 0.0005595684051513672 nb_pixel_total : 18240 time to create 1 rle with old method : 0.026325225830078125 length of segment : 265 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003151893615722656 length of segment : 22 time for calcul the mask position with numpy : 0.00010466575622558594 nb_pixel_total : 1946 time to create 1 rle with old method : 0.002397775650024414 length of segment : 76 time for calcul the mask position with numpy : 0.0001373291015625 nb_pixel_total : 3517 time to create 1 rle with old method : 0.004201412200927734 length of segment : 72 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 1787 time to create 1 rle with old method : 0.0023450851440429688 length of segment : 51 time for calcul the mask position with numpy : 0.00012230873107910156 nb_pixel_total : 2333 time to create 1 rle with old method : 0.004115104675292969 length of segment : 41 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0007927417755126953 length of segment : 24 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1283 time to create 1 rle with old method : 0.002382040023803711 length of segment : 24 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 699 time to create 1 rle with old method : 0.0012090206146240234 length of segment : 36 time for calcul the mask position with numpy : 0.00011181831359863281 nb_pixel_total : 2508 time to create 1 rle with old method : 0.0043485164642333984 length of segment : 62 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 1361 time to create 1 rle with old method : 0.00237274169921875 length of segment : 51 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00049591064453125 length of segment : 28 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0010323524475097656 length of segment : 39 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0004892349243164062 length of segment : 29 time for calcul the mask position with numpy : 0.00012230873107910156 nb_pixel_total : 2447 time to create 1 rle with old method : 0.0043795108795166016 length of segment : 62 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 2514 time to create 1 rle with old method : 0.0031175613403320312 length of segment : 88 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 2455 time to create 1 rle with old method : 0.002951383590698242 length of segment : 68 time for calcul the mask position with numpy : 0.0001842975616455078 nb_pixel_total : 4473 time to create 1 rle with old method : 0.005659818649291992 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.80938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 0.00017786026000976562 nb_pixel_total : 4976 time to create 1 rle with old method : 0.010101556777954102 length of segment : 108 time for calcul the mask position with numpy : 0.0001480579376220703 nb_pixel_total : 1845 time to create 1 rle with old method : 0.003345966339111328 length of segment : 84 time for calcul the mask position with numpy : 0.00015807151794433594 nb_pixel_total : 2828 time to create 1 rle with old method : 0.004873514175415039 length of segment : 74 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 933 time to create 1 rle with old method : 0.0018129348754882812 length of segment : 41 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0005993843078613281 length of segment : 20 time for calcul the mask position with numpy : 0.00011157989501953125 nb_pixel_total : 822 time to create 1 rle with old method : 0.001558065414428711 length of segment : 58 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 387 time to create 1 rle with old method : 0.000576019287109375 length of segment : 23 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1198 time to create 1 rle with old method : 0.0014989376068115234 length of segment : 53 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1157 time to create 1 rle with old method : 0.001636505126953125 length of segment : 34 time for calcul the mask position with numpy : 0.00015735626220703125 nb_pixel_total : 4144 time to create 1 rle with old method : 0.005155086517333984 length of segment : 159 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 541 time to create 1 rle with old method : 0.0007231235504150391 length of segment : 31 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.0011534690856933594 length of segment : 40 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003292560577392578 length of segment : 22 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006697177886962891 length of segment : 26 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 4272 time to create 1 rle with old method : 0.005142688751220703 length of segment : 93 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 658 time to create 1 rle with old method : 0.0009450912475585938 length of segment : 44 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0006859302520751953 length of segment : 36 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003273487091064453 length of segment : 26 time for calcul the mask position with numpy : 0.00014853477478027344 nb_pixel_total : 5551 time to create 1 rle with old method : 0.00631403923034668 length of segment : 141 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.0004971027374267578 length of segment : 26 time for calcul the mask position with numpy : 0.0004875659942626953 nb_pixel_total : 25354 time to create 1 rle with old method : 0.032126665115356445 length of segment : 163 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 659 time to create 1 rle with old method : 0.0008780956268310547 length of segment : 37 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0006873607635498047 length of segment : 23 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 712 time to create 1 rle with old method : 0.000957489013671875 length of segment : 38 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006172657012939453 length of segment : 35 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 545 time to create 1 rle with old method : 0.0007464885711669922 length of segment : 54 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006501674652099609 length of segment : 22 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 1238 time to create 1 rle with old method : 0.0015609264373779297 length of segment : 51 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1760 time to create 1 rle with old method : 0.0021495819091796875 length of segment : 90 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.02031 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 0.0002067089080810547 nb_pixel_total : 8610 time to create 1 rle with old method : 0.009764909744262695 length of segment : 148 time for calcul the mask position with numpy : 0.00018453598022460938 nb_pixel_total : 4705 time to create 1 rle with old method : 0.005762338638305664 length of segment : 93 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0005903244018554688 length of segment : 35 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 1410 time to create 1 rle with old method : 0.0017733573913574219 length of segment : 37 time for calcul the mask position with numpy : 0.00013375282287597656 nb_pixel_total : 1722 time to create 1 rle with old method : 0.002234220504760742 length of segment : 67 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 2068 time to create 1 rle with old method : 0.002542257308959961 length of segment : 56 time for calcul the mask position with numpy : 0.00013494491577148438 nb_pixel_total : 3272 time to create 1 rle with old method : 0.004011392593383789 length of segment : 91 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 1883 time to create 1 rle with old method : 0.002262115478515625 length of segment : 53 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1192 time to create 1 rle with old method : 0.0017061233520507812 length of segment : 28 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1477 time to create 1 rle with old method : 0.0018510818481445312 length of segment : 49 time for calcul the mask position with numpy : 0.0002205371856689453 nb_pixel_total : 6441 time to create 1 rle with old method : 0.007878780364990234 length of segment : 83 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 676 time to create 1 rle with old method : 0.0008842945098876953 length of segment : 40 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 2469 time to create 1 rle with old method : 0.003041982650756836 length of segment : 65 time for calcul the mask position with numpy : 0.00015282630920410156 nb_pixel_total : 4015 time to create 1 rle with old method : 0.004860639572143555 length of segment : 109 time for calcul the mask position with numpy : 0.00016736984252929688 nb_pixel_total : 3453 time to create 1 rle with old method : 0.004315376281738281 length of segment : 102 time for calcul the mask position with numpy : 0.00012040138244628906 nb_pixel_total : 3284 time to create 1 rle with old method : 0.004002809524536133 length of segment : 67 time for calcul the mask position with numpy : 0.0001456737518310547 nb_pixel_total : 610 time to create 1 rle with old method : 0.0009806156158447266 length of segment : 56 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1270 time to create 1 rle with old method : 0.0017538070678710938 length of segment : 27 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0006589889526367188 length of segment : 50 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0006144046783447266 length of segment : 24 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003762245178222656 length of segment : 18 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2033 time to create 1 rle with old method : 0.0024852752685546875 length of segment : 43 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1976 time to create 1 rle with old method : 0.002499103546142578 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.27813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 458 time to create 1 rle with old method : 0.0006456375122070312 length of segment : 62 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006341934204101562 length of segment : 81 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 2853 time to create 1 rle with old method : 0.003224611282348633 length of segment : 89 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0007121562957763672 length of segment : 18 time for calcul the mask position with numpy : 0.00016164779663085938 nb_pixel_total : 3669 time to create 1 rle with old method : 0.004287242889404297 length of segment : 81 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 1445 time to create 1 rle with old method : 0.0017571449279785156 length of segment : 46 time for calcul the mask position with numpy : 0.0001342296600341797 nb_pixel_total : 3616 time to create 1 rle with old method : 0.004346370697021484 length of segment : 82 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 890 time to create 1 rle with old method : 0.0012159347534179688 length of segment : 33 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0007686614990234375 length of segment : 52 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1407 time to create 1 rle with old method : 0.0017518997192382812 length of segment : 44 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 538 time to create 1 rle with old method : 0.000732421875 length of segment : 25 time for calcul the mask position with numpy : 8.940696716308594e-05 nb_pixel_total : 2825 time to create 1 rle with old method : 0.0034399032592773438 length of segment : 89 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00020074844360351562 length of segment : 21 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0012886524200439453 length of segment : 84 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1019 time to create 1 rle with old method : 0.0012328624725341797 length of segment : 48 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1307 time to create 1 rle with old method : 0.001678466796875 length of segment : 40 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1440 time to create 1 rle with old method : 0.001722574234008789 length of segment : 91 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1653 time to create 1 rle with old method : 0.001955270767211914 length of segment : 44 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 175.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 56.84453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004668235778808594 length of segment : 25 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0006191730499267578 length of segment : 35 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0005996227264404297 length of segment : 17 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0006318092346191406 length of segment : 31 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002231597900390625 length of segment : 15 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.000598907470703125 length of segment : 31 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 800 time to create 1 rle with old method : 0.0010640621185302734 length of segment : 36 time for calcul the mask position with numpy : 0.0003046989440917969 nb_pixel_total : 18006 time to create 1 rle with old method : 0.020173311233520508 length of segment : 268 time for calcul the mask position with numpy : 0.00010704994201660156 nb_pixel_total : 2188 time to create 1 rle with old method : 0.002693653106689453 length of segment : 63 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.000263214111328125 length of segment : 22 Processing 1 images image shape: (240, 400, 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: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1387 time to create 1 rle with old method : 0.0017235279083251953 length of segment : 53 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0005047321319580078 length of segment : 23 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006401538848876953 length of segment : 38 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002694129943847656 length of segment : 21 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 413 time to create 1 rle with old method : 0.0006411075592041016 length of segment : 27 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 75 time to create 1 rle with old method : 0.00019669532775878906 length of segment : 23 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 19 time to create 1 rle with old method : 7.009506225585938e-05 length of segment : 6 Processing 1 images image shape: (240, 400, 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: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 896 time to create 1 rle with old method : 0.0011968612670898438 length of segment : 38 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 855 time to create 1 rle with old method : 0.0010886192321777344 length of segment : 63 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0009684562683105469 length of segment : 30 time for calcul the mask position with numpy : 0.00019121170043945312 nb_pixel_total : 5745 time to create 1 rle with old method : 0.006655693054199219 length of segment : 93 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0006594657897949219 length of segment : 28 time for calcul the mask position with numpy : 0.00010561943054199219 nb_pixel_total : 1752 time to create 1 rle with old method : 0.0022661685943603516 length of segment : 45 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 829 time to create 1 rle with old method : 0.0011377334594726562 length of segment : 42 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0006039142608642578 length of segment : 76 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.0013053417205810547 length of segment : 42 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 718 time to create 1 rle with old method : 0.0009396076202392578 length of segment : 83 time for calcul the mask position with numpy : 0.00014853477478027344 nb_pixel_total : 1006 time to create 1 rle with old method : 0.001344442367553711 length of segment : 43 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 1638 time to create 1 rle with old method : 0.0035195350646972656 length of segment : 64 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 572 time to create 1 rle with old method : 0.0007960796356201172 length of segment : 74 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005650520324707031 length of segment : 29 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 845 time to create 1 rle with old method : 0.0011222362518310547 length of segment : 42 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 593 time to create 1 rle with old method : 0.0008435249328613281 length of segment : 27 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 779 time to create 1 rle with old method : 0.0010633468627929688 length of segment : 26 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.00024247169494628906 length of segment : 21 Processing 1 images image shape: (240, 400, 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: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0005316734313964844 length of segment : 32 time for calcul the mask position with numpy : 0.00013637542724609375 nb_pixel_total : 5971 time to create 1 rle with old method : 0.006971120834350586 length of segment : 90 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 685 time to create 1 rle with old method : 0.0009548664093017578 length of segment : 36 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 1870 time to create 1 rle with old method : 0.0029599666595458984 length of segment : 72 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002777576446533203 length of segment : 17 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 1496 time to create 1 rle with old method : 0.0020940303802490234 length of segment : 76 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006508827209472656 length of segment : 27 time for calcul the mask position with numpy : 0.0003352165222167969 nb_pixel_total : 10527 time to create 1 rle with old method : 0.012871742248535156 length of segment : 331 time for calcul the mask position with numpy : 0.00011324882507324219 nb_pixel_total : 2599 time to create 1 rle with old method : 0.0031931400299072266 length of segment : 99 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 2348 time to create 1 rle with old method : 0.002944469451904297 length of segment : 38 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1237 time to create 1 rle with old method : 0.0016617774963378906 length of segment : 30 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.000804901123046875 length of segment : 64 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.00038051605224609375 length of segment : 24 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 3353 time to create 1 rle with old method : 0.003883838653564453 length of segment : 92 time for calcul the mask position with numpy : 0.0001857280731201172 nb_pixel_total : 2335 time to create 1 rle with old method : 0.0030622482299804688 length of segment : 103 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 4470 time to create 1 rle with old method : 0.0052340030670166016 length of segment : 81 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1215 time to create 1 rle with old method : 0.001428365707397461 length of segment : 84 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.44375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 2060 time to create 1 rle with old method : 0.0025300979614257812 length of segment : 53 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0016629695892333984 length of segment : 27 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1775 time to create 1 rle with old method : 0.0021576881408691406 length of segment : 47 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007352828979492188 length of segment : 26 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.00032329559326171875 length of segment : 26 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1598 time to create 1 rle with old method : 0.0019609928131103516 length of segment : 34 time for calcul the mask position with numpy : 0.0001308917999267578 nb_pixel_total : 4650 time to create 1 rle with old method : 0.00536656379699707 length of segment : 107 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 545 time to create 1 rle with old method : 0.0007185935974121094 length of segment : 39 time for calcul the mask position with numpy : 9.846687316894531e-05 nb_pixel_total : 3303 time to create 1 rle with old method : 0.004088401794433594 length of segment : 98 time for calcul the mask position with numpy : 0.0004012584686279297 nb_pixel_total : 21429 time to create 1 rle with old method : 0.02574753761291504 length of segment : 164 time for calcul the mask position with numpy : 0.00019216537475585938 nb_pixel_total : 6892 time to create 1 rle with old method : 0.00788259506225586 length of segment : 210 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 2032 time to create 1 rle with old method : 0.0024476051330566406 length of segment : 55 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.000446319580078125 length of segment : 26 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 4094 time to create 1 rle with old method : 0.005136251449584961 length of segment : 49 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 1574 time to create 1 rle with old method : 0.0020008087158203125 length of segment : 49 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1510 time to create 1 rle with old method : 0.00191497802734375 length of segment : 55 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.23672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0006017684936523438 length of segment : 20 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 491 time to create 1 rle with old method : 0.0006935596466064453 length of segment : 45 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0012776851654052734 length of segment : 20 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 759 time to create 1 rle with old method : 0.0009915828704833984 length of segment : 38 time for calcul the mask position with numpy : 0.00031256675720214844 nb_pixel_total : 13669 time to create 1 rle with old method : 0.017301559448242188 length of segment : 148 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005829334259033203 length of segment : 16 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0010445117950439453 length of segment : 73 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0007250308990478516 length of segment : 33 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 251.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 130.88516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.00045228004455566406 length of segment : 32 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 791 time to create 1 rle with old method : 0.0010466575622558594 length of segment : 54 Processing 1 images image shape: (240, 160, 3) min: 13.00000 max: 116.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 10.46249 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Detection mask done ! Trying to reset tf kernel 3620557 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1615 tf kernel not reseted sub process len(results) : 518 len(list_Values) 518 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 518 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 : 568 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Catched exception ! Connect or reconnect ! Number saved : None batch 1 Loaded 518 chid ids of type : 4228 Number RLEs to save : 34548 save missing photos in datou_result : time spend for datou_step_exec : 25.83968496322632 time spend to save output : 2.185397148132324 total time spend for step 1 : 28.025082111358643 step2:brightness Wed Feb 5 12:20:56 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 inside step calcul brightness treat image : temp/1738754428_3620078_1334899197_c03810c745a051607b5ea280ecd2c877.jpg 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 : 1 time used for this insertion : 0.013556718826293945 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.012654781341552734 save missing photos in datou_result : time spend for datou_step_exec : 0.49871277809143066 time spend to save output : 0.03177356719970703 total time spend for step 2 : 0.5304863452911377 step3:blur_detection Wed Feb 5 12:20:57 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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/1738754428_3620078_1334899197_c03810c745a051607b5ea280ecd2c877.jpg resize: (1440, 2560) 1334899197 -8.31862993109965 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 : 1 time used for this insertion : 0.0109100341796875 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.010923147201538086 save missing photos in datou_result : time spend for datou_step_exec : 2.1922147274017334 time spend to save output : 0.026961565017700195 total time spend for step 3 : 2.2191762924194336 step4:rle_unique_nms_with_priority Wed Feb 5 12:20:59 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 Begin step rle-unique-nms batch 1 Loaded 518 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 512 nb_hashtags : 7 time to prepare the origin masks : 2.5874218940734863 time for calcul the mask position with numpy : 0.16013765335083008 nb_pixel_total : 2616905 time to create 1 rle with new method : 0.48909974098205566 time for calcul the mask position with numpy : 0.015163660049438477 nb_pixel_total : 210 time to create 1 rle with old method : 0.00027751922607421875 time for calcul the mask position with numpy : 0.015088558197021484 nb_pixel_total : 2911 time to create 1 rle with old method : 0.0033528804779052734 time for calcul the mask position with numpy : 0.015518426895141602 nb_pixel_total : 328 time to create 1 rle with old method : 0.00042724609375 time for calcul the mask position with numpy : 0.015329599380493164 nb_pixel_total : 9762 time to create 1 rle with old method : 0.011008739471435547 time for calcul the mask position with numpy : 0.01525259017944336 nb_pixel_total : 93 time to create 1 rle with old method : 0.0001926422119140625 time for calcul the mask position with numpy : 0.01582169532775879 nb_pixel_total : 2619 time to create 1 rle with old method : 0.004813671112060547 time for calcul the mask position with numpy : 0.01978015899658203 nb_pixel_total : 2556 time to create 1 rle with old method : 0.0042057037353515625 time for calcul the mask position with numpy : 0.019614219665527344 nb_pixel_total : 2697 time to create 1 rle with old method : 0.0036284923553466797 time for calcul the mask position with numpy : 0.014957904815673828 nb_pixel_total : 1609 time to create 1 rle with old method : 0.0018763542175292969 time for calcul the mask position with numpy : 0.015249252319335938 nb_pixel_total : 4952 time to create 1 rle with old method : 0.005990505218505859 time for calcul the mask position with numpy : 0.015956640243530273 nb_pixel_total : 582 time to create 1 rle with old method : 0.0007736682891845703 time for calcul the mask position with numpy : 0.01731109619140625 nb_pixel_total : 221 time to create 1 rle with old method : 0.00041294097900390625 time for calcul the mask position with numpy : 0.018563508987426758 nb_pixel_total : 744 time to create 1 rle with old method : 0.0015382766723632812 time for calcul the mask position with numpy : 0.01950812339782715 nb_pixel_total : 13370 time to create 1 rle with old method : 0.02512359619140625 time for calcul the mask position with numpy : 0.018071889877319336 nb_pixel_total : 39 time to create 1 rle with old method : 0.00012040138244628906 time for calcul the mask position with numpy : 0.01561737060546875 nb_pixel_total : 70 time to create 1 rle with old method : 0.00015473365783691406 time for calcul the mask position with numpy : 0.01546931266784668 nb_pixel_total : 512 time to create 1 rle with old method : 0.0006275177001953125 time for calcul the mask position with numpy : 0.014919281005859375 nb_pixel_total : 313 time to create 1 rle with old method : 0.0003604888916015625 time for calcul the mask position with numpy : 0.014295101165771484 nb_pixel_total : 258 time to create 1 rle with old method : 0.00033402442932128906 time for calcul the mask position with numpy : 0.01531219482421875 nb_pixel_total : 183 time to create 1 rle with old method : 0.00024771690368652344 time for calcul the mask position with numpy : 0.0159451961517334 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003325939178466797 time for calcul the mask position with numpy : 0.015594244003295898 nb_pixel_total : 50 time to create 1 rle with old method : 0.00011610984802246094 time for calcul the mask position with numpy : 0.015038251876831055 nb_pixel_total : 52 time to create 1 rle with old method : 0.00011277198791503906 time for calcul the mask position with numpy : 0.015092611312866211 nb_pixel_total : 593 time to create 1 rle with old method : 0.0007288455963134766 time for calcul the mask position with numpy : 0.01528024673461914 nb_pixel_total : 386 time to create 1 rle with old method : 0.0004954338073730469 time for calcul the mask position with numpy : 0.015424728393554688 nb_pixel_total : 99 time to create 1 rle with old method : 0.00015306472778320312 time for calcul the mask position with numpy : 0.014776229858398438 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003142356872558594 time for calcul the mask position with numpy : 0.0145263671875 nb_pixel_total : 1167 time to create 1 rle with old method : 0.0013418197631835938 time for calcul the mask position with numpy : 0.014686346054077148 nb_pixel_total : 599 time to create 1 rle with old method : 0.0006880760192871094 time for calcul the mask position with numpy : 0.014867305755615234 nb_pixel_total : 2942 time to create 1 rle with old method : 0.003271818161010742 time for calcul the mask position with numpy : 0.015024185180664062 nb_pixel_total : 15503 time to create 1 rle with old method : 0.02538919448852539 time for calcul the mask position with numpy : 0.017242908477783203 nb_pixel_total : 558 time to create 1 rle with old method : 0.0009446144104003906 time for calcul the mask position with numpy : 0.01715993881225586 nb_pixel_total : 289 time to create 1 rle with old method : 0.0005278587341308594 time for calcul the mask position with numpy : 0.01701831817626953 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002593994140625 time for calcul the mask position with numpy : 0.015007257461547852 nb_pixel_total : 65 time to create 1 rle with old method : 0.00011420249938964844 time for calcul the mask position with numpy : 0.015038013458251953 nb_pixel_total : 14730 time to create 1 rle with old method : 0.02190089225769043 time for calcul the mask position with numpy : 0.015713930130004883 nb_pixel_total : 557 time to create 1 rle with old method : 0.000720977783203125 time for calcul the mask position with numpy : 0.015143871307373047 nb_pixel_total : 726 time to create 1 rle with old method : 0.0008664131164550781 time for calcul the mask position with numpy : 0.014966964721679688 nb_pixel_total : 124 time to create 1 rle with old method : 0.0001590251922607422 time for calcul the mask position with numpy : 0.017288923263549805 nb_pixel_total : 168 time to create 1 rle with old method : 0.00030684471130371094 time for calcul the mask position with numpy : 0.017376184463500977 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005612373352050781 time for calcul the mask position with numpy : 0.015230655670166016 nb_pixel_total : 24 time to create 1 rle with old method : 7.05718994140625e-05 time for calcul the mask position with numpy : 0.015189170837402344 nb_pixel_total : 470 time to create 1 rle with old method : 0.0005903244018554688 time for calcul the mask position with numpy : 0.015050172805786133 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001442432403564453 time for calcul the mask position with numpy : 0.0150146484375 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005381107330322266 time for calcul the mask position with numpy : 0.014912843704223633 nb_pixel_total : 1380 time to create 1 rle with old method : 0.0016007423400878906 time for calcul the mask position with numpy : 0.015080690383911133 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004897117614746094 time for calcul the mask position with numpy : 0.015565633773803711 nb_pixel_total : 541 time to create 1 rle with old method : 0.0006666183471679688 time for calcul the mask position with numpy : 0.015007972717285156 nb_pixel_total : 1146 time to create 1 rle with old method : 0.0013959407806396484 time for calcul the mask position with numpy : 0.014459371566772461 nb_pixel_total : 2732 time to create 1 rle with old method : 0.0028748512268066406 time for calcul the mask position with numpy : 0.0146942138671875 nb_pixel_total : 905 time to create 1 rle with old method : 0.0011179447174072266 time for calcul the mask position with numpy : 0.014766454696655273 nb_pixel_total : 738 time to create 1 rle with old method : 0.0008563995361328125 time for calcul the mask position with numpy : 0.015569686889648438 nb_pixel_total : 1874 time to create 1 rle with old method : 0.002220630645751953 time for calcul the mask position with numpy : 0.015381336212158203 nb_pixel_total : 304 time to create 1 rle with old method : 0.0003502368927001953 time for calcul the mask position with numpy : 0.015018463134765625 nb_pixel_total : 2700 time to create 1 rle with old method : 0.0035593509674072266 time for calcul the mask position with numpy : 0.015357732772827148 nb_pixel_total : 1654 time to create 1 rle with old method : 0.0019025802612304688 time for calcul the mask position with numpy : 0.015834808349609375 nb_pixel_total : 44 time to create 1 rle with old method : 0.00011396408081054688 time for calcul the mask position with numpy : 0.016515731811523438 nb_pixel_total : 224 time to create 1 rle with old method : 0.000453948974609375 time for calcul the mask position with numpy : 0.018932342529296875 nb_pixel_total : 5113 time to create 1 rle with old method : 0.00563359260559082 time for calcul the mask position with numpy : 0.015247106552124023 nb_pixel_total : 2700 time to create 1 rle with old method : 0.0030841827392578125 time for calcul the mask position with numpy : 0.015088319778442383 nb_pixel_total : 336 time to create 1 rle with old method : 