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 : 3338360 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 : ['2579238'] with mtr_portfolio_ids : ['20475135'] and first list_photo_ids : [] new path : /proc/3338360/ 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 , BFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 3 ; length of list_pids : 3 ; length of list_args : 3 time to download the photos : 0.4081251621246338 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 12 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 : 3121 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-12 12:20:31.656102: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-12 12:20:31.683166: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-12 12:20:31.685419: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f81e8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-12 12:20:31.685473: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-12 12:20:31.689602: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-12 12:20:31.943867: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1a7a2070 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-12 12:20:31.943920: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-12 12:20:31.945018: 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 2025-02-12 12:20:31.945415: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 12:20:31.948582: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 12:20:31.951869: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 12:20:31.952173: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 12:20:31.954841: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 12:20:31.955970: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 12:20:31.960834: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 12:20:31.961880: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 12:20:31.961960: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 12:20:31.962494: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-12 12:20:31.962509: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-12 12:20:31.962520: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-12 12:20:31.963383: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2669 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. 2025-02-12 12:20:32.331915: 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 2025-02-12 12:20:32.332002: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 12:20:32.332023: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 12:20:32.332042: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 12:20:32.332061: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 12:20:32.332078: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 12:20:32.332096: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 12:20:32.332114: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 12:20:32.333177: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 12:20:32.334277: 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 2025-02-12 12:20:32.334319: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 12:20:32.334338: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 12:20:32.334356: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 12:20:32.334373: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 12:20:32.334391: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 12:20:32.334408: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 12:20:32.334426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 12:20:32.335501: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 12:20:32.335535: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-12 12:20:32.335546: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-12 12:20:32.335558: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-12 12:20:32.336601: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2669 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 : [] 2025-02-12 12:20:41.634959: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 12:20:41.791209: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 12:20:42.971572: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:42.971618: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:20:42.972253: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:42.972270: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:20:42.980209: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:42.980256: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:20:42.981242: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:42.981262: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:20:42.988430: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:42.988467: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB 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. 2025-02-12 12:20:42.989455: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:42.989476: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB 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. 2025-02-12 12:20:43.022542: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.022583: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:20:43.023579: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.023602: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:20:43.030009: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.030048: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB 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. 2025-02-12 12:20:43.031130: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.031156: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB 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. 2025-02-12 12:20:43.066513: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.067145: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.069126: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.069706: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.116162: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.116764: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.148112: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.148754: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.150507: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.151142: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.157854: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.158480: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.160448: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.161078: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.168039: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.168698: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.170504: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.171153: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.203930: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.204588: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.205223: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.205871: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.210355: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.211024: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.231079: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.231861: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.232489: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.233105: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.246295: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.246962: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.247580: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.248222: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.253104: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.253901: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.258929: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.259581: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.271807: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.272473: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.276771: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.277404: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.278021: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.278632: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.279633: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.280257: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.290951: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.291599: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.292238: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.292848: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.293458: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.294065: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.309242: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.309890: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.343012: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.343092: 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. 2025-02-12 12:20:43.344186: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.345265: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.352752: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.353825: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.361892: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.362530: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.375585: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.376235: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.376819: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.377383: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.381436: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.382054: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.382664: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.383296: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.384412: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.394504: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.395150: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.404231: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.404864: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.405485: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.406096: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.406695: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:20:43.407296: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2263744512 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 : 3 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 82.00000 max: 223.00000 molded_images shape: (1, 640, 640, 3) min: -41.70000 max: 117.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 127.00000 max: 226.00000 molded_images shape: (1, 640, 640, 3) min: 3.30000 max: 116.08047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 942 time to create 1 rle with old method : 0.0012652873992919922 length of segment : 31 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 948 time to create 1 rle with old method : 0.0013284683227539062 length of segment : 32 Processing 1 images image shape: (400, 400, 3) min: 83.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -37.01641 max: 147.19766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 52.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -48.31328 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2612 time to create 1 rle with old method : 0.0031824111938476562 length of segment : 55 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.00041174888610839844 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 112.00000 max: 172.00000 molded_images shape: (1, 640, 640, 3) min: -11.70000 max: 60.34219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 37.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -80.84063 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0005097389221191406 length of segment : 24 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0005865097045898438 length of segment : 25 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0008671283721923828 length of segment : 18 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00024366378784179688 length of segment : 21 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 2879 time to create 1 rle with old method : 0.004998922348022461 length of segment : 65 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1015 time to create 1 rle with old method : 0.0019652843475341797 length of segment : 24 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0004086494445800781 length of segment : 14 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1044 time to create 1 rle with old method : 0.0013725757598876953 length of segment : 44 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 2752 time to create 1 rle with old method : 0.003422975540161133 length of segment : 65 Processing 1 images image shape: (400, 160, 3) min: 26.00000 max: 221.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 102.50234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 101.00000 max: 221.00000 molded_images shape: (1, 640, 640, 3) min: -22.70000 max: 115.38516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 128.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: 4.30000 max: 144.51016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 69.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -50.08281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1217 time to create 1 rle with old method : 0.0016062259674072266 length of segment : 44 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001461505889892578 length of segment : 14 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1410 time to create 1 rle with old method : 0.0019474029541015625 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 54.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -60.24297 max: 150.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 62.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -53.52031 max: 138.55312 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0007703304290771484 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.15313 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 : 7.009506225585938e-05 nb_pixel_total : 629 time to create 1 rle with old method : 0.0011148452758789062 length of segment : 61 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1956 time to create 1 rle with old method : 0.003336668014526367 length of segment : 95 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0007293224334716797 length of segment : 33 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 959 time to create 1 rle with old method : 0.0014815330505371094 length of segment : 56 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0008080005645751953 length of segment : 42 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 415 time to create 1 rle with old method : 0.0008792877197265625 length of segment : 25 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0008406639099121094 length of segment : 48 time for calcul the mask position with numpy : 0.0001666545867919922 nb_pixel_total : 2375 time to create 1 rle with old method : 0.004242420196533203 length of segment : 112 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 693 time to create 1 rle with old method : 0.0011074542999267578 length of segment : 37 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 522 time to create 1 rle with old method : 0.0009839534759521484 length of segment : 67 Processing 1 images image shape: (400, 160, 3) min: 13.00000 max: 229.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 110.13359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 88.00000 max: 227.00000 molded_images shape: (1, 640, 640, 3) min: -35.70000 max: 122.12344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 138.00000 max: 198.00000 molded_images shape: (1, 640, 640, 3) min: 14.30000 max: 93.52969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00020432472229003906 nb_pixel_total : 3573 time to create 1 rle with old method : 0.007477760314941406 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 105.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -18.70000 max: 149.93984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0007386207580566406 length of segment : 47 Processing 1 images image shape: (400, 400, 3) min: 56.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -67.70000 max: 135.96328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 3422 time to create 1 rle with old method : 0.004224061965942383 length of segment : 60 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 3439 time to create 1 rle with old method : 0.0041370391845703125 length of segment : 57 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.92266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 1040 time to create 1 rle with old method : 0.002000093460083008 length of segment : 40 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0014545917510986328 length of segment : 28 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0005331039428710938 length of segment : 20 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 728 time to create 1 rle with old method : 0.0013854503631591797 length of segment : 33 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0005733966827392578 length of segment : 38 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0005183219909667969 length of segment : 19 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00034356117248535156 length of segment : 25 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0004494190216064453 length of segment : 11 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00013637542724609375 length of segment : 30 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0010707378387451172 length of segment : 30 time for calcul the mask position with numpy : 9.703636169433594e-05 nb_pixel_total : 4053 time to create 1 rle with old method : 0.0048220157623291016 length of segment : 56 time for calcul the mask position with numpy : 0.00013184547424316406 nb_pixel_total : 2479 time to create 1 rle with old method : 0.003674745559692383 length of segment : 50 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0007088184356689453 length of segment : 28 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00037479400634765625 length of segment : 20 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003104209899902344 length of segment : 24 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003657341003417969 length of segment : 18 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00043582916259765625 length of segment : 21 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1761 time to create 1 rle with old method : 0.0022280216217041016 length of segment : 68 time for calcul the mask position with numpy : 0.00012826919555664062 nb_pixel_total : 4286 time to create 1 rle with old method : 0.0056133270263671875 length of segment : 61 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 792 time to create 1 rle with old method : 0.0010950565338134766 length of segment : 37 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 2187 time to create 1 rle with old method : 0.0027861595153808594 length of segment : 61 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.43438 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 : 7.224082946777344e-05 nb_pixel_total : 990 time to create 1 rle with old method : 0.0014190673828125 length of segment : 42 time for calcul the mask position with numpy : 9.703636169433594e-05 nb_pixel_total : 2791 time to create 1 rle with old method : 0.0036504268646240234 length of segment : 56 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 1813 time to create 1 rle with old method : 0.0022974014282226562 length of segment : 78 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1562 time to create 1 rle with old method : 0.0020906925201416016 length of segment : 35 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0004131793975830078 length of segment : 29 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005567073822021484 length of segment : 39 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 3995 time to create 1 rle with old method : 0.005072593688964844 length of segment : 61 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 687 time to create 1 rle with old method : 0.0009732246398925781 length of segment : 37 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 1165 time to create 1 rle with old method : 0.00170135498046875 length of segment : 56 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.00033545494079589844 length of segment : 17 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 818 time to create 1 rle with old method : 0.0010712146759033203 length of segment : 82 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0010235309600830078 length of segment : 38 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006546974182128906 length of segment : 31 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 940 time to create 1 rle with old method : 0.0013914108276367188 length of segment : 37 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004200935363769531 length of segment : 17 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005581378936767578 length of segment : 25 time for calcul the mask position with numpy : 0.0001323223114013672 nb_pixel_total : 6377 time to create 1 rle with old method : 0.00855565071105957 length of segment : 97 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0008769035339355469 length of segment : 40 time for calcul the mask position with numpy : 0.000179290771484375 nb_pixel_total : 6457 time to create 1 rle with old method : 0.007722139358520508 length of segment : 171 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.000553131103515625 length of segment : 29 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 4028 time to create 1 rle with old method : 0.00516510009765625 length of segment : 111 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 1916 time to create 1 rle with old method : 0.0026085376739501953 length of segment : 71 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1719 time to create 1 rle with old method : 0.0028002262115478516 length of segment : 88 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1765 time to create 1 rle with old method : 0.0022192001342773438 length of segment : 53 time for calcul the mask position with numpy : 0.00013136863708496094 nb_pixel_total : 4714 time to create 1 rle with old method : 0.0056378841400146484 length of segment : 147 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 779 time to create 1 rle with old method : 0.0010304450988769531 length of segment : 23 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 652 time to create 1 rle with old method : 0.0008487701416015625 length of segment : 19 Processing 1 images image shape: (400, 160, 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 : 1 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0005676746368408203 length of segment : 19 Processing 1 images image shape: (240, 400, 3) min: 76.00000 max: 230.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 118.11953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 3998 time to create 1 rle with old method : 0.004799365997314453 length of segment : 56 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 2413 time to create 1 rle with old method : 0.003009319305419922 length of segment : 79 Processing 1 images image shape: (240, 400, 3) min: 64.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.18203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0010120868682861328 length of segment : 42 Processing 1 images image shape: (240, 400, 3) min: 73.