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 : 1735952 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 we have a portfolio with more photos than limit : 26>5 please execute split_portfolio.py -i 20162675 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2538706'] with mtr_portfolio_ids : ['20162675'] and first list_photo_ids : [] new path : /proc/1735952/ 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 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 0.7193803787231445 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 Mon Feb 3 08:20:30 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 : 10774 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-03 08:20:32.776846: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-03 08:20:32.803551: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493020000 Hz 2025-02-03 08:20:32.805641: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fbb5c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-03 08:20:32.805700: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-03 08:20:32.809855: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-03 08:20:33.049502: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2a86cf40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-03 08:20:33.049576: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-03 08:20:33.051048: 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 2025-02-03 08:20:33.051662: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-03 08:20:33.056113: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-03 08:20:33.059642: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-03 08:20:33.060593: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-03 08:20:33.065460: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-03 08:20:33.067767: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-03 08:20:33.076145: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-03 08:20:33.078348: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-03 08:20:33.078526: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-03 08:20:33.079603: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-03 08:20:33.079631: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-03 08:20:33.079647: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-03 08:20:33.081530: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 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. 2025-02-03 08:20:33.400136: 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 2025-02-03 08:20:33.400263: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-03 08:20:33.400282: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-03 08:20:33.400300: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-03 08:20:33.400316: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-03 08:20:33.400332: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-03 08:20:33.400348: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-03 08:20:33.400365: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-03 08:20:33.401552: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-03 08:20:33.402890: 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 2025-02-03 08:20:33.402925: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-03 08:20:33.402941: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-03 08:20:33.402955: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-03 08:20:33.402969: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-03 08:20:33.402983: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-03 08:20:33.402997: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-03 08:20:33.403012: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-03 08:20:33.404943: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-03 08:20:33.404980: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-03 08:20:33.404989: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-03 08:20:33.404996: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-03 08:20:33.406498: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 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 : [] 2025-02-03 08:20:40.997363: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-03 08:20:41.198041: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 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 : 5 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: -120.43438 max: 144.98672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00011849403381347656 nb_pixel_total : 913 time to create 1 rle with old method : 0.0024034976959228516 length of segment : 42 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 942 time to create 1 rle with old method : 0.0019023418426513672 length of segment : 42 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 900 time to create 1 rle with old method : 0.0018928050994873047 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.50078 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 : 6.437301635742188e-05 nb_pixel_total : 1954 time to create 1 rle with old method : 0.0024566650390625 length of segment : 42 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 3273 time to create 1 rle with old method : 0.004343748092651367 length of segment : 45 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0006356239318847656 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.66094 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 : 8.916854858398438e-05 nb_pixel_total : 2299 time to create 1 rle with old method : 0.002902984619140625 length of segment : 62 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 1070 time to create 1 rle with old method : 0.002607107162475586 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: -119.85234 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 : 3.8623809814453125e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.0003044605255126953 length of segment : 22 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.00041294097900390625 length of segment : 40 time for calcul the mask position with numpy : 0.0001595020294189453 nb_pixel_total : 9568 time to create 1 rle with old method : 0.011213302612304688 length of segment : 89 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.00022339820861816406 length of segment : 16 time for calcul the mask position with numpy : 0.0002830028533935547 nb_pixel_total : 11903 time to create 1 rle with old method : 0.013822078704833984 length of segment : 200 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 235.