0.00041484832763671875 time for calcul the mask position with numpy : 0.015236616134643555 nb_pixel_total : 1236 time to create 1 rle with old method : 0.0014317035675048828 time for calcul the mask position with numpy : 0.01509547233581543 nb_pixel_total : 162 time to create 1 rle with old method : 0.00020956993103027344 time for calcul the mask position with numpy : 0.014989137649536133 nb_pixel_total : 3752 time to create 1 rle with old method : 0.004315853118896484 time for calcul the mask position with numpy : 0.014969110488891602 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003635883331298828 time for calcul the mask position with numpy : 0.014999628067016602 nb_pixel_total : 416 time to create 1 rle with old method : 0.0004897117614746094 time for calcul the mask position with numpy : 0.015023469924926758 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002567768096923828 time for calcul the mask position with numpy : 0.015223026275634766 nb_pixel_total : 2940 time to create 1 rle with old method : 0.003431558609008789 time for calcul the mask position with numpy : 0.01532602310180664 nb_pixel_total : 813 time to create 1 rle with old method : 0.000986337661743164 time for calcul the mask position with numpy : 0.01581859588623047 nb_pixel_total : 565 time to create 1 rle with old method : 0.0010592937469482422 time for calcul the mask position with numpy : 0.017243623733520508 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006306171417236328 time for calcul the mask position with numpy : 0.015279054641723633 nb_pixel_total : 3536 time to create 1 rle with old method : 0.0040493011474609375 time for calcul the mask position with numpy : 0.014991044998168945 nb_pixel_total : 3137 time to create 1 rle with old method : 0.003930807113647461 time for calcul the mask position with numpy : 0.015109539031982422 nb_pixel_total : 2426 time to create 1 rle with old method : 0.0028564929962158203 time for calcul the mask position with numpy : 0.01513361930847168 nb_pixel_total : 2144 time to create 1 rle with old method : 0.0024635791778564453 time for calcul the mask position with numpy : 0.015515327453613281 nb_pixel_total : 4284 time to create 1 rle with old method : 0.004818916320800781 time for calcul the mask position with numpy : 0.015476226806640625 nb_pixel_total : 462 time to create 1 rle with old method : 0.0005962848663330078 time for calcul the mask position with numpy : 0.01513051986694336 nb_pixel_total : 540 time to create 1 rle with old method : 0.0006456375122070312 time for calcul the mask position with numpy : 0.014934778213500977 nb_pixel_total : 3224 time to create 1 rle with old method : 0.0036618709564208984 time for calcul the mask position with numpy : 0.0147857666015625 nb_pixel_total : 4309 time to create 1 rle with old method : 0.004642963409423828 time for calcul the mask position with numpy : 0.014729976654052734 nb_pixel_total : 6016 time to create 1 rle with old method : 0.006690025329589844 time for calcul the mask position with numpy : 0.015146732330322266 nb_pixel_total : 111 time to create 1 rle with old method : 0.0002510547637939453 time for calcul the mask position with numpy : 0.015180587768554688 nb_pixel_total : 270 time to create 1 rle with old method : 0.0004067420959472656 time for calcul the mask position with numpy : 0.015225410461425781 nb_pixel_total : 485 time to create 1 rle with old method : 0.0005884170532226562 time for calcul the mask position with numpy : 0.015478372573852539 nb_pixel_total : 2736 time to create 1 rle with old method : 0.0032186508178710938 time for calcul the mask position with numpy : 0.01571369171142578 nb_pixel_total : 513 time to create 1 rle with old method : 0.0006792545318603516 time for calcul the mask position with numpy : 0.01522517204284668 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005476474761962891 time for calcul the mask position with numpy : 0.0182340145111084 nb_pixel_total : 171 time to create 1 rle with old method : 0.00024127960205078125 time for calcul the mask position with numpy : 0.015003442764282227 nb_pixel_total : 31863 time to create 1 rle with old method : 0.03461575508117676 time for calcul the mask position with numpy : 0.01517939567565918 nb_pixel_total : 461 time to create 1 rle with old method : 0.0005590915679931641 time for calcul the mask position with numpy : 0.0150299072265625 nb_pixel_total : 2597 time to create 1 rle with old method : 0.0029914379119873047 time for calcul the mask position with numpy : 0.015040159225463867 nb_pixel_total : 301 time to create 1 rle with old method : 0.00039315223693847656 time for calcul the mask position with numpy : 0.015066385269165039 nb_pixel_total : 2 time to create 1 rle with old method : 2.4318695068359375e-05 time for calcul the mask position with numpy : 0.015612125396728516 nb_pixel_total : 2595 time to create 1 rle with old method : 0.002998828887939453 time for calcul the mask position with numpy : 0.01582956314086914 nb_pixel_total : 850 time to create 1 rle with old method : 0.0010187625885009766 time for calcul the mask position with numpy : 0.015337467193603516 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007429122924804688 time for calcul the mask position with numpy : 0.014687776565551758 nb_pixel_total : 932 time to create 1 rle with old method : 0.0010821819305419922 time for calcul the mask position with numpy : 0.01601123809814453 nb_pixel_total : 13175 time to create 1 rle with old method : 0.020642995834350586 time for calcul the mask position with numpy : 0.015405416488647461 nb_pixel_total : 4866 time to create 1 rle with old method : 0.005543947219848633 time for calcul the mask position with numpy : 0.015249490737915039 nb_pixel_total : 17 time to create 1 rle with old method : 6.318092346191406e-05 time for calcul the mask position with numpy : 0.015141487121582031 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003924369812011719 time for calcul the mask position with numpy : 0.015431880950927734 nb_pixel_total : 145 time to create 1 rle with old method : 0.0003445148468017578 time for calcul the mask position with numpy : 0.015790939331054688 nb_pixel_total : 4220 time to create 1 rle with old method : 0.004881620407104492 time for calcul the mask position with numpy : 0.015115976333618164 nb_pixel_total : 210 time to create 1 rle with old method : 0.00031113624572753906 time for calcul the mask position with numpy : 0.015218734741210938 nb_pixel_total : 1173 time to create 1 rle with old method : 0.0014011859893798828 time for calcul the mask position with numpy : 0.016788005828857422 nb_pixel_total : 358 time to create 1 rle with old method : 0.00044608116149902344 time for calcul the mask position with numpy : 0.01524662971496582 nb_pixel_total : 47 time to create 1 rle with old method : 0.00011301040649414062 time for calcul the mask position with numpy : 0.015229940414428711 nb_pixel_total : 770 time to create 1 rle with old method : 0.0009930133819580078 time for calcul the mask position with numpy : 0.015516519546508789 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005085468292236328 time for calcul the mask position with numpy : 0.015269041061401367 nb_pixel_total : 321 time to create 1 rle with old method : 0.00043773651123046875 time for calcul the mask position with numpy : 0.015153884887695312 nb_pixel_total : 439 time to create 1 rle with old method : 0.0005288124084472656 time for calcul the mask position with numpy : 0.015197992324829102 nb_pixel_total : 279 time to create 1 rle with old method : 0.00037097930908203125 time for calcul the mask position with numpy : 0.015502691268920898 nb_pixel_total : 407 time to create 1 rle with old method : 0.0005762577056884766 time for calcul the mask position with numpy : 0.016454696655273438 nb_pixel_total : 13 time to create 1 rle with old method : 0.0002307891845703125 time for calcul the mask position with numpy : 0.016292095184326172 nb_pixel_total : 373 time to create 1 rle with old method : 0.0006003379821777344 time for calcul the mask position with numpy : 0.015139579772949219 nb_pixel_total : 1734 time to create 1 rle with old method : 0.001995563507080078 time for calcul the mask position with numpy : 0.015358686447143555 nb_pixel_total : 3678 time to create 1 rle with old method : 0.004014253616333008 time for calcul the mask position with numpy : 0.014822959899902344 nb_pixel_total : 1285 time to create 1 rle with old method : 0.0014753341674804688 time for calcul the mask position with numpy : 0.014963150024414062 nb_pixel_total : 8611 time to create 1 rle with old method : 0.009781599044799805 time for calcul the mask position with numpy : 0.015906333923339844 nb_pixel_total : 2236 time to create 1 rle with old method : 0.002597332000732422 time for calcul the mask position with numpy : 0.015204906463623047 nb_pixel_total : 845 time to create 1 rle with old method : 0.0009958744049072266 time for calcul the mask position with numpy : 0.015221118927001953 nb_pixel_total : 4045 time to create 1 rle with old method : 0.0046160221099853516 time for calcul the mask position with numpy : 0.015152215957641602 nb_pixel_total : 33 time to create 1 rle with old method : 8.249282836914062e-05 time for calcul the mask position with numpy : 0.015125036239624023 nb_pixel_total : 5940 time to create 1 rle with old method : 0.006837368011474609 time for calcul the mask position with numpy : 0.016036272048950195 nb_pixel_total : 918 time to create 1 rle with old method : 0.0011234283447265625 time for calcul the mask position with numpy : 0.01702094078063965 nb_pixel_total : 189 time to create 1 rle with old method : 0.00041604042053222656 time for calcul the mask position with numpy : 0.01769089698791504 nb_pixel_total : 37 time to create 1 rle with old method : 7.62939453125e-05 time for calcul the mask position with numpy : 0.01501321792602539 nb_pixel_total : 297 time to create 1 rle with old method : 0.00034689903259277344 time for calcul the mask position with numpy : 0.01520848274230957 nb_pixel_total : 1602 time to create 1 rle with old method : 0.0018990039825439453 time for calcul the mask position with numpy : 0.01528787612915039 nb_pixel_total : 2055 time to create 1 rle with old method : 0.0026061534881591797 time for calcul the mask position with numpy : 0.015190601348876953 nb_pixel_total : 47 time to create 1 rle with old method : 0.00014734268188476562 time for calcul the mask position with numpy : 0.015166282653808594 nb_pixel_total : 768 time to create 1 rle with old method : 0.0009200572967529297 time for calcul the mask position with numpy : 0.015228271484375 nb_pixel_total : 1766 time to create 1 rle with old method : 0.002035379409790039 time for calcul the mask position with numpy : 0.015049934387207031 nb_pixel_total : 326 time to create 1 rle with old method : 0.00042438507080078125 time for calcul the mask position with numpy : 0.015033483505249023 nb_pixel_total : 638 time to create 1 rle with old method : 0.0007684230804443359 time for calcul the mask position with numpy : 0.015060186386108398 nb_pixel_total : 13859 time to create 1 rle with old method : 0.01499319076538086 time for calcul the mask position with numpy : 0.01509404182434082 nb_pixel_total : 1267 time to create 1 rle with old method : 0.001516580581665039 time for calcul the mask position with numpy : 0.015149831771850586 nb_pixel_total : 591 time to create 1 rle with old method : 0.0007126331329345703 time for calcul the mask position with numpy : 0.015305042266845703 nb_pixel_total : 2553 time to create 1 rle with old method : 0.002940654754638672 time for calcul the mask position with numpy : 0.01558995246887207 nb_pixel_total : 339 time to create 1 rle with old method : 0.00043487548828125 time for calcul the mask position with numpy : 0.01610565185546875 nb_pixel_total : 64 time to create 1 rle with old method : 0.000186920166015625 time for calcul the mask position with numpy : 0.015697956085205078 nb_pixel_total : 971 time to create 1 rle with old method : 0.0012111663818359375 time for calcul the mask position with numpy : 0.015388965606689453 nb_pixel_total : 3349 time to create 1 rle with old method : 0.003695964813232422 time for calcul the mask position with numpy : 0.015214681625366211 nb_pixel_total : 416 time to create 1 rle with old method : 0.0004968643188476562 time for calcul the mask position with numpy : 0.015135765075683594 nb_pixel_total : 1 time to create 1 rle with old method : 1.9311904907226562e-05 time for calcul the mask position with numpy : 0.015073299407958984 nb_pixel_total : 2 time to create 1 rle with old method : 2.6702880859375e-05 time for calcul the mask position with numpy : 0.01558542251586914 nb_pixel_total : 3292 time to create 1 rle with old method : 0.0037887096405029297 time for calcul the mask position with numpy : 0.015502691268920898 nb_pixel_total : 987 time to create 1 rle with old method : 0.001219034194946289 time for calcul the mask position with numpy : 0.01520085334777832 nb_pixel_total : 3217 time to create 1 rle with old method : 0.0036706924438476562 time for calcul the mask position with numpy : 0.01504659652709961 nb_pixel_total : 50 time to create 1 rle with old method : 0.00018596649169921875 time for calcul the mask position with numpy : 0.01503133773803711 nb_pixel_total : 503 time to create 1 rle with old method : 0.0006492137908935547 time for calcul the mask position with numpy : 0.014971017837524414 nb_pixel_total : 2410 time to create 1 rle with old method : 0.002765178680419922 time for calcul the mask position with numpy : 0.015048503875732422 nb_pixel_total : 88 time to create 1 rle with old method : 0.00012755393981933594 time for calcul the mask position with numpy : 0.014980316162109375 nb_pixel_total : 201 time to create 1 rle with old method : 0.0003151893615722656 time for calcul the mask position with numpy : 0.014981269836425781 nb_pixel_total : 886 time to create 1 rle with old method : 0.00107574462890625 time for calcul the mask position with numpy : 0.014966249465942383 nb_pixel_total : 3689 time to create 1 rle with old method : 0.004179239273071289 time for calcul the mask position with numpy : 0.014991998672485352 nb_pixel_total : 59 time to create 1 rle with old method : 0.0001862049102783203 time for calcul the mask position with numpy : 0.01506495475769043 nb_pixel_total : 17 time to create 1 rle with old method : 4.0531158447265625e-05 time for calcul the mask position with numpy : 0.01492929458618164 nb_pixel_total : 4635 time to create 1 rle with old method : 0.005237102508544922 time for calcul the mask position with numpy : 0.014982938766479492 nb_pixel_total : 1002 time to create 1 rle with old method : 0.0011742115020751953 time for calcul the mask position with numpy : 0.015026569366455078 nb_pixel_total : 950 time to create 1 rle with old method : 0.0011129379272460938 time for calcul the mask position with numpy : 0.015233993530273438 nb_pixel_total : 74 time to create 1 rle with old method : 0.00015497207641601562 time for calcul the mask position with numpy : 0.01520991325378418 nb_pixel_total : 6209 time to create 1 rle with old method : 0.0067882537841796875 time for calcul the mask position with numpy : 0.014993667602539062 nb_pixel_total : 68 time to create 1 rle with old method : 0.00010943412780761719 time for calcul the mask position with numpy : 0.015115737915039062 nb_pixel_total : 2092 time to create 1 rle with old method : 0.0023763179779052734 time for calcul the mask position with numpy : 0.015037059783935547 nb_pixel_total : 227 time to create 1 rle with old method : 0.00041961669921875 time for calcul the mask position with numpy : 0.015079021453857422 nb_pixel_total : 96 time to create 1 rle with old method : 0.00015044212341308594 time for calcul the mask position with numpy : 0.015299081802368164 nb_pixel_total : 531 time to create 1 rle with old method : 0.0006489753723144531 time for calcul the mask position with numpy : 0.015192747116088867 nb_pixel_total : 1240 time to create 1 rle with old method : 0.0014889240264892578 time for calcul the mask position with numpy : 0.015150070190429688 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004324913024902344 time for calcul the mask position with numpy : 0.015015125274658203 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002770423889160156 time for calcul the mask position with numpy : 0.015471220016479492 nb_pixel_total : 1363 time to create 1 rle with old method : 0.0016849040985107422 time for calcul the mask position with numpy : 0.01605677604675293 nb_pixel_total : 275 time to create 1 rle with old method : 0.00035691261291503906 time for calcul the mask position with numpy : 0.01504206657409668 nb_pixel_total : 141 time to create 1 rle with old method : 0.00020074844360351562 time for calcul the mask position with numpy : 0.015033245086669922 nb_pixel_total : 1096 time to create 1 rle with old method : 0.0012862682342529297 time for calcul the mask position with numpy : 0.014942646026611328 nb_pixel_total : 2598 time to create 1 rle with old method : 0.002979755401611328 time for calcul the mask position with numpy : 0.015026330947875977 nb_pixel_total : 3386 time to create 1 rle with old method : 0.0039010047912597656 time for calcul