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.72500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (240, 400, 3) min: 25.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.59609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 2852 time to create 1 rle with old method : 0.0037946701049804688 length of segment : 60 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 : 14 time for calcul the mask position with numpy : 0.0001418590545654297 nb_pixel_total : 4671 time to create 1 rle with old method : 0.008669137954711914 length of segment : 94 time for calcul the mask position with numpy : 0.00012159347534179688 nb_pixel_total : 3761 time to create 1 rle with old method : 0.0067250728607177734 length of segment : 81 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0008258819580078125 length of segment : 36 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005016326904296875 length of segment : 40 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 648 time to create 1 rle with old method : 0.0008661746978759766 length of segment : 35 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1119 time to create 1 rle with old method : 0.0014410018920898438 length of segment : 41 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.0007650852203369141 length of segment : 38 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 23 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 935 time to create 1 rle with old method : 0.0011734962463378906 length of segment : 40 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1203 time to create 1 rle with old method : 0.001489877700805664 length of segment : 62 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00039458274841308594 length of segment : 19 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.00033545494079589844 length of segment : 21 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 3677 time to create 1 rle with old method : 0.0044286251068115234 length of segment : 78 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 3863 time to create 1 rle with old method : 0.004711627960205078 length of segment : 62 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 : 8 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 908 time to create 1 rle with old method : 0.0012161731719970703 length of segment : 60 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0005102157592773438 length of segment : 21 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0005085468292236328 length of segment : 13 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 60 time to create 1 rle with old method : 0.00010776519775390625 length of segment : 11 time for calcul the mask position with numpy : 0.0003039836883544922 nb_pixel_total : 15542 time to create 1 rle with old method : 0.018887996673583984 length of segment : 138 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 651 time to create 1 rle with old method : 0.0010347366333007812 length of segment : 29 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.00014829635620117188 length of segment : 11 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 3172 time to create 1 rle with old method : 0.003863811492919922 length of segment : 60 Processing 1 images image shape: (240, 160, 3) min: 0.00000 max: 226.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 113.38784 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00030303001403808594 length of segment : 29 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 25.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -95.53203 max: 150.97109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1202 time to create 1 rle with old method : 0.0019490718841552734 length of segment : 25 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.00043320655822753906 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 29.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -86.05938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 560 time to create 1 rle with old method : 0.0009222030639648438 length of segment : 27 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0007586479187011719 length of segment : 22 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 2084 time to create 1 rle with old method : 0.0025811195373535156 length of segment : 54 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0007698535919189453 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.34844 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 : 0.00011658668518066406 nb_pixel_total : 6116 time to create 1 rle with old method : 0.0070705413818359375 length of segment : 106 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006668567657470703 length of segment : 47 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1640 time to create 1 rle with old method : 0.0021212100982666016 length of segment : 46 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003998279571533203 length of segment : 33 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 19 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 557 time to create 1 rle with old method : 0.0007708072662353516 length of segment : 27 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1559 time to create 1 rle with old method : 0.001978158950805664 length of segment : 49 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1177 time to create 1 rle with old method : 0.0016694068908691406 length of segment : 44 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003502368927001953 length of segment : 21 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 2362 time to create 1 rle with old method : 0.002979278564453125 length of segment : 103 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1000 time to create 1 rle with old method : 0.0015766620635986328 length of segment : 38 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 3673 time to create 1 rle with old method : 0.0044918060302734375 length of segment : 91 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 2287 time to create 1 rle with old method : 0.002722501754760742 length of segment : 101 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1099 time to create 1 rle with old method : 0.0014219284057617188 length of segment : 49 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1299 time to create 1 rle with old method : 0.0015676021575927734 length of segment : 32 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 3506 time to create 1 rle with old method : 0.004523515701293945 length of segment : 81 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -96.94609 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 : 8.130073547363281e-05 nb_pixel_total : 2900 time to create 1 rle with old method : 0.003753662109375 length of segment : 61 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00035858154296875 length of segment : 21 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005640983581542969 length of segment : 24 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005095005035400391 length of segment : 22 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0003895759582519531 length of segment : 16 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 3061 time to create 1 rle with old method : 0.0038340091705322266 length of segment : 58 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003497600555419922 length of segment : 22 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 3686 time to create 1 rle with old method : 0.004177570343017578 length of segment : 69 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0008578300476074219 length of segment : 32 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.00040650367736816406 length of segment : 18 time for calcul the mask position with numpy : 9.894371032714844e-05 nb_pixel_total : 5828 time to create 1 rle with old method : 0.0070722103118896484 length of segment : 93 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 737 time to create 1 rle with old method : 0.0010068416595458984 length of segment : 39 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00036263465881347656 length of segment : 19 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0006349086761474609 length of segment : 25 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.00033164024353027344 length of segment : 17 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006852149963378906 length of segment : 27 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1247 time to create 1 rle with old method : 0.0016078948974609375 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 107.00000 max: 248.00000 molded_images shape: (1, 640, 640, 3) min: -16.70000 max: 127.13125 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.98906 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.00028586387634277344 length of segment : 13 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1460 time to create 1 rle with old method : 0.0019276142120361328 length of segment : 54 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 736 time to create 1 rle with old method : 0.0009913444519042969 length of segment : 26 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.0002276897430419922 length of segment : 14 Processing 1 images image shape: (400, 160, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.64297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 3286 time to create 1 rle with old method : 0.004065752029418945 length of segment : 68 time for calcul the mask position with numpy : 0.00018358230590820312 nb_pixel_total : 11315 time to create 1 rle with old method : 0.013309717178344727 length of segment : 234 Processing 1 images image shape: (400, 400, 3) min: 19.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -94.60234 max: 149.71719 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 2912 time to create 1 rle with old method : 0.0035805702209472656 length of segment : 50 time for calcul the mask position with numpy : 0.00010704994201660156 nb_pixel_total : 5335 time to create 1 rle with old method : 0.006732940673828125 length of segment : 60 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 4179 time to create 1 rle with old method : 0.005152225494384766 length of segment : 71 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 4729 time to create 1 rle with old method : 0.0060176849365234375 length of segment : 55 Processing 1 images image shape: (400, 400, 3) min: 23.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -83.09453 max: 149.54922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -104.24297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0005335807800292969 length of segment : 25 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.0008819103240966797 length of segment : 30 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1007 time to create 1 rle with old method : 0.001415252685546875 length of segment : 34 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1176 time to create 1 rle with old method : 0.001813650131225586 length of segment : 37 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00023865699768066406 length of segment : 12 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0006892681121826172 length of segment : 21 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0007193088531494141 length of segment : 19 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 3889 time to create 1 rle with old method : 0.005147457122802734 length of segment : 103 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007686614990234375 length of segment : 24 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.0002601146697998047 length of segment : 15 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 560 time to create 1 rle with old method : 0.0008561611175537109 length of segment : 23 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0005142688751220703 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.18047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 2605 time to create 1 rle with old method : 0.0035245418548583984 length of segment : 51 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 612 time to create 1 rle with old method : 0.00093841552734375 length of segment : 23 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1694 time to create 1 rle with old method : 0.002278566360473633 length of segment : 73 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 563 time to create 1 rle with old method : 0.0009868144989013672 length of segment : 37 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.0012748241424560547 length of segment : 50 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006396770477294922 length of segment : 39 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002665519714355469 length of segment : 14 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 633 time to create 1 rle with old method : 0.0008475780487060547 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 42.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -72.66875 max: 140.92031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0006101131439208984 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.32109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005629062652587891 length of segment : 19 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 704 time to create 1 rle with old method : 0.0008440017700195312 length of segment : 51 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002994537353515625 length of segment : 44 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 469 time to create 1 rle with old method : 0.0006465911865234375 length of segment : 28 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1371 time to create 1 rle with old method : 0.0016531944274902344 length of segment : 93 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0004405975341796875 length of segment : 28 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1885 time to create 1 rle with old method : 0.0022475719451904297 length of segment : 111 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 2893 time to create 1 rle with old method : 0.0035867691040039062 length of segment : 98 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011587142944335938 length of segment : 12 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.90469 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0006844997406005859 length of segment : 36 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006353855133056641 length of segment : 27 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.00023984909057617188 length of segment : 16 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0005025863647460938 length of segment : 19 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0006835460662841797 length of segment : 23 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002732276916503906 length of segment : 11 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0005373954772949219 length of segment : 54 Processing 1 images image shape: (400, 400, 3) min: 25.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -82.79766 max: 146.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 24.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -91.70391 max: 150.87734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002899169921875 length of segment : 10 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1790 time to create 1 rle with old method : 0.0022001266479492188 length of segment : 73 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0011179447174072266 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 33.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -78.97734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 4637 time to create 1 rle with old method : 0.005589485168457031 length of segment : 100 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 2617 time to create 1 rle with old method : 0.003389120101928711 length of segment : 64 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.0004870891571044922 length of segment : 15 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1781 time to create 1 rle with old method : 0.0022363662719726562 length of segment : 67 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 2688 time to create 1 rle with old method : 0.0032927989959716797 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -101.95391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1084 time to create 1 rle with old method : 0.0015554428100585938 length of segment : 43 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005664825439453125 length of segment : 24 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1123 time to create 1 rle with old method : 0.0016613006591796875 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.44609 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.0005674362182617188 length of segment : 19 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005598068237304688 length of segment : 24 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004086494445800781 length of segment : 20 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.00024700164794921875 length of segment : 14 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 674 time to create 1 rle with old method : 0.0010476112365722656 length of segment : 36 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 4055 time to create 1 rle with old method : 0.004750728607177734 length of segment : 106 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1178 time to create 1 rle with old method : 0.0015554428100585938 length of segment : 46 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004069805145263672 length of segment : 32 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 33 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 4626 time to create 1 rle with old method : 0.005758523941040039 length of segment : 105 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003364086151123047 length of segment : 33 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00030922889709472656 length of segment : 10 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.02422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 28 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00044226646423339844 length of segment : 35 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.00046706199645996094 length of segment : 22 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006563663482666016 length of segment : 23 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.00041747093200683594 length of segment : 24 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002186298370361328 length of segment : 20 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0004909038543701172 length of segment : 25 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 969 time to create 1 rle with old method : 0.0012772083282470703 length of segment : 30 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 877 time to create 1 rle with old method : 0.001199483871459961 length of segment : 47 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 2563 time to create 1 rle with old method : 0.003062725067138672 length of segment : 63 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1607 time to create 1 rle with old method : 0.0019865036010742188 length of segment : 89 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 1770 time to create 1 rle with old method : 0.0022597312927246094 length of segment : 73 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.00024366378784179688 length of segment : 18 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005624294281005859 length of segment : 22 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006587505340576172 length of segment : 25 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 603 time to create 1 rle with old method : 0.0008215904235839844 length of segment : 38 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1837 time to create 1 rle with old method : 0.002483844757080078 length of segment : 62 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006690025329589844 length of segment : 23 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 4057 time to create 1 rle with old method : 0.004691123962402344 length of segment : 67 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 19 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.00016546249389648438 length of segment : 21 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0007910728454589844 length of segment : 27 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 539 time to create 1 rle with old method : 0.0007801055908203125 length of segment : 26 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00027298927307128906 length of segment : 14 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.0002541542053222656 length of segment : 11 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0002892017364501953 length of segment : 19 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 4049 time to create 1 rle with old method : 0.0045168399810791016 length of segment : 67 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1625 time to create 1 rle with old method : 0.0018229484558105469 length of segment : 85 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 433 time to create 1 rle with old method : 0.0005574226379394531 length of segment : 25 Processing 1 images image shape: (400, 160, 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 : 5.0067901611328125e-05 nb_pixel_total : 1643 time to create 1 rle with old method : 0.0020608901977539062 length of segment : 30 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 3181 time to create 1 rle with old method : 0.003753662109375 length of segment : 83 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005342960357666016 length of segment : 21 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 2932 time to create 1 rle with old method : 0.0037517547607421875 length of segment : 77 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0005497932434082031 length of segment : 47 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.00020575523376464844 length of segment : 15 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0006439685821533203 length of segment : 29 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 846 time to create 1 rle with old method : 0.0010251998901367188 length of segment : 45 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003495216369628906 length of segment : 23 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1904 time to create 1 rle with old method : 0.0023076534271240234 length of segment : 56 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.00025534629821777344 length of segment : 23 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004086494445800781 length of segment : 41 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.00043272972106933594 length of segment : 51 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006337165832519531 length of segment : 41 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0004723072052001953 length of segment : 70 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.00038433074951171875 length of segment : 20 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 886 time to create 1 rle with old method : 0.0011856555938720703 length of segment : 55 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 585 time to create 1 rle with old method : 0.0007600784301757812 length of segment : 70 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0009109973907470703 length of segment : 35 Processing 1 images image shape: (240, 400, 3) min: 16.