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 104.21719 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 : 472 time to create 1 rle with old method : 0.0006921291351318359 length of segment : 16 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1588 time to create 1 rle with old method : 0.0018856525421142578 length of segment : 111 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002849102020263672 length of segment : 21 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004329681396484375 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 191.00000 molded_images shape: (1, 640, 640, 3) min: -90.18438 max: 60.08437 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: -118.31719 max: 136.02969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 60 time to create 1 rle with old method : 0.00012540817260742188 length of segment : 8 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 800 time to create 1 rle with old method : 0.0010335445404052734 length of segment : 32 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.0002357959747314453 length of segment : 14 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0006945133209228516 length of segment : 27 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0007545948028564453 length of segment : 19 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005497932434082031 length of segment : 33 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0009522438049316406 length of segment : 39 time for calcul the mask position with numpy : 0.00040793418884277344 nb_pixel_total : 29527 time to create 1 rle with old method : 0.03425884246826172 length of segment : 241 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.0001418590545654297 length of segment : 15 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00030541419982910156 length of segment : 24 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004916191101074219 length of segment : 19 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 685 time to create 1 rle with old method : 0.0010035037994384766 length of segment : 39 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.80938 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 : 4.744529724121094e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006628036499023438 length of segment : 40 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1192 time to create 1 rle with old method : 0.001577615737915039 length of segment : 51 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.0010890960693359375 length of segment : 23 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 674 time to create 1 rle with old method : 0.0008959770202636719 length of segment : 30 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0005156993865966797 length of segment : 17 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 1057 time to create 1 rle with old method : 0.0014204978942871094 length of segment : 20 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.00041937828063964844 length of segment : 23 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0005285739898681641 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.28984 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 : 8.916854858398438e-05 nb_pixel_total : 1879 time to create 1 rle with old method : 0.0022389888763427734 length of segment : 151 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005190372467041016 length of segment : 24 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0008516311645507812 length of segment : 19 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.001125335693359375 length of segment : 43 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1025 time to create 1 rle with old method : 0.0014176368713378906 length of segment : 33 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1353 time to create 1 rle with old method : 0.0018868446350097656 length of segment : 44 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 1790 time to create 1 rle with old method : 0.0023157596588134766 length of segment : 103 time for calcul the mask position with numpy : 0.00013184547424316406 nb_pixel_total : 2214 time to create 1 rle with old method : 0.0029213428497314453 length of segment : 115 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 1790 time to create 1 rle with old method : 0.002348184585571289 length of segment : 92 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 228.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 103.76406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0007777214050292969 length of segment : 40 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0005824565887451172 length of segment : 38 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 1734 time to create 1 rle with old method : 0.0021402835845947266 length of segment : 85 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00038170814514160156 length of segment : 28 Processing 1 images image shape: (280, 400, 3) min: 9.00000 max: 164.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 42.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0006196498870849609 length of segment : 15 time for calcul the mask position with numpy : 0.001232147216796875 nb_pixel_total : 106434 time to create 1 rle with old method : 0.1434633731842041 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.34219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0008766651153564453 length of segment : 20 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.0005495548248291016 length of segment : 20 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.00045561790466308594 length of segment : 18 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 35 time to create 1 rle with old method : 0.00014090538024902344 length of segment : 17 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 38 time to create 1 rle with old method : 0.000125885009765625 length of segment : 9 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.0002529621124267578 length of segment : 16 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 413 time to create 1 rle with old method : 0.0007967948913574219 length of segment : 23 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.0004534721374511719 length of segment : 19 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 560 time to create 1 rle with old method : 0.0011150836944580078 length of segment : 25 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.09609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1991 time to create 1 rle with old method : 0.002397298812866211 length of segment : 45 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 2689 time to create 1 rle with old method : 0.003316164016723633 length of segment : 64 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00015354156494140625 length of segment : 14 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.00013637542724609375 length of segment : 8 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006093978881835938 length of segment : 31 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1313 time to create 1 rle with old method : 0.0016548633575439453 length of segment : 50 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004634857177734375 length of segment : 18 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 871 time to create 1 rle with old method : 0.0011138916015625 length of segment : 43 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0004317760467529297 length of segment : 21 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 2600 time to create 1 rle with old method : 0.0030982494354248047 length of segment : 79 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0006182193756103516 length of segment : 26 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00016498565673828125 length of segment : 16 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 2626 time to create 1 rle with old method : 0.0031991004943847656 length of segment : 72 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.62734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 580 time to create 1 rle with old method : 0.0007894039154052734 length of segment : 71 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.00012969970703125 length of segment : 23 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005366802215576172 length of segment : 26 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0006692409515380859 length of segment : 30 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0004134178161621094 length of segment : 20 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 139.