the mask position with numpy : 0.014954328536987305 nb_pixel_total : 14 time to create 1 rle with old method : 3.528594970703125e-05 time for calcul the mask position with numpy : 0.015333414077758789 nb_pixel_total : 8115 time to create 1 rle with old method : 0.009243488311767578 time for calcul the mask position with numpy : 0.015346527099609375 nb_pixel_total : 1195 time to create 1 rle with old method : 0.001474618911743164 time for calcul the mask position with numpy : 0.015303611755371094 nb_pixel_total : 2680 time to create 1 rle with old method : 0.003172159194946289 time for calcul the mask position with numpy : 0.015004634857177734 nb_pixel_total : 2818 time to create 1 rle with old method : 0.0033178329467773438 time for calcul the mask position with numpy : 0.01504969596862793 nb_pixel_total : 773 time to create 1 rle with old method : 0.0009377002716064453 time for calcul the mask position with numpy : 0.015512466430664062 nb_pixel_total : 284 time to create 1 rle with old method : 0.0004916191101074219 time for calcul the mask position with numpy : 0.015175104141235352 nb_pixel_total : 15729 time to create 1 rle with old method : 0.01727890968322754 time for calcul the mask position with numpy : 0.014974832534790039 nb_pixel_total : 333 time to create 1 rle with old method : 0.0004131793975830078 time for calcul the mask position with numpy : 0.014969348907470703 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005567073822021484 time for calcul the mask position with numpy : 0.015012502670288086 nb_pixel_total : 200 time to create 1 rle with old method : 0.00027489662170410156 time for calcul the mask position with numpy : 0.01706385612487793 nb_pixel_total : 4812 time to create 1 rle with old method : 0.00561070442199707 time for calcul the mask position with numpy : 0.01496124267578125 nb_pixel_total : 2725 time to create 1 rle with old method : 0.0032994747161865234 time for calcul the mask position with numpy : 0.01494908332824707 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006928443908691406 time for calcul the mask position with numpy : 0.014947652816772461 nb_pixel_total : 3047 time to create 1 rle with old method : 0.003531217575073242 time for calcul the mask position with numpy : 0.015215158462524414 nb_pixel_total : 139 time to create 1 rle with old method : 0.00018668174743652344 time for calcul the mask position with numpy : 0.015088319778442383 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005414485931396484 time for calcul the mask position with numpy : 0.015009403228759766 nb_pixel_total : 947 time to create 1 rle with old method : 0.0010819435119628906 time for calcul the mask position with numpy : 0.014939069747924805 nb_pixel_total : 502 time to create 1 rle with old method : 0.0006003379821777344 time for calcul the mask position with numpy : 0.014991283416748047 nb_pixel_total : 1085 time to create 1 rle with old method : 0.001600503921508789 time for calcul the mask position with numpy : 0.014997720718383789 nb_pixel_total : 795 time to create 1 rle with old method : 0.0009450912475585938 time for calcul the mask position with numpy : 0.014964103698730469 nb_pixel_total : 354 time to create 1 rle with old method : 0.0004220008850097656 time for calcul the mask position with numpy : 0.015401363372802734 nb_pixel_total : 8601 time to create 1 rle with old method : 0.009926080703735352 time for calcul the mask position with numpy : 0.015250205993652344 nb_pixel_total : 14909 time to create 1 rle with old method : 0.016379356384277344 time for calcul the mask position with numpy : 0.015108346939086914 nb_pixel_total : 622 time to create 1 rle with old method : 0.0007960796356201172 time for calcul the mask position with numpy : 0.015351057052612305 nb_pixel_total : 1036 time to create 1 rle with old method : 0.0012311935424804688 time for calcul the mask position with numpy : 0.015028715133666992 nb_pixel_total : 1115 time to create 1 rle with old method : 0.0013968944549560547 time for calcul the mask position with numpy : 0.015026092529296875 nb_pixel_total : 8998 time to create 1 rle with old method : 0.01044154167175293 time for calcul the mask position with numpy : 0.015111684799194336 nb_pixel_total : 413 time to create 1 rle with old method : 0.0005826950073242188 time for calcul the mask position with numpy : 0.014974117279052734 nb_pixel_total : 507 time to create 1 rle with old method : 0.0005960464477539062 time for calcul the mask position with numpy : 0.015051126480102539 nb_pixel_total : 4556 time to create 1 rle with old method : 0.005181074142456055 time for calcul the mask position with numpy : 0.01718878746032715 nb_pixel_total : 1629 time to create 1 rle with old method : 0.002818584442138672 time for calcul the mask position with numpy : 0.016693592071533203 nb_pixel_total : 14345 time to create 1 rle with old method : 0.016037464141845703 time for calcul the mask position with numpy : 0.015396595001220703 nb_pixel_total : 9231 time to create 1 rle with old method : 0.01027679443359375 time for calcul the mask position with numpy : 0.015588521957397461 nb_pixel_total : 953 time to create 1 rle with old method : 0.0013756752014160156 time for calcul the mask position with numpy : 0.015275239944458008 nb_pixel_total : 292 time to create 1 rle with old method : 0.00045418739318847656 time for calcul the mask position with numpy : 0.015072345733642578 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005724430084228516 time for calcul the mask position with numpy : 0.015122652053833008 nb_pixel_total : 305 time to create 1 rle with old method : 0.0003998279571533203 time for calcul the mask position with numpy : 0.015192985534667969 nb_pixel_total : 1735 time to create 1 rle with old method : 0.0020427703857421875 time for calcul the mask position with numpy : 0.015047788619995117 nb_pixel_total : 634 time to create 1 rle with old method : 0.0007557868957519531 time for calcul the mask position with numpy : 0.015187978744506836 nb_pixel_total : 1600 time to create 1 rle with old method : 0.0018351078033447266 time for calcul the mask position with numpy : 0.015098333358764648 nb_pixel_total : 436 time to create 1 rle with old method : 0.0007841587066650391 time for calcul the mask position with numpy : 0.01510930061340332 nb_pixel_total : 2021 time to create 1 rle with old method : 0.0023381710052490234 time for calcul the mask position with numpy : 0.015063047409057617 nb_pixel_total : 3904 time to create 1 rle with old method : 0.004422426223754883 time for calcul the mask position with numpy : 0.015556573867797852 nb_pixel_total : 3412 time to create 1 rle with old method : 0.0038449764251708984 time for calcul the mask position with numpy : 0.015151023864746094 nb_pixel_total : 2594 time to create 1 rle with old method : 0.0029668807983398438 time for calcul the mask position with numpy : 0.014951467514038086 nb_pixel_total : 785 time to create 1 rle with old method : 0.000988006591796875 time for calcul the mask position with numpy : 0.01498556137084961 nb_pixel_total : 418 time to create 1 rle with old method : 0.0004971027374267578 time for calcul the mask position with numpy : 0.014976978302001953 nb_pixel_total : 582 time to create 1 rle with old method : 0.0006861686706542969 time for calcul the mask position with numpy : 0.015005826950073242 nb_pixel_total : 1520 time to create 1 rle with old method : 0.0017521381378173828 time for calcul the mask position with numpy : 0.015023231506347656 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0011563301086425781 time for calcul the mask position with numpy : 0.014970064163208008 nb_pixel_total : 1763 time to create 1 rle with old method : 0.002026796340942383 time for calcul the mask position with numpy : 0.014972209930419922 nb_pixel_total : 180 time to create 1 rle with old method : 0.00021791458129882812 time for calcul the mask position with numpy : 0.015041828155517578 nb_pixel_total : 968 time to create 1 rle with old method : 0.0011754035949707031 time for calcul the mask position with numpy : 0.015089988708496094 nb_pixel_total : 81 time to create 1 rle with old method : 0.00017690658569335938 time for calcul the mask position with numpy : 0.015135526657104492 nb_pixel_total : 903 time to create 1 rle with old method : 0.001093149185180664 time for calcul the mask position with numpy : 0.015021562576293945 nb_pixel_total : 1505 time to create 1 rle with old method : 0.0017752647399902344 time for calcul the mask position with numpy : 0.01494741439819336 nb_pixel_total : 1191 time to create 1 rle with old method : 0.0014147758483886719 time for calcul the mask position with numpy : 0.015387296676635742 nb_pixel_total : 25023 time to create 1 rle with old method : 0.027660369873046875 time for calcul the mask position with numpy : 0.01517343521118164 nb_pixel_total : 413 time to create 1 rle with old method : 0.0006728172302246094 time for calcul the mask position with numpy : 0.015096902847290039 nb_pixel_total : 32 time to create 1 rle with old method : 5.8650970458984375e-05 time for calcul the mask position with numpy : 0.014966964721679688 nb_pixel_total : 76 time to create 1 rle with old method : 0.00011610984802246094 time for calcul the mask position with numpy : 0.01506948471069336 nb_pixel_total : 16629 time to create 1 rle with old method : 0.018629789352416992 time for calcul the mask position with numpy : 0.015046358108520508 nb_pixel_total : 571 time to create 1 rle with old method : 0.0006737709045410156 time for calcul the mask position with numpy : 0.017441511154174805 nb_pixel_total : 1650 time to create 1 rle with old method : 0.002718210220336914 time for calcul the mask position with numpy : 0.015079021453857422 nb_pixel_total : 950 time to create 1 rle with old method : 0.0012156963348388672 time for calcul the mask position with numpy : 0.015074014663696289 nb_pixel_total : 559 time to create 1 rle with old method : 0.0006556510925292969 time for calcul the mask position with numpy : 0.014655351638793945 nb_pixel_total : 274 time to create 1 rle with old method : 0.00030422210693359375 time for calcul the mask position with numpy : 0.014762401580810547 nb_pixel_total : 784 time to create 1 rle with old method : 0.000982522964477539 time for calcul the mask position with numpy : 0.015609025955200195 nb_pixel_total : 718 time to create 1 rle with old method : 0.0009520053863525391 time for calcul the mask position with numpy : 0.01501321792602539 nb_pixel_total : 2251 time to create 1 rle with old method : 0.002561807632446289 time for calcul the mask position with numpy : 0.015013933181762695 nb_pixel_total : 3705 time to create 1 rle with old method : 0.004223346710205078 time for calcul the mask position with numpy : 0.015186309814453125 nb_pixel_total : 5701 time to create 1 rle with old method : 0.009220600128173828 time for calcul the mask position with numpy : 0.017418622970581055 nb_pixel_total : 1821 time to create 1 rle with old method : 0.002160310745239258 time for calcul the mask position with numpy : 0.015012741088867188 nb_pixel_total : 711 time to create 1 rle with old method : 0.0008885860443115234 time for calcul the mask position with numpy : 0.015088558197021484 nb_pixel_total : 1995 time to create 1 rle with old method : 0.0023086071014404297 time for calcul the mask position with numpy : 0.015250205993652344 nb_pixel_total : 1649 time to create 1 rle with old method : 0.0025217533111572266 time for calcul the mask position with numpy : 0.015313386917114258 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005917549133300781 time for calcul the mask position with numpy : 0.015071392059326172 nb_pixel_total : 83 time to create 1 rle with old method : 0.00013375282287597656 time for calcul the mask position with numpy : 0.015070676803588867 nb_pixel_total : 2128 time to create 1 rle with old method : 0.002404451370239258 time for calcul the mask position with numpy : 0.015100717544555664 nb_pixel_total : 13735 time to create 1 rle with old method : 0.01507258415222168 time for calcul the mask position with numpy : 0.01505899429321289 nb_pixel_total : 8025 time to create 1 rle with old method : 0.009111166000366211 time for calcul the mask position with numpy : 0.015021562576293945 nb_pixel_total : 1706 time to create 1 rle with old method : 0.0020599365234375 time for calcul the mask position with numpy : 0.01502227783203125 nb_pixel_total : 64 time to create 1 rle with old method : 0.00015282630920410156 time for calcul the mask position with numpy : 0.01510763168334961 nb_pixel_total : 737 time to create 1 rle with old method : 0.0008618831634521484 time for calcul the mask position with numpy : 0.015243768692016602 nb_pixel_total : 318 time to create 1 rle with old method : 0.0004146099090576172 time for calcul the mask position with numpy : 0.015321969985961914 nb_pixel_total : 3431 time to create 1 rle with old method : 0.004051923751831055 time for calcul the mask position with numpy : 0.01508331298828125 nb_pixel_total : 1418 time to create 1 rle with old method : 0.002324342727661133 time for calcul the mask position with numpy : 0.018589496612548828 nb_pixel_total : 4450 time to create 1 rle with old method : 0.005610227584838867 time for calcul the mask position with numpy : 0.015704870223999023 nb_pixel_total : 2907 time to create 1 rle with old method : 0.0033440589904785156 time for calcul the mask position with numpy : 0.015093088150024414 nb_pixel_total : 1115 time to create 1 rle with old method : 0.0013074874877929688 time for calcul the mask position with numpy : 0.015051126480102539 nb_pixel_total : 1850 time to create 1 rle with old method : 0.002103567123413086 time for calcul the mask position with numpy : 0.015031814575195312 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005004405975341797 time for calcul the mask position with numpy : 0.015071392059326172 nb_pixel_total : 957 time to create 1 rle with old method : 0.0010883808135986328 time for calcul the mask position with numpy : 0.015014171600341797 nb_pixel_total : 687 time to create 1 rle with old method : 0.0008091926574707031 time for calcul the mask position with numpy : 0.015190362930297852 nb_pixel_total : 178 time to create 1 rle with old method : 0.0003006458282470703 time for calcul the mask position with numpy : 0.015209197998046875 nb_pixel_total : 12358 time to create 1 rle with old method : 0.01399850845336914 time for calcul the mask position with numpy : 0.015683650970458984 nb_pixel_total : 734 time to create 1 rle with old method : 0.0008935928344726562 time for calcul the mask position with numpy : 0.015217065811157227 nb_pixel_total : 10111 time to create 1 rle with old method : 0.011346578598022461 time for calcul the mask position with numpy : 0.015081644058227539 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002512931823730469 time for calcul the mask position with numpy : 0.01509547233581543 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003535747528076172 time for calcul the mask position with numpy : 0.016114473342895508 nb_pixel_total : 2623 time to create 1 rle with old method : 0.003039836883544922 time for calcul the mask position with numpy : 0.01514124870300293 nb_pixel_total : 12114 time to create 1 rle with old method : 0.013289213180541992 time for calcul the mask position with numpy : 0.016188383102416992 nb_pixel_total : 1157 time to create 1 rle with old method : 0.0014109611511230469 time for calcul the mask position with numpy : 0.015193700790405273 nb_pixel_total : 547 time to create 1 rle with old method : 0.0007193088531494141 time for calcul the mask position with numpy : 0.015084981918334961 nb_pixel_total : 194 time to create 1 rle with old method : 0.00023055076599121094 time for calcul the mask position with numpy : 0.015038490295410156 nb_pixel_total : 229 time to create 1 rle with old method : 0.00031280517578125 time for calcul the mask position with numpy : 0.015246868133544922 nb_pixel_total : 518 time to create 1 rle with old method : 0.0006399154663085938 time for calcul the mask position with numpy : 0.015083074569702148 nb_pixel_total : 4791 time to create 1 rle with old method : 0.00533604621887207 time for calcul the mask position with numpy : 0.015109062194824219 nb_pixel_total : 934 time to create 1 rle with old method : 0.001093149185180664 time for calcul the mask position with numpy : 0.014988183975219727 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005056858062744141 time for calcul the mask position with numpy : 0.015036344528198242 nb_pixel_total : 299 time to create 1 rle with old method : 0.00037860870361328125 time for calcul the mask position with numpy : 0.014940500259399414 nb_pixel_total : 4445 time to create 1 rle with old method : 0.005027294158935547 time for calcul the mask position with numpy : 0.014978885650634766 nb_pixel_total : 518 time to create 1 rle with old method : 0.0006210803985595703 time for calcul the mask position with numpy : 0.014962434768676758 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011229515075683594 time for calcul the mask position with numpy : 0.014889240264892578 nb_pixel_total : 1079 time to create 1 rle with old method : 0.001260519027709961 time for calcul the mask position with numpy : 