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.59219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.00034356117248535156 length of segment : 11 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 2690 time to create 1 rle with old method : 0.003082752227783203 length of segment : 60 Processing 1 images image shape: (240, 400, 3) min: 26.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.52578 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0011713504791259766 length of segment : 17 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 1243 time to create 1 rle with old method : 0.0017266273498535156 length of segment : 22 Processing 1 images image shape: (240, 400, 3) min: 28.00000 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 : 3 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00017905235290527344 length of segment : 8 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00024008750915527344 length of segment : 11 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0006558895111083984 length of segment : 22 Processing 1 images image shape: (240, 400, 3) min: 8.00000 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 : 3 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 914 time to create 1 rle with old method : 0.0015728473663330078 length of segment : 22 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0004279613494873047 length of segment : 20 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0006015300750732422 length of segment : 26 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: 150.95937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1088 time to create 1 rle with old method : 0.0013806819915771484 length of segment : 45 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0007255077362060547 length of segment : 28 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.0007159709930419922 length of segment : 27 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.00047206878662109375 length of segment : 25 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0004360675811767578 length of segment : 25 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.00044536590576171875 length of segment : 24 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: 146.79922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.00034546852111816406 length of segment : 28 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0004992485046386719 length of segment : 22 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 780 time to create 1 rle with old method : 0.0009562969207763672 length of segment : 51 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003211498260498047 length of segment : 20 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 165 time to create 1 rle with old method : 0.0002453327178955078 length of segment : 19 Processing 1 images image shape: (240, 160, 3) min: 6.00000 max: 241.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 129.65255 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 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: -117.14531 max: 150.76016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 829 time to create 1 rle with old method : 0.0012857913970947266 length of segment : 50 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 3177 time to create 1 rle with old method : 0.004075288772583008 length of segment : 108 Processing 1 images image shape: (400, 400, 3) min: 14.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -101.34844 max: 150.96328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0006690025329589844 length of segment : 29 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1129 time to create 1 rle with old method : 0.0014493465423583984 length of segment : 44 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005290508270263672 length of segment : 21 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0008995532989501953 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.61016 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 : 5.125999450683594e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006301403045654297 length of segment : 22 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1048 time to create 1 rle with old method : 0.0013723373413085938 length of segment : 44 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0004191398620605469 length of segment : 21 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 1258 time to create 1 rle with old method : 0.0017371177673339844 length of segment : 47 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 2734 time to create 1 rle with old method : 0.0031690597534179688 length of segment : 62 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.001138448715209961 length of segment : 23 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 1452 time to create 1 rle with old method : 0.002925395965576172 length of segment : 39 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0004832744598388672 length of segment : 24 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1425 time to create 1 rle with old method : 0.0018618106842041016 length of segment : 36 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00035119056701660156 length of segment : 17 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0003097057342529297 length of segment : 20 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0006549358367919922 length of segment : 63 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006012916564941406 length of segment : 25 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.00027441978454589844 length of segment : 19 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003046989440917969 length of segment : 16 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 2887 time to create 1 rle with old method : 0.0033979415893554688 length of segment : 62 Processing 1 images image shape: (400, 400, 3) min: 9.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -95.46953 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 : 4.124641418457031e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006711483001708984 length of segment : 20 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 2560 time to create 1 rle with old method : 0.003151416778564453 length of segment : 77 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.00023698806762695312 length of segment : 13 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 932 time to create 1 rle with old method : 0.00133514404296875 length of segment : 21 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002894401550292969 length of segment : 15 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.0004029273986816406 length of segment : 13 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1206 time to create 1 rle with old method : 0.001425027847290039 length of segment : 58 Processing 1 images image shape: (400, 400, 3) min: 113.00000 max: 235.00000 molded_images shape: (1, 640, 640, 3) min: -10.70000 max: 112.35781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.66094 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 880 time to create 1 rle with old method : 0.0011730194091796875 length of segment : 48 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0006618499755859375 length of segment : 24 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002751350402832031 length of segment : 20 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0006082057952880859 length of segment : 38 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00018167495727539062 length of segment : 12 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006947517395019531 length of segment : 20 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 584 time to create 1 rle with old method : 0.0008111000061035156 length of segment : 38 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0012700557708740234 length of segment : 43 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003864765167236328 length of segment : 18 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 2625 time to create 1 rle with old method : 0.0034592151641845703 length of segment : 53 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 2590 time to create 1 rle with old method : 0.003458261489868164 length of segment : 45 Processing 1 images image shape: (400, 160, 3) min: 11.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 116.72891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0004987716674804688 length of segment : 32 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0004012584686279297 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.50859 max: 148.29922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 4520 time to create 1 rle with old method : 0.005513191223144531 length of segment : 62 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004990100860595703 length of segment : 40 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1258 time to create 1 rle with old method : 0.0016193389892578125 length of segment : 82 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 1022 time to create 1 rle with old method : 0.0013523101806640625 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.61406 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.00036025047302246094 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 13.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -98.56719 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 : 4.6253204345703125e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.000255584716796875 length of segment : 23 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002551078796386719 length of segment : 19 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 742 time to create 1 rle with old method : 0.0008556842803955078 length of segment : 65 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.00040531158447265625 length of segment : 32 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0008299350738525391 length of segment : 49 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.00036025047302246094 length of segment : 22 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1651 time to create 1 rle with old method : 0.0020329952239990234 length of segment : 69 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00030159950256347656 length of segment : 13 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 1608 time to create 1 rle with old method : 0.002232074737548828 length of segment : 50 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1379 time to create 1 rle with old method : 0.0024824142456054688 length of segment : 45 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0007069110870361328 length of segment : 28 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0007171630859375 length of segment : 23 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0007369518280029297 length of segment : 26 time for calcul the mask position with numpy : 0.00016164779663085938 nb_pixel_total : 6113 time to create 1 rle with old method : 0.010280609130859375 length of segment : 125 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.00019478797912597656 length of segment : 10 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 856 time to create 1 rle with old method : 0.0015447139739990234 length of segment : 38 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1169 time to create 1 rle with old method : 0.002062559127807617 length of segment : 41 time for calcul the mask position with numpy : 0.00013756752014160156 nb_pixel_total : 6156 time to create 1 rle with old method : 0.010695457458496094 length of segment : 131 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.00037670135498046875 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 19.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -86.87969 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004582405090332031 length of segment : 18 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0007357597351074219 length of segment : 24 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0004951953887939453 length of segment : 18 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0007538795471191406 length of segment : 35 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0009791851043701172 length of segment : 30 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1131 time to create 1 rle with old method : 0.0014920234680175781 length of segment : 43 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002753734588623047 length of segment : 14 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 2053 time to create 1 rle with old method : 0.002588987350463867 length of segment : 65 Processing 1 images image shape: (400, 400, 3) min: 66.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -50.89531 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005686283111572266 length of segment : 25 time for calcul the mask position with numpy : 0.00037169456481933594 nb_pixel_total : 28580 time to create 1 rle with old method : 0.03438258171081543 length of segment : 228 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 972 time to create 1 rle with old method : 0.0013134479522705078 length of segment : 35 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1587 time to create 1 rle with old method : 0.0019156932830810547 length of segment : 61 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.01250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 30 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 788 time to create 1 rle with old method : 0.001138448715209961 length of segment : 37 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.00091552734375 length of segment : 11 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.000514984130859375 length of segment : 26 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0006647109985351562 length of segment : 23 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.00048160552978515625 length of segment : 21 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.0003674030303955078 length of segment : 23 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006732940673828125 length of segment : 23 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0002903938293457031 length of segment : 14 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1078 time to create 1 rle with old method : 0.001287221908569336 length of segment : 103 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.00046515464782714844 length of segment : 30 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1799 time to create 1 rle with old method : 0.002204418182373047 length of segment : 51 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0005216598510742188 length of segment : 22 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.00043272972106933594 length of segment : 25 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003807544708251953 length of segment : 15 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 664 time to create 1 rle with old method : 0.0008518695831298828 length of segment : 95 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1340 time to create 1 rle with old method : 0.0016863346099853516 length of segment : 64 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 1396 time to create 1 rle with old method : 0.001752614974975586 length of segment : 90 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.0008263587951660156 length of segment : 40 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1298 time to create 1 rle with old method : 0.0016870498657226562 length of segment : 66 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 906 time to create 1 rle with old method : 0.0014524459838867188 length of segment : 51 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 1080 time to create 1 rle with old method : 0.0015151500701904297 length of segment : 61 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 996 time to create 1 rle with old method : 0.0012786388397216797 length of segment : 87 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.0004487037658691406 length of segment : 25 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0005800724029541016 length of segment : 19 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 651 time to create 1 rle with old method : 0.0010209083557128906 length of segment : 42 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006601810455322266 length of segment : 83 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005064010620117188 length of segment : 34 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00037550926208496094 length of segment : 18 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1770 time to create 1 rle with old method : 0.0021610260009765625 length of segment : 49 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0015506744384765625 length of segment : 64 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.18594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0002231597900390625 length of segment : 17 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00023651123046875 length of segment : 26 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0004515647888183594 length of segment : 30 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009284019470214844 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.45781 max: 147.84609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -107.66484 max: 149.87344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.00035691261291503906 length of segment : 13 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 369 time to create 1 rle with old method : 0.0004925727844238281 length of segment : 28 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 938 time to create 1 rle with old method : 0.0012726783752441406 length of segment : 32 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -107.46953 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 : 5.841255187988281e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0007407665252685547 length of segment : 22 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 995 time to create 1 rle with old method : 0.0014505386352539062 length of segment : 29 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0012247562408447266 length of segment : 36 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0007045269012451172 length of segment : 21 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003826618194580078 length of segment : 24 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0007185935974121094 length of segment : 35 time for calcul the mask position with numpy : 0.0001766681671142578 nb_pixel_total : 8946 time to create 1 rle with old method : 0.010618925094604492 length of segment : 133 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 6921 time to create 1 rle with old method : 0.008656024932861328 length of segment : 75 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002486705780029297 length of segment : 23 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 972 time to create 1 rle with old method : 0.001302480697631836 length of segment : 33 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0007619857788085938 length of segment : 33 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1705 time to create 1 rle with old method : 0.0020627975463867188 length of segment : 67 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.00039315223693847656 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 14.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.69609 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 0.0003046989440917969 nb_pixel_total : 21387 time to create 1 rle with old method : 0.025913715362548828 length of segment : 159 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 404 time to create 1 rle with old method : 0.0005731582641601562 length of segment : 22 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0012657642364501953 length of segment : 63 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003027915954589844 length of segment : 19 time for calcul the mask position with numpy : 0.0001876354217529297 nb_pixel_total : 10637 time to create 1 rle with old method : 0.012429237365722656 length of segment : 134 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0008869171142578125 length of segment : 21 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 809 time to create 1 rle with old method : 0.0011179447174072266 length of segment : 70 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1881 time to create 1 rle with old method : 0.0022962093353271484 length of segment : 63 time for calcul the mask position with numpy : 0.00017380714416503906 nb_pixel_total : 10694 time to create 1 rle with old method : 0.013180971145629883 length of segment : 134 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -102.85625 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 : 4.76837158203125e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005996227264404297 length of segment : 21 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.0012636184692382812 length of segment : 32 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1196 time to create 1 rle with old method : 0.0015418529510498047 length of segment : 51 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 3354 time to create 1 rle with old method : 0.003937721252441406 length of segment : 78 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.00034356117248535156 length of segment : 19 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.0005400180816650391 length of segment : 34 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 3594 time to create 1 rle with old method : 0.004489421844482422 length of segment : 70 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.89922 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 : 4.792213439941406e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002582073211669922 length of segment : 21 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003561973571777344 length of segment : 20 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0009446144104003906 length of segment : 34 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 892 time to create 1 rle with old method : 0.0011310577392578125 length of segment : 57 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0003383159637451172 length of segment : 21 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002834796905517578 length of segment : 14 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.00069427490234375 length of segment : 56 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003192424774169922 length of segment : 17 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0006196498870849609 length of segment : 25 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.00014257431030273438 length of segment : 10 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 1596 time to create 1 rle with old method : 0.0017824172973632812 length of segment : 56 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1754 time to create 1 rle with old method : 0.002137899398803711 length of segment : 42 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0005660057067871094 length of segment : 34 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 26 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.00028014183044433594 length of segment : 27 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001494884490966797 length of segment : 13 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 552 time to create 1 rle with old method : 0.0007145404815673828 length of segment : 53 time for calcul