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 : 3093893 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 : ['2595728'] with mtr_portfolio_ids : ['20630969'] and first list_photo_ids : [] new path : /proc/3093893/ 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 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.4432194232940674 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 18 10:20:29 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 : 6840 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-18 10:20:32.351684: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-18 10:20:32.383090: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-18 10:20:32.385172: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f788c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-18 10:20:32.385225: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-18 10:20:32.389251: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-18 10:20:32.553862: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x13c5ca20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-18 10:20:32.553916: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-18 10:20:32.555223: 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 2025-02-18 10:20:32.555637: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-18 10:20:32.558716: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-18 10:20:32.561595: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-18 10:20:32.562084: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-18 10:20:32.564902: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-18 10:20:32.565880: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-18 10:20:32.570454: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-18 10:20:32.571749: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-18 10:20:32.571828: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-18 10:20:32.572497: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-18 10:20:32.572514: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-18 10:20:32.572523: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-18 10:20:32.573652: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5897 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. 2025-02-18 10:20:32.849387: 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 2025-02-18 10:20:32.849528: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-18 10:20:32.849558: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-18 10:20:32.849584: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-18 10:20:32.849611: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-18 10:20:32.849635: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-18 10:20:32.849660: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-18 10:20:32.849685: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-18 10:20:32.851418: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-18 10:20:32.852762: 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 2025-02-18 10:20:32.852803: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-18 10:20:32.852819: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-18 10:20:32.852833: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-18 10:20:32.852847: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-18 10:20:32.852861: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-18 10:20:32.852875: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-18 10:20:32.852889: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-18 10:20:32.853871: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-18 10:20:32.853907: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-18 10:20:32.853915: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-18 10:20:32.853922: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-18 10:20:32.854936: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5897 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 : [] 2025-02-18 10:20:41.841488: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-18 10:20:42.057245: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-18 10:20:43.581314: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.581875: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.582378: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.24G (3478923264 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.582877: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3131030784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.583497: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.62G (2817927680 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.584373: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.36G (2536134912 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.584978: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2282521344 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.585010: 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. 2025-02-18 10:20:43.585542: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.585558: 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. 2025-02-18 10:20:43.591731: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.591764: 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. 2025-02-18 10:20:43.592282: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.592298: 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. 2025-02-18 10:20:43.598317: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.598351: 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. 2025-02-18 10:20:43.598878: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.598918: 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. 2025-02-18 10:20:43.625243: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.625288: 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. 2025-02-18 10:20:43.625812: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.625828: 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. 2025-02-18 10:20:43.631164: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.631186: 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. 2025-02-18 10:20:43.631708: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.631724: 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. 2025-02-18 10:20:43.660884: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.661707: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.663695: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.664489: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.701335: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.702148: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.704358: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.705155: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.730322: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.730856: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.732395: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.732888: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.738217: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.738707: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.740307: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.740825: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.746446: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.746983: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.748694: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.749562: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.776230: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.776767: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.777275: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.777772: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.781273: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.781803: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.797129: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.797660: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.798180: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.798661: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.811395: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.812080: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.812592: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.813114: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.817434: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.817953: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.822507: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.823075: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.835024: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.835550: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.839615: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.840138: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.840629: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.841108: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.841852: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.842384: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.853015: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.853543: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.854087: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.854599: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.855159: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.855674: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.856184: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.856701: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.866225: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.866773: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.872984: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.873497: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.942185: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.942714: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.950691: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.951253: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.968065: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.969024: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.969976: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.970883: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.975001: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.975517: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.976026: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.976533: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.977509: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.977525: 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. 2025-02-18 10:20:43.987715: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.988189: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.997090: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.997569: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.998049: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.998545: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.999083: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-18 10:20:43.999628: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 2 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: -118.20000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0015716552734375 length of segment : 28 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0012347698211669922 length of segment : 36 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0005903244018554688 length of segment : 14 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 720 time to create 1 rle with old method : 0.008412837982177734 length of segment : 34 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0012707710266113281 length of segment : 30 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 669 time to create 1 rle with old method : 0.0012044906616210938 length of segment : 31 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 790 time to create 1 rle with old method : 0.0014493465423583984 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: -113.63750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0008666515350341797 length of segment : 16 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00022864341735839844 length of segment : 12 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1969 time to create 1 rle with old method : 0.002460956573486328 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 27.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -93.63750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.001142263412475586 length of segment : 19 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.0002415180206298828 length of segment : 9 Processing 1 images image shape: (400, 400, 3) min: 16.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -99.73750 max: 150.27969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0005095005035400391 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 13.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.15703 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.0003705024719238281 length of segment : 16 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0002593994140625 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 2.00000 max: 226.00000 molded_images shape: (1, 640, 640, 3) min: -121.51641 max: 112.65078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 178.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 66.81094 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0001857280731201172 nb_pixel_total : 11894 time to create 1 rle with old method : 0.013322830200195312 length of segment : 204 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.55547 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 : 7.724761962890625e-05 nb_pixel_total : 1175 time to create 1 rle with old method : 0.0015246868133544922 length of segment : 49 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.0003211498260498047 length of segment : 21 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1333 time to create 1 rle with old method : 0.0016436576843261719 length of segment : 46 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0016779899597167969 length of segment : 39 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004353523254394531 length of segment : 12 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004646778106689453 length of segment : 27 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.00032639503479003906 length of segment : 29 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 649 time to create 1 rle with old method : 0.0008196830749511719 length of segment : 30 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1658 time to create 1 rle with old method : 0.001981973648071289 length of segment : 63 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00016641616821289062 length of segment : 11 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002002716064453125 length of segment : 15 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0005419254302978516 length of segment : 28 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005044937133789062 length of segment : 24 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.00044608116149902344 length of segment : 25 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1143 time to create 1 rle with old method : 