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 : 1377166 load datou : 4234 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2573998'] with mtr_portfolio_ids : ['20421897'] and first list_photo_ids : [] new path : /proc/1377166/ 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 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 1.0623071193695068 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 Tue Feb 11 06:20:30 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 : 3791 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-11 06:20:33.267790: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-11 06:20:33.299046: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-11 06:20:33.300529: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fb64c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-11 06:20:33.300562: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-11 06:20:33.304435: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-11 06:20:33.551071: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x35f51580 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-11 06:20:33.551120: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-11 06:20:33.555631: 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 2025-02-11 06:20:33.556406: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-11 06:20:33.560821: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-11 06:20:33.567185: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-11 06:20:33.567583: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-11 06:20:33.577570: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-11 06:20:33.580001: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-11 06:20:33.594657: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-11 06:20:33.595925: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-11 06:20:33.596017: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-11 06:20:33.596691: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-11 06:20:33.596710: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-11 06:20:33.596721: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-11 06:20:33.597899: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3339 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. 2025-02-11 06:20:33.896733: 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 2025-02-11 06:20:33.896844: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-11 06:20:33.896878: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-11 06:20:33.896908: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-11 06:20:33.896937: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-11 06:20:33.896966: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-11 06:20:33.896995: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-11 06:20:33.897024: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-11 06:20:33.898472: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-11 06:20:33.900033: 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 2025-02-11 06:20:33.900124: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-11 06:20:33.900151: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-11 06:20:33.900175: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-11 06:20:33.900200: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-11 06:20:33.900224: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-11 06:20:33.900248: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-11 06:20:33.900272: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-11 06:20:33.901758: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-11 06:20:33.901802: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-11 06:20:33.901817: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-11 06:20:33.901831: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-11 06:20:33.903443: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3339 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 : [] 2025-02-11 06:20:42.338795: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-11 06:20:42.530629: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-11 06:20:44.181677: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.182258: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.49G (2669661440 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.182803: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.24G (2402695168 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.182833: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.183417: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.183435: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.192499: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.192521: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.193094: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.193109: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.199613: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.199634: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.200205: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.200221: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.230812: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.230850: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.231423: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.231440: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.237194: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.237213: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.237742: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.237757: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-11 06:20:44.271560: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.272104: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.273920: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.274454: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.318296: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.318850: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.321079: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.321659: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.352011: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.352557: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.354225: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.354760: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.361189: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.361765: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.363667: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.364201: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.370330: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.370882: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.372439: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.372981: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.399398: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.399989: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.400566: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.401097: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.404591: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.405139: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.420455: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.421042: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.421617: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.422152: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.434348: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.434883: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.435447: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.436024: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.440238: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.440807: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.445290: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.445823: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.457745: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.458328: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.462433: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.463063: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.463647: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.464224: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.464979: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.465560: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.476318: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.476904: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.477498: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.478074: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.478650: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.479240: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.479836: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.480415: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.495199: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.495786: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.544088: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.545095: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.546075: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.547000: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.555642: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.556349: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.572653: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.573274: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.573866: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.574424: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.578537: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.579171: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.579784: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.580386: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.581611: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.581634: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-02-11 06:20:44.591910: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.592559: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.602096: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.602762: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.603411: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.604031: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.604657: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-11 06:20:44.605276: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.76G (2966290432 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 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: -123.63750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 0.00016069412231445312 nb_pixel_total : 3271 time to create 1 rle with old method : 0.006356239318847656 length of segment : 82 time for calcul the mask position with numpy : 0.0001266002655029297 nb_pixel_total : 2045 time to create 1 rle with old method : 0.004170656204223633 length of segment : 63 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 915 time to create 1 rle with old method : 0.0013213157653808594 length of segment : 27 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 735 time to create 1 rle with old method : 0.0010738372802734375 length of segment : 52 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 1055 time to create 1 rle with old method : 0.0019071102142333984 length of segment : 59 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003802776336669922 length of segment : 16 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0006000995635986328 length of segment : 24 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0005161762237548828 length of segment : 20 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003364086151123047 length of segment : 28 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1734 time to create 1 rle with old method : 0.0026712417602539062 length of segment : 58 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 915 time to create 1 rle with old method : 0.0014195442199707031 length of segment : 37 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.00022482872009277344 length of segment : 14 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0011074542999267578 length of segment : 41 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 954 time to create 1 rle with old method : 0.0014085769653320312 length of segment : 36 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.00036406517028808594 length of segment : 15 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 649 time to create 1 rle with old method : 0.0010609626770019531 length of segment : 62 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 1612 time to create 1 rle with old method : 0.002298593521118164 length of segment : 48 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00028705596923828125 length of segment : 8 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 9 time to create 1 rle with old method : 4.839897155761719e-05 length of segment : 7 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0005137920379638672 length of segment : 38 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0007960796356201172 length of segment : 48 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00018525123596191406 length of segment : 11 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003833770751953125 length of segment : 17 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 935 time to create 1 rle with old method : 0.001325845718383789 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 931 time to create 1 rle with old method : 0.0014240741729736328 length of segment : 44 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1686 time to create 1 rle with old method : 0.002741575241088867 length of segment : 47 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 2999 time to create 1 rle with old method : 0.0040323734283447266 length of segment : 69 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 2070 time to create 1 rle with old method : 0.0028069019317626953 length of segment : 41 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0007326602935791016 length of segment : 36 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0008828639984130859 length of segment : 24 time for calcul the mask position with numpy : 0.00010013580322265625 nb_pixel_total : 2692 time to create 1 rle with old method : 0.0035207271575927734 length of segment : 72 time for calcul the mask position with numpy : 0.00024819374084472656 nb_pixel_total : 11631 time to create 1 rle with old method : 0.015222787857055664 length of segment : 158 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1168 time to create 1 rle with old method : 0.0018134117126464844 length of segment : 35 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0008895397186279297 length of segment : 26 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.000225067138671875 length of segment : 13 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0004756450653076172 length of segment : 25 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0006678104400634766 length of segment : 19 time for calcul the mask position with numpy : 0.00010323524475097656 nb_pixel_total : 2795 time to create 1 rle with old method : 0.0040318965911865234 length of segment : 85 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 480 time to create 1 rle with old method : 0.0007188320159912109 length of segment : 31 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0006611347198486328 length of segment : 48 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0007605552673339844 length of segment : 26 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0007607936859130859 length of segment : 40 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 1342 time to create 1 rle with old method : 0.0020782947540283203 length of segment : 67 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.0009641647338867188 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.66094 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 1791 time to create 1 rle with old method : 0.0026993751525878906 length of segment : 56 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1986 time to create 1 rle with old method : 0.0027408599853515625 length of segment : 58 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0005061626434326172 length of segment : 20 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0008742809295654297 length of segment : 35 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 2764 time to create 1 rle with old method : 0.0037174224853515625 length of segment : 55 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0006008148193359375 