the mask position with numpy : 0.00018167495727539062 nb_pixel_total : 11862 time to create 1 rle with old method : 0.013581514358520508 length of segment : 158 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.67812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 623 time to create 1 rle with old method : 0.0008339881896972656 length of segment : 36 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00027298927307128906 length of segment : 23 time for calcul the mask position with numpy : 2.8133392333984375e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.00012969970703125 length of segment : 12 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 711 time to create 1 rle with old method : 0.0009558200836181641 length of segment : 55 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00021076202392578125 length of segment : 23 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 165 time to create 1 rle with old method : 0.0003037452697753906 length of segment : 34 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 580 time to create 1 rle with old method : 0.0006997585296630859 length of segment : 35 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1396 time to create 1 rle with old method : 0.0017285346984863281 length of segment : 64 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 2320 time to create 1 rle with old method : 0.003109455108642578 length of segment : 76 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.0010142326354980469 length of segment : 40 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0007061958312988281 length of segment : 24 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: 148.76016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 1626 time to create 1 rle with old method : 0.0031766891479492188 length of segment : 71 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0007166862487792969 length of segment : 16 Processing 1 images image shape: (240, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0008084774017333984 length of segment : 32 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 986 time to create 1 rle with old method : 0.0014710426330566406 length of segment : 29 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001933574676513672 length of segment : 11 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0007014274597167969 length of segment : 15 Processing 1 images image shape: (240, 400, 3) min: 11.00000 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 : 15 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00041866302490234375 length of segment : 14 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0005190372467041016 length of segment : 13 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 676 time to create 1 rle with old method : 0.0008676052093505859 length of segment : 39 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00031948089599609375 length of segment : 12 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004544258117675781 length of segment : 26 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1188 time to create 1 rle with old method : 0.0015456676483154297 length of segment : 62 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.0005059242248535156 length of segment : 21 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.00019621849060058594 length of segment : 12 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1114 time to create 1 rle with old method : 0.001505136489868164 length of segment : 37 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 2345 time to create 1 rle with old method : 0.0029463768005371094 length of segment : 68 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0005331039428710938 length of segment : 13 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 2030 time to create 1 rle with old method : 0.002613544464111328 length of segment : 56 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 1382 time to create 1 rle with old method : 0.001840829849243164 length of segment : 77 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 1105 time to create 1 rle with old method : 0.0014519691467285156 length of segment : 38 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.0006632804870605469 length of segment : 15 Processing 1 images image shape: (240, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0004889965057373047 length of segment : 30 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1305 time to create 1 rle with old method : 0.0018575191497802734 length of segment : 20 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1026 time to create 1 rle with old method : 0.0013098716735839844 length of segment : 53 time for calcul the mask position with numpy : 0.0001201629638671875 nb_pixel_total : 6691 time to create 1 rle with old method : 0.008032560348510742 length of segment : 85 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006475448608398438 length of segment : 25 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00041985511779785156 length of segment : 20 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1210 time to create 1 rle with old method : 0.0017337799072265625 length of segment : 36 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002524852752685547 length of segment : 16 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 : 5 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 2031 time to create 1 rle with old method : 0.002599954605102539 length of segment : 76 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 4533 time to create 1 rle with old method : 0.005627632141113281 length of segment : 79 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0002396106719970703 length of segment : 12 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 4379 time to create 1 rle with old method : 0.005697727203369141 length of segment : 78 time for calcul the mask position with numpy : 0.000125885009765625 nb_pixel_total : 2800 time to create 1 rle with old method : 0.0058248043060302734 length of segment : 79 Processing 1 images image shape: (240, 400, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1723 time to create 1 rle with old method : 0.0033388137817382812 length of segment : 41 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0007052421569824219 length of segment : 28 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 658 time to create 1 rle with old method : 0.0009522438049316406 length of segment : 37 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.00017189979553222656 length of segment : 10 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002307891845703125 length of segment : 24 time for calcul the mask position with numpy : 0.00010466575622558594 nb_pixel_total : 1604 time to create 1 rle with old method : 0.0022814273834228516 length of segment : 60 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.00015044212341308594 length of segment : 13 Processing 1 images image shape: (240, 160, 3) min: 17.00000 max: 234.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 119.80595 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.0001342296600341797 length of segment : 20 Detection mask done ! Trying to reset tf kernel 3338843 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2149 tf kernel not reseted sub process len(results) : 499 len(list_Values) 499 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 499 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 : 3342 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 499 chid ids of type : 4228 Number RLEs to save : 20762 save missing photos in datou_result : time spend for datou_step_exec : 32.327200174331665 time spend to save output : 1.4407048225402832 total time spend for step 1 : 33.76790499687195 step2:brightness Wed Feb 12 12:21:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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/1739359228_3338360_1337076765_a669a8ae797aabd86942d4603dd6a890.jpg treat image : temp/1739359228_3338360_1337071718_3d6a3df0a2a9a5974591e38654b40244.jpg treat image : temp/1739359228_3338360_1337066805_b1eca0c3be1c6ac0a8534a31e27746af.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 : 3 time used for this insertion : 0.012734651565551758 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 3 time used for this insertion : 0.011941909790039062 save missing photos in datou_result : time spend for datou_step_exec : 1.2645928859710693 time spend to save output : 0.029800891876220703 total time spend for step 2 : 1.29439377784729 step3:blur_detection Wed Feb 12 12:21:03 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/1739359228_3338360_1337076765_a669a8ae797aabd86942d4603dd6a890.jpg resize: (1440, 2560) 1337076765 -5.074280294964117 treat image : temp/1739359228_3338360_1337071718_3d6a3df0a2a9a5974591e38654b40244.jpg resize: (1440, 2560) 1337071718 -7.438322156840488 treat image : temp/1739359228_3338360_1337066805_b1eca0c3be1c6ac0a8534a31e27746af.jpg resize: (1440, 2560) 1337066805 -7.449701398093394 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 : 3 time used for this insertion : 0.013348817825317383 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 3 time used for this insertion : 0.012721061706542969 save missing photos in datou_result : time spend for datou_step_exec : 5.129812002182007 time spend to save output : 0.030972957611083984 total time spend for step 3 : 5.160784959793091 step4:rle_unique_nms_with_priority Wed Feb 12 12:21:09 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 Begin step rle-unique-nms batch 1 Loaded 499 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 105 nb_hashtags : 6 time to prepare the origin masks : 1.7455923557281494 time for calcul the mask position with numpy : 0.5393471717834473 nb_pixel_total : 3554704 time to create 1 rle with new method : 0.3777322769165039 time for calcul the mask position with numpy : 0.014337539672851562 nb_pixel_total : 2612 time to create 1 rle with old method : 0.0031871795654296875 time for calcul the mask position with numpy : 0.014305591583251953 nb_pixel_total : 942 time to create 1 rle with old method : 0.0011954307556152344 time for calcul the mask position with numpy : 0.014461994171142578 nb_pixel_total : 23 time to create 1 rle with old method : 6.699562072753906e-05 time for calcul the mask position with numpy : 0.014434576034545898 nb_pixel_total : 119 time to create 1 rle with old method : 0.00016379356384277344 time for calcul the mask position with numpy : 0.01492452621459961 nb_pixel_total : 2879 time to create 1 rle with old method : 0.0037539005279541016 time for calcul the mask position with numpy : 0.015480279922485352 nb_pixel_total : 293 time to create 1 rle with old method : 0.00039577484130859375 time for calcul the mask position with numpy : 0.015184879302978516 nb_pixel_total : 1015 time to create 1 rle with old method : 0.0013375282287597656 time for calcul the mask position with numpy : 0.014937877655029297 nb_pixel_total : 1044 time to create 1 rle with old method : 0.0013306140899658203 time for calcul the mask position with numpy : 0.01492166519165039 nb_pixel_total : 21 time to create 1 rle with old method : 7.009506225585938e-05 time for calcul the mask position with numpy : 0.014417648315429688 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003104209899902344 time for calcul the mask position with numpy : 0.014542102813720703 nb_pixel_total : 424 time to create 1 rle with old method : 0.0005590915679931641 time for calcul the mask position with numpy : 0.014965057373046875 nb_pixel_total : 289 time to create 1 rle with old method : 0.00037550926208496094 time for calcul the mask position with numpy : 0.015040159225463867 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003294944763183594 time for calcul the mask position with numpy : 0.014940023422241211 nb_pixel_total : 478 time to create 1 rle with old method : 0.0005831718444824219 time for calcul the mask position with numpy : 0.014867544174194336 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005040168762207031 time for calcul the mask position with numpy : 0.014931917190551758 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001227855682373047 time for calcul the mask position with numpy : 0.015316009521484375 nb_pixel_total : 415 time to create 1 rle with old method : 0.0005502700805664062 time for calcul the mask position with numpy : 0.015532493591308594 nb_pixel_total : 693 time to create 1 rle with old method : 0.0009620189666748047 time for calcul the mask position with numpy : 0.014950275421142578 nb_pixel_total : 1217 time to create 1 rle with old method : 0.0015788078308105469 time for calcul the mask position with numpy : 0.014829874038696289 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005345344543457031 time for calcul the mask position with numpy : 0.014837265014648438 nb_pixel_total : 1410 time to create 1 rle with old method : 0.0018317699432373047 time for calcul the mask position with numpy : 0.014336585998535156 nb_pixel_total : 2375 time to create 1 rle with old method : 0.0030088424682617188 time for calcul the mask position with numpy : 0.014953851699829102 nb_pixel_total : 522 time to create 1 rle with old method : 0.0007662773132324219 time for calcul the mask position with numpy : 0.015004873275756836 nb_pixel_total : 629 time to create 1 rle with old method : 0.0008006095886230469 time for calcul the mask position with numpy : 0.0151214599609375 nb_pixel_total : 1415 time to create 1 rle with old method : 0.001825571060180664 time for calcul the mask position with numpy : 0.015133857727050781 nb_pixel_total : 959 time to create 1 rle with old method : 0.0012557506561279297 time for calcul the mask position with numpy : 0.015110015869140625 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005497932434082031 time for calcul the mask position with numpy : 0.015075445175170898 nb_pixel_total : 6225 time to create 1 rle with old method : 0.0075702667236328125 time for calcul the mask position with numpy : 0.01668405532836914 nb_pixel_total : 792 time to create 1 rle with old method : 0.0010275840759277344 time for calcul the mask position with numpy : 0.017538070678710938 nb_pixel_total : 1813 time to create 1 rle with old method : 0.0022797584533691406 time for calcul the mask position with numpy : 0.015453338623046875 nb_pixel_total : 81 time to create 1 rle with old method : 0.00013303756713867188 time for calcul the mask position with numpy : 0.015231609344482422 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004143714904785156 time for calcul the mask position with numpy : 0.014845132827758789 nb_pixel_total : 1916 time to create 1 rle with old method : 0.0024743080139160156 time for calcul the mask position with numpy : 0.014866828918457031 nb_pixel_total : 1761 time to create 1 rle with old method : 0.002294301986694336 time for calcul the mask position with numpy : 0.014759540557861328 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006496906280517578 time for calcul the mask position with numpy : 0.014537334442138672 nb_pixel_total : 250 time to create 1 rle with old method : 0.00032520294189453125 time for calcul the mask position with numpy : 0.014987468719482422 nb_pixel_total : 760 time to create 1 rle with old method : 0.0009589195251464844 time for calcul the mask position with numpy : 0.014984130859375 nb_pixel_total : 1040 time to create 1 rle with old method : 0.0013306140899658203 time for calcul the mask position with numpy : 0.014913320541381836 nb_pixel_total : 779 time to create 1 rle with old method : 0.0010099411010742188 time for calcul the mask position with numpy : 0.014960765838623047 nb_pixel_total : 687 time to create 1 rle with old method : 0.0008897781372070312 time for calcul the mask position with numpy : 0.014893770217895508 nb_pixel_total : 231 time to create 1 rle with old method : 0.00030350685119628906 time for calcul the mask position with numpy : 0.014927387237548828 nb_pixel_total : 2791 time to create 1 rle with old method : 0.003551959991455078 time for calcul the mask position with numpy : 0.015302896499633789 nb_pixel_total : 940 time to create 1 rle with old method : 0.001138925552368164 time for calcul the mask position with numpy : 0.015553474426269531 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002186298370361328 time for calcul the mask position with numpy : 0.015025615692138672 nb_pixel_total : 515 time to create 1 rle with old method : 0.0006601810455322266 time for calcul the mask position with numpy : 0.014830589294433594 nb_pixel_total : 3836 time to create 1 rle with old method : 0.004857063293457031 time for calcul the mask position with numpy : 0.014827728271484375 nb_pixel_total : 775 time to create 1 rle with old method : 0.0009644031524658203 time for calcul the mask position with numpy : 0.014183521270751953 nb_pixel_total : 600 time to create 1 rle with old method : 0.0008389949798583984 time for calcul the mask position with numpy : 0.0146484375 nb_pixel_total : 472 time to create 1 rle with old method : 0.0005915164947509766 time for calcul the mask position with numpy : 0.014867067337036133 nb_pixel_total : 2479 time to create 1 rle with old method : 0.003020048141479492 time for calcul the mask position with numpy : 0.015359640121459961 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004024505615234375 time for calcul the mask position with numpy : 0.015121698379516602 nb_pixel_total : 13 time to create 1 rle with old method : 0.00010323524475097656 time for calcul the mask position with numpy : 0.015463113784790039 nb_pixel_total : 357 time to create 1 rle with old method : 0.0004811286926269531 time for calcul the mask position with numpy : 0.01502084732055664 nb_pixel_total : 230 time to create 1 rle with old method : 0.00030541419982910156 time for calcul the mask position with numpy : 0.014934778213500977 nb_pixel_total : 298 time to create 1 rle with old method : 0.00038886070251464844 time for calcul the mask position with numpy : 0.014721393585205078 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003502368927001953 time for calcul the mask position with numpy : 0.014713525772094727 nb_pixel_total : 656 time to create 1 rle with old method : 0.0008897781372070312 time for calcul the mask position with numpy : 0.015902996063232422 nb_pixel_total : 1165 time to create 1 rle with old method : 0.0021255016326904297 time for calcul the mask position with numpy : 0.01717519760131836 nb_pixel_total : 818 time to create 1 rle with old method : 0.0014619827270507812 time for calcul the mask position with numpy : 0.01710343360900879 nb_pixel_total : 15 time to create 1 rle with old method : 5.91278076171875e-05 time for calcul the mask position with numpy : 0.017081260681152344 nb_pixel_total : 247 time to create 1 rle with old method : 0.0004603862762451172 time for calcul the mask position with numpy : 0.017040729522705078 nb_pixel_total : 5153 time to create 1 rle with old method : 0.006521940231323242 time for calcul the mask position with numpy : 0.015380382537841797 nb_pixel_total : 990 time to create 1 rle with old method : 0.0015919208526611328 time for calcul the mask position with numpy : 0.01566934585571289 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005273818969726562 time for calcul the mask position with numpy : 0.014899015426635742 nb_pixel_total : 427 time to create 1 rle with old method : 0.000545501708984375 time for calcul the mask position with numpy : 0.014749526977539062 nb_pixel_total : 3422 time to create 1 rle with old method : 0.003933429718017578 time for calcul the mask position with numpy : 0.014909982681274414 nb_pixel_total : 126 time to create 1 rle with old method : 0.00024080276489257812 time for calcul the mask position with numpy : 0.014718770980834961 nb_pixel_total : 1765 time to create 1 rle with old method : 0.00214385986328125 time for calcul the mask position with numpy : 0.01654195785522461 nb_pixel_total : 3993 time to create 1 rle with old method : 0.00488734245300293 time for calcul the mask position with numpy : 0.01497793197631836 nb_pixel_total : 4053 time to create 1 rle with old method : 0.004957914352416992 time for calcul the mask position with numpy : 0.014959335327148438 nb_pixel_total : 728 time to create 1 rle with old method : 0.0009164810180664062 time for calcul the mask position with numpy : 0.014911413192749023 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003190040588378906 time for calcul the mask position with numpy : 0.015073537826538086 nb_pixel_total : 20 time to create 1 rle with old method : 4.38690185546875e-05 time for calcul the mask position with numpy : 0.01663041114807129 nb_pixel_total : 721 time to create 1 rle with old method : 0.0008213520050048828 time for calcul the mask position with numpy : 0.01506662368774414 nb_pixel_total : 3573 time to create 1 rle with old method : 0.005032539367675781 time for calcul the mask position with numpy : 0.01783132553100586 nb_pixel_total : 293 time to create 1 rle with old method : 0.0004177093505859375 time for calcul the mask position with numpy : 0.015485048294067383 nb_pixel_total : 1562 time to create 1 rle with old method : 0.002020120620727539 time for calcul the mask position with numpy : 0.015253067016601562 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003447532653808594 time for calcul the mask position with numpy : 0.014915943145751953 nb_pixel_total : 258 time to create 1 rle with old method : 0.000339508056640625 time for calcul the mask position with numpy : 0.014864683151245117 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005161762237548828 time for calcul the mask position with numpy : 0.014657735824584961 nb_pixel_total : 3761 time to create 1 rle with old method : 0.0045168399810791016 time for calcul the mask position with numpy : 0.014955520629882812 nb_pixel_total : 610 time to create 1 rle with old method : 0.00079345703125 time for calcul the mask position with numpy : 0.015030384063720703 nb_pixel_total : 13964 time to create 1 rle with old method : 0.017189979553222656 time for calcul the mask position with numpy : 0.01599264144897461 nb_pixel_total : 908 time to create 1 rle with old method : 0.0014216899871826172 time for calcul the mask position with numpy : 0.016808032989501953 nb_pixel_total : 44 time to create 1 rle with old method : 0.00010991096496582031 time for calcul the mask position with numpy : 0.015221834182739258 nb_pixel_total : 644 time to create 1 rle with old method : 0.000858306884765625 time for calcul the mask position with numpy : 0.015597820281982422 nb_pixel_total : 1203 time to create 1 rle with old method : 0.0015666484832763672 time for calcul the mask position with numpy : 0.015474796295166016 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003905296325683594 time for calcul the mask position with numpy : 0.014950037002563477 nb_pixel_total : 333 time to create 1 rle with old method : 0.0004341602325439453 time for calcul the mask position with numpy : 0.01715373992919922 nb_pixel_total : 3151 time to create 1 rle with old method : 0.003793478012084961 time for calcul the mask position with numpy : 0.014225244522094727 nb_pixel_total : 648 time to create 1 rle with old method : 0.0008096694946289062 time for calcul the mask position with numpy : 0.014588117599487305 nb_pixel_total : 2852 time to create 1 rle with old method : 0.003279447555541992 time for calcul the mask position with numpy : 0.014995574951171875 nb_pixel_total : 935 time to create 1 rle with old method : 0.0012078285217285156 time for calcul the mask position with numpy : 0.01490163803100586 nb_pixel_total : 344 time to create 1 rle with