0.015005111694335938 nb_pixel_total : 835 time to create 1 rle with old method : 0.0009589195251464844 time for calcul the mask position with numpy : 0.01500558853149414 nb_pixel_total : 238 time to create 1 rle with old method : 0.0002751350402832031 time for calcul the mask position with numpy : 0.01497793197631836 nb_pixel_total : 3886 time to create 1 rle with old method : 0.004463672637939453 time for calcul the mask position with numpy : 0.015049934387207031 nb_pixel_total : 450 time to create 1 rle with old method : 0.0005631446838378906 time for calcul the mask position with numpy : 0.015505313873291016 nb_pixel_total : 3030 time to create 1 rle with old method : 0.005079507827758789 time for calcul the mask position with numpy : 0.017565011978149414 nb_pixel_total : 1358 time to create 1 rle with old method : 0.002333402633666992 time for calcul the mask position with numpy : 0.01725935935974121 nb_pixel_total : 24 time to create 1 rle with old method : 0.00010204315185546875 time for calcul the mask position with numpy : 0.017116785049438477 nb_pixel_total : 573 time to create 1 rle with old method : 0.0010008811950683594 time for calcul the mask position with numpy : 0.01718306541442871 nb_pixel_total : 227 time to create 1 rle with old method : 0.00027370452880859375 time for calcul the mask position with numpy : 0.015008687973022461 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001404285430908203 time for calcul the mask position with numpy : 0.014734983444213867 nb_pixel_total : 4705 time to create 1 rle with old method : 0.006493330001831055 time for calcul the mask position with numpy : 0.015252113342285156 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006723403930664062 time for calcul the mask position with numpy : 0.01560664176940918 nb_pixel_total : 119 time to create 1 rle with old method : 0.00018715858459472656 time for calcul the mask position with numpy : 0.0150146484375 nb_pixel_total : 3204 time to create 1 rle with old method : 0.0037696361541748047 time for calcul the mask position with numpy : 0.015030622482299805 nb_pixel_total : 1198 time to create 1 rle with old method : 0.0013885498046875 time for calcul the mask position with numpy : 0.015019655227661133 nb_pixel_total : 484 time to create 1 rle with old method : 0.0007872581481933594 time for calcul the mask position with numpy : 0.01499629020690918 nb_pixel_total : 451 time to create 1 rle with old method : 0.0005626678466796875 time for calcul the mask position with numpy : 0.014981269836425781 nb_pixel_total : 658 time to create 1 rle with old method : 0.000762939453125 time for calcul the mask position with numpy : 0.015213489532470703 nb_pixel_total : 1283 time to create 1 rle with old method : 0.001506805419921875 time for calcul the mask position with numpy : 0.015014171600341797 nb_pixel_total : 551 time to create 1 rle with old method : 0.0007264614105224609 time for calcul the mask position with numpy : 0.01512002944946289 nb_pixel_total : 1317 time to create 1 rle with old method : 0.001550912857055664 time for calcul the mask position with numpy : 0.015003204345703125 nb_pixel_total : 379 time to create 1 rle with old method : 0.0004863739013671875 time for calcul the mask position with numpy : 0.015329599380493164 nb_pixel_total : 167 time to create 1 rle with old method : 0.0003001689910888672 time for calcul the mask position with numpy : 0.01562786102294922 nb_pixel_total : 3210 time to create 1 rle with old method : 0.003737926483154297 time for calcul the mask position with numpy : 0.015030860900878906 nb_pixel_total : 24 time to create 1 rle with old method : 4.9591064453125e-05 time for calcul the mask position with numpy : 0.015030860900878906 nb_pixel_total : 94 time to create 1 rle with old method : 0.0001952648162841797 time for calcul the mask position with numpy : 0.014967203140258789 nb_pixel_total : 8610 time to create 1 rle with old method : 0.009438753128051758 time for calcul the mask position with numpy : 0.01645684242248535 nb_pixel_total : 23504 time to create 1 rle with old method : 0.025766372680664062 time for calcul the mask position with numpy : 0.015314817428588867 nb_pixel_total : 591 time to create 1 rle with old method : 0.00072479248046875 time for calcul the mask position with numpy : 0.015147686004638672 nb_pixel_total : 5764 time to create 1 rle with old method : 0.006326436996459961 time for calcul the mask position with numpy : 0.014980316162109375 nb_pixel_total : 130 time to create 1 rle with old method : 0.0001742839813232422 time for calcul the mask position with numpy : 0.014879941940307617 nb_pixel_total : 492 time to create 1 rle with old method : 0.0005342960357666016 time for calcul the mask position with numpy : 0.014720916748046875 nb_pixel_total : 9362 time to create 1 rle with old method : 0.010199308395385742 time for calcul the mask position with numpy : 0.01625370979309082 nb_pixel_total : 162 time to create 1 rle with old method : 0.0007441043853759766 time for calcul the mask position with numpy : 0.017304658889770508 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0014681816101074219 time for calcul the mask position with numpy : 0.01499795913696289 nb_pixel_total : 676 time to create 1 rle with old method : 0.0007946491241455078 time for calcul the mask position with numpy : 0.015043973922729492 nb_pixel_total : 465 time to create 1 rle with old method : 0.0005819797515869141 time for calcul the mask position with numpy : 0.015511512756347656 nb_pixel_total : 224 time to create 1 rle with old method : 0.00031876564025878906 time for calcul the mask position with numpy : 0.015366554260253906 nb_pixel_total : 2068 time to create 1 rle with old method : 0.002428770065307617 time for calcul the mask position with numpy : 0.015053987503051758 nb_pixel_total : 1946 time to create 1 rle with old method : 0.0022232532501220703 time for calcul the mask position with numpy : 0.015005350112915039 nb_pixel_total : 545 time to create 1 rle with old method : 0.0006959438323974609 time for calcul the mask position with numpy : 0.014934062957763672 nb_pixel_total : 4976 time to create 1 rle with old method : 0.00547480583190918 time for calcul the mask position with numpy : 0.014913558959960938 nb_pixel_total : 1440 time to create 1 rle with old method : 0.0016698837280273438 time for calcul the mask position with numpy : 0.014921426773071289 nb_pixel_total : 4015 time to create 1 rle with old method : 0.005586385726928711 time for calcul the mask position with numpy : 0.01566147804260254 nb_pixel_total : 19 time to create 1 rle with old method : 7.05718994140625e-05 time for calcul the mask position with numpy : 0.014934062957763672 nb_pixel_total : 20019 time to create 1 rle with old method : 0.022896766662597656 time for calcul the mask position with numpy : 0.01504969596862793 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005483627319335938 time for calcul the mask position with numpy : 0.01466679573059082 nb_pixel_total : 437 time to create 1 rle with old method : 0.00048804283142089844 time for calcul the mask position with numpy : 0.014816522598266602 nb_pixel_total : 11496 time to create 1 rle with old method : 0.012732267379760742 time for calcul the mask position with numpy : 0.014798879623413086 nb_pixel_total : 343 time to create 1 rle with old method : 0.00041031837463378906 time for calcul the mask position with numpy : 0.014878988265991211 nb_pixel_total : 3669 time to create 1 rle with old method : 0.004232883453369141 time for calcul the mask position with numpy : 0.015111684799194336 nb_pixel_total : 1019 time to create 1 rle with old method : 0.0012006759643554688 time for calcul the mask position with numpy : 0.014972686767578125 nb_pixel_total : 3100 time to create 1 rle with old method : 0.003531217575073242 time for calcul the mask position with numpy : 0.015035629272460938 nb_pixel_total : 1285 time to create 1 rle with old method : 0.0015177726745605469 time for calcul the mask position with numpy : 0.015067815780639648 nb_pixel_total : 636 time to create 1 rle with old method : 0.0007646083831787109 time for calcul the mask position with numpy : 0.01497960090637207 nb_pixel_total : 63 time to create 1 rle with old method : 0.00011444091796875 time for calcul the mask position with numpy : 0.0149383544921875 nb_pixel_total : 1270 time to create 1 rle with old method : 0.0014498233795166016 time for calcul the mask position with numpy : 0.014942407608032227 nb_pixel_total : 25 time to create 1 rle with old method : 9.560585021972656e-05 time for calcul the mask position with numpy : 0.014990091323852539 nb_pixel_total : 218 time to create 1 rle with old method : 0.0002624988555908203 time for calcul the mask position with numpy : 0.015093326568603516 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003368854522705078 time for calcul the mask position with numpy : 0.015073299407958984 nb_pixel_total : 201 time to create 1 rle with old method : 0.00025272369384765625 time for calcul the mask position with numpy : 0.014931201934814453 nb_pixel_total : 2853 time to create 1 rle with old method : 0.0031583309173583984 time for calcul the mask position with numpy : 0.014661550521850586 nb_pixel_total : 40 time to create 1 rle with old method : 7.772445678710938e-05 time for calcul the mask position with numpy : 0.014991521835327148 nb_pixel_total : 18240 time to create 1 rle with old method : 0.020618200302124023 time for calcul the mask position with numpy : 0.015129566192626953 nb_pixel_total : 1192 time to create 1 rle with old method : 0.0014948844909667969 time for calcul the mask position with numpy : 0.01540517807006836 nb_pixel_total : 4775 time to create 1 rle with old method : 0.0057451725006103516 time for calcul the mask position with numpy : 0.015160560607910156 nb_pixel_total : 68 time to create 1 rle with old method : 0.00016617774963378906 time for calcul the mask position with numpy : 0.015222787857055664 nb_pixel_total : 1231 time to create 1 rle with old method : 0.0014874935150146484 time for calcul the mask position with numpy : 0.015391111373901367 nb_pixel_total : 387 time to create 1 rle with old method : 0.0004668235778808594 time for calcul the mask position with numpy : 0.01494741439819336 nb_pixel_total : 1845 time to create 1 rle with old method : 0.0021016597747802734 time for calcul the mask position with numpy : 0.014916658401489258 nb_pixel_total : 3517 time to create 1 rle with old method : 0.0038411617279052734 time for calcul the mask position with numpy : 0.014908075332641602 nb_pixel_total : 890 time to create 1 rle with old method : 0.0010330677032470703 time for calcul the mask position with numpy : 0.01512289047241211 nb_pixel_total : 21 time to create 1 rle with old method : 7.62939453125e-05 time for calcul the mask position with numpy : 0.014951467514038086 nb_pixel_total : 6475 time to create 1 rle with old method : 0.007211446762084961 time for calcul the mask position with numpy : 0.015079975128173828 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003497600555419922 time for calcul the mask position with numpy : 0.01524043083190918 nb_pixel_total : 1019 time to create 1 rle with old method : 0.0012595653533935547 time for calcul the mask position with numpy : 0.015427589416503906 nb_pixel_total : 1407 time to create 1 rle with old method : 0.0016543865203857422 time for calcul the mask position with numpy : 0.015041351318359375 nb_pixel_total : 15448 time to create 1 rle with old method : 0.017653226852416992 time for calcul the mask position with numpy : 0.015095949172973633 nb_pixel_total : 435 time to create 1 rle with old method : 0.0005526542663574219 time for calcul the mask position with numpy : 0.015009403228759766 nb_pixel_total : 1477 time to create 1 rle with old method : 0.001688241958618164 time for calcul the mask position with numpy : 0.014984846115112305 nb_pixel_total : 1883 time to create 1 rle with old method : 0.00214385986328125 time for calcul the mask position with numpy : 0.014936208724975586 nb_pixel_total : 4270 time to create 1 rle with old method : 0.004824638366699219 time for calcul the mask position with numpy : 0.014724493026733398 nb_pixel_total : 461 time to create 1 rle with old method : 0.0005817413330078125 time for calcul the mask position with numpy : 0.014795303344726562 nb_pixel_total : 145 time to create 1 rle with old method : 0.00016951560974121094 time for calcul the mask position with numpy : 0.014957427978515625 nb_pixel_total : 1722 time to create 1 rle with old method : 0.002033710479736328 time for calcul the mask position with numpy : 0.01528787612915039 nb_pixel_total : 541 time to create 1 rle with old method : 0.0006051063537597656 time for calcul the mask position with numpy : 0.015431404113769531 nb_pixel_total : 1001 time to create 1 rle with old method : 0.001224517822265625 time for calcul the mask position with numpy : 0.015401601791381836 nb_pixel_total : 55 time to create 1 rle with old method : 0.00013494491577148438 time for calcul the mask position with numpy : 0.015159845352172852 nb_pixel_total : 659 time to create 1 rle with old method : 0.0007801055908203125 time for calcul the mask position with numpy : 0.015331029891967773 nb_pixel_total : 3272 time to create 1 rle with old method : 0.003751516342163086 time for calcul the mask position with numpy : 0.01504206657409668 nb_pixel_total : 2469 time to create 1 rle with old method : 0.0028002262115478516 time for calcul the mask position with numpy : 0.015094757080078125 nb_pixel_total : 3194 time to create 1 rle with old method : 0.0035719871520996094 time for calcul the mask position with numpy : 0.01513814926147461 nb_pixel_total : 822 time to create 1 rle with old method : 0.0011234283447265625 time for calcul the mask position with numpy : 0.01503443717956543 nb_pixel_total : 5522 time to create 1 rle with old method : 0.006242275238037109 time for calcul the mask position with numpy : 0.014996528625488281 nb_pixel_total : 458 time to create 1 rle with old method : 0.0005559921264648438 time for calcul the mask position with numpy : 0.014914751052856445 nb_pixel_total : 800 time to create 1 rle with old method : 0.0009369850158691406 time for calcul the mask position with numpy : 0.014904975891113281 nb_pixel_total : 6440 time to create 1 rle with old method : 0.007325887680053711 time for calcul the mask position with numpy : 0.015088081359863281 nb_pixel_total : 583 time to create 1 rle with old method : 0.0006844997406005859 time for calcul the mask position with numpy : 0.014959573745727539 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0011560916900634766 time for calcul the mask position with numpy : 0.014912843704223633 nb_pixel_total : 588 time to create 1 rle with old method : 0.0006906986236572266 time for calcul the mask position with numpy : 0.015891313552856445 nb_pixel_total : 322 time to create 1 rle with old method : 0.000423431396484375 time for calcul the mask position with numpy : 0.015264511108398438 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003733634948730469 time for calcul the mask position with numpy : 0.015253067016601562 nb_pixel_total : 17425 time to create 1 rle with old method : 0.019240617752075195 time for calcul the mask position with numpy : 0.015138387680053711 nb_pixel_total : 1309 time to create 1 rle with old method : 0.0015163421630859375 time for calcul the mask position with numpy : 0.014990568161010742 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0015833377838134766 time for calcul the mask position with numpy : 0.014969587326049805 nb_pixel_total : 1445 time to create 1 rle with old method : 0.0016527175903320312 time for calcul the mask position with numpy : 0.01490163803100586 nb_pixel_total : 16 time to create 1 rle with old method : 7.891654968261719e-05 time for calcul the mask position with numpy : 0.022171974182128906 nb_pixel_total : 2010 time to create 1 rle with old method : 0.0023365020751953125 time for calcul the mask position with numpy : 0.015209197998046875 nb_pixel_total : 929 time to create 1 rle with old method : 0.0011179447174072266 time for calcul the mask position with numpy : 0.01856374740600586 nb_pixel_total : 103 time to create 1 rle with old method : 0.0002052783966064453 time for calcul the mask position with numpy : 0.015811681747436523 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002624988555908203 time for calcul the mask position with numpy : 0.015256166458129883 nb_pixel_total : 2828 time to create 1 rle with old method : 0.0032682418823242188 time for calcul the mask position with numpy : 0.015070676803588867 nb_pixel_total : 84 time to create 1 rle with old method : 0.00014734268188476562 time for calcul the mask position with numpy : 0.01510763168334961 nb_pixel_total : 1183 time to create 1 rle with old method : 0.0013949871063232422 time for calcul the mask position with numpy : 0.015019416809082031 nb_pixel_total : 1157 time to create 1 rle with old method : 0.0013794898986816406 time for calcul the mask position with numpy : 0.015788555145263672 nb_pixel_total : 409 time to create 1 rle with old method : 0.0005514621734619141 time for calcul the mask position with numpy : 0.015418767929077148 