length of segment : 28 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00034046173095703125 length of segment : 11 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0010690689086914062 length of segment : 31 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0008599758148193359 length of segment : 34 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 1904 time to create 1 rle with old method : 0.006766319274902344 length of segment : 45 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 1215 time to create 1 rle with old method : 0.0053484439849853516 length of segment : 33 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0010333061218261719 length of segment : 40 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 889 time to create 1 rle with old method : 0.004014730453491211 length of segment : 40 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 480 time to create 1 rle with old method : 0.0007152557373046875 length of segment : 23 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.0008289813995361328 length of segment : 24 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 748 time to create 1 rle with old method : 0.0011250972747802734 length of segment : 24 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0007224082946777344 length of segment : 33 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 815 time to create 1 rle with old method : 0.0013070106506347656 length of segment : 42 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0007622241973876953 length of segment : 20 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.001093149185180664 length of segment : 28 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0009465217590332031 length of segment : 49 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.0011210441589355469 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.68828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 34 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0007612705230712891 length of segment : 43 time for calcul the mask position with numpy : 0.00015878677368164062 nb_pixel_total : 2909 time to create 1 rle with old method : 0.005383968353271484 length of segment : 69 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 433 time to create 1 rle with old method : 0.0006592273712158203 length of segment : 25 time for calcul the mask position with numpy : 0.00015878677368164062 nb_pixel_total : 4535 time to create 1 rle with old method : 0.0071680545806884766 length of segment : 59 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 568 time to create 1 rle with old method : 0.0009057521820068359 length of segment : 24 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 686 time to create 1 rle with old method : 0.0010311603546142578 length of segment : 38 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 634 time to create 1 rle with old method : 0.0009479522705078125 length of segment : 29 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 990 time to create 1 rle with old method : 0.0015213489532470703 length of segment : 28 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1162 time to create 1 rle with old method : 0.0026416778564453125 length of segment : 49 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 850 time to create 1 rle with old method : 0.0019025802612304688 length of segment : 40 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 735 time to create 1 rle with old method : 0.0021164417266845703 length of segment : 25 time for calcul the mask position with numpy : 0.00014257431030273438 nb_pixel_total : 1445 time to create 1 rle with old method : 0.002719402313232422 length of segment : 55 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0031054019927978516 length of segment : 25 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 880 time to create 1 rle with old method : 0.0016319751739501953 length of segment : 36 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1069 time to create 1 rle with old method : 0.0017409324645996094 length of segment : 40 time for calcul the mask position with numpy : 0.00032806396484375 nb_pixel_total : 10164 time to create 1 rle with old method : 0.01216268539428711 length of segment : 118 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.00033354759216308594 length of segment : 24 time for calcul the mask position with numpy : 0.0001342296600341797 nb_pixel_total : 1763 time to create 1 rle with old method : 0.0037679672241210938 length of segment : 36 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1225 time to create 1 rle with old method : 0.0017292499542236328 length of segment : 35 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002949237823486328 length of segment : 17 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0008955001831054688 length of segment : 25 time for calcul the mask position with numpy : 0.0001316070556640625 nb_pixel_total : 1834 time to create 1 rle with old method : 0.0029621124267578125 length of segment : 94 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.00034427642822265625 length of segment : 16 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1044 time to create 1 rle with old method : 0.0013709068298339844 length of segment : 51 time for calcul the mask position with numpy : 0.0001499652862548828 nb_pixel_total : 1444 time to create 1 rle with old method : 0.002000570297241211 length of segment : 77 time for calcul the mask position with numpy : 0.00011801719665527344 nb_pixel_total : 2816 time to create 1 rle with old method : 0.0035054683685302734 length of segment : 69 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1023 time to create 1 rle with old method : 0.0013942718505859375 length of segment : 43 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 3476 time to create 1 rle with old method : 0.004331827163696289 length of segment : 75 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0009622573852539062 length of segment : 23 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 1974 time to create 1 rle with old method : 0.002526521682739258 length of segment : 71 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 883 time to create 1 rle with old method : 0.0011646747589111328 length of segment : 34 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 3390 time to create 1 rle with old method : 0.004259347915649414 length of segment : 75 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 2586 time to create 1 rle with old method : 0.0033140182495117188 length of segment : 73 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006461143493652344 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.58281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00039124488830566406 length of segment : 22 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0009195804595947266 length of segment : 27 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1075 time to create 1 rle with old method : 0.0015552043914794922 length of segment : 40 time for calcul the mask position with numpy : 0.00015926361083984375 nb_pixel_total : 4822 time to create 1 rle with old method : 0.007381439208984375 length of segment : 65 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006597042083740234 length of segment : 28 time for calcul the mask position with numpy : 0.00033593177795410156 nb_pixel_total : 17095 time to create 1 rle with old method : 0.019942283630371094 length of segment : 192 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0004990100860595703 length of segment : 36 time for calcul the mask position with numpy : 0.00047016143798828125 nb_pixel_total : 26009 time to create 1 rle with old method : 0.029401779174804688 length of segment : 183 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003523826599121094 length of segment : 13 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00033593177795410156 length of segment : 17 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 700 time to create 1 rle with old method : 0.0010178089141845703 length of segment : 58 time for calcul the mask position with numpy : 0.00012159347534179688 nb_pixel_total : 2656 time to create 1 rle with old method : 0.0034401416778564453 length of segment : 100 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.00021839141845703125 length of segment : 7 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0005259513854980469 