old method : 0.00046324729919433594 time for calcul the mask position with numpy : 0.014902353286743164 nb_pixel_total : 546 time to create 1 rle with old method : 0.0007202625274658203 time for calcul the mask position with numpy : 0.014872074127197266 nb_pixel_total : 60 time to create 1 rle with old method : 8.96453857421875e-05 time for calcul the mask position with numpy : 0.014882326126098633 nb_pixel_total : 3862 time to create 1 rle with old method : 0.004880428314208984 time for calcul the mask position with numpy : 0.015095710754394531 nb_pixel_total : 4671 time to create 1 rle with old method : 0.005931854248046875 time for calcul the mask position with numpy : 0.015271902084350586 nb_pixel_total : 1119 time to create 1 rle with old method : 0.001458883285522461 time for calcul the mask position with numpy : 0.014941692352294922 nb_pixel_total : 3998 time to create 1 rle with old method : 0.005014181137084961 time for calcul the mask position with numpy : 0.016174793243408203 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003581047058105469 time for calcul the mask position with numpy : 0.014694690704345703 nb_pixel_total : 400 time to create 1 rle with old method : 0.0004470348358154297 time for calcul the mask position with numpy : 0.014263391494750977 nb_pixel_total : 2413 time to create 1 rle with old method : 0.003086566925048828 time for calcul the mask position with numpy : 0.015185356140136719 nb_pixel_total : 392 time to create 1 rle with old method : 0.0007619857788085938 time for calcul the mask position with numpy : 0.01735663414001465 nb_pixel_total : 221 time to create 1 rle with old method : 0.0004112720489501953 create new chi : 2.7015864849090576 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 : 0.011877298355102539 batch 1 Loaded 106 chid ids of type : 4230 Number RLEs to save : 10064 TO DO : save crop sub photo not yet done ! save time : 0.6290717124938965 nb_obj : 177 nb_hashtags : 6 time to prepare the origin masks : 3.563883066177368 time for calcul the mask position with numpy : 0.6597075462341309 nb_pixel_total : 3516109 time to create 1 rle with new method : 0.6947331428527832 time for calcul the mask position with numpy : 0.011376619338989258 nb_pixel_total : 1299 time to create 1 rle with old method : 0.0015969276428222656 time for calcul the mask position with numpy : 0.011150836944580078 nb_pixel_total : 560 time to create 1 rle with old method : 0.0006611347198486328 time for calcul the mask position with numpy : 0.015364885330200195 nb_pixel_total : 225 time to create 1 rle with old method : 0.00031757354736328125 time for calcul the mask position with numpy : 0.016966819763183594 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003063678741455078 time for calcul the mask position with numpy : 0.018115758895874023 nb_pixel_total : 2900 time to create 1 rle with old method : 0.003664255142211914 time for calcul the mask position with numpy : 0.013359308242797852 nb_pixel_total : 1202 time to create 1 rle with old method : 0.0015897750854492188 time for calcul the mask position with numpy : 0.011825323104858398 nb_pixel_total : 230 time to create 1 rle with old method : 0.0002880096435546875 time for calcul the mask position with numpy : 0.01089167594909668 nb_pixel_total : 737 time to create 1 rle with old method : 0.0009288787841796875 time for calcul the mask position with numpy : 0.010609865188598633 nb_pixel_total : 295 time to create 1 rle with old method : 0.0003643035888671875 time for calcul the mask position with numpy : 0.010824918746948242 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002560615539550781 time for calcul the mask position with numpy : 0.01106572151184082 nb_pixel_total : 1559 time to create 1 rle with old method : 0.0020177364349365234 time for calcul the mask position with numpy : 0.010918617248535156 nb_pixel_total : 1247 time to create 1 rle with old method : 0.0016183853149414062 time for calcul the mask position with numpy : 0.010968685150146484 nb_pixel_total : 555 time to create 1 rle with old method : 0.0013260841369628906 time for calcul the mask position with numpy : 0.013358116149902344 nb_pixel_total : 2084 time to create 1 rle with old method : 0.0026030540466308594 time for calcul the mask position with numpy : 0.011339902877807617 nb_pixel_total : 650 time to create 1 rle with old method : 0.0007586479187011719 time for calcul the mask position with numpy : 0.011117219924926758 nb_pixel_total : 8 time to create 1 rle with old method : 4.220008850097656e-05 time for calcul the mask position with numpy : 0.01076960563659668 nb_pixel_total : 143 time to create 1 rle with old method : 0.00020837783813476562 time for calcul the mask position with numpy : 0.011415243148803711 nb_pixel_total : 237 time to create 1 rle with old method : 0.00032401084899902344 time for calcul the mask position with numpy : 0.01045083999633789 nb_pixel_total : 478 time to create 1 rle with old method : 0.004184722900390625 time for calcul the mask position with numpy : 0.011105775833129883 nb_pixel_total : 12 time to create 1 rle with old method : 5.173683166503906e-05 time for calcul the mask position with numpy : 0.010908126831054688 nb_pixel_total : 6116 time to create 1 rle with old method : 0.0073506832122802734 time for calcul the mask position with numpy : 0.011085271835327148 nb_pixel_total : 3686 time to create 1 rle with old method : 0.004175662994384766 time for calcul the mask position with numpy : 0.010637521743774414 nb_pixel_total : 1460 time to create 1 rle with old method : 0.001928091049194336 time for calcul the mask position with numpy : 0.0110015869140625 nb_pixel_total : 784 time to create 1 rle with old method : 0.0009393692016601562 time for calcul the mask position with numpy : 0.010628700256347656 nb_pixel_total : 5828 time to create 1 rle with old method : 0.007232189178466797 time for calcul the mask position with numpy : 0.011147260665893555 nb_pixel_total : 1640 time to create 1 rle with old method : 0.0021271705627441406 time for calcul the mask position with numpy : 0.010721206665039062 nb_pixel_total : 9517 time to create 1 rle with old method : 0.011857748031616211 time for calcul the mask position with numpy : 0.011248111724853516 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005927085876464844 time for calcul the mask position with numpy : 0.011457443237304688 nb_pixel_total : 1000 time to create 1 rle with old method : 0.0013086795806884766 time for calcul the mask position with numpy : 0.011255025863647461 nb_pixel_total : 3061 time to create 1 rle with old method : 0.003771066665649414 time for calcul the mask position with numpy : 0.010763168334960938 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006539821624755859 time for calcul the mask position with numpy : 0.010541439056396484 nb_pixel_total : 3286 time to create 1 rle with old method : 0.0038115978240966797 time for calcul the mask position with numpy : 0.01184391975402832 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005142688751220703 time for calcul the mask position with numpy : 0.011279582977294922 nb_pixel_total : 2362 time to create 1 rle with old method : 0.0028281211853027344 time for calcul the mask position with numpy : 0.012063026428222656 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003695487976074219 time for calcul the mask position with numpy : 0.011993169784545898 nb_pixel_total : 79 time to create 1 rle with old method : 0.00014781951904296875 time for calcul the mask position with numpy : 0.011607885360717773 nb_pixel_total : 3525 time to create 1 rle with old method : 0.004297018051147461 time for calcul the mask position with numpy : 0.011312723159790039 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005621910095214844 time for calcul the mask position with numpy : 0.011226892471313477 nb_pixel_total : 273 time to create 1 rle with old method : 0.0003731250762939453 time for calcul the mask position with numpy : 0.011530637741088867 nb_pixel_total : 557 time to create 1 rle with old method : 0.0007014274597167969 time for calcul the mask position with numpy : 0.011608362197875977 nb_pixel_total : 736 time to create 1 rle with old method : 0.0008890628814697266 time for calcul the mask position with numpy : 0.011004209518432617 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002608299255371094 time for calcul the mask position with numpy : 0.01108551025390625 nb_pixel_total : 1177 time to create 1 rle with old method : 0.0012879371643066406 time for calcul the mask position with numpy : 0.011385917663574219 nb_pixel_total : 381 time to create 1 rle with old method : 0.000514984130859375 time for calcul the mask position with numpy : 0.010808944702148438 nb_pixel_total : 408 time to create 1 rle with old method : 0.00047135353088378906 time for calcul the mask position with numpy : 0.010689973831176758 nb_pixel_total : 156 time to create 1 rle with old method : 0.0001995563507080078 time for calcul the mask position with numpy : 0.011433839797973633 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007014274597167969 time for calcul the mask position with numpy : 0.01106405258178711 nb_pixel_total : 2605 time to create 1 rle with old method : 0.002850770950317383 time for calcul the mask position with numpy : 0.010536432266235352 nb_pixel_total : 2912 time to create 1 rle with old method : 0.003541231155395508 time for calcul the mask position with numpy : 0.010936260223388672 nb_pixel_total : 28 time to create 1 rle with old method : 8.440017700195312e-05 time for calcul the mask position with numpy : 0.010514020919799805 nb_pixel_total : 377 time to create 1 rle with old method : 0.0004723072052001953 time for calcul the mask position with numpy : 0.010699748992919922 nb_pixel_total : 913 time to create 1 rle with old method : 0.0011107921600341797 time for calcul the mask position with numpy : 0.010403871536254883 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003407001495361328 time for calcul the mask position with numpy : 0.010154247283935547 nb_pixel_total : 318 time to create 1 rle with old method : 0.0003981590270996094 time for calcul the mask position with numpy : 0.010648488998413086 nb_pixel_total : 430 time to create 1 rle with old method : 0.0007832050323486328 time for calcul the mask position with numpy : 0.010732412338256836 nb_pixel_total : 462 time to create 1 rle with old method : 0.0005514621734619141 time for calcul the mask position with numpy : 0.010560274124145508 nb_pixel_total : 563 time to create 1 rle with old method : 0.0006909370422363281 time for calcul the mask position with numpy : 0.010597467422485352 nb_pixel_total : 116 time to create 1 rle with old method : 0.0001609325408935547 time for calcul the mask position with numpy : 0.010288476943969727 nb_pixel_total : 333 time to create 1 rle with old method : 0.00042724609375 time for calcul the mask position with numpy : 0.01068735122680664 nb_pixel_total : 515 time to create 1 rle with old method : 0.0006623268127441406 time for calcul the mask position with numpy : 0.010760307312011719 nb_pixel_total : 582 time to create 1 rle with old method : 0.0007460117340087891 time for calcul the mask position with numpy : 0.010851383209228516 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005011558532714844 time for calcul the mask position with numpy : 0.010916709899902344 nb_pixel_total : 1007 time to create 1 rle with old method : 0.0012669563293457031 time for calcul the mask position with numpy : 0.011179924011230469 nb_pixel_total : 158 time to create 1 rle with old method : 0.0002224445343017578 time for calcul the mask position with numpy : 0.011219978332519531 nb_pixel_total : 153 time to create 1 rle with old method : 0.00021696090698242188 time for calcul the mask position with numpy : 0.012014389038085938 nb_pixel_total : 68 time to create 1 rle with old method : 0.00010633468627929688 time for calcul the mask position with numpy : 0.011703252792358398 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005993843078613281 time for calcul the mask position with numpy : 0.011710643768310547 nb_pixel_total : 633 time to create 1 rle with old method : 0.0007834434509277344 time for calcul the mask position with numpy : 0.011332511901855469 nb_pixel_total : 704 time to create 1 rle with old method : 0.0008900165557861328 time for calcul the mask position with numpy : 0.010934829711914062 nb_pixel_total : 142 time to create 1 rle with old method : 0.0001876354217529297 time for calcul the mask position with numpy : 0.011069774627685547 nb_pixel_total : 1694 time to create 1 rle with old method : 0.0020172595977783203 time for calcul the mask position with numpy : 0.011711835861206055 nb_pixel_total : 1176 time to create 1 rle with old method : 0.0014636516571044922 time for calcul the mask position with numpy : 0.011588573455810547 nb_pixel_total : 2893 time to create 1 rle with old method : 0.0032820701599121094 time for calcul the mask position with numpy : 0.011759281158447266 nb_pixel_total : 449 time to create 1 rle with old method : 0.0008187294006347656 time for calcul the mask position with numpy : 0.012595176696777344 nb_pixel_total : 466 time to create 1 rle with old method : 0.0005869865417480469 time for calcul the mask position with numpy : 0.013628005981445312 nb_pixel_total : 3889 time to create 1 rle with old method : 0.0047414302825927734 time for calcul the mask position with numpy : 0.01191258430480957 nb_pixel_total : 1061 time to create 1 rle with old method : 0.0013170242309570312 time for calcul the mask position with numpy : 0.010993003845214844 nb_pixel_total : 612 time to create 1 rle with old method : 0.0008108615875244141 time for calcul the mask position with numpy : 0.011098623275756836 nb_pixel_total : 1371 time to create 1 rle with old method : 0.0017383098602294922 time for calcul the mask position with numpy : 0.010856389999389648 nb_pixel_total : 469 time to create 1 rle with old method : 0.0006153583526611328 time for calcul the mask position with numpy : 0.01094508171081543 nb_pixel_total : 201 time to create 1 rle with old method : 0.00026416778564453125 time for calcul the mask position with numpy : 0.010915994644165039 nb_pixel_total : 5335 time to create 1 rle with old method : 0.00604701042175293 time for calcul the mask position with numpy : 0.01100611686706543 nb_pixel_total : 19 time to create 1 rle with old method : 7.462501525878906e-05 time for calcul the mask position with numpy : 0.010969877243041992 nb_pixel_total : 42 time to create 1 rle with old method : 9.489059448242188e-05 time for calcul the mask position with numpy : 0.0129241943359375 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005598068237304688 time for calcul the mask position with numpy : 0.010933399200439453 nb_pixel_total : 341 time to create 1 rle with old method : 0.0004355907440185547 time for calcul the mask position with numpy : 0.011566400527954102 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006797313690185547 time for calcul the mask position with numpy : 0.01110696792602539 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006422996520996094 time for calcul the mask position with numpy : 0.01127314567565918 nb_pixel_total : 697 time to create 1 rle with old method : 0.0009353160858154297 time for calcul the mask position with numpy : 0.011049032211303711 nb_pixel_total : 2617 time to create 1 rle with old method : 0.0032083988189697266 time for calcul the mask position with numpy : 0.011268138885498047 nb_pixel_total : 795 time to create 1 rle with old method : 0.000980377197265625 time for calcul the mask position with numpy : 0.010695457458496094 nb_pixel_total : 375 time to create 1 rle with old method : 0.0004668235778808594 time for calcul the mask position with numpy : 0.010964155197143555 nb_pixel_total : 1837 time to create 1 rle with old method : 0.002231121063232422 time for calcul the mask position with numpy : 0.011270523071289062 nb_pixel_total : 176 time to create 1 rle with old method : 0.00023412704467773438 time for calcul the mask position with numpy : 0.014141321182250977 nb_pixel_total : 2 time to create 1 rle with old method : 3.409385681152344e-05 time for calcul the mask position with numpy : 0.013213634490966797 nb_pixel_total : 540 time to create 1 rle with old method : 0.0006735324859619141 time for calcul the mask position with numpy : 0.011246919631958008 nb_pixel_total : 570 time to create 1 rle with old method : 0.0006799697875976562 time for calcul the mask position with numpy : 0.011360883712768555 nb_pixel_total : 68 time to create 1 rle with old method : 0.00015974044799804688 time for calcul the mask position with numpy : 0.011746644973754883 nb_pixel_total : 4057 time to create 1 rle with old method : 0.004853010177612305 time for calcul the mask position with numpy : 0.012959480285644531 nb_pixel_total : 311 time to create 1 rle with old method : 0.0005218982696533203 time for calcul the mask position with numpy : 0.011578083038330078 nb_pixel_total : 1643 time to create 1 rle with old method : 0.0021233558654785156 time for calcul the mask position with numpy : 0.011008977890014648 nb_pixel_total : 299 time to create 1 rle with old method : 0.0003948211669921875 time for calcul the mask position with numpy : 0.011001110076904297 nb_pixel_total : 537 time to create 1 rle with old method : 0.0007047653198242188 time for calcul the mask position with numpy : 0.010953426361083984 nb_pixel_total : 1904 time to create 1 rle with old method : 0.002421140670776367 time for calcul the mask position with numpy : 0.011130332946777344 nb_pixel_total : 313 time to create 1 rle with old method : 0.00043702125549316406 time for calcul the mask position with numpy : 0.01580643653869629 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002655982971191406 time for calcul the mask position with numpy : 0.017203092575073242 nb_pixel_total : 846 time to create 1 rle with old method : 0.0015382766723632812 time for calcul the mask position with numpy : 0.01717972755432129 nb_pixel_total : 62 time to create 1 rle with old method : 0.00022721290588378906 time for calcul the mask position with numpy : 0.017208576202392578 nb_pixel_total : 1084 time to create 1 rle with old method : 0.002028942108154297 time for calcul the mask position with numpy : 0.016873598098754883 nb_pixel_total : 1 time to create 1 rle with old method : 1.811981201171875e-05 time for calcul the mask position with numpy : 0.014873743057250977 nb_pixel_total : 397 time to create 1 rle with old method : 0.00047469139099121094 time for calcul the mask position with numpy : 0.014550924301147461 nb_pixel_total : 2932 time to create 1 rle with old method : 0.0036449432373046875 time for calcul the mask position with numpy : 0.014865875244140625 nb_pixel_total : 877 time to create 1 rle with old method : 0.0011172294616699219 time for calcul the mask position with numpy : 0.014890670776367188 nb_pixel_total : 1781 time to create 1 rle with old method : 0.0022280216217041016 time for calcul the mask position with numpy : 0.014956951141357422 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004124641418457031 time for calcul the mask position with numpy : 0.014995336532592773 nb_pixel_total : 585 time to create 1 rle with old method : 0.0007596015930175781 time for calcul the mask position with numpy : 0.015013456344604492 nb_pixel_total : 26 time to create 1 rle with old method : 5.078315734863281e-05 time for calcul the mask position with numpy : 0.015039443969726562 nb_pixel_total : 103 time to create 1 rle with old method : 0.00016188621520996094 time for calcul the mask position with numpy : 0.015074968338012695 nb_pixel_total : 292 time to create 1 rle with old method : 0.0003535747528076172 time for calcul the mask position with numpy : 0.01486659049987793 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002505779266357422 time for calcul the mask position with numpy : 0.014330863952636719 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.014476776123046875 nb_pixel_total : 407 time to create 1 rle with old method : 0.00048732757568359375 time for calcul the mask position with numpy : 0.014221906661987305 nb_pixel_total : 140 time to create 1 rle with old method : 0.0001919269561767578 time for calcul the mask position with numpy : 0.014592170715332031 nb_pixel_total : 3181 time to create 1 rle with old method : 0.0044786930084228516 time for calcul the mask position with numpy : 0.014560699462890625 nb_pixel_total : 47 time to create 1 rle with old method : 8.559226989746094e-05 time for calcul the mask position with numpy : 0.014918088912963867 nb_pixel_total : 354 time to create 1 rle with old method : 0.00045108795166015625 time for calcul the mask position with numpy : 0.014885663986206055 nb_pixel_total : 4626 time to create 1 rle with old method : 0.00518345832824707 time for calcul the mask position with numpy : 0.014874696731567383 nb_pixel_total : 4055 time to create 1 rle with old method : 0.004851102828979492 time for calcul the mask position with numpy : 0.014969348907470703 nb_pixel_total : 260 time to create 1 rle with old method : 0.00037217140197753906 time for calcul the mask position with numpy : 0.01509714126586914 nb_pixel_total : 1770 time to create 1 rle with old method : 0.002250194549560547 time for calcul the mask position with numpy : 0.014985799789428711 nb_pixel_total : 1790 time to create 1 rle with old method : 0.00220489501953125 time for calcul the mask position with numpy : 0.014966249465942383 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006093978881835938 time for calcul the mask position with numpy : 0.014906167984008789 nb_pixel_total : 27 time to create 1 rle with old method : 5.91278076171875e-05 time for calcul the mask position with numpy : 0.016726255416870117 nb_pixel_total : 410 time to create 1 rle with old method : 0.000507354736328125 time for calcul the mask position with numpy : 0.014693737030029297 nb_pixel_total : 333 time to create 1 rle with old method : 0.0004324913024902344 time for calcul the mask position with numpy : 0.014991044998168945 nb_pixel_total : 440 time to create 1 rle with old method : 0.0005230903625488281 time for calcul the mask position with numpy : 0.014800071716308594 nb_pixel_total : 2563 time to create 1 rle with old method : 0.0035064220428466797 time for calcul the mask position with numpy : 0.016399383544921875 nb_pixel_total : 171 time to create 1 rle with old method : 0.00031638145446777344 time for calcul the mask position with numpy : 0.016319751739501953 nb_pixel_total : 969 time to create 1 rle with old method : 0.0017809867858886719 time for calcul the mask position with numpy : 0.01702880859375 nb_pixel_total : 603 time to create 1 rle with old method : 0.0010688304901123047 time for calcul the mask position with numpy : 0.016812801361083984 nb_pixel_total : 4637 time to create 1 rle with old method : 0.005433320999145508 time for calcul the mask position with numpy : 0.014944791793823242 nb_pixel_total : 301 time to create 1 rle with old method : 0.00040078163146972656 time for calcul the mask position with numpy : 0.014955520629882812 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003077983856201172 time for calcul the mask position with numpy : 0.014963150024414062 nb_pixel_total : 1178 time to create 1 rle with old method : 0.0014946460723876953 time for calcul the mask position with numpy : 0.014984607696533203 nb_pixel_total : 177 time to create 1 rle with old method : 0.00023365020751953125 time for calcul the mask position with numpy : 0.014954328536987305 nb_pixel_total : 883 time to create 1 rle with old method : 0.0011260509490966797 