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006256103515625 time for calcul the mask position with numpy : 0.015324831008911133 nb_pixel_total : 455 time to create 1 rle with old method : 0.0005548000335693359 time for calcul the mask position with numpy : 0.015360832214355469 nb_pixel_total : 13 time to create 1 rle with old method : 5.841255187988281e-05 time for calcul the mask position with numpy : 0.016894817352294922 nb_pixel_total : 37 time to create 1 rle with old method : 9.036064147949219e-05 time for calcul the mask position with numpy : 0.014923810958862305 nb_pixel_total : 538 time to create 1 rle with old method : 0.0005953311920166016 time for calcul the mask position with numpy : 0.017490386962890625 nb_pixel_total : 3223 time to create 1 rle with old method : 0.003715991973876953 time for calcul the mask position with numpy : 0.01504826545715332 nb_pixel_total : 103 time to create 1 rle with old method : 0.00017142295837402344 time for calcul the mask position with numpy : 0.015099287033081055 nb_pixel_total : 1370 time to create 1 rle with old method : 0.0016300678253173828 time for calcul the mask position with numpy : 0.015389680862426758 nb_pixel_total : 1410 time to create 1 rle with old method : 0.0016367435455322266 time for calcul the mask position with numpy : 0.015097856521606445 nb_pixel_total : 926 time to create 1 rle with old method : 0.0010929107666015625 time for calcul the mask position with numpy : 0.015100955963134766 nb_pixel_total : 1116 time to create 1 rle with old method : 0.0012826919555664062 time for calcul the mask position with numpy : 0.0161283016204834 nb_pixel_total : 103 time to create 1 rle with old method : 0.00016927719116210938 time for calcul the mask position with numpy : 0.01510763168334961 nb_pixel_total : 761 time to create 1 rle with old method : 0.0009167194366455078 time for calcul the mask position with numpy : 0.015944242477416992 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005183219909667969 time for calcul the mask position with numpy : 0.015198230743408203 nb_pixel_total : 4144 time to create 1 rle with old method : 0.004648923873901367 time for calcul the mask position with numpy : 0.015153646469116211 nb_pixel_total : 1307 time to create 1 rle with old method : 0.0015554428100585938 time for calcul the mask position with numpy : 0.01671600341796875 nb_pixel_total : 1787 time to create 1 rle with old method : 0.002454042434692383 time for calcul the mask position with numpy : 0.016761064529418945 nb_pixel_total : 7152 time to create 1 rle with old method : 0.007926225662231445 time for calcul the mask position with numpy : 0.01592707633972168 nb_pixel_total : 21 time to create 1 rle with old method : 9.512901306152344e-05 time for calcul the mask position with numpy : 0.015207529067993164 nb_pixel_total : 243 time to create 1 rle with old method : 0.00029754638671875 time for calcul the mask position with numpy : 0.015090703964233398 nb_pixel_total : 1799 time to create 1 rle with old method : 0.002082347869873047 time for calcul the mask position with numpy : 0.01505279541015625 nb_pixel_total : 1725 time to create 1 rle with old method : 0.0020530223846435547 time for calcul the mask position with numpy : 0.01510167121887207 nb_pixel_total : 46 time to create 1 rle with old method : 0.00010633468627929688 time for calcul the mask position with numpy : 0.015317201614379883 nb_pixel_total : 2514 time to create 1 rle with old method : 0.00286865234375 time for calcul the mask position with numpy : 0.015199661254882812 nb_pixel_total : 699 time to create 1 rle with old method : 0.0008139610290527344 time for calcul the mask position with numpy : 0.015000104904174805 nb_pixel_total : 3765 time to create 1 rle with old method : 0.005280494689941406 time for calcul the mask position with numpy : 0.015234708786010742 nb_pixel_total : 1384 time to create 1 rle with old method : 0.0016427040100097656 time for calcul the mask position with numpy : 0.015084505081176758 nb_pixel_total : 2508 time to create 1 rle with old method : 0.0028505325317382812 time for calcul the mask position with numpy : 0.014978170394897461 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005056858062744141 time for calcul the mask position with numpy : 0.014334678649902344 nb_pixel_total : 237 time to create 1 rle with old method : 0.00034737586975097656 time for calcul the mask position with numpy : 0.017893314361572266 nb_pixel_total : 27 time to create 1 rle with old method : 0.00012922286987304688 time for calcul the mask position with numpy : 0.015014886856079102 nb_pixel_total : 3284 time to create 1 rle with old method : 0.0037603378295898438 time for calcul the mask position with numpy : 0.015036582946777344 nb_pixel_total : 347 time to create 1 rle with old method : 0.00038695335388183594 time for calcul the mask position with numpy : 0.014992237091064453 nb_pixel_total : 2333 time to create 1 rle with old method : 0.0026552677154541016 time for calcul the mask position with numpy : 0.014939308166503906 nb_pixel_total : 191 time to create 1 rle with old method : 0.00023603439331054688 time for calcul the mask position with numpy : 0.01502680778503418 nb_pixel_total : 51 time to create 1 rle with old method : 0.0001227855682373047 time for calcul the mask position with numpy : 0.015119552612304688 nb_pixel_total : 593 time to create 1 rle with old method : 0.0007321834564208984 time for calcul the mask position with numpy : 0.01482081413269043 nb_pixel_total : 983 time to create 1 rle with old method : 0.0011682510375976562 time for calcul the mask position with numpy : 0.014657974243164062 nb_pixel_total : 207 time to create 1 rle with old method : 0.00027441978454589844 time for calcul the mask position with numpy : 0.014780282974243164 nb_pixel_total : 1752 time to create 1 rle with old method : 0.0020668506622314453 time for calcul the mask position with numpy : 0.01493382453918457 nb_pixel_total : 7261 time to create 1 rle with old method : 0.008072614669799805 time for calcul the mask position with numpy : 0.014960050582885742 nb_pixel_total : 1496 time to create 1 rle with old method : 0.0017805099487304688 time for calcul the mask position with numpy : 0.014969587326049805 nb_pixel_total : 20327 time to create 1 rle with old method : 0.023059606552124023 time for calcul the mask position with numpy : 0.014929771423339844 nb_pixel_total : 13669 time to create 1 rle with old method : 0.014897584915161133 time for calcul the mask position with numpy : 0.015010356903076172 nb_pixel_total : 1990 time to create 1 rle with old method : 0.0022640228271484375 time for calcul the mask position with numpy : 0.014976739883422852 nb_pixel_total : 422 time to create 1 rle with old method : 0.0005123615264892578 time for calcul the mask position with numpy : 0.014947891235351562 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0012671947479248047 time for calcul the mask position with numpy : 0.014885902404785156 nb_pixel_total : 4650 time to create 1 rle with old method : 0.00526118278503418 time for calcul the mask position with numpy : 0.014615774154663086 nb_pixel_total : 11 time to create 1 rle with old method : 2.3603439331054688e-05 time for calcul the mask position with numpy : 0.0149383544921875 nb_pixel_total : 171 time to create 1 rle with old method : 0.00021409988403320312 time for calcul the mask position with numpy : 0.014927864074707031 nb_pixel_total : 413 time to create 1 rle with old method : 0.0004961490631103516 time for calcul the mask position with numpy : 0.015022516250610352 nb_pixel_total : 779 time to create 1 rle with old method : 0.0009160041809082031 time for calcul the mask position with numpy : 0.015157222747802734 nb_pixel_total : 130 time to create 1 rle with old method : 0.00017905235290527344 time for calcul the mask position with numpy : 0.015231132507324219 nb_pixel_total : 685 time to create 1 rle with old method : 0.0008356571197509766 time for calcul the mask position with numpy : 0.01513671875 nb_pixel_total : 997 time to create 1 rle with old method : 0.0012249946594238281 time for calcul the mask position with numpy : 0.015405893325805664 nb_pixel_total : 1870 time to create 1 rle with old method : 0.0022420883178710938 time for calcul the mask position with numpy : 0.01537179946899414 nb_pixel_total : 5745 time to create 1 rle with old method : 0.006331920623779297 time for calcul the mask position with numpy : 0.016962051391601562 nb_pixel_total : 409 time to create 1 rle with old method : 0.0005047321319580078 time for calcul the mask position with numpy : 0.014996051788330078 nb_pixel_total : 397 time to create 1 rle with old method : 0.0004813671112060547 time for calcul the mask position with numpy : 0.015002250671386719 nb_pixel_total : 346 time to create 1 rle with old method : 0.0004076957702636719 time for calcul the mask position with numpy : 0.015002250671386719 nb_pixel_total : 6892 time to create 1 rle with old method : 0.007813215255737305 time for calcul the mask position with numpy : 0.014903545379638672 nb_pixel_total : 2032 time to create 1 rle with old method : 0.002324819564819336 time for calcul the mask position with numpy : 0.014955520629882812 nb_pixel_total : 123 time to create 1 rle with old method : 0.00016450881958007812 time for calcul the mask position with numpy : 0.014208555221557617 nb_pixel_total : 508 time to create 1 rle with old method : 0.0005555152893066406 time for calcul the mask position with numpy : 0.014568567276000977 nb_pixel_total : 896 time to create 1 rle with old method : 0.00103759765625 time for calcul the mask position with numpy : 0.014898300170898438 nb_pixel_total : 1387 time to create 1 rle with old method : 0.001596212387084961 time for calcul the mask position with numpy : 0.014971256256103516 nb_pixel_total : 5971 time to create 1 rle with old method : 0.006614208221435547 time for calcul the mask position with numpy : 0.014989614486694336 nb_pixel_total : 35 time to create 1 rle with old method : 8.416175842285156e-05 time for calcul the mask position with numpy : 0.01497030258178711 nb_pixel_total : 829 time to create 1 rle with old method : 0.000990152359008789 time for calcul the mask position with numpy : 0.014977693557739258 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006470680236816406 time for calcul the mask position with numpy : 0.014968395233154297 nb_pixel_total : 718 time to create 1 rle with old method : 0.0008487701416015625 time for calcul the mask position with numpy : 0.01501321792602539 nb_pixel_total : 491 time to create 1 rle with old method : 0.0006017684936523438 time for calcul the mask position with numpy : 0.015184640884399414 nb_pixel_total : 791 time to create 1 rle with old method : 0.0009334087371826172 time for calcul the mask position with numpy : 0.014991521835327148 nb_pixel_total : 64 time to create 1 rle with old method : 0.00011181831359863281 time for calcul the mask position with numpy : 0.016674518585205078 nb_pixel_total : 427 time to create 1 rle with old method : 0.0008358955383300781 time for calcul the mask position with numpy : 0.015012741088867188 nb_pixel_total : 1628 time to create 1 rle with old method : 0.0018458366394042969 time for calcul the mask position with numpy : 0.015069723129272461 nb_pixel_total : 241 time to create 1 rle with old method : 0.00031185150146484375 time for calcul the mask position with numpy : 0.015062808990478516 nb_pixel_total : 759 time to create 1 rle with old method : 0.0008943080902099609 time for calcul the mask position with numpy : 0.01495051383972168 nb_pixel_total : 410 time to create 1 rle with old method : 0.0004937648773193359 time for calcul the mask position with numpy : 0.014956235885620117 nb_pixel_total : 3353 time to create 1 rle with old method : 0.0038385391235351562 time for calcul the mask position with numpy : 0.01526498794555664 nb_pixel_total : 75 time to create 1 rle with old method : 0.00014495849609375 time for calcul the mask position with numpy : 0.015378236770629883 nb_pixel_total : 1215 time to create 1 rle with old method : 0.0015065670013427734 time for calcul the mask position with numpy : 0.015313148498535156 nb_pixel_total : 1775 time to create 1 rle with old method : 0.0023293495178222656 time for calcul the mask position with numpy : 0.01807546615600586 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006132125854492188 time for calcul the mask position with numpy : 0.015936613082885742 nb_pixel_total : 1237 time to create 1 rle with old method : 0.0014729499816894531 time for calcul the mask position with numpy : 0.015217781066894531 nb_pixel_total : 706 time to create 1 rle with old method : 0.000885009765625 time for calcul the mask position with numpy : 0.015071868896484375 nb_pixel_total : 2060 time to create 1 rle with old method : 0.002373933792114258 time for calcul the mask position with numpy : 0.01476430892944336 nb_pixel_total : 336 time to create 1 rle with old method : 0.0003757476806640625 time for calcul the mask position with numpy : 0.014555215835571289 nb_pixel_total : 855 time to create 1 rle with old method : 0.0009770393371582031 time for calcul the mask position with numpy : 0.014825582504272461 nb_pixel_total : 4470 time to create 1 rle with old method : 0.0050504207611083984 time for calcul the mask position with numpy : 0.015837669372558594 nb_pixel_total : 3303 time to create 1 rle with old method : 0.0037424564361572266 time for calcul the mask position with numpy : 0.015198469161987305 nb_pixel_total : 1460 time to create 1 rle with old method : 0.0017642974853515625 time for calcul the mask position with numpy : 0.020325183868408203 nb_pixel_total : 115 time to create 1 rle with old method : 0.00037670135498046875 time for calcul the mask position with numpy : 0.01656651496887207 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007226467132568359 time for calcul the mask position with numpy : 0.016348838806152344 nb_pixel_total : 545 time to create 1 rle with old method : 0.0008442401885986328 time for calcul the mask position with numpy : 0.01782083511352539 nb_pixel_total : 4094 time to create 1 rle with old method : 0.00471949577331543 time for calcul the mask position with numpy : 0.01424551010131836 nb_pixel_total : 186 time to create 1 rle with old method : 0.00022935867309570312 time for calcul the mask position with numpy : 0.014531373977661133 nb_pixel_total : 477 time to create 1 rle with old method : 0.0005483627319335938 time for calcul the mask position with numpy : 0.01434779167175293 nb_pixel_total : 386 time to create 1 rle with old method : 0.0004639625549316406 time for calcul the mask position with numpy : 0.014879226684570312 nb_pixel_total : 2348 time to create 1 rle with old method : 0.0026404857635498047 time for calcul the mask position with numpy : 0.016149044036865234 nb_pixel_total : 545 time to create 1 rle with old method : 0.0007190704345703125 time for calcul the mask position with numpy : 0.015148162841796875 nb_pixel_total : 1598 time to create 1 rle with old method : 0.0017957687377929688 time for calcul the mask position with numpy : 0.018650531768798828 nb_pixel_total : 740 time to create 1 rle with old method : 0.0009496212005615234 create new chi : 9.830803155899048 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.022755861282348633 batch 1 Loaded 513 chid ids of type : 4230 Number RLEs to save : 60755 TO DO : save crop sub photo not yet done ! save time : 7.887466907501221 map_output_result : {1334899197: (0.0, 'Should be the crop_list due to order', 0.0)} 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 [1334899197] Looping around the photos to save general results len do output : 1 /1334899197.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 ('4234', None, None, None, None, None, None, None, '2551234') ('4234', '20255472', '1334899197', None, None, None, None, None, '2551234') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.011719942092895508 save_final save missing photos in datou_result : time spend for datou_step_exec : 20.705260276794434 time spend to save output : 0.012252330780029297 total time spend for step 4 : 20.717512607574463 step5:crop_condition Wed Feb 5 12:21:20 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 1 ! batch 1 Loaded 513 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 224 About to insert : list_path_to_insert length 224 new photo from crops ! About to upload 224 photos upload in portfolio : 4869462 init cache_photo without model_param we have 224 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738754487_3620078 we have uploaded 224 photos in the portfolio 4869462 time of upload the photos Elapsed time : 55.392375230789185 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 114 About to insert : list_path_to_insert length 114 new photo from crops ! About to upload 114 photos upload in portfolio : 4869462 init cache_photo without model_param we have 114 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738754546_3620078 we have uploaded 114 photos in the portfolio 4869462 time of upload the photos Elapsed time : 27.896102905273438 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738754574_3620078 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.6260771751403809 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 11 About to insert : list_path_to_insert length 11 new photo from crops ! About to upload 11 photos upload in portfolio : 4869462 init cache_photo without model_param we have 11 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738754576_3620078 we have uploaded 11 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.302048444747925 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! About to upload 13 photos upload in portfolio : 4869462 init cache_photo without model_param we have 13 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738754580_3620078 we have uploaded 13 photos in the portfolio 4869462 time of upload the photos Elapsed time : 2.913311719894409 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 4869462 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738754583_3620078 we have uploaded 3 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.954932451248169 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 Next one ! Next one ! Next one ! 