0.0014586448669433594 length of segment : 48 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 801 time to create 1 rle with old method : 0.001092672348022461 length of segment : 36 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002932548522949219 length of segment : 13 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0004115104675292969 length of segment : 16 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.00042510032653808594 length of segment : 29 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.0010895729064941406 length of segment : 29 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004296302795410156 length of segment : 22 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.0004761219024658203 length of segment : 23 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0011026859283447266 length of segment : 30 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.00021123886108398438 length of segment : 16 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.001207113265991211 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.96563 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 : 7.891654968261719e-05 nb_pixel_total : 1474 time to create 1 rle with old method : 0.001851797103881836 length of segment : 50 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007355213165283203 length of segment : 35 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003368854522705078 length of segment : 23 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002961158752441406 length of segment : 29 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0004918575286865234 length of segment : 35 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.000308990478515625 length of segment : 17 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006809234619140625 length of segment : 28 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 827 time to create 1 rle with old method : 0.0010654926300048828 length of segment : 29 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0003972053527832031 length of segment : 19 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004832744598388672 length of segment : 24 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1142 time to create 1 rle with old method : 0.001302480697631836 length of segment : 34 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0007467269897460938 length of segment : 28 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0007710456848144531 length of segment : 21 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0003237724304199219 length of segment : 19 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003719329833984375 length of segment : 22 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005145072937011719 length of segment : 25 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 612 time to create 1 rle with old method : 0.0008642673492431641 length of segment : 37 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.00042247772216796875 length of segment : 21 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005600452423095703 length of segment : 23 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006494522094726562 length of segment : 24 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00038051605224609375 length of segment : 42 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.00041294097900390625 length of segment : 33 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1132 time to create 1 rle with old method : 0.00152587890625 length of segment : 37 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0006861686706542969 length of segment : 38 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00046372413635253906 length of segment : 18 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00013065338134765625 length of segment : 9 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0009908676147460938 length of segment : 28 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.0004515647888183594 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.52031 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 698 time to create 1 rle with old method : 0.0013206005096435547 length of segment : 24 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0007014274597167969 length of segment : 18 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0004394054412841797 length of segment : 21 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0004322528839111328 length of segment : 25 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1125 time to create 1 rle with old method : 0.0020546913146972656 length of segment : 46 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0011966228485107422 length of segment : 24 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.0019519329071044922 length of segment : 39 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00041174888610839844 length of segment : 19 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004208087921142578 length of segment : 18 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1483 time to create 1 rle with old method : 0.0017855167388916016 length of segment : 41 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 987 time to create 1 rle with old method : 0.0013518333435058594 length of segment : 48 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002567768096923828 length of segment : 17 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005037784576416016 length of segment : 21 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.0006775856018066406 length of segment : 36 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002613067626953125 length of segment : 17 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0004780292510986328 length of segment : 24 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 2227 time to create 1 rle with old method : 0.0028312206268310547 length of segment : 77 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002415180206298828 length of segment : 15 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.00023126602172851562 length of segment : 14 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 945 time to create 1 rle with old method : 0.001241445541381836 length of segment : 52 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 956 time to create 1 rle with old method : 0.0011513233184814453 length of segment : 46 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0006461143493652344 length of segment : 21 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 380 time to create 1 rle with old method : 0.00048804283142089844 length of segment : 26 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1752 time to create 1 rle with old method : 0.0019345283508300781 length of segment : 72 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005033016204833984 length of segment : 30 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0006513595581054688 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: -119.68047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 41 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0007116794586181641 length of segment : 26 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1057 time to create 1 rle with old method : 0.0013766288757324219 length of segment : 42 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 1921 time to create 1 rle with old method : 0.0023818016052246094 length of segment : 58 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 575 time to create 1 rle with old method : 0.0006997585296630859 length of segment : 28 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002758502960205078 length of segment : 25 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 487 time to create 1 rle with old method : 0.0006175041198730469 length of segment : 36 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 813 time to create 1 rle with old method : 0.0010442733764648438 length of segment : 34 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 714 time to create 1 rle with old method : 0.0008549690246582031 length of segment : 43 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 737 time to create 1 rle with old method : 0.0009691715240478516 length of segment : 26 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0007603168487548828 length of segment : 13 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1121 time to create 1 rle with old method : 0.0013954639434814453 length of segment : 42 time for calcul the mask position with numpy : 0.00010156631469726562 nb_pixel_total : 3749 time to create 1 rle with old method : 0.0044705867767333984 length of segment : 72 time for calcul the mask position with numpy : 0.00012612342834472656 nb_pixel_total : 4469 time to create 1 rle with old method : 0.005390644073486328 length of segment : 72 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 850 time to create 1 rle with old method : 0.0010838508605957031 length of segment : 22 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006756782531738281 length of segment : 24 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005316734313964844 length of segment : 20 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 2007 time to create 1 rle with old method : 0.002492189407348633 length of segment : 57 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 634 time to create 1 rle with old method : 0.0008170604705810547 length of segment : 30 time for calcul the mask position with numpy : 0.00010037422180175781 nb_pixel_total : 3647 time to create 1 rle with old method : 0.004385471343994141 length of segment : 65 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 658 time to create 1 rle with old method : 0.0007977485656738281 length of segment : 64 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0010161399841308594 length of segment : 27 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0005154609680175781 length of segment : 25 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0005784034729003906 length of segment : 32 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0006427764892578125 length of segment : 20 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0004966259002685547 length of segment : 23 time for calcul the mask position with numpy : 0.00010228157043457031 nb_pixel_total : 1919 time to create 1 rle with old method : 0.0033943653106689453 length of segment : 49 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00039124488830566406 length of segment : 18 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0005292892456054688 length of segment : 17 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.0006747245788574219 length of segment : 48 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 750 time to create 1 rle with old method : 0.0014233589172363281 length of segment : 59 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1225 time to create 1 rle with old method : 0.002130270004272461 length of segment : 41 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0014116764068603516 length of segment : 34 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0008535385131835938 length of segment : 31 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 867 time to create 1 rle with old method : 0.0015158653259277344 length of segment : 34 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.0006029605865478516 length of segment : 21 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 2133 time to create 1 rle with old method : 0.00261688232421875 length of segment : 83 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1298 time to create 1 rle with old method : 0.0016357898712158203 length of segment : 60 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 593 time to create 1 rle with old method : 0.00081634521484375 length of segment : 28 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 2495 time to create 1 rle with old method : 0.002898693084716797 length of segment : 63 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 3132 time to create 1 rle with old method : 0.005574464797973633 length of segment : 55 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1264 time to create 1 rle with old method : 0.0015077590942382812 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.03984 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 717 time to create 1 rle with old method : 0.0022292137145996094 length of segment : 40 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0007708072662353516 length of segment : 24 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 2288 time to create 1 rle with old method : 0.003820657730102539 length of segment : 84 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0007545948028564453 length of segment : 41 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0009875297546386719 length of segment : 29 time for calcul the mask position with numpy : 0.00013780593872070312 nb_pixel_total : 1306 time to create 1 rle with old method : 0.002221822738647461 length of segment : 46 time for calcul the mask position with numpy : 0.00011491775512695312 nb_pixel_total : 1663 time to create 1 rle with old method : 0.0024662017822265625 length of segment : 43 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0005052089691162109 length of segment : 14 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 887 time to create 1 rle with old method : 0.0016176700592041016 length of segment : 82 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 19 time to create 1 rle with old method : 0.00021409988403320312 length of segment : 4 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 458 time to create 1 rle with old method : 0.0010695457458496094 length of segment : 21 time for calcul the mask position with numpy : 0.0001442432403564453 nb_pixel_total : 2510 time to create 1 rle with old method : 0.0044934749603271484 length of segment : 51 time for calcul the mask position with numpy : 0.00023555755615234375 nb_pixel_total : 3527 time to create 1 rle with old method : 0.006203413009643555 length of segment : 77 time for calcul the mask position with numpy : 0.00020265579223632812 nb_pixel_total : 833 time to create 1 rle with old method : 0.0019385814666748047 length of segment : 48 time for calcul the mask position with numpy : 0.0001742839813232422 nb_pixel_total : 1932 time to create 1 rle with old method : 0.0039560794830322266 length of segment : 58 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0006995201110839844 length of segment : 26 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00032210350036621094 length of segment : 16 time for calcul the mask position with numpy : 0.0002963542938232422 nb_pixel_total : 1523 time to create 1 rle with old method : 0.005460262298583984 length of segment : 42 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.0007321834564208984 length of segment : 23 time for calcul the mask position with numpy : 0.00010776519775390625 nb_pixel_total : 306 time to create 1 rle with old method : 0.0009555816650390625 length of segment : 16 time for calcul the mask position with numpy : 0.0003788471221923828 nb_pixel_total : 6925 time to create 1 rle with old method : 0.011313438415527344 length of segment : 115 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 38 time to create 1 rle with old method : 0.00031876564025878906 length of segment : 16 time for calcul the mask position with numpy : 0.00015854835510253906 nb_pixel_total : 762 time to create 1 rle with old method : 0.0022547245025634766 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.91094 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 23 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.0003800392150878906 length of segment : 13 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.0007312297821044922 length of segment : 31 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 38 time to create 1 rle with old method : 0.00019621849060058594 length of segment : 23 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 200.