length of segment : 24 time for calcul the mask position with numpy : 0.00014781951904296875 nb_pixel_total : 3035 time to create 1 rle with old method : 0.004084348678588867 length of segment : 94 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.00014090538024902344 length of segment : 11 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0005114078521728516 length of segment : 34 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.00034356117248535156 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.73516 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 : 4.291534423828125e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005164146423339844 length of segment : 34 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1049 time to create 1 rle with old method : 0.0013763904571533203 length of segment : 42 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00043487548828125 length of segment : 16 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 618 time to create 1 rle with old method : 0.0008938312530517578 length of segment : 22 time for calcul the mask position with numpy : 0.0002796649932861328 nb_pixel_total : 11485 time to create 1 rle with old method : 0.01835036277770996 length of segment : 172 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.00019598007202148438 length of segment : 12 Processing 1 images image shape: (400, 160, 3) min: 7.00000 max: 148.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 32.06484 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: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0008990764617919922 length of segment : 45 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.00042724609375 length of segment : 17 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004658699035644531 length of segment : 16 time for calcul the mask position with numpy : 0.0003266334533691406 nb_pixel_total : 18643 time to create 1 rle with old method : 0.022457599639892578 length of segment : 188 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 2484 time to create 1 rle with old method : 0.0031418800354003906 length of segment : 127 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 2766 time to create 1 rle with old method : 0.003534078598022461 length of segment : 87 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 741 time to create 1 rle with old method : 0.0010335445404052734 length of segment : 23 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.00039458274841308594 length of segment : 28 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1239 time to create 1 rle with old method : 0.0014984607696533203 length of segment : 73 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00027871131896972656 length of segment : 25 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1022 time to create 1 rle with old method : 0.00127410888671875 length of segment : 42 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 2428 time to create 1 rle with old method : 0.002962827682495117 length of segment : 97 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1484 time to create 1 rle with old method : 0.001990795135498047 length of segment : 74 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 918 time to create 1 rle with old method : 0.0012156963348388672 length of segment : 37 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.00043201446533203125 length of segment : 24 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0003910064697265625 length of segment : 23 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 845 time to create 1 rle with old method : 0.0011026859283447266 length of segment : 36 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 920 time to create 1 rle with old method : 0.0011577606201171875 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 27 time for calcul the mask position with numpy : 0.00011301040649414062 nb_pixel_total : 4321 time to create 1 rle with old method : 0.005028963088989258 length of segment : 107 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 3370 time to create 1 rle with old method : 0.0041010379791259766 length of segment : 114 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 2188 time to create 1 rle with old method : 0.0032525062561035156 length of segment : 54 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004115104675292969 length of segment : 45 time for calcul the mask position with numpy : 0.00013303756713867188 nb_pixel_total : 4924 time to create 1 rle with old method : 0.005744218826293945 length of segment : 129 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0004162788391113281 length of segment : 34 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1945 time to create 1 rle with old method : 0.002341747283935547 length of segment : 90 time for calcul the mask position with numpy : 0.00029468536376953125 nb_pixel_total : 16057 time to create 1 rle with old method : 0.01914215087890625 length of segment : 214 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0008361339569091797 length of segment : 46 time for calcul the mask position with numpy : 0.00012063980102539062 nb_pixel_total : 5752 time to create 1 rle with old method : 0.0069293975830078125 length of segment : 104 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 3535 time to create 1 rle with old method : 0.004224061965942383 length of segment : 160 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 615 time to create 1 rle with old method : 0.0008592605590820312 length of segment : 42 time for calcul the mask position with numpy : 9.036064147949219e-05 nb_pixel_total : 2654 time to create 1 rle with old method : 0.004102230072021484 length of segment : 53 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1104 time to create 1 rle with old method : 0.0013194084167480469 length of segment : 46 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.00014972686767578125 length of segment : 14 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007839202880859375 length of segment : 24 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00033402442932128906 length of segment : 18 time for calcul the mask position with numpy : 0.0005462169647216797 nb_pixel_total : 19198 time to create 1 rle with old method : 0.02133321762084961 length of segment : 263 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002541542053222656 length of segment : 23 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 838 time to create 1 rle with old method : 0.0011048316955566406 length of segment : 34 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 469 time to create 1 rle with old method : 0.0006821155548095703 length of segment : 60 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002541542053222656 length of segment : 16 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 870 time to create 1 rle with old method : 0.0011143684387207031 length of segment : 55 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.0006368160247802734 length of segment : 22 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 2824 time to create 1 rle with old method : 0.0033957958221435547 length of segment : 131 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 3225 time to create 1 rle with old method : 0.0038661956787109375 length of segment : 67 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0006678104400634766 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.53594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 34 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 788 time to create 1 rle with old method : 0.0010347366333007812 length of segment : 55 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 2105 time to create 1 rle with old method : 0.002519845962524414 length of segment : 58 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005359649658203125 length of segment : 37 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 1342 time to create 1 rle with old method : 0.0017750263214111328 length of segment : 57 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1238 time to create 1 rle with old method : 0.001623392105102539 length of segment : 43 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 40 time to create 1 rle with old method : 0.0002067089080810547 length of segment : 6 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 703 