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 60 time to create 1 rle with old method : 0.00023484230041503906 length of segment : 32 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 20 time to create 1 rle with old method : 5.555152893066406e-05 length of segment : 4 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: -120.26250 max: 144.97891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 871 time to create 1 rle with old method : 0.0011260509490966797 length of segment : 38 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.0013468265533447266 length of segment : 39 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004630088806152344 length of segment : 35 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 899 time to create 1 rle with old method : 0.0012214183807373047 length of segment : 37 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 774 time to create 1 rle with old method : 0.0010912418365478516 length of segment : 37 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1049 time to create 1 rle with old method : 0.0015633106231689453 length of segment : 86 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 709 time to create 1 rle with old method : 0.000993967056274414 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.11797 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 : 0.00013518333435058594 nb_pixel_total : 2555 time to create 1 rle with old method : 0.004791736602783203 length of segment : 53 time for calcul the mask position with numpy : 0.00011920928955078125 nb_pixel_total : 555 time to create 1 rle with old method : 0.0011608600616455078 length of segment : 41 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.0017802715301513672 length of segment : 36 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.0002455711364746094 length of segment : 11 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0008282661437988281 length of segment : 24 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 433 time to create 1 rle with old method : 0.0010654926300048828 length of segment : 17 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0006022453308105469 length of segment : 39 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0012552738189697266 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.58281 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 : 7.510185241699219e-05 nb_pixel_total : 2358 time to create 1 rle with old method : 0.0034122467041015625 length of segment : 56 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.45391 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 : 0.00018525123596191406 nb_pixel_total : 12984 time to create 1 rle with old method : 0.01613759994506836 length of segment : 96 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.00045180320739746094 length of segment : 38 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003075599670410156 length of segment : 22 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.00028252601623535156 length of segment : 17 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.00018072128295898438 length of segment : 7 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 237.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 103.01016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0006279945373535156 length of segment : 16 time for calcul the mask position with numpy : 0.0007352828979492188 nb_pixel_total : 62257 time to create 1 rle with old method : 0.10274028778076172 length of segment : 244 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00021338462829589844 length of segment : 12 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.0004489421844482422 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 199.00000 molded_images shape: (1, 640, 640, 3) min: -92.46953 max: 62.56484 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: -118.17656 max: 146.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00013709068298339844 length of segment : 9 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00043082237243652344 length of segment : 43 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.0002307891845703125 length of segment : 14 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.001081228256225586 length of segment : 54 time for calcul the mask position with numpy : 0.00017547607421875 nb_pixel_total : 7675 time to create 1 rle with old method : 0.009433507919311523 length of segment : 166 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 65 time to create 1 rle with old method : 0.00013494491577148438 length of segment : 10 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 861 time to create 1 rle with old method : 0.0011696815490722656 length of segment : 34 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00035953521728515625 length of segment : 15 time for calcul the mask position with numpy : 0.00014352798461914062 nb_pixel_total : 7710 time to create 1 rle with old method : 0.00924229621887207 length of segment : 145 time for calcul the mask position with numpy : 0.0003757476806640625 nb_pixel_total : 27107 time to create 1 rle with old method : 0.030243396759033203 length of segment : 217 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0004315376281738281 length of segment : 17 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 858 time to create 1 rle with old method : 0.0011355876922607422 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.03203 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 : 5.2928924560546875e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0005900859832763672 length of segment : 15 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0005135536193847656 length of segment : 25 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0005280971527099609 length of segment : 23 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 904 time to create 1 rle with old method : 0.0012950897216796875 length of segment : 41 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1093 time to create 1 rle with old method : 0.0014033317565917969 length of segment : 46 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 664 time to create 1 rle with old method : 0.0008730888366699219 length of segment : 29 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0004467964172363281 length of segment : 38 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 696 time to create 1 rle with old method : 0.001020669937133789 length of segment : 24 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.0011076927185058594 length of segment : 23 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 759 time to create 1 rle with old method : 0.0009927749633789062 length of segment : 40 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 655 time to create 1 rle with old method : 0.0009472370147705078 length of segment : 19 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004062652587890625 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.02813 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 : 9.679794311523438e-05 nb_pixel_total : 2283 time to create 1 rle with old method : 0.002691030502319336 length of segment : 149 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0008575916290283203 length of segment : 19 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 890 time to create 1 rle with old method : 0.0012097358703613281 length of segment : 31 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.00083160400390625 length of segment : 18 time for calcul the mask position with numpy : 0.00016951560974121094 nb_pixel_total : 1914 time to create 1 rle with old method : 0.003933906555175781 length of segment : 94 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 830 time to create 1 rle with old method : 0.0010383129119873047 length of segment : 38 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1485 time to create 1 rle with old method : 0.0020461082458496094 length of segment : 43 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 2007 time to create 1 rle with old method : 0.002531290054321289 length of segment : 131 time for calcul the mask position with numpy : 0.00011420249938964844 nb_pixel_total : 2147 time to create 1 rle with old method : 0.0026340484619140625 length of segment : 108 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 1982 time to create 1 rle with old method : 0.0024988651275634766 length of segment : 123 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 2330 time to create 1 rle with old method : 0.00289154052734375 length of segment : 108 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 227.