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 92.26016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 1228 time to create 1 rle with old method : 0.002708911895751953 length of segment : 96 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.99688 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0006930828094482422 length of segment : 24 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0005261898040771484 length of segment : 22 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0005025863647460938 length of segment : 23 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00032591819763183594 length of segment : 17 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.000301361083984375 length of segment : 15 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 825 time to create 1 rle with old method : 0.0012586116790771484 length of segment : 38 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0005218982696533203 length of segment : 13 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 966 time to create 1 rle with old method : 0.0017371177673339844 length of segment : 25 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0004520416259765625 length of segment : 27 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0007555484771728516 length of segment : 28 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 699 time to create 1 rle with old method : 0.0013294219970703125 length of segment : 29 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.000232696533203125 length of segment : 16 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.0005080699920654297 length of segment : 12 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 980 time to create 1 rle with old method : 0.002166748046875 length of segment : 26 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.0005567073822021484 length of segment : 13 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0005059242248535156 length of segment : 17 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 141 time to create 1 rle with old method : 0.0006220340728759766 length of segment : 11 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.16094 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 35 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0018901824951171875 length of segment : 45 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0005431175231933594 length of segment : 20 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0011157989501953125 length of segment : 31 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0007128715515136719 length of segment : 27 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 932 time to create 1 rle with old method : 0.0015864372253417969 length of segment : 36 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.001499176025390625 length of segment : 42 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 847 time to create 1 rle with old method : 0.001626729965209961 length of segment : 34 time for calcul the mask position with numpy : 0.00012063980102539062 nb_pixel_total : 306 time to create 1 rle with old method : 0.0009610652923583984 length of segment : 22 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0007817745208740234 length of segment : 31 time for calcul the mask position with numpy : 0.00026798248291015625 nb_pixel_total : 2778 time to create 1 rle with old method : 0.004645347595214844 length of segment : 102 time for calcul the mask position with numpy : 0.00016880035400390625 nb_pixel_total : 1387 time to create 1 rle with old method : 0.0019497871398925781 length of segment : 107 time for calcul the mask position with numpy : 0.0001468658447265625 nb_pixel_total : 2011 time to create 1 rle with old method : 0.0029740333557128906 length of segment : 128 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 866 time to create 1 rle with old method : 0.001458883285522461 length of segment : 38 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0011708736419677734 length of segment : 45 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0011403560638427734 length of segment : 25 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1043 time to create 1 rle with old method : 0.0017628669738769531 length of segment : 32 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0006530284881591797 length of segment : 16 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 863 time to create 1 rle with old method : 0.0014748573303222656 length of segment : 26 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 1111 time to create 1 rle with old method : 0.0024042129516601562 length of segment : 45 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 875 time to create 1 rle with old method : 0.00140380859375 length of segment : 73 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1217 time to create 1 rle with old method : 0.0014116764068603516 length of segment : 43 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 538 time to create 1 rle with old method : 0.0007090568542480469 length of segment : 32 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0013186931610107422 length of segment : 84 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 708 time to create 1 rle with old method : 0.0011124610900878906 length of segment : 58 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.00033926963806152344 length of segment : 25 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002598762512207031 length of segment : 10 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.00028586387634277344 length of segment : 18 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0007016658782958984 length of segment : 16 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1247 time to create 1 rle with old method : 0.00154876708984375 length of segment : 45 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 955 time to create 1 rle with old method : 0.0012505054473876953 length of segment : 44 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 980 time to create 1 rle with old method : 0.0015869140625 length of segment : 39 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 2277 time to create 1 rle with old method : 0.0028221607208251953 length of segment : 65 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 623 time to create 1 rle with old method : 0.0008435249328613281 length of segment : 33 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 968 time to create 1 rle with old method : 0.001226663589477539 length of segment : 40 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005469322204589844 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.13359 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 33 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0007851123809814453 length of segment : 31 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 511 time to create 1 rle with old method : 0.0009355545043945312 length of segment : 23 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006341934204101562 length of segment : 32 time for calcul the mask position with numpy : 0.00019240379333496094 nb_pixel_total : 3150 time to create 1 rle with old method : 0.0038352012634277344 length of segment : 184 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0008909702301025391 length of segment : 33 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00041484832763671875 length of segment : 24 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003972053527832031 length of segment : 16 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0004622936248779297 length of segment : 22 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1372 time to create 1 rle with old method : 0.002517223358154297 length of segment : 49 time for calcul the mask position with numpy : 0.00010180473327636719 nb_pixel_total : 3422 time to create 1 rle with old method : 0.004909992218017578 length of segment : 85 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.0002498626708984375 length of segment : 14 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005388259887695312 length of segment : 22 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.001129150390625 length of segment : 33 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.00028204917907714844 length of segment : 14 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.001127481460571289 length of segment : 38 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.00034737586975097656 length of segment : 20 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0004951953887939453 length of segment : 20 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 3547 time to create 1 rle with old method : 0.0051157474517822266 length of segment : 62 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.00043702125549316406 length of segment : 16 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 1385 time to create 1 rle with old method : 0.0022683143615722656 length of segment : 49 time for calcul the mask position with numpy : 0.00011157989501953125 nb_pixel_total : 2377 time to create 1 rle with old method : 0.003618955612182617 length of segment : 89 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003895759582519531 length of segment : 23 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.00046634674072265625 length of segment : 29 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003337860107421875 length of segment : 50 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 691 time to create 1 rle with old method : 0.0008747577667236328 length of segment : 37 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0008308887481689453 length of segment : 30 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0004012584686279297 length of segment : 19 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 1500 time to create 1 rle with old method : 0.0019381046295166016 length of segment : 69 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005276203155517578 length of segment : 32 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005166530609130859 length of segment : 23 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1652 time to create 1 rle with old method : 0.002189159393310547 length of segment : 45 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1673 time to create 1 rle with old method : 0.0024950504302978516 length of segment : 49 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 1519 time to create 1 rle with old method : 0.0020182132720947266 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: -123.06719 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 51 time for calcul the mask position with numpy : 9.703636169433594e-05 nb_pixel_total : 529 time to create 1 rle with old method : 0.0007297992706298828 length of segment : 40 time for calcul the mask position with numpy : 0.00016307830810546875 nb_pixel_total : 4999 time to create 1 rle with old method : 0.006334066390991211 length of segment : 117 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 2175 time to create 1 rle with old method : 0.002594470977783203 length of segment : 64 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006844997406005859 length of segment : 45 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 696 time to create 1 rle with old method : 0.0009033679962158203 length of segment : 39 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005087852478027344 length of segment : 26 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00034999847412109375 length of segment : 20 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.00047016143798828125 length of segment : 17 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0012903213500976562 length of segment : 42 time for calcul the mask position with numpy : 0.00013256072998046875 nb_pixel_total : 1128 time to create 1 rle with old method : 0.002610445022583008 length of segment : 62 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 521 time to create 1 rle with old method : 0.0007326602935791016 length of segment : 30 time for calcul the mask position with numpy : 0.0003247261047363281 nb_pixel_total : 7564 time to create 1 rle with old method : 0.013038158416748047 length of segment : 104 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1556 time to create 1 rle with old method : 0.001956462860107422 length of segment : 36 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0005648136138916016 length of segment : 17 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1472 time to create 1 rle with old method : 0.0022766590118408203 length of segment : 52 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 994 time to create 1 rle with old method : 0.0013842582702636719 length of segment : 41 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004696846008300781 length of segment : 23 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00035762786865234375 length of segment : 14 time for calcul the mask position with numpy : 0.00015020370483398438 nb_pixel_total : 3036 time to create 1 rle with old method : 0.0040585994720458984 length of segment : 95 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1374 time to create 1 rle with old method : 0.0016956329345703125 length of segment : 59 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0006594657897949219 length of segment : 39 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0005671977996826172 length of segment : 20 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0008156299591064453 length of segment : 52 time for calcul the mask position with numpy : 0.000156402587890625 nb_pixel_total : 1537 time to create 1 rle with old method : 0.001957416534423828 length of segment : 63 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 804 time to create 1 rle with old method : 0.001117706298828125 length of segment : 30 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00025463104248046875 length of segment : 8 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1402 time to create 1 rle with old method : 0.0016646385192871094 length of segment : 58 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0010647773742675781 length of segment : 30 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 1567 time to create 1 rle with old method : 0.002222299575805664 length of segment : 68 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00038743019104003906 length of segment : 21 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0009262561798095703 length of segment : 35 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004076957702636719 length of segment : 32 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0009770393371582031 length of segment : 31 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003504753112792969 length of segment : 24 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0003523826599121094 length of segment : 53 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1563 time to create 1 rle with old method : 0.0018303394317626953 length of segment : 62 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0010733604431152344 length of segment : 18 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.0005500316619873047 length of segment : 20 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0007078647613525391 length of segment : 38 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0004394054412841797 length of segment : 28 time for calcul the mask position with numpy : 0.00012636184692382812 nb_pixel_total : 4079 time to create 1 rle with old method : 0.004887819290161133 length of segment : 121 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0006353855133056641 length of segment : 28 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.00039267539978027344 length of segment : 13 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00039839744567871094 length of segment : 47 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.00023293495178222656 length of segment : 26 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 2793 time to create 1 rle with old method : 0.004244565963745117 length of segment : 59 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.0008652210235595703 length of segment : 19 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 991 time to create 1 rle with old method : 0.0013327598571777344 length of segment : 45 time for calcul the mask position with numpy : 8.940696716308594e-05 nb_pixel_total : 951 time to create 1 rle with old method : 0.0018591880798339844 length of segment : 40 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0009970664978027344 length of segment : 42 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 2885 time to create 1 rle with old method : 0.0033812522888183594 length of segment : 65 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.62578 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 30 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0006821155548095703 length of segment : 31 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0004241466522216797 length of segment : 21 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00045418739318847656 length of segment : 21 time for calcul the mask position with numpy : 0.0001220703125 nb_pixel_total : 1783 time to create 1 rle with old method : 0.0023512840270996094 length of segment : 72 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 1620 time to create 1 rle with old method : 0.0024089813232421875 length of segment : 57 time for calcul the mask position with numpy : 0.00011420249938964844 nb_pixel_total : 1658 time to create 1 rle with old method : 0.0021820068359375 length of segment : 67 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0005745887756347656 length of segment : 24 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0007193088531494141 length of segment : 62 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0009570121765136719 length of segment : 42 time for calcul the mask position with numpy : 0.0001266002655029297 nb_pixel_total : 3214 time to create 1 rle with old method : 0.005005359649658203 length of segment : 76 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 1968 time to create 1 rle with old method : 0.002555370330810547 length of segment : 54 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00030875205993652344 length of segment : 20 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 2405 time to create 1 rle with old method : 0.002911090850830078 length of segment : 60 time for calcul the mask position with numpy : 0.000179290771484375 nb_pixel_total : 2183 time to create 1 rle with old method : 0.002965211868286133 length of segment : 130 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005848407745361328 length of segment : 25 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 894 time to create 1 rle with old method : 0.0011129379272460938 length of segment : 58 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 748 time to create 1 rle with old method : 0.0010175704956054688 length of segment : 46 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0005853176116943359 length of segment : 29 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00020885467529296875 length of segment : 18 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 743 time to create 1 rle with old method : 0.000978231430053711 length of segment : 40 time for calcul the mask position with numpy : 0.0001327991485595703 nb_pixel_total : 910 time to create 1 rle with old method : 0.0017001628875732422 length of segment : 87 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 2405 time to create 1 rle with old method : 0.004522085189819336 length of segment : 54 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.0007367134094238281 length of segment : 22 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1975 time to create 1 rle with old method : 0.002561330795288086 length of segment : 53 time for calcul the mask position with numpy : 0.00013947486877441406 nb_pixel_total : 2243 time to create 1 rle with old method : 0.0033745765686035156 length of segment : 96 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 2027 time to create 1 rle with old method : 0.003058910369873047 length of segment : 91 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.00044608116149902344 length of segment : 19 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1778 time to create 1 rle with old method : 0.0022721290588378906 length of segment : 51 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 2057 time to create 1 rle with old method : 0.002405881881713867 length of segment : 84 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 2015 time to create 1 rle with old method : 0.0027549266815185547 length of segment : 56 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.78594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005247592926025391 length of segment : 22 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 67 time to create 1 rle with old method : 0.00021266937255859375 length of segment : 27 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1267 time to create 1 rle with old method : 0.0015361309051513672 length of segment : 59 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.0007560253143310547 length of segment : 31 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 53 time to create 1 rle with old method : 9.822845458984375e-05 length of segment : 12 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1093 time to create 1 rle with old method : 0.0014107227325439453 length of segment : 33 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1379 time to create 1 rle with old method : 0.0018651485443115234 length of segment : 57 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1681 time to create 1 rle with old method : 0.002105236053466797 length of segment : 58 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0009551048278808594 length of segment : 25 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1305 time to create 1 rle with old method : 0.002044677734375 length of segment : 42 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 179.