time to create 1 rle with old method : 0.0009400844573974609 length of segment : 42 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004570484161376953 length of segment : 26 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 2553 time to create 1 rle with old method : 0.0031244754791259766 length of segment : 44 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.0002593994140625 length of segment : 7 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005018711090087891 length of segment : 19 time for calcul the mask position with numpy : 0.00011515617370605469 nb_pixel_total : 893 time to create 1 rle with old method : 0.0012445449829101562 length of segment : 89 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 745 time to create 1 rle with old method : 0.0009975433349609375 length of segment : 35 time for calcul the mask position with numpy : 0.0002665519714355469 nb_pixel_total : 16117 time to create 1 rle with old method : 0.018402099609375 length of segment : 162 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003008842468261719 length of segment : 25 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 963 time to create 1 rle with old method : 0.0012891292572021484 length of segment : 40 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0005865097045898438 length of segment : 24 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0010304450988769531 length of segment : 36 time for calcul the mask position with numpy : 0.0002923011779785156 nb_pixel_total : 16445 time to create 1 rle with old method : 0.01854538917541504 length of segment : 175 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004730224609375 length of segment : 19 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.00040149688720703125 length of segment : 43 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004329681396484375 length of segment : 19 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.0002608299255371094 length of segment : 14 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1905 time to create 1 rle with old method : 0.002296924591064453 length of segment : 84 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0013959407806396484 length of segment : 56 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 778 time to create 1 rle with old method : 0.001020669937133789 length of segment : 32 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 752 time to create 1 rle with old method : 0.0009815692901611328 length of segment : 35 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 1785 time to create 1 rle with old method : 0.0023119449615478516 length of segment : 69 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004878044128417969 length of segment : 29 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 684 time to create 1 rle with old method : 0.0009012222290039062 length of segment : 34 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003457069396972656 length of segment : 23 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 1547 time to create 1 rle with old method : 0.002005338668823242 length of segment : 53 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 2275 time to create 1 rle with old method : 0.0028121471405029297 length of segment : 67 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 952 time to create 1 rle with old method : 0.0012307167053222656 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.60625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.00031065940856933594 length of segment : 15 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1129 time to create 1 rle with old method : 0.0014889240264892578 length of segment : 40 time for calcul the mask position with numpy : 0.00010538101196289062 nb_pixel_total : 2750 time to create 1 rle with old method : 0.0035228729248046875 length of segment : 59 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 593 time to create 1 rle with old method : 0.0010297298431396484 length of segment : 35 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003199577331542969 length of segment : 13 time for calcul the mask position with numpy : 0.0003197193145751953 nb_pixel_total : 14600 time to create 1 rle with old method : 0.01696467399597168 length of segment : 140 time for calcul the mask position with numpy : 0.0002722740173339844 nb_pixel_total : 13281 time to create 1 rle with old method : 0.015250921249389648 length of segment : 128 time for calcul the mask position with numpy : 0.0001220703125 nb_pixel_total : 4422 time to create 1 rle with old method : 0.0053560733795166016 length of segment : 89 time for calcul the mask position with numpy : 0.00014257431030273438 nb_pixel_total : 4043 time to create 1 rle with old method : 0.005251169204711914 length of segment : 67 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0006024837493896484 length of segment : 24 time for calcul the mask position with numpy : 0.0002410411834716797 nb_pixel_total : 9690 time to create 1 rle with old method : 0.011606931686401367 length of segment : 147 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0005085468292236328 length of segment : 18 time for calcul the mask position with numpy : 0.0006909370422363281 nb_pixel_total : 29941 time to create 1 rle with old method : 0.034557342529296875 length of segment : 195 time for calcul the mask position with numpy : 0.00011992454528808594 nb_pixel_total : 1265 time to create 1 rle with old method : 0.0016660690307617188 length of segment : 41 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 3429 time to create 1 rle with old method : 0.004064083099365234 length of segment : 90 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 590 time to create 1 rle with old method : 0.0009074211120605469 length of segment : 40 time for calcul the mask position with numpy : 0.00010371208190917969 nb_pixel_total : 3565 time to create 1 rle with old method : 0.004206418991088867 length of segment : 97 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.00045680999755859375 length of segment : 25 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0008563995361328125 length of segment : 38 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 731 time to create 1 rle with old method : 0.001024484634399414 length of segment : 27 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.0009272098541259766 length of segment : 25 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0010330677032470703 length of segment : 24 time for calcul the mask position with numpy : 0.00010967254638671875 nb_pixel_total : 4024 time to create 1 rle with old method : 0.004877328872680664 length of segment : 66 time for calcul the mask position with numpy : 0.00010728836059570312 nb_pixel_total : 4287 time to create 1 rle with old method : 0.005292654037475586 length of segment : 91 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 28 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 1470 time to create 1 rle with old method : 0.0018818378448486328 length of segment : 33 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004379749298095703 length of segment : 29 time for calcul the mask position with numpy : 0.0001583099365234375 nb_pixel_total : 6699 time to create 1 rle with old method : 0.008031845092773438 length of segment : 87 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 454 time to create 1 rle with old method : 0.0006098747253417969 length of segment : 34 time for calcul the mask position with numpy : 0.00021719932556152344 nb_pixel_total : 3215 time to create 1 rle with old method : 0.00402379035949707 length of segment : 122 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 653 time to create 1 rle with old method : 0.0008585453033447266 length of segment : 34 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 945 time to create 1 rle with old method : 0.0013124942779541016 length of segment : 44 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0005483627319335938 length of segment : 28 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1253 time to create 1 rle with old method : 0.0015842914581298828 length of segment : 73 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 934 time to create 1 rle with old method : 0.0013761520385742188 length of segment : 17 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 1079 time to create 1 rle with old method : 