time for calcul the mask position with numpy : 0.014955282211303711 nb_pixel_total : 1607 time to create 1 rle with old method : 0.0020301342010498047 time for calcul the mask position with numpy : 0.015024662017822266 nb_pixel_total : 104 time to create 1 rle with old method : 0.00017976760864257812 time for calcul the mask position with numpy : 0.015130758285522461 nb_pixel_total : 327 time to create 1 rle with old method : 0.00046062469482421875 time for calcul the mask position with numpy : 0.014970064163208008 nb_pixel_total : 134 time to create 1 rle with old method : 0.00017499923706054688 time for calcul the mask position with numpy : 0.015155553817749023 nb_pixel_total : 251 time to create 1 rle with old method : 0.00030922889709472656 time for calcul the mask position with numpy : 0.014940500259399414 nb_pixel_total : 129 time to create 1 rle with old method : 0.000186920166015625 time for calcul the mask position with numpy : 0.015300273895263672 nb_pixel_total : 150 time to create 1 rle with old method : 0.00021719932556152344 time for calcul the mask position with numpy : 0.014735221862792969 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006613731384277344 time for calcul the mask position with numpy : 0.014862775802612305 nb_pixel_total : 381 time to create 1 rle with old method : 0.0004878044128417969 time for calcul the mask position with numpy : 0.014876365661621094 nb_pixel_total : 303 time to create 1 rle with old method : 0.00036144256591796875 time for calcul the mask position with numpy : 0.014968156814575195 nb_pixel_total : 165 time to create 1 rle with old method : 0.00019359588623046875 time for calcul the mask position with numpy : 0.014873027801513672 nb_pixel_total : 1088 time to create 1 rle with old method : 0.0013432502746582031 time for calcul the mask position with numpy : 0.014966726303100586 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003840923309326172 time for calcul the mask position with numpy : 0.01460719108581543 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003609657287597656 time for calcul the mask position with numpy : 0.014885187149047852 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002651214599609375 time for calcul the mask position with numpy : 0.014860153198242188 nb_pixel_total : 327 time to create 1 rle with old method : 0.00042128562927246094 time for calcul the mask position with numpy : 0.014050483703613281 nb_pixel_total : 7 time to create 1 rle with old method : 2.6464462280273438e-05 time for calcul the mask position with numpy : 0.014490604400634766 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004570484161376953 time for calcul the mask position with numpy : 0.014547586441040039 nb_pixel_total : 780 time to create 1 rle with old method : 0.0009851455688476562 time for calcul the mask position with numpy : 0.014885902404785156 nb_pixel_total : 2 time to create 1 rle with old method : 1.2159347534179688e-05 time for calcul the mask position with numpy : 0.014870405197143555 nb_pixel_total : 85 time to create 1 rle with old method : 0.0001201629638671875 time for calcul the mask position with numpy : 0.014854907989501953 nb_pixel_total : 536 time to create 1 rle with old method : 0.0006771087646484375 time for calcul the mask position with numpy : 0.014885425567626953 nb_pixel_total : 531 time to create 1 rle with old method : 0.0006680488586425781 time for calcul the mask position with numpy : 0.014852762222290039 nb_pixel_total : 914 time to create 1 rle with old method : 0.0011858940124511719 time for calcul the mask position with numpy : 0.014873266220092773 nb_pixel_total : 87 time to create 1 rle with old method : 0.00014400482177734375 time for calcul the mask position with numpy : 0.014396905899047852 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005905628204345703 time for calcul the mask position with numpy : 0.014325857162475586 nb_pixel_total : 439 time to create 1 rle with old method : 0.0005593299865722656 time for calcul the mask position with numpy : 0.013961315155029297 nb_pixel_total : 148 time to create 1 rle with old method : 0.0001728534698486328 time for calcul the mask position with numpy : 0.014353752136230469 nb_pixel_total : 2690 time to create 1 rle with old method : 0.003263235092163086 time for calcul the mask position with numpy : 0.015018939971923828 nb_pixel_total : 611 time to create 1 rle with old method : 0.000812530517578125 time for calcul the mask position with numpy : 0.014753580093383789 nb_pixel_total : 639 time to create 1 rle with old method : 0.0008113384246826172 create new chi : 3.8803586959838867 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 : 0.0018112659454345703 batch 1 Loaded 178 chid ids of type : 4230 Number RLEs to save : 14102 TO DO : save crop sub photo not yet done ! save time : 0.793964147567749 nb_obj : 214 nb_hashtags : 6 time to prepare the origin masks : 3.7858645915985107 time for calcul the mask position with numpy : 0.04985189437866211 nb_pixel_total : 3447859 time to create 1 rle with new method : 0.17773699760437012 time for calcul the mask position with numpy : 0.011124372482299805 nb_pixel_total : 492 time to create 1 rle with old method : 0.0006124973297119141 time for calcul the mask position with numpy : 0.010782241821289062 nb_pixel_total : 829 time to create 1 rle with old method : 0.0009913444519042969 time for calcul the mask position with numpy : 0.010991573333740234 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002636909484863281 time for calcul the mask position with numpy : 0.010933637619018555 nb_pixel_total : 287 time to create 1 rle with old method : 0.0003859996795654297 time for calcul the mask position with numpy : 0.01075434684753418 nb_pixel_total : 174 time to create 1 rle with old method : 0.00021219253540039062 time for calcul the mask position with numpy : 0.01753997802734375 nb_pixel_total : 2560 time to create 1 rle with old method : 0.0031387805938720703 time for calcul the mask position with numpy : 0.01731562614440918 nb_pixel_total : 932 time to create 1 rle with old method : 0.0011548995971679688 time for calcul the mask position with numpy : 0.015392065048217773 nb_pixel_total : 189 time to create 1 rle with old method : 0.00024127960205078125 time for calcul the mask position with numpy : 0.018142223358154297 nb_pixel_total : 101 time to create 1 rle with old method : 0.00018072128295898438 time for calcul the mask position with numpy : 0.017351388931274414 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007116794586181641 time for calcul the mask position with numpy : 0.011336088180541992 nb_pixel_total : 1129 time to create 1 rle with old method : 0.001379251480102539 time for calcul the mask position with numpy : 0.011338233947753906 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002834796905517578 time for calcul the mask position with numpy : 0.011054277420043945 nb_pixel_total : 2734 time to create 1 rle with old method : 0.0032720565795898438 time for calcul the mask position with numpy : 0.011180400848388672 nb_pixel_total : 438 time to create 1 rle with old method : 0.0004813671112060547 time for calcul the mask position with numpy : 0.010856866836547852 nb_pixel_total : 71 time to create 1 rle with old method : 0.00010514259338378906 time for calcul the mask position with numpy : 0.011157035827636719 nb_pixel_total : 584 time to create 1 rle with old method : 0.0008060932159423828 time for calcul the mask position with numpy : 0.011873006820678711 nb_pixel_total : 128 time to create 1 rle with old method : 0.0001842975616455078 time for calcul the mask position with numpy : 0.011632680892944336 nb_pixel_total : 1452 time to create 1 rle with old method : 0.0017282962799072266 time for calcul the mask position with numpy : 0.010948419570922852 nb_pixel_total : 51 time to create 1 rle with old method : 0.000118255615234375 time for calcul the mask position with numpy : 0.010972738265991211 nb_pixel_total : 3177 time to create 1 rle with old method : 0.003832101821899414 time for calcul the mask position with numpy : 0.011133670806884766 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002346038818359375 time for calcul the mask position with numpy : 0.010892391204833984 nb_pixel_total : 499 time to create 1 rle with old method : 0.0006697177886962891 time for calcul the mask position with numpy : 0.010714054107666016 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006382465362548828 time for calcul the mask position with numpy : 0.01140141487121582 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005090236663818359 time for calcul the mask position with numpy : 0.010596275329589844 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003192424774169922 time for calcul the mask position with numpy : 0.01066136360168457 nb_pixel_total : 113 time to create 1 rle with old method : 0.00016546249389648438 time for calcul the mask position with numpy : 0.01041102409362793 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006108283996582031 time for calcul the mask position with numpy : 0.010467052459716797 nb_pixel_total : 880 time to create 1 rle with old method : 0.0011262893676757812 time for calcul the mask position with numpy : 0.01063394546508789 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002827644348144531 time for calcul the mask position with numpy : 0.010616779327392578 nb_pixel_total : 375 time to create 1 rle with old method : 0.0004687309265136719 time for calcul the mask position with numpy : 0.011144399642944336 nb_pixel_total : 171 time to create 1 rle with old method : 0.00020551681518554688 time for calcul the mask position with numpy : 0.010933160781860352 nb_pixel_total : 232 time to create 1 rle with old method : 0.0002951622009277344 time for calcul the mask position with numpy : 0.011053085327148438 nb_pixel_total : 1048 time to create 1 rle with old method : 0.0013310909271240234 time for calcul the mask position with numpy : 0.011196136474609375 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003592967987060547 time for calcul the mask position with numpy : 0.011125564575195312 nb_pixel_total : 2625 time to create 1 rle with old method : 0.003154754638671875 time for calcul the mask position with numpy : 0.011532783508300781 nb_pixel_total : 115 time to create 1 rle with old method : 0.00021505355834960938 time for calcul the mask position with numpy : 0.010933399200439453 nb_pixel_total : 357 time to create 1 rle with old method : 0.00047588348388671875 time for calcul the mask position with numpy : 0.010823726654052734 nb_pixel_total : 1258 time to create 1 rle with old method : 0.00164031982421875 time for calcul the mask position with numpy : 0.010926961898803711 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005443096160888672 time for calcul the mask position with numpy : 0.010504007339477539 nb_pixel_total : 453 time to create 1 rle with old method : 0.0005609989166259766 time for calcul the mask position with numpy : 0.010605096817016602 nb_pixel_total : 467 time to create 1 rle with old method : 0.0005927085876464844 time for calcul the mask position with numpy : 0.0102996826171875 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002028942108154297 time for calcul the mask position with numpy : 0.010623693466186523 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005970001220703125 time for calcul the mask position with numpy : 0.01070094108581543 nb_pixel_total : 259 time to create 1 rle with old method : 0.0005414485931396484 time for calcul the mask position with numpy : 0.011930704116821289 nb_pixel_total : 466 time to create 1 rle with old method : 0.0006024837493896484 time for calcul the mask position with numpy : 0.010867595672607422 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003635883331298828 time for calcul the mask position with numpy : 0.010583639144897461 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003120899200439453 time for calcul the mask position with numpy : 0.010301589965820312 nb_pixel_total : 497 time to create 1 rle with old method : 0.0005726814270019531 time for calcul the mask position with numpy : 0.010216236114501953 nb_pixel_total : 421 time to create 1 rle with old method : 0.0005230903625488281 time for calcul the mask position with numpy : 0.010421037673950195 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002589225769042969 time for calcul the mask position with numpy : 0.010508537292480469 nb_pixel_total : 1131 time to create 1 rle with old method : 0.001367807388305664 time for calcul the mask position with numpy : 0.010559558868408203 nb_pixel_total : 132 time to create 1 rle with old method : 0.0001862049102783203 time for calcul the mask position with numpy : 0.011263608932495117 nb_pixel_total : 1298 time to create 1 rle with old method : 0.0016183853149414062 time for calcul the mask position with numpy : 0.011059999465942383 nb_pixel_total : 67 time to create 1 rle with old method : 0.00011038780212402344 time for calcul the mask position with numpy : 0.01126408576965332 nb_pixel_total : 332 time to create 1 rle with old method : 0.00044989585876464844 time for calcul the mask position with numpy : 0.012968778610229492 nb_pixel_total : 61 time to create 1 rle with old method : 0.00015687942504882812 time for calcul the mask position with numpy : 0.010673999786376953 nb_pixel_total : 1605 time to create 1 rle with old method : 0.002048492431640625 time for calcul the mask position with numpy : 0.011010169982910156 nb_pixel_total : 329 time to create 1 rle with old method : 0.0004115104675292969 time for calcul the mask position with numpy : 0.011772632598876953 nb_pixel_total : 1799 time to create 1 rle with old method : 0.0020842552185058594 time for calcul the mask position with numpy : 0.010992050170898438 nb_pixel_total : 148 time to create 1 rle with old method : 0.00021958351135253906 time for calcul the mask position with numpy : 0.011224508285522461 nb_pixel_total : 742 time to create 1 rle with old method : 0.0009551048278808594 time for calcul the mask position with numpy : 0.011125802993774414 nb_pixel_total : 40 time to create 1 rle with old method : 0.00011324882507324219 time for calcul the mask position with numpy : 0.012278556823730469 nb_pixel_total : 264 time to create 1 rle with old method : 0.0003647804260253906 time for calcul the mask position with numpy : 0.011299610137939453 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009171962738037109 time for calcul the mask position with numpy : 0.011363983154296875 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005247592926025391 time for calcul the mask position with numpy : 0.011132001876831055 nb_pixel_total : 666 time to create 1 rle with old method : 0.0008099079132080078 time for calcul the mask position with numpy : 0.010838508605957031 nb_pixel_total : 86 time to create 1 rle with old method : 0.0001285076141357422 time for calcul the mask position with numpy : 0.010519266128540039 nb_pixel_total : 345 time to create 1 rle with old method : 0.00047135353088378906 time for calcul the mask position with numpy : 0.01063227653503418 nb_pixel_total : 307 time to create 1 rle with old method : 0.0003676414489746094 time for calcul the mask position with numpy : 0.010640144348144531 nb_pixel_total : 314 time to create 1 rle with old method : 0.00044083595275878906 time for calcul the mask position with numpy : 0.011461019515991211 nb_pixel_total : 856 time to create 1 rle with old method : 0.0011034011840820312 time for calcul the mask position with numpy : 0.01136159896850586 nb_pixel_total : 2053 time to create 1 rle with old method : 0.0026068687438964844 time for calcul the mask position with numpy : 0.011312007904052734 nb_pixel_total : 254 time to create 1 rle with old method : 0.00034046173095703125 time for calcul the mask position with numpy : 0.011186361312866211 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003566741943359375 time for calcul the mask position with numpy : 0.011556625366210938 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003097057342529297 time for calcul the mask position with numpy : 0.011061906814575195 nb_pixel_total : 374 time to create 1 rle with old method : 0.0004956722259521484 time for calcul the mask position with numpy : 0.011210203170776367 nb_pixel_total : 255 time to create 1 rle with old method : 0.0003402233123779297 time for calcul the mask position with numpy : 0.011452198028564453 nb_pixel_total : 27 time to create 1 rle with old method : 0.00013518333435058594 time for calcul the mask position with numpy : 0.010994672775268555 nb_pixel_total : 635 time to create 1 rle with old method : 0.0008270740509033203 time for calcul the mask position with numpy : 0.011617183685302734 nb_pixel_total : 235 time to create 1 rle with old method : 0.00032258033752441406 time for calcul the mask position with numpy : 0.010962963104248047 nb_pixel_total : 6113 time to create 1 rle with old method : 0.007627725601196289 time for calcul the mask position with numpy : 0.011349916458129883 nb_pixel_total : 1075 time to create 1 rle with old method : 0.0013163089752197266 time for calcul the mask position with numpy : 0.010789632797241211 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004699230194091797 time for calcul the mask position with numpy : 0.011350154876708984 nb_pixel_total : 357 time to create 1 rle with old method : 0.00046443939208984375 time for calcul the mask position with numpy : 0.010923147201538086 nb_pixel_total : 1258 time to create 1 rle with old method : 0.0016069412231445312 time for calcul the mask position with numpy : 0.011388778686523438 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002548694610595703 time for calcul the mask position with numpy : 0.01100301742553711 nb_pixel_total : 1022 time to create 1 rle with old method : 0.00133514404296875 time for calcul the mask position with numpy : 0.011793851852416992 nb_pixel_total : 533 time to create 1 rle with old method : 0.0006966590881347656 time for calcul the mask position with numpy : 0.011252164840698242 nb_pixel_total : 664 time to create 1 rle with old method : 0.0008935928344726562 time for calcul the mask position with numpy : 0.011152505874633789 nb_pixel_total : 28166 time to create 1 rle with old method : 0.033483028411865234 time for calcul the mask position with numpy : 0.01104879379272461 nb_pixel_total : 32 time to create 1 rle with old method : 8.0108642578125e-05 time for calcul the mask position with numpy : 0.011733531951904297 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005419254302978516 time for calcul the mask position with numpy : 0.012031078338623047 nb_pixel_total : 1078 time to create 1 rle with old method : 0.001361846923828125 time for calcul the mask position with numpy : 0.01154637336730957 nb_pixel_total : 302 time to create 1 rle with old method : 0.0003845691680908203 time for calcul the mask position with numpy : 0.011440038681030273 nb_pixel_total : 1587 time to create 1 rle with old method : 0.0019707679748535156 time for calcul the mask position with numpy : 0.01294708251953125 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004184246063232422 time for calcul the mask position with numpy : 0.01103520393371582 nb_pixel_total : 1340 time to create 1 rle with old method : 0.0016982555389404297 time for calcul the mask position with numpy : 0.011614084243774414 nb_pixel_total : 64 time to create 1 rle with old method : 0.00011920928955078125 time for calcul the mask position with numpy : 0.011475801467895508 nb_pixel_total : 315 time to create 1 rle with old method : 0.0004119873046875 time for calcul the mask position with numpy : 0.012078046798706055 nb_pixel_total : 906 time to create 1 rle with old method : 0.0011806488037109375 time for calcul the mask position with numpy : 0.012119293212890625 nb_pixel_total : 788 time to create 1 rle with old method : 0.0010123252868652344 time for calcul the mask position with numpy : 0.012354373931884766 nb_pixel_total : 294 time to create 1 rle with old method : 0.00040411949157714844 time for calcul the mask position with numpy : 0.013155460357666016 nb_pixel_total : 125 time to create 1 rle with old method : 0.0001895427703857422 time for calcul the mask position with numpy : 0.012064456939697266 nb_pixel_total : 1396 time to create 1 rle with old method : 0.0018308162689208984 time for calcul the mask position with numpy : 0.012918472290039062 nb_pixel_total : 350 time to create 1 rle with old method : 0.0004782676696777344 time for calcul the mask position with numpy : 0.01372385025024414 nb_pixel_total : 4520 time to create 1 rle with old method : 0.005652427673339844 time for calcul the mask position with numpy : 0.012467145919799805 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003311634063720703 time for calcul the mask position with numpy : 0.012729883193969727 nb_pixel_total : 1651 time to create 1 rle with old method : 0.00211334228515625 time for calcul the mask position with numpy : 0.011721372604370117 nb_pixel_total : 377 time to create 1 rle with old method : 0.0004963874816894531 time for calcul the mask position with numpy : 0.011319160461425781 nb_pixel_total : 598 time to create 1 rle with old method : 0.0006902217864990234 time for calcul the mask position with numpy : 0.0108795166015625 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002703666687011719 time for calcul the mask position with numpy : 0.010791301727294922 nb_pixel_total : 938 time to create 1 rle with old method : 0.0012180805206298828 time for calcul the mask position with numpy : 0.010788917541503906 nb_pixel_total : 1596 time to create 1 rle with old method : 0.001963376998901367 time for calcul the mask position with numpy : 0.011002540588378906 nb_pixel_total : 165 time to create 1 rle with old method : 0.0002429485321044922 time for calcul the mask position with numpy : 0.01132345199584961 nb_pixel_total : 2320 time to create 1 rle with old method : 0.003027200698852539 time for calcul the mask position with numpy : 0.01220846176147461 nb_pixel_total : 8946 time to create 1 rle with old method : 0.010709762573242188 time for calcul the mask position with numpy : 0.011857032775878906 nb_pixel_total : 141 time to create 1 rle with old method : 0.00019502639770507812 time for calcul the mask position with numpy : 0.012502670288085938 nb_pixel_total : 226 time to create 1 rle with old method : 0.00031948089599609375 time for calcul the mask position with numpy : 0.011635303497314453 nb_pixel_total : 892 time to create 1 rle with old method : 0.0011262893676757812 time for calcul the mask position with numpy : 0.011428117752075195 nb_pixel_total : 204 time to create 1 rle with old method : 0.00025534629821777344 time for calcul the mask position with numpy : 0.011868953704833984 nb_pixel_total : 789 time to create 1 rle with old method : 0.0009799003601074219 time for calcul the mask position with numpy : 0.012049436569213867 nb_pixel_total : 83 time to create 1 rle with old method : 0.0001304149627685547 time for calcul the mask position with numpy : 0.01138615608215332 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003249645233154297 time for calcul the mask position with numpy : 0.011778831481933594 nb_pixel_total : 665 time to create 1 rle with old method : 0.0008554458618164062 time for calcul the mask position with numpy : 0.011099815368652344 nb_pixel_total : 251 time to create 1 rle with old method : 0.00034117698669433594 time for calcul the mask position with numpy : 0.01091313362121582 nb_pixel_total : 995 time to create 1 rle with old method : 0.001294851303100586 time for calcul the mask position with numpy : 