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 102.19375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0007882118225097656 length of segment : 36 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.001001596450805664 length of segment : 41 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0015676021575927734 length of segment : 35 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 1775 time to create 1 rle with old method : 0.003125429153442383 length of segment : 88 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0004177093505859375 length of segment : 31 time for calcul the mask position with numpy : 0.00019025802612304688 nb_pixel_total : 4210 time to create 1 rle with old method : 0.0050220489501953125 length of segment : 206 time for calcul the mask position with numpy : 0.00016999244689941406 nb_pixel_total : 7015 time to create 1 rle with old method : 0.00807046890258789 length of segment : 321 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0008890628814697266 length of segment : 41 Processing 1 images image shape: (280, 400, 3) min: 14.00000 max: 163.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 44.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009026527404785156 nb_pixel_total : 106288 time to create 1 rle with old method : 0.11563563346862793 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.79531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0004775524139404297 length of segment : 18 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 42 time to create 1 rle with old method : 9.489059448242188e-05 length of segment : 8 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 954 time to create 1 rle with old method : 0.0012302398681640625 length of segment : 66 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0005979537963867188 length of segment : 21 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 253.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.99453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 2037 time to create 1 rle with old method : 0.002482175827026367 length of segment : 46 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0003001689910888672 length of segment : 23 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003685951232910156 length of segment : 27 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 2578 time to create 1 rle with old method : 0.003311634063720703 length of segment : 59 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.00015497207641601562 length of segment : 12 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004456043243408203 length of segment : 19 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 2812 time to create 1 rle with old method : 0.0035223960876464844 length of segment : 62 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0006780624389648438 length of segment : 24 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1145 time to create 1 rle with old method : 0.0015385150909423828 length of segment : 53 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 939 time to create 1 rle with old method : 0.0011837482452392578 length of segment : 43 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.62734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 47 time to create 1 rle with old method : 0.00017189979553222656 length of segment : 23 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0005183219909667969 length of segment : 30 time for calcul the mask position with numpy : 0.0003902912139892578 nb_pixel_total : 22412 time to create 1 rle with old method : 0.02599334716796875 length of segment : 247 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0005178451538085938 length of segment : 30 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 37 time to create 1 rle with old method : 9.799003601074219e-05 length of segment : 7 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00023245811462402344 length of segment : 12 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00011992454528808594 length of segment : 22 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00016450881958007812 length of segment : 27 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0006983280181884766 length of segment : 46 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.85000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 46 time to create 1 rle with old method : 0.0001163482666015625 length of segment : 23 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: -119.58281 max: 147.65078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 901 time to create 1 rle with old method : 0.0012552738189697266 length of segment : 43 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 979 time to create 1 rle with old method : 0.00139617919921875 length of segment : 42 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 938 time to create 1 rle with old method : 0.0013628005981445312 length of segment : 41 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.00045228004455566406 length of segment : 33 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007541179656982422 length of segment : 44 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.12969 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 : 7.772445678710938e-05 nb_pixel_total : 2116 time to create 1 rle with old method : 0.0026450157165527344 length of segment : 42 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 27 time to create 1 rle with old method : 6.461143493652344e-05 length of segment : 7 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1064 time to create 1 rle with old method : 0.0014336109161376953 length of segment : 33 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 25 time to create 1 rle with old method : 6.389617919921875e-05 length of segment : 5 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.21563 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 : 0.00010538101196289062 nb_pixel_total : 2350 time to create 1 rle with old method : 0.0031616687774658203 length of segment : 80 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 2335 time to create 1 rle with old method : 0.0030739307403564453 length of segment : 48 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 766 time to create 1 rle with old method : 0.0010554790496826172 length of segment : 42 time for calcul the mask position with numpy : 0.0001494884490966797 nb_pixel_total : 2853 time to create 1 rle with old method : 0.0037775039672851562 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.65703 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 : 0.0001888275146484375 nb_pixel_total : 11458 time to create 1 rle with old method : 0.013364315032958984 length of segment : 97 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.00035881996154785156 length of segment : 23 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006146430969238281 length of segment : 65 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00027680397033691406 length of segment : 17 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0006680488586425781 length of segment : 23 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 104.34219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0006504058837890625 length of segment : 15 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 1423 time to create 1 rle with old method : 0.0017750263214111328 length of segment : 115 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0005071163177490234 length of segment : 21 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 366 time to create 1 rle with old method : 0.0005095005035400391 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 200.00000 molded_images shape: (1, 640, 640, 3) min: -91.35234 max: 66.00625 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: -121.77031 max: 146.