0.0014536380767822266 length of segment : 44 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003116130828857422 length of segment : 21 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 580 time to create 1 rle with old method : 0.0009517669677734375 length of segment : 23 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1441 time to create 1 rle with old method : 0.0017437934875488281 length of segment : 61 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005080699920654297 length of segment : 23 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005257129669189453 length of segment : 28 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003268718719482422 length of segment : 17 time for calcul the mask position with numpy : 0.0001366138458251953 nb_pixel_total : 3044 time to create 1 rle with old method : 0.003683805465698242 length of segment : 98 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0007307529449462891 length of segment : 18 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1068 time to create 1 rle with old method : 0.0015528202056884766 length of segment : 18 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004589557647705078 length of segment : 15 time for calcul the mask position with numpy : 0.000171661376953125 nb_pixel_total : 6888 time to create 1 rle with old method : 0.008240699768066406 length of segment : 103 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 1344 time to create 1 rle with old method : 0.0017163753509521484 length of segment : 59 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 754 time to create 1 rle with old method : 0.0009870529174804688 length of segment : 60 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 853 time to create 1 rle with old method : 0.0011670589447021484 length of segment : 27 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1041 time to create 1 rle with old method : 0.0013585090637207031 length of segment : 36 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 575 time to create 1 rle with old method : 0.0008721351623535156 length of segment : 21 time for calcul the mask position with numpy : 0.0001647472381591797 nb_pixel_total : 2805 time to create 1 rle with old method : 0.003574848175048828 length of segment : 90 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.17656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005621910095214844 length of segment : 46 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0010881423950195312 length of segment : 21 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00013113021850585938 length of segment : 11 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003447532653808594 length of segment : 20 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0009593963623046875 length of segment : 38 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1563 time to create 1 rle with old method : 0.0019953250885009766 length of segment : 45 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005397796630859375 length of segment : 32 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 19 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0006976127624511719 length of segment : 39 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.0002384185791015625 length of segment : 30 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1246 time to create 1 rle with old method : 0.0016560554504394531 length of segment : 41 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.96719 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0006530284881591797 length of segment : 32 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0006048679351806641 length of segment : 21 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0004057884216308594 length of segment : 36 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0008561611175537109 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 25 time for calcul the mask position with numpy : 0.00011944770812988281 nb_pixel_total : 1632 time to create 1 rle with old method : 0.0020723342895507812 length of segment : 61 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.000335693359375 length of segment : 18 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002741813659667969 length of segment : 18 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1564 time to create 1 rle with old method : 0.001997232437133789 length of segment : 44 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1000 time to create 1 rle with old method : 0.0012505054473876953 length of segment : 70 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1122 time to create 1 rle with old method : 0.0014493465423583984 length of segment : 39 time for calcul the mask position with numpy : 9.751319885253906e-05 nb_pixel_total : 1208 time to create 1 rle with old method : 0.0016396045684814453 length of segment : 78 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 1670 time to create 1 rle with old method : 0.0022470951080322266 length of segment : 76 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.0007596015930175781 length of segment : 22 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 2669 time to create 1 rle with old method : 0.003377199172973633 length of segment : 105 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 1933 time to create 1 rle with old method : 0.002410411834716797 length of segment : 73 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1054 time to create 1 rle with old method : 0.0013470649719238281 length of segment : 84 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004360675811767578 length of segment : 13 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1397 time to create 1 rle with old method : 0.001953125 length of segment : 62 time for calcul the mask position with numpy : 0.00010323524475097656 nb_pixel_total : 2322 time to create 1 rle with old method : 0.0029227733612060547 length of segment : 46 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.00033092498779296875 length of segment : 17 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0004229545593261719 length of segment : 27 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 755 time to create 1 rle with old method : 0.001047372817993164 length of segment : 53 time for calcul the mask position with numpy : 0.00018835067749023438 nb_pixel_total : 5421 time to create 1 rle with old method : 0.0070307254791259766 length of segment : 213 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 917 time to create 1 rle with old method : 0.001180887222290039 length of segment : 61 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00024127960205078125 length of segment : 32 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.0001976490020751953 length of segment : 16 time for calcul the mask position with numpy : 0.0001804828643798828 nb_pixel_total : 5633 time to create 1 rle with old method : 0.006914615631103516 length of segment : 228 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1578 time to create 1 rle with old method : 0.0019767284393310547 length of segment : 71 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 2967 time to create 1 rle with old method : 0.0037949085235595703 length of segment : 52 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.26250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.0003864765167236328 length of segment : 16 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0006203651428222656 length of segment : 23 time for calcul the mask position with numpy : 0.00020551681518554688 nb_pixel_total : 5861 time to create 1 rle with old method : 0.006979942321777344 length of segment : 161 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.0010378360748291016 length of segment : 46 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1163 time to create 1 rle with old method : 0.0014569759368896484 length of segment : 58 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1299 time to create 1 rle with old method : 0.0017242431640625 length of segment : 38 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1548 time to create 1 rle with old method : 0.0020139217376708984 length of segment : 82 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1483 time to create 1 rle with old method : 0.0018720626831054688 length of segment : 35 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0006155967712402344 