0.010767221450805664 nb_pixel_total : 408 time to create 1 rle with old method : 0.0005211830139160156 time for calcul the mask position with numpy : 0.010802268981933594 nb_pixel_total : 11862 time to create 1 rle with old method : 0.014297008514404297 time for calcul the mask position with numpy : 0.011560916900634766 nb_pixel_total : 89 time to create 1 rle with old method : 0.00013709068298339844 time for calcul the mask position with numpy : 0.015806913375854492 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006029605865478516 time for calcul the mask position with numpy : 0.01133275032043457 nb_pixel_total : 711 time to create 1 rle with old method : 0.0009407997131347656 time for calcul the mask position with numpy : 0.011662721633911133 nb_pixel_total : 580 time to create 1 rle with old method : 0.0007493495941162109 time for calcul the mask position with numpy : 0.011651277542114258 nb_pixel_total : 251 time to create 1 rle with old method : 0.00045800209045410156 time for calcul the mask position with numpy : 0.011603355407714844 nb_pixel_total : 10637 time to create 1 rle with old method : 0.01259613037109375 time for calcul the mask position with numpy : 0.01127767562866211 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003027915954589844 time for calcul the mask position with numpy : 0.011473894119262695 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003676414489746094 time for calcul the mask position with numpy : 0.010929346084594727 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002732276916503906 time for calcul the mask position with numpy : 0.010826349258422852 nb_pixel_total : 369 time to create 1 rle with old method : 0.00045943260192871094 time for calcul the mask position with numpy : 0.010810375213623047 nb_pixel_total : 6921 time to create 1 rle with old method : 0.008363962173461914 time for calcul the mask position with numpy : 0.01074075698852539 nb_pixel_total : 217 time to create 1 rle with old method : 0.00028204917907714844 time for calcul the mask position with numpy : 0.010691642761230469 nb_pixel_total : 1196 time to create 1 rle with old method : 0.0014190673828125 time for calcul the mask position with numpy : 0.01076960563659668 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002570152282714844 time for calcul the mask position with numpy : 0.011094331741333008 nb_pixel_total : 950 time to create 1 rle with old method : 0.0012421607971191406 time for calcul the mask position with numpy : 0.010471105575561523 nb_pixel_total : 210 time to create 1 rle with old method : 0.00029659271240234375 time for calcul the mask position with numpy : 0.010816812515258789 nb_pixel_total : 972 time to create 1 rle with old method : 0.0012214183807373047 time for calcul the mask position with numpy : 0.010918617248535156 nb_pixel_total : 215 time to create 1 rle with old method : 0.00031757354736328125 time for calcul the mask position with numpy : 0.01065516471862793 nb_pixel_total : 3354 time to create 1 rle with old method : 0.004177093505859375 time for calcul the mask position with numpy : 0.010503530502319336 nb_pixel_total : 186 time to create 1 rle with old method : 0.00026679039001464844 time for calcul the mask position with numpy : 0.010924100875854492 nb_pixel_total : 21387 time to create 1 rle with old method : 0.024541616439819336 time for calcul the mask position with numpy : 0.010591268539428711 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004990100860595703 time for calcul the mask position with numpy : 0.010695457458496094 nb_pixel_total : 1705 time to create 1 rle with old method : 0.0020225048065185547 time for calcul the mask position with numpy : 0.010642290115356445 nb_pixel_total : 404 time to create 1 rle with old method : 0.0005290508270263672 time for calcul the mask position with numpy : 0.010542631149291992 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006763935089111328 time for calcul the mask position with numpy : 0.010467529296875 nb_pixel_total : 809 time to create 1 rle with old method : 0.001071929931640625 time for calcul the mask position with numpy : 0.010511398315429688 nb_pixel_total : 787 time to create 1 rle with old method : 0.0009257793426513672 time for calcul the mask position with numpy : 0.010575532913208008 nb_pixel_total : 76 time to create 1 rle with old method : 0.00012230873107910156 time for calcul the mask position with numpy : 0.010529756546020508 nb_pixel_total : 141 time to create 1 rle with old method : 0.00019693374633789062 time for calcul the mask position with numpy : 0.010693788528442383 nb_pixel_total : 483 time to create 1 rle with old method : 0.0006363391876220703 time for calcul the mask position with numpy : 0.010484457015991211 nb_pixel_total : 543 time to create 1 rle with old method : 0.00064849853515625 time for calcul the mask position with numpy : 0.01107478141784668 nb_pixel_total : 1881 time to create 1 rle with old method : 0.003148317337036133 time for calcul the mask position with numpy : 0.01142263412475586 nb_pixel_total : 602 time to create 1 rle with old method : 0.001055002212524414 time for calcul the mask position with numpy : 0.011505126953125 nb_pixel_total : 30 time to create 1 rle with old method : 0.00010395050048828125 time for calcul the mask position with numpy : 0.011379718780517578 nb_pixel_total : 556 time to create 1 rle with old method : 0.0009675025939941406 time for calcul the mask position with numpy : 0.011345624923706055 nb_pixel_total : 425 time to create 1 rle with old method : 0.0007314682006835938 time for calcul the mask position with numpy : 0.011427164077758789 nb_pixel_total : 200 time to create 1 rle with old method : 0.0003476142883300781 time for calcul the mask position with numpy : 0.011272192001342773 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0012814998626708984 time for calcul the mask position with numpy : 0.010676145553588867 nb_pixel_total : 623 time to create 1 rle with old method : 0.000812530517578125 time for calcul the mask position with numpy : 0.010502338409423828 nb_pixel_total : 1396 time to create 1 rle with old method : 0.0016620159149169922 time for calcul the mask position with numpy : 0.010475873947143555 nb_pixel_total : 879 time to create 1 rle with old method : 0.0011582374572753906 time for calcul the mask position with numpy : 0.010524988174438477 nb_pixel_total : 1754 time to create 1 rle with old method : 0.002058267593383789 time for calcul the mask position with numpy : 0.010447502136230469 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005216598510742188 time for calcul the mask position with numpy : 0.010525941848754883 nb_pixel_total : 483 time to create 1 rle with old method : 0.0006208419799804688 time for calcul the mask position with numpy : 0.010489702224731445 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002536773681640625 time for calcul the mask position with numpy : 0.010350704193115234 nb_pixel_total : 1305 time to create 1 rle with old method : 0.0016078948974609375 time for calcul the mask position with numpy : 0.010614395141601562 nb_pixel_total : 1723 time to create 1 rle with old method : 0.0021343231201171875 time for calcul the mask position with numpy : 0.010435104370117188 nb_pixel_total : 4533 time to create 1 rle with old method : 0.005072593688964844 time for calcul the mask position with numpy : 0.010614395141601562 nb_pixel_total : 63 time to create 1 rle with old method : 0.0001697540283203125 time for calcul the mask position with numpy : 0.014679670333862305 nb_pixel_total : 1604 time to create 1 rle with old method : 0.0019364356994628906 time for calcul the mask position with numpy : 0.01450800895690918 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002472400665283203 time for calcul the mask position with numpy : 0.014605283737182617 nb_pixel_total : 2800 time to create 1 rle with old method : 0.003442525863647461 time for calcul the mask position with numpy : 0.01490330696105957 nb_pixel_total : 676 time to create 1 rle with old method : 0.0008709430694580078 time for calcul the mask position with numpy : 0.014926433563232422 nb_pixel_total : 346 time to create 1 rle with old method : 0.00042939186096191406 time for calcul the mask position with numpy : 0.014967203140258789 nb_pixel_total : 294 time to create 1 rle with old method : 0.0003910064697265625 time for calcul the mask position with numpy : 0.014964818954467773 nb_pixel_total : 330 time to create 1 rle with old method : 0.0003833770751953125 time for calcul the mask position with numpy : 0.014959573745727539 nb_pixel_total : 6 time to create 1 rle with old method : 4.4345855712890625e-05 time for calcul the mask position with numpy : 0.014902114868164062 nb_pixel_total : 43 time to create 1 rle with old method : 9.72747802734375e-05 time for calcul the mask position with numpy : 0.014930009841918945 nb_pixel_total : 1114 time to create 1 rle with old method : 0.0013210773468017578 time for calcul the mask position with numpy : 0.01497340202331543 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002570152282714844 time for calcul the mask position with numpy : 0.014924287796020508 nb_pixel_total : 255 time to create 1 rle with old method : 0.0003383159637451172 time for calcul the mask position with numpy : 0.0149383544921875 nb_pixel_total : 125 time to create 1 rle with old method : 0.00017452239990234375 time for calcul the mask position with numpy : 0.016077518463134766 nb_pixel_total : 112 time to create 1 rle with old method : 0.00019168853759765625 time for calcul the mask position with numpy : 0.016045331954956055 nb_pixel_total : 589 time to create 1 rle with old method : 0.0007436275482177734 time for calcul the mask position with numpy : 0.014852762222290039 nb_pixel_total : 135 time to create 1 rle with old method : 0.00016880035400390625 time for calcul the mask position with numpy : 0.01482534408569336 nb_pixel_total : 1327 time to create 1 rle with old method : 0.0016751289367675781 time for calcul the mask position with numpy : 0.014918088912963867 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005412101745605469 time for calcul the mask position with numpy : 0.01486825942993164 nb_pixel_total : 12 time to create 1 rle with old method : 2.7418136596679688e-05 time for calcul the mask position with numpy : 0.015002965927124023 nb_pixel_total : 117 time to create 1 rle with old method : 0.00015783309936523438 time for calcul the mask position with numpy : 0.01490926742553711 nb_pixel_total : 1210 time to create 1 rle with old method : 0.0015707015991210938 time for calcul the mask position with numpy : 0.014675378799438477 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004322528839111328 time for calcul the mask position with numpy : 0.014736413955688477 nb_pixel_total : 81 time to create 1 rle with old method : 0.00010848045349121094 time for calcul the mask position with numpy : 0.014842748641967773 nb_pixel_total : 1188 time to create 1 rle with old method : 0.0013687610626220703 time for calcul the mask position with numpy : 0.014443635940551758 nb_pixel_total : 2345 time to create 1 rle with old method : 0.00286865234375 time for calcul the mask position with numpy : 0.014955997467041016 nb_pixel_total : 1026 time to create 1 rle with old method : 0.0012841224670410156 time for calcul the mask position with numpy : 0.016386747360229492 nb_pixel_total : 2031 time to create 1 rle with old method : 0.0023381710052490234 time for calcul the mask position with numpy : 0.014997005462646484 nb_pixel_total : 6691 time to create 1 rle with old method : 0.008532047271728516 time for calcul the mask position with numpy : 0.014991283416748047 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005536079406738281 time for calcul the mask position with numpy : 0.014890432357788086 nb_pixel_total : 2030 time to create 1 rle with old method : 0.0025441646575927734 time for calcul the mask position with numpy : 0.015235662460327148 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003037452697753906 time for calcul the mask position with numpy : 0.014560461044311523 nb_pixel_total : 425 time to create 1 rle with old method : 0.0004956722259521484 time for calcul the mask position with numpy : 0.014893770217895508 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001316070556640625 time for calcul the mask position with numpy : 0.01648569107055664 nb_pixel_total : 1626 time to create 1 rle with old method : 0.002553701400756836 time for calcul the mask position with numpy : 0.014898300170898438 nb_pixel_total : 80 time to create 1 rle with old method : 0.0001220703125 time for calcul the mask position with numpy : 0.014633655548095703 nb_pixel_total : 986 time to create 1 rle with old method : 0.001346588134765625 time for calcul the mask position with numpy : 0.014899015426635742 nb_pixel_total : 12 time to create 1 rle with old method : 6.437301635742188e-05 create new chi : 3.106422185897827 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 : 0.002321004867553711 batch 1 Loaded 215 chid ids of type : 4230 Number RLEs to save : 17345 TO DO : save crop sub photo not yet done ! save time : 1.036825180053711 map_output_result : {1337076765: (0.0, 'Should be the crop_list due to order', 0.0), 1337071718: (0.0, 'Should be the crop_list due to order', 0.0), 1337066805: (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 [1337076765, 1337071718, 1337066805] Looping around the photos to save general results len do output : 3 /1337076765.Didn't retrieve data . /1337071718.Didn't retrieve data . /1337066805.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, '2579238') ('4234', '20475135', '1337076765', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337071718', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337066805', None, None, None, None, None, '2579238') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.012684822082519531 save_final save missing photos in datou_result : time spend for datou_step_exec : 22.051619052886963 time spend to save output : 0.012991905212402344 total time spend for step 4 : 22.064610958099365 step5:crop_condition Wed Feb 12 12:21:31 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 : 3 ! batch 1 Loaded 499 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 244 About to insert : list_path_to_insert length 244 new photo from crops ! About to upload 244 photos upload in portfolio : 4869462 init cache_photo without model_param we have 244 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739359296_3338360 we have uploaded 244 photos in the portfolio 4869462 time of upload the photos Elapsed time : 57.11230993270874 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 ! map_result returned by crop_photo_return_map_crop : length : 56 About to insert : list_path_to_insert length 56 new photo from crops ! About to upload 56 photos upload in portfolio : 4869462 init cache_photo without model_param we have 56 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739359354_3338360 we have uploaded 56 photos in the portfolio 4869462 time of upload the photos Elapsed time : 11.757981538772583 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 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 42 About to insert : list_path_to_insert length 42 new photo from crops ! About to upload 42 photos upload in portfolio : 4869462 init cache_photo without model_param we have 42 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739359367_3338360 we have uploaded 42 photos in the portfolio 4869462 time of upload the photos Elapsed time : 12.691458225250244 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 ! 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 : 24 About to insert : list_path_to_insert length 24 new photo from crops ! About to upload 24 photos upload in portfolio : 4869462 init cache_photo without model_param we have 24 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739359381_3338360 we have uploaded 24 photos in the portfolio 4869462 time of upload the photos Elapsed time : 6.02684760093689 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 ! 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/1739359387_3338360 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.5388364791870117 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 ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739359388_3338360 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 1.0251035690307617 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 [1337076765, 1337071718, 1337066805] Looping around the photos to save general results len do output : 369 /1337083440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083460Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083474Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083494Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083578Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337083967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337084130Didn'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, '2579238') ('4234', '20475135', '1337076765', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337071718', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337066805', None, None, None, None, None, '2579238') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1110 time used for this insertion : 0.0509037971496582 save_final save missing photos in datou_result : time spend for datou_step_exec : 98.05348181724548 time spend to save output : 0.06038665771484375 total time spend for step 5 : 98.11386847496033 step6:thcl Wed Feb 12 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 : 0.025635957717895508 time to convert the images to numpy array : 0.1177530288696289 time to import caffe and check if the image exist : 0.02068042755126953 time to convert the images to numpy array : 0.13155889511108398 time to import caffe and check if the image exist : 0.02771735191345215 time to convert the images to numpy array : 0.13237547874450684 time to import caffe and check if the image exist : 0.033170461654663086 time to convert the images to numpy array : 0.13460421562194824 time to import caffe and check if the image exist : 0.034418582916259766 time to convert the images to numpy array : 0.1357283592224121 time to import caffe and check if the image exist : 0.03863859176635742 time to convert the images to numpy array : 0.1318988800048828 time to import caffe and check if the image exist : 0.0309293270111084 time to convert the images to numpy array : 0.13915801048278809 time to import caffe and check if the image exist : 0.04243636131286621 time to convert the images to numpy array : 0.13016366958618164 time to import caffe and check if the image exist : 0.029551982879638672 time to convert the images to numpy array : 0.14271140098571777 time to import caffe and check if the image exist : 0.05276155471801758 time to convert the images to numpy array : 0.12256026268005371 total time to convert the images to numpy array : 0.428142786026001 list photo_ids error: [] list photo_ids correct : [1337083926, 1337083927, 1337083928, 1337083929, 1337083930, 1337083931, 1337083932, 1337083933, 1337083934, 1337083935, 1337083936, 1337083937, 1337083938, 1337083939, 1337083940, 1337083941, 1337083943, 1337083944, 1337083945, 1337083946, 1337083947, 1337083948, 1337083949, 1337083950, 1337083951, 1337083952, 1337083953, 1337083954, 1337083955, 1337083956, 1337083957, 1337083958, 1337083959, 1337083960, 1337083961, 1337083962, 1337083963, 1337083440, 1337083441, 1337083442, 1337083443, 1337083444, 1337083445, 1337083446, 1337083447, 1337083448, 1337083449, 1337083450, 1337083451, 1337083452, 1337083453, 1337083454, 1337083455, 1337083456, 1337083457, 1337083458, 1337083459, 1337083460, 1337083461, 1337083462, 1337083463, 1337083464, 1337083465, 1337083466, 1337083467, 1337083468, 1337083469, 1337083470, 1337083471, 1337083472, 1337083473, 1337083474, 1337083475, 1337083476, 1337083553, 1337083554, 1337083555, 1337083556, 1337083558, 1337083559, 1337083560, 1337083561, 1337083562, 1337083563, 1337083564, 1337083565, 1337083566, 1337083567, 1337083568, 1337083569, 1337083570, 1337083571, 1337083572, 1337083573, 1337083574, 1337083575, 1337083576, 1337083577, 1337083578, 1337083579, 1337083580, 1337083581, 1337083582, 1337083583, 1337083584, 1337083585, 1337083586, 1337083587, 1337083588, 1337083589, 1337083590, 1337083516, 1337083517, 1337083518, 1337083519, 1337083520, 1337083521, 1337083522, 1337083523, 1337083524, 1337083525, 1337083526, 1337083527, 1337083528, 1337083529, 1337083530, 1337083531, 1337083532, 1337083533, 1337083534, 1337083535, 1337083536, 1337083537, 1337083538, 1337083539, 1337083540, 1337083541, 1337083542, 1337083543, 1337083544, 1337083545, 1337083546, 1337083547, 1337083548, 1337083549, 1337083550, 1337083551, 1337083552, 1337083477, 1337083478, 1337083479, 1337083480, 1337083481, 1337083482, 1337083483, 1337083484, 1337083485, 1337083486, 1337083487, 1337083488, 1337083489, 1337083490, 1337083491, 1337083492, 1337083493, 1337083494, 1337083495, 1337083496, 1337083497, 1337083498, 1337083499, 1337083500, 1337083501, 1337083502, 1337083504, 1337083505, 1337083506, 1337083507, 1337083508, 1337083509, 1337083510, 1337083512, 1337083513, 1337083514, 1337083515, 1337083591, 1337083592, 1337083593, 1337083594, 1337083595, 1337083596, 1337083597, 1337083598, 1337083599, 1337083600, 1337083601, 1337083602, 1337083604, 1337083606, 1337083607, 1337083608, 1337083609, 1337083610, 1337083611, 1337083612, 1337083613, 1337083614, 1337083615, 1337083616, 1337083617, 1337083618, 1337083619, 1337083620, 1337083621, 1337083622, 1337083623, 1337083624, 1337083625, 1337083626, 1337083627, 1337083628, 1337083629, 1337083700, 1337083702, 1337083704, 1337083706, 1337083708, 1337083710, 1337083712, 1337083714, 1337083716, 1337083718, 1337083720, 1337083722, 1337083724, 1337083726, 1337083728, 1337083730, 1337083732, 1337083734, 1337083736, 1337083738, 1337083740, 1337083742, 1337083910, 1337083911, 1337083912, 1337083914, 1337083915, 1337083916, 1337083917, 1337083918, 1337083919, 1337083920, 1337083921, 1337083922, 1337083923, 1337083924, 1337083925, 1337083630, 1337083631, 1337083632, 1337083633, 1337083634, 1337083635, 1337083637, 1337083639, 1337083641, 1337083643, 1337083645, 1337083647, 1337083649, 1337083651, 1337083653, 1337083655, 1337083657, 1337083659, 1337083661, 1337083663, 1337083665, 1337083667, 1337083669, 1337083671, 1337083673, 1337083675, 1337083677, 1337083679, 1337083681, 1337083683, 1337083685, 1337083687, 1337083689, 1337083692, 1337083694, 1337083696, 1337083698, 1337084072, 1337084073, 1337084074, 1337084075, 1337084076, 1337084077, 1337084078, 1337084079, 1337084080, 1337084103, 1337084104, 1337084105, 1337084106, 1337084107, 1337084108, 1337084109, 1337084110, 1337084111, 1337084112, 1337084113, 1337084114, 1337084115, 1337084116, 1337084117, 1337084118, 1337084119, 1337084120, 1337084121, 1337084122, 1337084123, 1337084124, 1337084125, 1337084126, 1337084127, 1337084129, 1337084130, 1337083964, 1337083965, 1337083966, 1337083967, 1337084027, 1337084029, 1337084031, 1337084033, 1337084035, 1337084037, 1337084039, 1337084041, 1337084043, 1337084045, 1337084047, 1337084048, 1337084049, 1337084050, 1337084051, 1337084052, 1337084053, 1337084054, 1337084055, 1337084056, 1337084057, 1337084058, 1337084059, 1337084060, 1337084061, 1337084062, 1337084063, 1337084064, 1337084065, 1337084066, 1337084068, 1337084070, 1337084071] number of photos to traite : 369 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 l 3637 free memory gpu now : 3342 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 : 3123 