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 : 4869462 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738754585_3620078 we have uploaded 4 photos in the portfolio 4869462 time of upload the photos Elapsed time : 2.003610849380493 we have finished the crop for the class : pet_fonce delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1334899197] Looping around the photos to save general results len do output : 370 /1334909323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909342Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909392Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909394Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909396Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909398Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909399Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909401Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909404Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909405Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909406Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909407Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909408Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909409Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909410Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909412Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909413Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909414Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909415Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909416Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909417Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909418Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909419Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909420Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909421Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909422Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909423Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909424Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909425Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909426Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909427Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909428Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909460Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909474Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909494Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334909978Didn'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 ('4234', None, None, None, None, None, None, None, '2551234') ('4234', '20255472', '1334899197', None, None, None, None, None, '2551234') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1111 time used for this insertion : 1.846297025680542 save_final save missing photos in datou_result : time spend for datou_step_exec : 107.17188858985901 time spend to save output : 1.878443956375122 total time spend for step 5 : 109.05033254623413 step6:thcl Wed Feb 5 12:23:09 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 Beginning of datou step Thcl ! we are using the classfication for only one thcl 3237 time to import caffe and check if the image exist : 0.02041912078857422 time to convert the images to numpy array : 0.10770249366760254 time to import caffe and check if the image exist : 0.047396183013916016 time to convert the images to numpy array : 0.11756467819213867 time to import caffe and check if the image exist : 0.036618709564208984 time to convert the images to numpy array : 0.13086938858032227 time to import caffe and check if the image exist : 0.028366804122924805 time to convert the images to numpy array : 0.1398007869720459 time to import caffe and check if the image exist : 0.04262566566467285 time to convert the images to numpy array : 0.12954306602478027 time to import caffe and check if the image exist : 0.043969154357910156 time to convert the images to numpy array : 0.12984466552734375 time to import caffe and check if the image exist : 0.03791332244873047 time to convert the images to numpy array : 0.1382122039794922 time to import caffe and check if the image exist : 0.043733835220336914 time to convert the images to numpy array : 0.13717079162597656 time to import caffe and check if the image exist : 0.05030417442321777 time to convert the images to numpy array : 0.1315290927886963 time to import caffe and check if the image exist : 0.048891305923461914 time to convert the images to numpy array : 0.14396882057189941 total time to convert the images to numpy array : 0.7157604694366455 list photo_ids error: [] list photo_ids correct : [1334909323, 1334909324, 1334909325, 1334909326, 1334909327, 1334909328, 1334909329, 1334909330, 1334909331, 1334909332, 1334909333, 1334909334, 1334909335, 1334909336, 1334909337, 1334909338, 1334909339, 1334909340, 1334909341, 1334909342, 1334909343, 1334909344, 1334909345, 1334909346, 1334909347, 1334909348, 1334909349, 1334909350, 1334909351, 1334909352, 1334909353, 1334909354, 1334909355, 1334909356, 1334909357, 1334909358, 1334909359, 1334909508, 1334909509, 1334909510, 1334909511, 1334909512, 1334909513, 1334909514, 1334909515, 1334909516, 1334909517, 1334909518, 1334909519, 1334909520, 1334909521, 1334909522, 1334909523, 1334909524, 1334909525, 1334909526, 1334909527, 1334909528, 1334909529, 1334909530, 1334909531, 1334909532, 1334909533, 1334909534, 1334909535, 1334909536, 1334909537, 1334909538, 1334909539, 1334909540, 1334909541, 1334909542, 1334909543, 1334909544, 1334909360, 1334909361, 1334909362, 1334909363, 1334909364, 1334909365, 1334909366, 1334909367, 1334909368, 1334909369, 1334909370, 1334909371, 1334909372, 1334909373, 1334909374, 1334909375, 1334909376, 1334909377, 1334909378, 1334909379, 1334909380, 1334909381, 1334909382, 1334909383, 1334909384, 1334909385, 1334909386, 1334909387, 1334909388, 1334909389, 1334909390, 1334909391, 1334909392, 1334909393, 1334909394, 1334909395, 1334909396, 1334909925, 1334909926, 1334909927, 1334909928, 1334909929, 1334909933, 1334909936, 1334909937, 1334909938, 1334909939, 1334909940, 1334909941, 1334909942, 1334909943, 1334909944, 1334909945, 1334909946, 1334909950, 1334909951, 1334909952, 1334909954, 1334909955, 1334909956, 1334909957, 1334909958, 1334909959, 1334909960, 1334909961, 1334909962, 1334909963, 1334909968, 1334909969, 1334909970, 1334909975, 1334909976, 1334909977, 1334909978, 1334909545, 1334909546, 1334909764, 1334909766, 1334909769, 1334909771, 1334909773, 1334909775, 1334909777, 1334909779, 1334909781, 1334909783, 1334909785, 1334909787, 1334909789, 1334909790, 1334909792, 1334909794, 1334909796, 1334909798, 1334909800, 1334909802, 1334909804, 1334909806, 1334909808, 1334909810, 1334909812, 1334909814, 1334909816, 1334909818, 1334909820, 1334909822, 1334909824, 1334909826, 1334909828, 1334909830, 1334909832, 1334909471, 1334909472, 1334909473, 1334909474, 1334909475, 1334909476, 1334909477, 1334909478, 1334909479, 1334909480, 1334909481, 1334909482, 1334909483, 1334909484, 1334909485, 1334909486, 1334909487, 1334909488, 1334909489, 1334909490, 1334909491, 1334909492, 1334909493, 1334909494, 1334909495, 1334909496, 1334909497, 1334909498, 1334909499, 1334909500, 1334909501, 1334909502, 1334909503, 1334909504, 1334909505, 1334909506, 1334909507, 1334909834, 1334909836, 1334909838, 1334909840, 1334909842, 1334909844, 1334909846, 1334909848, 1334909850, 1334909852, 1334909854, 1334909856, 1334909858, 1334909859, 1334909860, 1334909861, 1334909862, 1334909864, 1334909865, 1334909866, 1334909867, 1334909868, 1334909869, 1334909871, 1334909872, 1334909873, 1334909874, 1334909875, 1334909876, 1334909877, 1334909878, 1334909879, 1334909880, 1334909881, 1334909882, 1334909883, 1334909884, 1334909434, 1334909435, 1334909436, 1334909437, 1334909438, 1334909439, 1334909440, 1334909441, 1334909442, 1334909443, 1334909444, 1334909445, 1334909446, 1334909447, 1334909448, 1334909449, 1334909450, 1334909451, 1334909452, 1334909453, 1334909454, 1334909455, 1334909456, 1334909457, 1334909458, 1334909459, 1334909460, 1334909461, 1334909462, 1334909463, 1334909464, 1334909465, 1334909466, 1334909467, 1334909468, 1334909469, 1334909470, 1334909885, 1334909886, 1334909887, 1334909888, 1334909889, 1334909890, 1334909891, 1334909892, 1334909893, 1334909894, 1334909895, 1334909896, 1334909897, 1334909898, 1334909899, 1334909901, 1334909902, 1334909903, 1334909904, 1334909905, 1334909906, 1334909908, 1334909909, 1334909910, 1334909911, 1334909913, 1334909914, 1334909915, 1334909916, 1334909917, 1334909918, 1334909919, 1334909920, 1334909921, 1334909922, 1334909923, 1334909924, 1334909397, 1334909398, 1334909399, 1334909400, 1334909401, 1334909402, 1334909403, 1334909404, 1334909405, 1334909406, 1334909407, 1334909408, 1334909409, 1334909410, 1334909411, 1334909412, 1334909413, 1334909414, 1334909415, 1334909416, 1334909417, 1334909418, 1334909419, 1334909420, 1334909421, 1334909422, 1334909423, 1334909424, 1334909425, 1334909426, 1334909427, 1334909428, 1334909429, 1334909430, 1334909431, 1334909432, 1334909433] number of photos to traite : 370 try to delete the photos incorrect in DB tagging for thcl : 3237 To do loadFromThcl(), then load ParamDescType : thcl3237 thcls : [{'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'}] thcl {'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'} Update svm_hashtag_type_desc : 5561 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) To loadFromThcl() : net_5561 begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 1288 wait 20 seconds l 3637 free memory gpu now : 1288 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_rubbia_refus_2500 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_rubbia_refus_2500 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_rubbia_refus_2500 /data/models_weight/learn_rubbia_refus_2500/caffemodel size_local : 94358479 size in s3 : 94358479 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:16 caffemodel already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt size_local : 32544 size in s3 : 32544 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:15 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:09:52 mean.npy already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/synset_words.txt size_local : 334 size in s3 : 334 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:10:06 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /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/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt caffemodel_filename : /data/models_weight/learn_rubbia_refus_2500/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3167 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 2.301079511642456 time used to do the prediction : 1.4622864723205566 save descriptor for thcl : 3237 time to traite the descriptors : 2.193025827407837 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1334909323 To insert : 1334909324 To insert : 1334909325 To insert : 1334909326 To insert : 1334909327 To insert : 1334909328 To insert : 1334909329 To insert : 1334909330 To insert : 1334909331 To insert : 1334909332 To insert : 1334909333 To insert : 1334909334 To insert : 1334909335 To insert : 1334909336 To insert : 1334909337 To insert : 1334909338 To insert : 1334909339 To insert : 1334909340 To insert : 1334909341 To insert : 1334909342 To insert : 1334909343 To insert : 1334909344 To insert : 1334909345 To insert : 1334909346 To insert : 1334909347 To insert : 1334909348 To insert : 1334909349 To insert : 1334909350 To insert : 1334909351 To insert : 1334909352 To insert : 1334909353 To insert : 1334909354 To insert : 1334909355 To insert : 1334909356 To insert : 1334909357 To insert : 1334909358 To insert : 1334909359 To insert : 1334909508 To insert : 1334909509 To insert : 1334909510 To insert : 1334909511 To insert : 1334909512 To insert : 1334909513 To insert : 1334909514 To insert : 1334909515 To insert : 1334909516 To insert : 1334909517 To insert : 1334909518 To insert : 1334909519 To insert : 1334909520 To insert : 1334909521 To insert : 1334909522 To insert : 1334909523 To insert : 1334909524 To insert : 1334909525 To insert : 1334909526 To insert : 1334909527 To insert : 1334909528 To insert : 1334909529 To insert : 1334909530 To insert : 1334909531 To insert : 1334909532 To insert : 1334909533 To insert : 1334909534 To insert : 1334909535 To insert : 1334909536 To insert : 1334909537 To insert : 1334909538 To insert : 1334909539 To insert : 1334909540 To insert : 1334909541 To insert : 1334909542 To insert : 1334909543 To insert : 1334909544 To insert : 1334909360 To insert : 1334909361 To insert : 1334909362 To insert : 1334909363 To insert : 1334909364 To insert : 1334909365 To insert : 1334909366 To insert : 1334909367 To insert : 1334909368 To insert : 1334909369 To insert : 1334909370 To insert : 1334909371 To insert : 1334909372 To insert : 1334909373 To insert : 1334909374 To insert : 1334909375 To insert : 1334909376 To insert : 1334909377 To insert : 1334909378 To insert : 1334909379 To insert : 1334909380 To insert : 1334909381 To insert : 1334909382 To insert : 1334909383 To insert : 1334909384 To insert : 1334909385 To insert : 1334909386 To insert : 1334909387 To insert : 1334909388 To insert : 1334909389 To insert : 1334909390 To insert : 1334909391 To insert : 1334909392 To insert : 1334909393 To insert : 1334909394 To insert : 1334909395 To insert : 1334909396 To insert : 1334909925 To insert : 1334909926 To insert : 1334909927 To insert : 1334909928 To insert : 1334909929 To insert : 1334909933 To insert : 1334909936 To insert : 1334909937 To insert : 1334909938 To insert : 1334909939 To insert : 1334909940 To insert : 1334909941 To insert : 1334909942 To insert : 1334909943 To insert : 1334909944 To insert : 1334909945 To insert : 1334909946 To insert : 1334909950 To insert : 1334909951 To insert : 1334909952 To insert : 1334909954 To insert : 1334909955 To insert : 1334909956 To insert : 1334909957 To insert : 1334909958 To insert : 1334909959 To insert : 1334909960 To insert : 1334909961 To insert : 1334909962 To insert : 1334909963 To insert : 1334909968 To insert : 1334909969 To insert : 1334909970 To insert : 1334909975 To insert : 1334909976 To insert : 1334909977 To insert : 1334909978 To insert : 1334909545 To insert : 1334909546 To insert : 1334909764 To insert : 1334909766 To insert : 1334909769 To insert : 1334909771 To insert : 1334909773 To insert : 1334909775 To insert : 1334909777 To insert : 1334909779 To insert : 1334909781 To insert : 1334909783 To insert : 1334909785 To insert : 1334909787 To insert : 1334909789 To insert : 1334909790 To insert : 1334909792 To insert : 1334909794 To insert : 1334909796 To insert : 1334909798 To insert : 1334909800 To insert : 1334909802 To insert : 1334909804 To insert : 1334909806 To insert : 1334909808 To insert : 1334909810 To insert : 1334909812 To insert : 1334909814 To insert : 1334909816 To insert : 1334909818 To insert : 1334909820 To insert : 1334909822 To insert : 1334909824 To insert : 1334909826 To insert : 1334909828 To insert : 1334909830 To insert : 1334909832 To insert : 1334909471 To insert : 1334909472 To insert : 1334909473 To insert : 1334909474 To insert : 1334909475 To insert : 1334909476 To insert : 1334909477 To insert : 1334909478 To insert : 1334909479 To insert : 1334909480 To insert : 1334909481 To insert : 1334909482 To insert : 1334909483 To insert : 1334909484 To insert : 1334909485 To insert : 1334909486 To insert : 1334909487 To insert : 1334909488 To insert : 1334909489 To insert : 1334909490 To insert : 1334909491 To insert : 1334909492 To insert : 1334909493 To insert : 1334909494 To insert : 1334909495 To insert : 1334909496 To insert : 1334909497 To insert : 1334909498 To insert : 1334909499 To insert : 1334909500 To insert : 1334909501 To insert : 1334909502 To insert : 1334909503 To insert : 1334909504 To insert : 1334909505 To insert : 1334909506 To insert : 1334909507 To insert : 1334909834 To insert : 1334909836 To insert : 1334909838 To insert : 1334909840 To insert : 1334909842 To insert : 1334909844 To insert : 1334909846 To insert : 1334909848 To insert : 1334909850 To insert : 1334909852 To insert : 1334909854 To insert : 1334909856 To insert : 1334909858 To insert : 1334909859 To insert : 1334909860 To insert : 1334909861 To insert : 1334909862 To insert : 1334909864 To insert : 1334909865 To insert : 1334909866 To insert : 1334909867 To insert : 1334909868 To insert : 1334909869 To insert : 1334909871 To insert : 1334909872 To insert : 1334909873 To insert : 1334909874 To insert : 1334909875 To insert : 1334909876 To insert : 1334909877 To insert : 1334909878 To insert : 1334909879 To insert : 1334909880 To insert : 1334909881 To insert : 1334909882 To insert : 1334909883 To insert : 1334909884 To insert : 1334909434 To insert : 1334909435 To insert : 1334909436 To insert : 1334909437 To insert : 1334909438 To insert : 1334909439 To insert : 1334909440 To insert : 1334909441 To insert : 1334909442 To insert : 1334909443 To insert : 1334909444 To insert : 1334909445 To insert : 1334909446 To insert : 1334909447 To insert : 1334909448 To insert : 1334909449 To insert : 1334909450 To insert : 1334909451 To insert : 1334909452 To insert : 1334909453 To insert : 1334909454 To insert : 1334909455 To insert : 1334909456 To insert : 1334909457 To insert : 1334909458 To insert : 1334909459 To insert : 1334909460 To insert : 1334909461 To insert : 1334909462 To insert : 1334909463 To insert : 1334909464 To insert : 1334909465 To insert : 1334909466 To insert : 1334909467 To insert : 1334909468 To insert : 1334909469 To insert : 1334909470 To insert : 1334909885 To insert : 1334909886 To insert : 1334909887 To insert : 1334909888 To insert : 1334909889 To insert : 1334909890 To insert : 1334909891 To insert : 1334909892 To insert : 1334909893 To insert : 1334909894 To insert : 1334909895 To insert : 1334909896 To insert : 1334909897 To insert : 1334909898 To insert : 1334909899 To insert : 1334909901 To insert : 1334909902 To insert : 1334909903 To insert : 1334909904 To insert : 1334909905 To insert : 1334909906 To insert : 1334909908 To insert : 1334909909 To insert : 1334909910 To insert : 1334909911 To insert : 1334909913 To insert : 1334909914 To insert : 1334909915 To insert : 1334909916 To insert : 1334909917 To insert : 1334909918 To insert : 1334909919 To insert : 1334909920 To insert : 1334909921 To insert : 1334909922 To insert : 1334909923 To insert : 1334909924 To insert : 1334909397 To insert : 1334909398 To insert : 1334909399 To insert : 1334909400 To insert : 1334909401 To insert : 1334909402 To insert : 1334909403 To insert : 1334909404 To insert : 1334909405 To insert : 1334909406 To insert : 1334909407 To insert : 1334909408 To insert : 1334909409 To insert : 1334909410 To insert : 1334909411 To insert : 1334909412 To insert : 1334909413 To insert : 1334909414 To insert : 1334909415 To insert : 1334909416 To insert : 1334909417 To insert : 1334909418 To insert : 1334909419 To insert : 1334909420 To insert : 1334909421 To insert : 1334909422 To insert : 1334909423 To insert : 1334909424 To insert : 1334909425 To insert : 1334909426 To insert : 1334909427 To insert : 1334909428 To insert : 1334909429 To insert : 1334909430 To insert : 1334909431 To insert : 1334909432 To insert : 1334909433 time to insert the descriptors : 62.69611430168152 Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos SAVE THCL : begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 544 time used for this insertion : 0.04538702964782715 save missing photos in datou_result : time spend for datou_step_exec : 97.85230350494385 time spend to save output : 0.10119509696960449 total time spend for step 6 : 97.95349860191345 step7:ventilate_hashtags_in_portfolio Wed Feb 5 12:24:47 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 : 20255472 get user id for portfolio 20255472 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`=20255472 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('metal','PET_fonce','flou','pehd','pet_fonce','environnement','Film_plastique','Carton','PET_clair','Papier','pet_clair','autre','PEHD','refus','Tetrapak','mal_croppe','carton','papier')) AND mptpi.`min_score`=0.6 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`=20255472 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('metal','PET_fonce','flou','pehd','pet_fonce','environnement','Film_plastique','Carton','PET_clair','Papier','pet_clair','autre','PEHD','refus','Tetrapak','mal_croppe','carton','papier')) AND mptpi.`min_score`=0.6 To do Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=20255472 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('metal','PET_fonce','flou','pehd','pet_fonce','environnement','Film_plastique','Carton','PET_clair','Papier','pet_clair','autre','PEHD','refus','Tetrapak','mal_croppe','carton','papier')) AND mptpi.`min_score`=0.6 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`=20255472 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('metal','PET_fonce','flou','pehd','pet_fonce','environnement','Film_plastique','Carton','PET_clair','Papier','pet_clair','autre','PEHD','refus','Tetrapak','mal_croppe','carton','papier')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20256222,20256226,20256224,20256235,20256227,20256228,20256239,20256233,20256240,20256234,20256236,20256237,20256238?tags=metal,pet_fonce,flou,pehd,environnement,film_plastique,carton,pet_clair,papier,autre,refus,tetrapak,mal_croppe&datou_id_consolidate=4235&port_consolidate=20255472 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1334899197] Looping around the photos to save general results len do output : 1 /20255472. 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 ('4234', None, None, None, None, None, None, None, '2551234') ('4234', '20255472', '1334899197', None, None, None, None, None, '2551234') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.012508869171142578 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.431999444961548 time spend to save output : 0.012728214263916016 total time spend for step 7 : 2.444727659225464 step8:final Wed Feb 5 12:24:49 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 : {1334899197: ('0.45571640976470107',)} new output for save of step final : {1334899197: ('0.45571640976470107',)} [1334899197] Looping around the photos to save general results len do output : 1 /1334899197.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 ('4234', None, None, None, None, None, None, None, '2551234') ('4234', '20255472', '1334899197', None, None, None, None, None, '2551234') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.012549638748168945 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11146831512451172 time spend to save output : 0.013602972030639648 total time spend for step 8 : 0.12507128715515137 step9:velours_tree Wed Feb 5 12:24:49 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 list_portfolios : 20256222,20256226,20256224,20256235,20256227,20256228,20256239,20256233,20256240,20256234,20256236,20256237,20256238 photo desc type : 5561 - Retrieving photos to tag... query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256222 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256226 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256224 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256235 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256227 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256228 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256239 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256233 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256240 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256234 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256236 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256237 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20256238 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 370 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [1 2 1 2 4 3 4 1 2 1 0 2 2 1 5 2 0 0 0 5 5 4 1 0 1 1 1 1 1 0 5 5 0 3 4 0 5 2 0 1 1 0 4 4 4 3 5 4 5 4 2 2 1 1 3 2 5 0 5 5 1 5 0 2 2 2 2 1 4 2 0 2 2 2 0 5 0 1 3 0 5 4 3 3 5 3 3 2 5 0 3 2 0 2 5 3 1 5 2 2 4 5 5 2 2 2 2 2 4 2 2 5 3 3 3 2 1 1 2 1 1 2 1 0 4 2 4 1 4 2 2 3 2 2 2 3 0 0 2 2 2 1 2 2 2 2 1 2 3 1 3 3 2 2 2 2 0 0 2 2 1 4 1 4 2 2 2 1 1 1 2 2 2 2 4 2 2 5 2 2 4 2 1 2 2 1 3 1 2 3 1 2 2 1 4 1 1 1 2 1 3 2 2 2 2 2 2 3 2 2 1 2 2 2 2 1 2 2 2 2 2 2 2 2 2 3 2 1 3 1 5 2 0 2 0 1 0 1 0 2 5 3 1 1 2 5 1 0 1 1 5 4 0 2 5 2 5 1 0 0 1 3 3 0 2 2 2 1 2 4 1 2 4 2 1 3 3 0 1 5 1 5 3 5 1 4 3 2 1 2 2 2 0 2 3 5 1 5 2 2 2 2 2 2 0 2 2 1 1 1 4 1 1 2 2 1 3 5 2 2 1 4 2 2 3 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 0 1 0 0 1 1 2 3 1 1 3 1 1 1 2 3 3 1 3 1 1 2 2 2 2 2 3 1 3 2] Elapsed time: 0.08046817779541016 graph_id used : 76277 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20256222,20256226,20256224,20256235,20256227,20256228,20256239,20256233,20256240,20256234,20256236,20256237,20256238?tags=metal,pet_fonce,flou,pehd,environnement,film_plastique,carton,pet_clair,papier,autre,refus,tetrapak,mal_croppe&datou_id_consolidate=4235&port_consolidate=20255472&tree_id=76277 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1334899197] Looping around the photos to save general results len do output : 1 /20255472Didn'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 ('4234', None, None, None, None, None, None, None, '2551234') ('4234', '20255472', '1334899197', None, None, None, None, None, '2551234') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.01190495491027832 save_final save missing photos in datou_result : time spend for datou_step_exec : 27.410258293151855 time spend to save output : 0.012200593948364258 total time spend for step 9 : 27.42245888710022 step10:send_mail_cod Wed Feb 5 12:25:17 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 complete output_args for input 2 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_Qualipapia_P20255472_05-02-2025_12_25_17.pdf 20256204 change filename to text .imagette202562041738754717 20256208 change filename to text .change filename to text .change filename to text .change filename to text .imagette202562081738754717 20256206 imagette202562061738754717 20256216 change filename to text .change filename to text .change filename to text .imagette202562161738754717 20256210 imagette202562101738754717 20256220 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 .imagette202562201738754717 20256214 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 .imagette202562141738754718 20256221 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 .imagette202562211738754719 20256215 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 .imagette202562151738754719 20256217 imagette202562171738754720 20256218 imagette202562181738754720 20256219 imagette202562191738754720 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20255472 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20256222,20256226,20256224,20256235,20256227,20256228,20256239,20256233,20256240,20256234,20256236,20256237,20256238?tags=metal,pet_fonce,flou,pehd,environnement,film_plastique,carton,pet_clair,papier,autre,refus,tetrapak,mal_croppe&datou_id_consolidate=4235&port_consolidate=20255472&tree_id=76277 your option no_mail is active, we will not send the real mail to your client args[1334899197] : ((1334899197, -8.31862993109965, 492609224), (1334899197, -0.1126964560732834, 496442774), '0.45571640976470107') We are sending mail with results at cod@fotonower.com refus_total : 0.45571640976470107 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=20255472 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_Qualipapia_P20255472_05-02-2025_12_25_17.pdf results_Qualipapia_P20255472_05-02-2025_12_25_17.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20255472_05-02-2025_12_25_17.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('4234','20255472','results_Qualipapia_P20255472_05-02-2025_12_25_17.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20255472_05-02-2025_12_25_17.pdf','pdf','','0.16','0.45571640976470107') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1334899197] 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 ('4234', None, None, None, None, None, None, None, '2551234') ('4234', '20255472', '1334899197', None, None, None, None, None, '2551234') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.011812210083007812 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.74206280708313 time spend to save output : 0.011963844299316406 total time spend for step 10 : 4.754026651382446 step11:split_time_score Wed Feb 5 12:25:21 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 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 begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 3442, 'mtr_user_id': 31, 'name': 'classifieur_2camions_valcor_021122_v1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'deux_camions,camion_droite,camion_gauche,pas_de_camion', 'svm_portfolios_learning': '7659379,7659034,7657685,7657114', 'photo_hashtag_type': 4458, 'photo_desc_type': 5723, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107760533,2107760534,2107760535,2107760536'}] 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'}] (('20', 1),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 05022025 20255472 Nombre de photos uploadées : 1 / 23040 (0%) 05022025 20255472 Nombre de photos taguées (types de déchets): 0 / 1 (0%) 05022025 20255472 Nombre de photos taguées (volume) : 0 / 1 (0%) elapsed_time : load_data_split_time_score 4.0531158447265625e-06 elapsed_time : order_list_meta_photo_and_scores 1.0728836059570312e-05 ? elapsed_time : fill_and_build_computed_from_old_data 0.00018930435180664062 elapsed_time : insert_dashboard_record_day_entry 0.023430824279785156 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20234143 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20234144 order by id desc limit 1 Qualite : 0.4819854710597584 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20236365_05-02-2025_03_24_49.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20236365 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20236365 AND mptpi.`type`=4230 To do Qualite : 0.4953034350347567 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20238850_05-02-2025_04_21_11.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20238850 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20238850 AND mptpi.`type`=4230 To do Qualite : 0.4843527460175656 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20240727_05-02-2025_05_15_12.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20240727 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20240727 AND mptpi.`type`=4230 To do Qualite : 0.5022373871344483 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20242595_05-02-2025_06_32_19.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20242595 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20242595 AND mptpi.`type`=4230 To do Qualite : 0.5048123418368646 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20244662_05-02-2025_08_52_08.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20244662 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20244662 AND mptpi.`type`=4230 To do Qualite : 0.4916522506498492 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20246688_05-02-2025_08_38_11.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20246688 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20246688 AND mptpi.`type`=4230 To do Qualite : 0.5061355778305443 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20248247_05-02-2025_09_16_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20248247 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20248247 AND mptpi.`type`=4230 To do Qualite : 0.5350368974632249 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20250696_05-02-2025_10_24_15.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20250696 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20250696 AND mptpi.`type`=4230 To do Qualite : 0.47757503600827267 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20252721_05-02-2025_11_17_24.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20252721 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20252721 AND mptpi.`type`=4230 To do Qualite : 0.45571640976470107 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20255472_05-02-2025_12_25_17.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20255472 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20255472 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'05022025': {'nb_upload': 1, '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 [1334899197] Looping around the photos to save general results len do output : 1 /20255472Didn'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 ('4234', None, None, None, None, None, None, None, '2551234') ('4234', '20255472', '1334899197', None, None, None, None, None, '2551234') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.012039899826049805 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.3588788509368896 time spend to save output : 0.012198448181152344 total time spend for step 11 : 2.371077299118042 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 1 set_done_treatment 57.54user 28.85system 5:00.36elapsed 28%CPU (0avgtext+0avgdata 2384920maxresident)k 971008inputs+29984outputs (11395major+5187023minor)pagefaults 0swaps