length of segment : 20 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0011746883392333984 length of segment : 45 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0010325908660888672 length of segment : 21 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0008037090301513672 length of segment : 20 time for calcul the mask position with numpy : 0.0003046989440917969 nb_pixel_total : 10764 time to create 1 rle with old method : 0.012654781341552734 length of segment : 218 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0004639625549316406 length of segment : 34 time for calcul the mask position with numpy : 0.00010704994201660156 nb_pixel_total : 2268 time to create 1 rle with old method : 0.002846956253051758 length of segment : 63 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 2352 time to create 1 rle with old method : 0.00403141975402832 length of segment : 51 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.001065969467163086 length of segment : 50 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 1404 time to create 1 rle with old method : 0.002540111541748047 length of segment : 66 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0007405281066894531 length of segment : 15 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 925 time to create 1 rle with old method : 0.0015721321105957031 length of segment : 70 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 1299 time to create 1 rle with old method : 0.0021991729736328125 length of segment : 59 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0009288787841796875 length of segment : 24 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 1508 time to create 1 rle with old method : 0.0026006698608398438 length of segment : 59 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 1320 time to create 1 rle with old method : 0.002276182174682617 length of segment : 65 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00025773048400878906 length of segment : 10 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1307 time to create 1 rle with old method : 0.0015785694122314453 length of segment : 54 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1121 time to create 1 rle with old method : 0.0014736652374267578 length of segment : 52 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005717277526855469 length of segment : 22 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0007624626159667969 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 0.0001571178436279297 nb_pixel_total : 6930 time to create 1 rle with old method : 0.008215904235839844 length of segment : 87 time for calcul the mask position with numpy : 0.0001461505889892578 nb_pixel_total : 5038 time to create 1 rle with old method : 0.006440401077270508 length of segment : 89 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.001051187515258789 length of segment : 53 time for calcul the mask position with numpy : 0.0001232624053955078 nb_pixel_total : 3433 time to create 1 rle with old method : 0.004204273223876953 length of segment : 61 time for calcul the mask position with numpy : 0.0003769397735595703 nb_pixel_total : 14007 time to create 1 rle with old method : 0.01621699333190918 length of segment : 157 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.00037479400634765625 length of segment : 19 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 3537 time to create 1 rle with old method : 0.004424333572387695 length of segment : 73 time for calcul the mask position with numpy : 0.0003285408020019531 nb_pixel_total : 15715 time to create 1 rle with old method : 0.018070459365844727 length of segment : 145 time for calcul the mask position with numpy : 0.00019669532775878906 nb_pixel_total : 7318 time to create 1 rle with old method : 0.009169578552246094 length of segment : 86 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0009367465972900391 length of segment : 24 time for calcul the mask position with numpy : 0.0006089210510253906 nb_pixel_total : 27366 time to create 1 rle with old method : 0.04224872589111328 length of segment : 244 time for calcul the mask position with numpy : 0.0003383159637451172 nb_pixel_total : 12964 time to create 1 rle with old method : 0.014893531799316406 length of segment : 131 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.00040411949157714844 length of segment : 43 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1647 time to create 1 rle with old method : 0.002148151397705078 length of segment : 55 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 2557 time to create 1 rle with old method : 0.0031409263610839844 length of segment : 61 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005538463592529297 length of segment : 33 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0008003711700439453 length of segment : 23 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0003809928894042969 length of segment : 19 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005426406860351562 length of segment : 34 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 804 time to create 1 rle with old method : 0.0010519027709960938 length of segment : 32 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 816 time to create 1 rle with old method : 0.0010533332824707031 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: -123.57109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 27 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 2220 time to create 1 rle with old method : 0.0027506351470947266 length of segment : 50 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 1480 time to create 1 rle with old method : 0.0019030570983886719 length of segment : 70 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0008358955383300781 length of segment : 56 time for calcul the mask position with numpy : 0.0004642009735107422 nb_pixel_total : 22662 time to create 1 rle with old method : 0.026569128036499023 length of segment : 264 time for calcul the mask position with numpy : 0.00012636184692382812 nb_pixel_total : 2829 time to create 1 rle with old method : 0.0036118030548095703 length of segment : 61 time for calcul the mask position with numpy : 0.00015735626220703125 nb_pixel_total : 6313 time to create 1 rle with old method : 0.007378816604614258 length of segment : 106 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 252 time to create 1 rle with old method : 0.0004017353057861328 length of segment : 27 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003726482391357422 length of segment : 23 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0007257461547851562 length of segment : 27 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 2297 time to create 1 rle with old method : 0.00279998779296875 length of segment : 77 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1890 time to create 1 rle with old method : 0.0024275779724121094 length of segment : 69 time for calcul the mask position with numpy : 0.0001342296600341797 nb_pixel_total : 5115 time to create 1 rle with old method : 0.006471872329711914 length of segment : 63 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.00048732757568359375 length of segment : 25 time for calcul the mask position with numpy : 0.0001277923583984375 nb_pixel_total : 5110 time to create 1 rle with old method : 0.006352663040161133 length of segment : 89 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 2192 time to create 1 rle with old method : 0.002844095230102539 length of segment : 56 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 2836 time to create 1 rle with old method : 0.0034096240997314453 length of segment : 85 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0009102821350097656 length of segment : 38 time for calcul the mask position with numpy : 0.00015544891357421875 nb_pixel_total : 5701 time to create 1 rle with old method : 0.006775379180908203 length of segment : 144 time for calcul the mask position with numpy : 0.00020933151245117188 nb_pixel_total : 5980 time to create 1 rle with old method : 0.006848573684692383 length of segment : 184 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 2198 time to create 1 rle with old method : 0.0027627944946289062 length of segment : 54 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0012447834014892578 length of segment : 49 