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 1.6918184757232666 time used to do the prediction : 1.3087966442108154 save descriptor for thcl : 3237 time to traite the descriptors : 2.156764507293701 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1337083926 To insert : 1337083927 To insert : 1337083928 To insert : 1337083929 To insert : 1337083930 To insert : 1337083931 To insert : 1337083932 To insert : 1337083933 To insert : 1337083934 To insert : 1337083935 To insert : 1337083936 To insert : 1337083937 To insert : 1337083938 To insert : 1337083939 To insert : 1337083940 To insert : 1337083941 To insert : 1337083943 To insert : 1337083944 To insert : 1337083945 To insert : 1337083946 To insert : 1337083947 To insert : 1337083948 To insert : 1337083949 To insert : 1337083950 To insert : 1337083951 To insert : 1337083952 To insert : 1337083953 To insert : 1337083954 To insert : 1337083955 To insert : 1337083956 To insert : 1337083957 To insert : 1337083958 To insert : 1337083959 To insert : 1337083960 To insert : 1337083961 To insert : 1337083962 To insert : 1337083963 To insert : 1337083440 To insert : 1337083441 To insert : 1337083442 To insert : 1337083443 To insert : 1337083444 To insert : 1337083445 To insert : 1337083446 To insert : 1337083447 To insert : 1337083448 To insert : 1337083449 To insert : 1337083450 To insert : 1337083451 To insert : 1337083452 To insert : 1337083453 To insert : 1337083454 To insert : 1337083455 To insert : 1337083456 To insert : 1337083457 To insert : 1337083458 To insert : 1337083459 To insert : 1337083460 To insert : 1337083461 To insert : 1337083462 To insert : 1337083463 To insert : 1337083464 To insert : 1337083465 To insert : 1337083466 To insert : 1337083467 To insert : 1337083468 To insert : 1337083469 To insert : 1337083470 To insert : 1337083471 To insert : 1337083472 To insert : 1337083473 To insert : 1337083474 To insert : 1337083475 To insert : 1337083476 To insert : 1337083553 To insert : 1337083554 To insert : 1337083555 To insert : 1337083556 To insert : 1337083558 To insert : 1337083559 To insert : 1337083560 To insert : 1337083561 To insert : 1337083562 To insert : 1337083563 To insert : 1337083564 To insert : 1337083565 To insert : 1337083566 To insert : 1337083567 To insert : 1337083568 To insert : 1337083569 To insert : 1337083570 To insert : 1337083571 To insert : 1337083572 To insert : 1337083573 To insert : 1337083574 To insert : 1337083575 To insert : 1337083576 To insert : 1337083577 To insert : 1337083578 To insert : 1337083579 To insert : 1337083580 To insert : 1337083581 To insert : 1337083582 To insert : 1337083583 To insert : 1337083584 To insert : 1337083585 To insert : 1337083586 To insert : 1337083587 To insert : 1337083588 To insert : 1337083589 To insert : 1337083590 To insert : 1337083516 To insert : 1337083517 To insert : 1337083518 To insert : 1337083519 To insert : 1337083520 To insert : 1337083521 To insert : 1337083522 To insert : 1337083523 To insert : 1337083524 To insert : 1337083525 To insert : 1337083526 To insert : 1337083527 To insert : 1337083528 To insert : 1337083529 To insert : 1337083530 To insert : 1337083531 To insert : 1337083532 To insert : 1337083533 To insert : 1337083534 To insert : 1337083535 To insert : 1337083536 To insert : 1337083537 To insert : 1337083538 To insert : 1337083539 To insert : 1337083540 To insert : 1337083541 To insert : 1337083542 To insert : 1337083543 To insert : 1337083544 To insert : 1337083545 To insert : 1337083546 To insert : 1337083547 To insert : 1337083548 To insert : 1337083549 To insert : 1337083550 To insert : 1337083551 To insert : 1337083552 To insert : 1337083477 To insert : 1337083478 To insert : 1337083479 To insert : 1337083480 To insert : 1337083481 To insert : 1337083482 To insert : 1337083483 To insert : 1337083484 To insert : 1337083485 To insert : 1337083486 To insert : 1337083487 To insert : 1337083488 To insert : 1337083489 To insert : 1337083490 To insert : 1337083491 To insert : 1337083492 To insert : 1337083493 To insert : 1337083494 To insert : 1337083495 To insert : 1337083496 To insert : 1337083497 To insert : 1337083498 To insert : 1337083499 To insert : 1337083500 To insert : 1337083501 To insert : 1337083502 To insert : 1337083504 To insert : 1337083505 To insert : 1337083506 To insert : 1337083507 To insert : 1337083508 To insert : 1337083509 To insert : 1337083510 To insert : 1337083512 To insert : 1337083513 To insert : 1337083514 To insert : 1337083515 To insert : 1337083591 To insert : 1337083592 To insert : 1337083593 To insert : 1337083594 To insert : 1337083595 To insert : 1337083596 To insert : 1337083597 To insert : 1337083598 To insert : 1337083599 To insert : 1337083600 To insert : 1337083601 To insert : 1337083602 To insert : 1337083604 To insert : 1337083606 To insert : 1337083607 To insert : 1337083608 To insert : 1337083609 To insert : 1337083610 To insert : 1337083611 To insert : 1337083612 To insert : 1337083613 To insert : 1337083614 To insert : 1337083615 To insert : 1337083616 To insert : 1337083617 To insert : 1337083618 To insert : 1337083619 To insert : 1337083620 To insert : 1337083621 To insert : 1337083622 To insert : 1337083623 To insert : 1337083624 To insert : 1337083625 To insert : 1337083626 To insert : 1337083627 To insert : 1337083628 To insert : 1337083629 To insert : 1337083700 To insert : 1337083702 To insert : 1337083704 To insert : 1337083706 To insert : 1337083708 To insert : 1337083710 To insert : 1337083712 To insert : 1337083714 To insert : 1337083716 To insert : 1337083718 To insert : 1337083720 To insert : 1337083722 To insert : 1337083724 To insert : 1337083726 To insert : 1337083728 To insert : 1337083730 To insert : 1337083732 To insert : 1337083734 To insert : 1337083736 To insert : 1337083738 To insert : 1337083740 To insert : 1337083742 To insert : 1337083910 To insert : 1337083911 To insert : 1337083912 To insert : 1337083914 To insert : 1337083915 To insert : 1337083916 To insert : 1337083917 To insert : 1337083918 To insert : 1337083919 To insert : 1337083920 To insert : 1337083921 To insert : 1337083922 To insert : 1337083923 To insert : 1337083924 To insert : 1337083925 To insert : 1337083630 To insert : 1337083631 To insert : 1337083632 To insert : 1337083633 To insert : 1337083634 To insert : 1337083635 To insert : 1337083637 To insert : 1337083639 To insert : 1337083641 To insert : 1337083643 To insert : 1337083645 To insert : 1337083647 To insert : 1337083649 To insert : 1337083651 To insert : 1337083653 To insert : 1337083655 To insert : 1337083657 To insert : 1337083659 To insert : 1337083661 To insert : 1337083663 To insert : 1337083665 To insert : 1337083667 To insert : 1337083669 To insert : 1337083671 To insert : 1337083673 To insert : 1337083675 To insert : 1337083677 To insert : 1337083679 To insert : 1337083681 To insert : 1337083683 To insert : 1337083685 To insert : 1337083687 To insert : 1337083689 To insert : 1337083692 To insert : 1337083694 To insert : 1337083696 To insert : 1337083698 To insert : 1337084072 To insert : 1337084073 To insert : 1337084074 To insert : 1337084075 To insert : 1337084076 To insert : 1337084077 To insert : 1337084078 To insert : 1337084079 To insert : 1337084080 To insert : 1337084103 To insert : 1337084104 To insert : 1337084105 To insert : 1337084106 To insert : 1337084107 To insert : 1337084108 To insert : 1337084109 To insert : 1337084110 To insert : 1337084111 To insert : 1337084112 To insert : 1337084113 To insert : 1337084114 To insert : 1337084115 To insert : 1337084116 To insert : 1337084117 To insert : 1337084118 To insert : 1337084119 To insert : 1337084120 To insert : 1337084121 To insert : 1337084122 To insert : 1337084123 To insert : 1337084124 To insert : 1337084125 To insert : 1337084126 To insert : 1337084127 To insert : 1337084129 To insert : 1337084130 To insert : 1337083964 To insert : 1337083965 To insert : 1337083966 To insert : 1337083967 To insert : 1337084027 To insert : 1337084029 To insert : 1337084031 To insert : 1337084033 To insert : 1337084035 To insert : 1337084037 To insert : 1337084039 To insert : 1337084041 To insert : 1337084043 To insert : 1337084045 To insert : 1337084047 To insert : 1337084048 To insert : 1337084049 To insert : 1337084050 To insert : 1337084051 To insert : 1337084052 To insert : 1337084053 To insert : 1337084054 To insert : 1337084055 To insert : 1337084056 To insert : 1337084057 To insert : 1337084058 To insert : 1337084059 To insert : 1337084060 To insert : 1337084061 To insert : 1337084062 To insert : 1337084063 To insert : 1337084064 To insert : 1337084065 To insert : 1337084066 To insert : 1337084068 To insert : 1337084070 To insert : 1337084071 time to insert the descriptors : 73.10416793823242 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 : 568 time used for this insertion : 0.046381235122680664 save missing photos in datou_result : time spend for datou_step_exec : 82.68057513237 time spend to save output : 0.10219764709472656 total time spend for step 6 : 82.78277277946472 step7:ventilate_hashtags_in_portfolio Wed Feb 12 12:24:31 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 : 20475135 get user id for portfolio 20475135 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`=20475135 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Tetrapak','autre','pet_clair','papier','refus','pet_fonce','environnement','flou','mal_croppe','pehd','PET_clair','PET_fonce','Carton','carton','Film_plastique','metal','Papier','PEHD')) 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`=20475135 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Tetrapak','autre','pet_clair','papier','refus','pet_fonce','environnement','flou','mal_croppe','pehd','PET_clair','PET_fonce','Carton','carton','Film_plastique','metal','Papier','PEHD')) 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`=20475135 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Tetrapak','autre','pet_clair','papier','refus','pet_fonce','environnement','flou','mal_croppe','pehd','PET_clair','PET_fonce','Carton','carton','Film_plastique','metal','Papier','PEHD')) 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`=20475135 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Tetrapak','autre','pet_clair','papier','refus','pet_fonce','environnement','flou','mal_croppe','pehd','PET_clair','PET_fonce','Carton','carton','Film_plastique','metal','Papier','PEHD')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20476227,20476228,20476237,20476243,20476231,20476238,20476233,20476234,20476235,20476244,20476240,20476241,20476242?tags=tetrapak,autre,pet_clair,papier,refus,pet_fonce,environnement,flou,mal_croppe,pehd,carton,film_plastique,metal&datou_id_consolidate=4235&port_consolidate=20475135 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1337076765, 1337071718, 1337066805] Looping around the photos to save general results len do output : 1 /20475135. 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, '2579238') ('4234', '20475135', '1337076765', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337071718', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337066805', None, None, None, None, None, '2579238') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.012520074844360352 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.382697582244873 time spend to save output : 0.012823104858398438 total time spend for step 7 : 2.3955206871032715 step8:final Wed Feb 12 12:24:34 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : {1337076765: ('0.8907392409333823',), 1337071718: ('0.8907392409333823',), 1337066805: ('0.8907392409333823',)} new output for save of step final : {1337076765: ('0.8907392409333823',), 1337071718: ('0.8907392409333823',), 1337066805: ('0.8907392409333823',)} [1337076765, 1337071718, 1337066805] Looping around the photos to save general results len do output : 3 /1337076765.Didn't retrieve data . /1337071718.Didn't retrieve data . /1337066805.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, '2579238') ('4234', '20475135', '1337076765', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337071718', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337066805', None, None, None, None, None, '2579238') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.014769792556762695 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.17916202545166016 time spend to save output : 0.014985322952270508 total time spend for step 8 : 0.19414734840393066 step9:velours_tree Wed Feb 12 12:24:34 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure list_portfolios : 20476227,20476228,20476237,20476243,20476231,20476238,20476233,20476234,20476235,20476244,20476240,20476241,20476242 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=20476227 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=20476228 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=20476237 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=20476243 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=20476231 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=20476238 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=20476233 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=20476234 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=20476235 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=20476244 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=20476240 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=20476241 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=20476242 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 369 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [3 5 5 2 5 1 0 1 5 2 3 5 1 0 2 2 3 3 2 1 2 2 3 2 2 2 2 4 1 5 4 2 0 3 3 5 3 4 5 5 1 2 1 4 3 2 3 2 4 2 1 2 0 1 3 3 4 5 5 5 0 3 1 2 1 3 0 5 3 3 0 2 3 3 1 5 2 2 0 1 3 2 0 5 1 4 4 2 5 2 2 2 2 2 2 5 2 3 0 2 2 0 2 2 3 0 5 2 2 0 1 2 2 2 1 2 2 2 2 2 2 2 2 3 3 3 2 1 2 4 2 2 4 2 1 2 2 1 2 5 1 3 3 5 0 1 2 1 4 1 1 4 2 2 2 0 2 2 3 2 2 2 2 2 2 0 1 2 2 3 5 2 0 3 3 3 1 2 1 2 2 5 5 2 0 5 2 0 0 2 0 1 2 1 1 2 2 5 0 3 1 5 3 2 2 3 5 2 2 1 5 3 0 4 5 5 2 2 1 1 5 3 1 5 1 1 0 2 1 2 2 5 2 4 2 4 5 1 1 5 1 2 2 2 0 2 1 3 0 1 5 0 1 0 1 3 1 1 0 5 1 5 5 0 3 2 1 1 3 1 1 2 1 0 2 2 2 5 2 4 5 1 5 2 1 0 2 0 3 1 1 2 3 2 1 2 5 5 0 5 3 5 3 0 0 3 0 2 3 5 3 0 0 4 0 0 3 3 2 2 2 0 3 0 5 0 3 0 2 0 3 0 5 0 0 3 0 4 5 4 2 2 1 3 1 5 3 5 3 3 5 3 5 5 5 2 3 5 5 3 1 1 5 5 1 5 3 0 3] Elapsed time: 0.08047771453857422 graph_id used : 78126 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20476227,20476228,20476237,20476243,20476231,20476238,20476233,20476234,20476235,20476244,20476240,20476241,20476242?tags=tetrapak,autre,pet_clair,papier,refus,pet_fonce,environnement,flou,mal_croppe,pehd,carton,film_plastique,metal&datou_id_consolidate=4235&port_consolidate=20475135&tree_id=78126 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1337076765, 1337071718, 1337066805] Looping around the photos to save general results len do output : 1 /20475135Didn'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, '2579238') ('4234', '20475135', '1337076765', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337071718', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337066805', None, None, None, None, None, '2579238') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.012589693069458008 save_final save missing photos in datou_result : time spend for datou_step_exec : 23.232249975204468 time spend to save output : 0.013053655624389648 total time spend for step 9 : 23.245303630828857 step10:send_mail_cod Wed Feb 12 12:24:57 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 complete output_args for input 1 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 2 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_P20475135_12-02-2025_12_24_57.pdf 20476209 imagette204762091739359497 20476210 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 .imagette204762101739359497 20476219 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 .imagette204762191739359498 20476225 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 .imagette204762251739359499 20476213 imagette204762131739359500 20476220 change filename to text .change filename to text .imagette204762201739359500 20476216 imagette204762161739359500 20476217 imagette204762171739359500 20476226 change filename to text .imagette204762261739359500 20476222 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 .imagette204762221739359500 20476223 imagette204762231739359501 20476224 imagette204762241739359501 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20475135 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20476227,20476228,20476237,20476243,20476231,20476238,20476233,20476234,20476235,20476244,20476240,20476241,20476242?tags=tetrapak,autre,pet_clair,papier,refus,pet_fonce,environnement,flou,mal_croppe,pehd,carton,film_plastique,metal&datou_id_consolidate=4235&port_consolidate=20475135&tree_id=78126 your option no_mail is active, we will not send the real mail to your client args[1337076765] : ((1337076765, -5.074280294964117, 492609224), (1337076765, 0.8496888347283273, 2107752395), '0.8907392409333823') apple ((1337076765, -5.074280294964117, 492609224), (1337076765, 0.8496888347283273, 2107752395), '0.8907392409333823') We are sending mail with results at cod@fotonower.com args[1337071718] : ((1337071718, -7.438322156840488, 492609224), (1337071718, 0.49685647298275276, 2107752395), '0.8907392409333823') apple ((1337071718, -7.438322156840488, 492609224), (1337071718, 0.49685647298275276, 2107752395), '0.8907392409333823') We are sending mail with results at cod@fotonower.com args[1337066805] : ((1337066805, -7.449701398093394, 492609224), (1337066805, 0.4278713908448854, 2107752395), '0.8907392409333823') apple ((1337066805, -7.449701398093394, 492609224), (1337066805, 0.4278713908448854, 2107752395), '0.8907392409333823') We are sending mail with results at cod@fotonower.com refus_total : 0.8907392409333823 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=20475135 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_P20475135_12-02-2025_12_24_57.pdf results_Qualipapia_P20475135_12-02-2025_12_24_57.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20475135_12-02-2025_12_24_57.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','20475135','results_Qualipapia_P20475135_12-02-2025_12_24_57.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20475135_12-02-2025_12_24_57.pdf','pdf','','0.18','0.8907392409333823') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1337076765, 1337071718, 1337066805] 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, '2579238') ('4234', '20475135', '1337076765', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337071718', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337066805', None, None, None, None, None, '2579238') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.012682437896728516 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.9100751876831055 time spend to save output : 0.013022184371948242 total time spend for step 10 : 4.923097372055054 step11:split_time_score Wed Feb 12 12:25:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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', 3),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 12022025 20475135 Nombre de photos uploadées : 3 / 23040 (0%) 12022025 20475135 Nombre de photos taguées (types de déchets): 0 / 3 (0%) 12022025 20475135 Nombre de photos taguées (volume) : 0 / 3 (0%) elapsed_time : load_data_split_time_score 1.6689300537109375e-06 elapsed_time : order_list_meta_photo_and_scores 5.245208740234375e-06 ??? elapsed_time : fill_and_build_computed_from_old_data 0.00025343894958496094 elapsed_time : insert_dashboard_record_day_entry 0.02346181869506836 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.8442171249854891 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20465376_12-02-2025_03_32_43.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20465376 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`=20465376 AND mptpi.`type`=4230 To do Qualite : 0.8058515908019713 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20465378_12-02-2025_02_01_33.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20465378 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`=20465378 AND mptpi.`type`=4230 To do Qualite : 0.758681820755458 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20466230_12-02-2025_03_03_12.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20466230 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`=20466230 AND mptpi.`type`=4230 To do Qualite : 0.844000415830928 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20466806_12-02-2025_04_00_58.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20466806 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`=20466806 AND mptpi.`type`=4230 To do Qualite : 0.826842448433579 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20468057_12-02-2025_06_17_28.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20468057 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`=20468057 AND mptpi.`type`=4230 To do Qualite : 0.8640876766652383 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20468744_12-02-2025_07_07_55.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20468744 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`=20468744 AND mptpi.`type`=4230 To do Qualite : 0.8115520336927352 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20469170_12-02-2025_08_17_37.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20469170 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`=20469170 AND mptpi.`type`=4230 To do Qualite : 0.8460528747384131 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20469929_12-02-2025_09_00_59.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20469929 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`=20469929 AND mptpi.`type`=4230 To do Qualite : 0.8328794699010701 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20470671_12-02-2025_10_02_41.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20470671 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`=20470671 AND mptpi.`type`=4230 To do Qualite : 0.721398086826361 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20472334_12-02-2025_11_29_25.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20472334 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`=20472334 AND mptpi.`type`=4230 To do Qualite : 0.8907392409333823 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20475135_12-02-2025_12_24_57.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20475135 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`=20475135 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'12022025': {'nb_upload': 3, '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 [1337076765, 1337071718, 1337066805] Looping around the photos to save general results len do output : 1 /20475135Didn'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, '2579238') ('4234', '20475135', '1337076765', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337071718', None, None, None, None, None, '2579238') ('4234', None, None, None, None, None, None, None, '2579238') ('4234', '20475135', '1337066805', None, None, None, None, None, '2579238') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.012467384338378906 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.8431370258331299 time spend to save output : 0.012636899948120117 total time spend for step 11 : 0.85577392578125 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 3 set_done_treatment 63.78user 40.23system 4:38.48elapsed 37%CPU (0avgtext+0avgdata 5910872maxresident)k 767784inputs+24752outputs (382major+4480997minor)pagefaults 0swaps