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.000148773193359375 length of segment : 10 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.0004138946533203125 length of segment : 44 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002651214599609375 length of segment : 18 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.00040650367736816406 length of segment : 14 time for calcul the mask position with numpy : 0.0001385211944580078 nb_pixel_total : 6460 time to create 1 rle with old method : 0.00786447525024414 length of segment : 116 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 821 time to create 1 rle with old method : 0.0010700225830078125 length of segment : 36 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.0001556873321533203 length of segment : 10 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0007457733154296875 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.16484 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 : 6.222724914550781e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.0002396106719970703 length of segment : 8 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0007147789001464844 length of segment : 23 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0007507801055908203 length of segment : 38 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 914 time to create 1 rle with old method : 0.0021431446075439453 length of segment : 40 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0024404525756835938 length of segment : 51 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 712 time to create 1 rle with old method : 0.0012822151184082031 length of segment : 37 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.0013861656188964844 length of segment : 19 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0008666515350341797 length of segment : 28 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.00047659873962402344 length of segment : 12 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00017762184143066406 length of segment : 11 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0006058216094970703 length of segment : 20 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0005168914794921875 length of segment : 27 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0005166530609130859 length of segment : 21 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0004093647003173828 length of segment : 21 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0003380775451660156 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.64141 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 : 0.00012183189392089844 nb_pixel_total : 2339 time to create 1 rle with old method : 0.0030629634857177734 length of segment : 151 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 911 time to create 1 rle with old method : 0.0013933181762695312 length of segment : 30 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 982 time to create 1 rle with old method : 0.001386880874633789 length of segment : 33 time for calcul the mask position with numpy : 9.989738464355469e-05 nb_pixel_total : 1297 time to create 1 rle with old method : 0.002228975296020508 length of segment : 44 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007679462432861328 length of segment : 50 time for calcul the mask position with numpy : 0.0001304149627685547 nb_pixel_total : 1945 time to create 1 rle with old method : 0.002540111541748047 length of segment : 103 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0007455348968505859 length of segment : 49 time for calcul the mask position with numpy : 0.0001430511474609375 nb_pixel_total : 1952 time to create 1 rle with old method : 0.002489805221557617 length of segment : 127 time for calcul the mask position with numpy : 0.000141143798828125 nb_pixel_total : 1974 time to create 1 rle with old method : 0.0024824142456054688 length of segment : 129 time for calcul the mask position with numpy : 0.00015211105346679688 nb_pixel_total : 2218 time to create 1 rle with old method : 0.002946138381958008 length of segment : 109 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0009331703186035156 length of segment : 19 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 606 time to create 1 rle with old method : 0.000919342041015625 length of segment : 19 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 2398 time to create 1 rle with old method : 0.0029366016387939453 length of segment : 129 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 231.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 107.89297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0013048648834228516 length of segment : 43 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0009658336639404297 length of segment : 36 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.000347137451171875 length of segment : 29 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1824 time to create 1 rle with old method : 0.002242565155029297 length of segment : 91 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0010120868682861328 length of segment : 43 time for calcul the mask position with numpy : 0.0001952648162841797 nb_pixel_total : 3837 time to create 1 rle with old method : 0.004866600036621094 length of segment : 213 time for calcul the mask position with numpy : 0.00015401840209960938 nb_pixel_total : 4245 time to create 1 rle with old method : 0.0051381587982177734 length of segment : 229 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 808 time to create 1 rle with old method : 0.0010869503021240234 length of segment : 35 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1627 time to create 1 rle with old method : 0.002019643783569336 length of segment : 78 Processing 1 images image shape: (280, 400, 3) min: 10.00000 max: 168.