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0003254413604736328 length of segment : 40 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1568 time to create 1 rle with old method : 0.002177715301513672 length of segment : 33 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 1190 time to create 1 rle with old method : 0.0016417503356933594 length of segment : 51 time for calcul the mask position with numpy : 0.0004482269287109375 nb_pixel_total : 22369 time to create 1 rle with old method : 0.02647852897644043 length of segment : 257 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0006961822509765625 length of segment : 27 time for calcul the mask position with numpy : 0.00013399124145507812 nb_pixel_total : 2737 time to create 1 rle with old method : 0.003484010696411133 length of segment : 90 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.45391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 32 time for calcul the mask position with numpy : 0.00024056434631347656 nb_pixel_total : 10554 time to create 1 rle with old method : 0.01254582405090332 length of segment : 180 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0005757808685302734 length of segment : 31 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005216598510742188 length of segment : 39 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 608 time to create 1 rle with old method : 0.0008234977722167969 length of segment : 55 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 387 time to create 1 rle with old method : 0.0005655288696289062 length of segment : 32 time for calcul the mask position with numpy : 0.00025343894958496094 nb_pixel_total : 11047 time to create 1 rle with old method : 0.012689352035522461 length of segment : 129 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.0009105205535888672 length of segment : 110 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006339550018310547 length of segment : 29 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1905 time to create 1 rle with old method : 0.0024390220642089844 length of segment : 58 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 776 time to create 1 rle with old method : 0.0011072158813476562 length of segment : 25 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1073 time to create 1 rle with old method : 0.0014722347259521484 length of segment : 68 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 432 time to create 1 rle with old method : 0.0007088184356689453 length of segment : 20 time for calcul the mask position with numpy : 0.00012612342834472656 nb_pixel_total : 3773 time to create 1 rle with old method : 0.004576683044433594 length of segment : 82 time for calcul the mask position with numpy : 0.00010895729064941406 nb_pixel_total : 3417 time to create 1 rle with old method : 0.004181385040283203 length of segment : 63 time for calcul the mask position with numpy : 0.00010728836059570312 nb_pixel_total : 3633 time to create 1 rle with old method : 0.004305124282836914 length of segment : 106 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 928 time to create 1 rle with old method : 0.0011546611785888672 length of segment : 37 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 757 time to create 1 rle with old method : 0.0009510517120361328 length of segment : 34 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 929 time to create 1 rle with old method : 0.0012102127075195312 length of segment : 24 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 918 time to create 1 rle with old method : 0.001169443130493164 length of segment : 37 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 2717 time to create 1 rle with old method : 0.003413677215576172 length of segment : 38 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1849 time to create 1 rle with old method : 0.0022110939025878906 length of segment : 56 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0006978511810302734 length of segment : 28 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0005044937133789062 length of segment : 20 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0008931159973144531 length of segment : 39 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0008134841918945312 length of segment : 55 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 792 time to create 1 rle with old method : 0.001312255859375 length of segment : 48 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 2081 time to create 1 rle with old method : 0.0025548934936523438 length of segment : 40 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1710 time to create 1 rle with old method : 0.0020837783813476562 length of segment : 58 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 4513 time to create 1 rle with old method : 0.005516767501831055 length of segment : 69 time for calcul the mask position with numpy : 0.00012874603271484375 nb_pixel_total : 4777 time to create 1 rle with old method : 0.005899190902709961 length of segment : 71 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.0001785755157470703 length of segment : 12 time for calcul the mask position with numpy : 9.775161743164062e-05 nb_pixel_total : 4725 time to create 1 rle with old method : 0.0058557987213134766 length of segment : 55 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.83672 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 1730 time to create 1 rle with old method : 0.0021209716796875 length of segment : 57 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0006935596466064453 length of segment : 51 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 860 time to create 1 rle with old method : 0.001111745834350586 length of segment : 37 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005869865417480469 length of segment : 16 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0004973411560058594 length of segment : 20 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1925 time to create 1 rle with old method : 0.0023987293243408203 length of segment : 67 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 7939 time to create 1 rle with old method : 0.009723424911499023 length of segment : 81 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005362033843994141 length of segment : 15 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 3448 time to create 1 rle with old method : 0.004136085510253906 length of segment : 92 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 3175 time to create 1 rle with old method : 0.0038542747497558594 length of segment : 72 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 3123 time to create 1 rle with old method : 0.0037724971771240234 length of segment : 71 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1445 time to create 1 rle with old method : 0.0018148422241210938 length of segment : 48 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005161762237548828 length of segment : 28 time for calcul the mask position with numpy : 0.00011229515075683594 nb_pixel_total : 7019 time to create 1 rle with old method : 0.00807332992553711 length of segment : 72 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007460117340087891 length of segment : 29 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0009627342224121094 length of segment : 48 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005261898040771484 length of segment : 29 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.000986337661743164 length of segment : 48 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005383491516113281 length of segment : 28 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 189.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 79.72109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 754 time to create 1 rle with old method : 0.0009834766387939453 length of segment : 52 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.0001621246337890625 length of segment : 20 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00040912628173828125 length of segment : 27 2025-02-11 06:20:52.019549: 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 2025-02-11 06:20:52.019627: 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 ! 18.76user 13.08system 1:00:08elapsed 0%CPU (0avgtext+0avgdata 2429692maxresident)k 466080inputs+5688outputs (12675major+791857minor)pagefaults 0swaps