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 48.65859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009527206420898438 nb_pixel_total : 107151 time to create 1 rle with old method : 0.12000250816345215 length of segment : 283 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.33047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003879070281982422 length of segment : 17 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 814 time to create 1 rle with old method : 0.0010895729064941406 length of segment : 38 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006480216979980469 length of segment : 21 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 30 time to create 1 rle with old method : 8.20159912109375e-05 length of segment : 7 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00042724609375 length of segment : 29 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1119 time to create 1 rle with old method : 0.0014376640319824219 length of segment : 66 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.24453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0005757808685302734 length of segment : 20 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 2075 time to create 1 rle with old method : 0.0025835037231445312 length of segment : 46 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 2576 time to create 1 rle with old method : 0.0033020973205566406 length of segment : 61 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00017714500427246094 length of segment : 16 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.00034427642822265625 length of segment : 19 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.00022649765014648438 length of segment : 16 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 1493 time to create 1 rle with old method : 0.0018990039825439453 length of segment : 53 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.0002009868621826172 length of segment : 14 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 2325 time to create 1 rle with old method : 0.0029103755950927734 length of segment : 51 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1534 time to create 1 rle with old method : 0.0019969940185546875 length of segment : 53 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.29141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003101825714111328 length of segment : 24 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0005831718444824219 length of segment : 60 time for calcul the mask position with numpy : 0.0003921985626220703 nb_pixel_total : 24243 time to create 1 rle with old method : 0.029284238815307617 length of segment : 246 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 49 time to create 1 rle with old method : 0.0001385211944580078 length of segment : 8 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 20 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00014925003051757812 length of segment : 24 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 41 time to create 1 rle with old method : 8.511543273925781e-05 length of segment : 17 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.91250 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: -119.68047 max: 145.15078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0021643638610839844 length of segment : 42 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 933 time to create 1 rle with old method : 0.0019681453704833984 length of segment : 40 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 896 time to create 1 rle with old method : 0.0015401840209960938 length of segment : 34 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 849 time to create 1 rle with old method : 0.0012018680572509766 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.36016 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 : 6.4849853515625e-05 nb_pixel_total : 2360 time to create 1 rle with old method : 0.002959012985229492 length of segment : 49 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 2253 time to create 1 rle with old method : 0.0028634071350097656 length of segment : 50 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.16094 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 : 4.291534423828125e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.0001761913299560547 length of segment : 18 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 2417 time to create 1 rle with old method : 0.0029439926147460938 length of segment : 72 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2482 time to create 1 rle with old method : 0.0032112598419189453 length of segment : 81 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.52813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 0.00018596649169921875 nb_pixel_total : 12897 time to create 1 rle with old method : 0.015578031539916992 length of segment : 93 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.00033283233642578125 length of segment : 23 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.0007226467132568359 length of segment : 48 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.00013136863708496094 length of segment : 13 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.00028324127197265625 length of segment : 11 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002779960632324219 length of segment : 17 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 233.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 104.34219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0006253719329833984 length of segment : 16 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.00048089027404785156 length of segment : 22 time for calcul the mask position with numpy : 0.0008604526519775391 nb_pixel_total : 53365 time to create 1 rle with old method : 0.06669998168945312 length of segment : 268 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 192.00000 molded_images shape: (1, 640, 640, 3) min: -91.50469 max: 62.03359 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: -122.51641 max: 146.07266 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.00013828277587890625 length of segment : 9 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 45 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1346 time to create 1 rle with old method : 0.0017230510711669922 length of segment : 47 time for calcul the mask position with numpy : 0.0001533031463623047 nb_pixel_total : 3177 time to create 1 rle with old method : 0.0046765804290771484 length of segment : 99 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.00013685226440429688 length of segment : 9 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00021266937255859375 length of segment : 13 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00016736984252929688 length of segment : 7 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00020933151245117188 length of segment : 15 time for calcul the mask position with numpy : 0.0003497600555419922 nb_pixel_total : 21938 time to create 1 rle with old method : 0.02527904510498047 length of segment : 200 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.35625 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 : 0.00011444091796875 nb_pixel_total : 90 time to create 1 rle with old method : 0.00019121170043945312 length of segment : 7 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0005810260772705078 length of segment : 29 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.000743865966796875 length of segment : 45 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0005033016204833984 length of segment : 21 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0005846023559570312 length of segment : 14 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003352165222167969 length of segment : 20 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0007345676422119141 length of segment : 27 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0010437965393066406 length of segment : 20 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 755 time to create 1 rle with old method : 0.0011265277862548828 length of segment : 37 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.00017547607421875 length of segment : 11 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1228 time to create 1 rle with old method : 0.0015978813171386719 length of segment : 52 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003867149353027344 length of segment : 37 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1072 time to create 1 rle with old method : 0.0015168190002441406 length of segment : 29 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 575 time to create 1 rle with old method : 0.0007574558258056641 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.14141 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 : 0.0001163482666015625 nb_pixel_total : 2378 time to create 1 rle with old method : 0.002951383590698242 length of segment : 154 time for calcul the mask position with numpy : 0.00012159347534179688 nb_pixel_total : 2044 time to create 1 rle with old method : 0.002626180648803711 length of segment : 106 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 876 time to create 1 rle with old method : 0.0011377334594726562 length of segment : 40 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1277 time to create 1 rle with old method : 0.0018420219421386719 length of segment : 43 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006949901580810547 length of segment : 17 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003504753112792969 length of segment : 28 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 872 time to create 1 rle with old method : 0.0012476444244384766 length of segment : 30 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1036 time to create 1 rle with old method : 0.001512765884399414 length of segment : 32 time for calcul the mask position with numpy : 0.00013256072998046875 nb_pixel_total : 2302 time to create 1 rle with old method : 0.0029773712158203125 length of segment : 120 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 99.90469 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005640983581542969 length of segment : 37 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0006422996520996094 length of segment : 38 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0004248619079589844 length of segment : 27 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 1722 time to create 1 rle with old method : 0.0036423206329345703 length of segment : 82 time for calcul the mask position with numpy : 0.00017976760864257812 nb_pixel_total : 3454 time to create 1 rle with old method : 0.0043184757232666016 length of segment : 189 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0004138946533203125 length of segment : 16 Processing 1 images image shape: (280, 400, 3) min: 3.00000 max: 170.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 46.92812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0010619163513183594 nb_pixel_total : 106308 time to create 1 rle with old method : 0.12405228614807129 length of segment : 279 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 142.17031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003845691680908203 length of segment : 20 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.00016117095947265625 length of segment : 20 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 38 time to create 1 rle with old method : 9.34600830078125e-05 length of segment : 8 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.64687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 2100 time to create 1 rle with old method : 0.0026013851165771484 length of segment : 46 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001780986785888672 length of segment : 16 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002300739288330078 length of segment : 18 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.00045990943908691406 length of segment : 21 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00023508071899414062 length of segment : 14 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0008008480072021484 length of segment : 29 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1485 time to create 1 rle with old method : 0.0018763542175292969 length of segment : 57 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 2579 time to create 1 rle with old method : 0.0033109188079833984 length of segment : 86 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 1510 time to create 1 rle with old method : 0.0021986961364746094 length of segment : 53 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0012056827545166016 length of segment : 45 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.62734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003180503845214844 length of segment : 18 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006756782531738281 length of segment : 71 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002574920654296875 length of segment : 45 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00020456314086914062 length of segment : 17 time for calcul the mask position with numpy : 0.00033664703369140625 nb_pixel_total : 13767 time to create 1 rle with old method : 0.016463756561279297 length of segment : 305 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00015425682067871094 length of segment : 9 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 42 time to create 1 rle with old method : 8.893013000488281e-05 length of segment : 7 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.16250 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: -120.32500 max: 145.04922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 956 time to create 1 rle with old method : 0.0012171268463134766 length of segment : 39 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0006251335144042969 length of segment : 17 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 925 time to create 1 rle with old method : 0.001230478286743164 length of segment : 38 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0007290840148925781 length of segment : 49 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 924 time to create 1 rle with old method : 0.0012729167938232422 length of segment : 39 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003809928894042969 length of segment : 35 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 921 time to create 1 rle with old method : 0.0013227462768554688 length of segment : 40 time for calcul the mask position with numpy : 0.0001823902130126953 nb_pixel_total : 2051 time to create 1 rle with old method : 0.0026340484619140625 length of segment : 96 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0005280971527099609 length of segment : 30 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1442 time to create 1 rle with old method : 0.0020580291748046875 length of segment : 60 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0010249614715576172 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.12969 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 : 8.058547973632812e-05 nb_pixel_total : 2435 time to create 1 rle with old method : 0.003036022186279297 length of segment : 50 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 204 2025-02-03 08:20:56.909603: E tensorflow/stream_executor/cuda/cuda_event.cc:29] Error polling for event status: failed to query event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered 2025-02-03 08:20:56.909666: F tensorflow/core/common_runtime/gpu/gpu_event_mgr.cc:273] Unexpected Event status: 1 max_time_sub_proc : 3600 Catched exception ! Connect or reconnect ! in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 24.85user 22.14system 1:00:06elapsed 1%CPU (0avgtext+0avgdata 2502304maxresident)k 128792inputs+2688outputs (9166major+756838minor)pagefaults 0swaps