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 69.74844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.01797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 1576 time to create 1 rle with old method : 0.0036110877990722656 length of segment : 39 time for calcul the mask position with numpy : 0.0007054805755615234 nb_pixel_total : 53100 time to create 1 rle with old method : 0.06415176391601562 length of segment : 220 Processing 1 images image shape: (240, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00024437904357910156 length of segment : 18 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00023627281188964844 length of segment : 9 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.00016760826110839844 length of segment : 16 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.00042319297790527344 length of segment : 18 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 927 time to create 1 rle with old method : 0.001210927963256836 length of segment : 42 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.0002071857452392578 length of segment : 5 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 676 time to create 1 rle with old method : 0.0009181499481201172 length of segment : 27 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006406307220458984 length of segment : 21 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00020074844360351562 length of segment : 14 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.00017309188842773438 length of segment : 15 time for calcul the mask position with numpy : 0.00013065338134765625 nb_pixel_total : 4707 time to create 1 rle with old method : 0.00644993782043457 length of segment : 103 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 31 time to create 1 rle with old method : 0.00011229515075683594 length of segment : 9 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00013828277587890625 length of segment : 7 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 487 time to create 1 rle with old method : 0.0007166862487792969 length of segment : 27 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1576 time to create 1 rle with old method : 0.0033605098724365234 length of segment : 46 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 1528 time to create 1 rle with old method : 0.002741575241088867 length of segment : 35 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 2284 time to create 1 rle with old method : 0.0028638839721679688 length of segment : 71 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.0003294944763183594 length of segment : 22 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0006127357482910156 length of segment : 19 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1383 time to create 1 rle with old method : 0.0016477108001708984 length of segment : 43 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0007326602935791016 length of segment : 32 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 2101 time to create 1 rle with old method : 0.0027685165405273438 length of segment : 53 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006697177886962891 length of segment : 30 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.00040340423583984375 length of segment : 25 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0007815361022949219 length of segment : 23 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 778 time to create 1 rle with old method : 0.0010476112365722656 length of segment : 32 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0004477500915527344 length of segment : 24 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0005326271057128906 length of segment : 17 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002956390380859375 length of segment : 27 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0004994869232177734 length of segment : 30 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1767 time to create 1 rle with old method : 0.0036461353302001953 length of segment : 61 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.00034356117248535156 length of segment : 21 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.0002295970916748047 length of segment : 20 time for calcul the mask position with numpy : 0.00015854835510253906 nb_pixel_total : 5898 time to create 1 rle with old method : 0.009056568145751953 length of segment : 144 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005583763122558594 length of segment : 26 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0004668235778808594 length of segment : 16 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.0005021095275878906 length of segment : 21 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1546 time to create 1 rle with old method : 0.0019447803497314453 length of segment : 76 time for calcul the mask position with numpy : 0.0001285076141357422 nb_pixel_total : 1717 time to create 1 rle with old method : 0.0032286643981933594 length of segment : 72 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0006997585296630859 length of segment : 24 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1158 time to create 1 rle with old method : 0.0016753673553466797 length of segment : 33 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.0003991127014160156 length of segment : 22 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1468 time to create 1 rle with old method : 0.002046346664428711 length of segment : 49 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.0003662109375 length of segment : 21 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 636 time to create 1 rle with old method : 0.0008208751678466797 length of segment : 19 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 2530 time to create 1 rle with old method : 0.0029854774475097656 length of segment : 55 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 561 time to create 1 rle with old method : 0.0008060932159423828 length of segment : 30 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0006463527679443359 length of segment : 21 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0006344318389892578 length of segment : 53 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005557537078857422 length of segment : 21 time for calcul the mask position with numpy : 0.00012183189392089844 nb_pixel_total : 2363 time to create 1 rle with old method : 0.0030412673950195312 length of segment : 49 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0002353191375732422 length of segment : 10 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 0.00012302398681640625 nb_pixel_total : 1826 time to create 1 rle with old method : 0.003057718276977539 length of segment : 43 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.0002295970916748047 length of segment : 13 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005414485931396484 length of segment : 35 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.000701904296875 length of segment : 28 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0005519390106201172 length of segment : 22 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0006337165832519531 length of segment : 17 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0006709098815917969 length of segment : 25 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0003211498260498047 length of segment : 14 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002579689025878906 length of segment : 11 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.0002620220184326172 length of segment : 20 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002818107604980469 length of segment : 10 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 488 time to create 1 rle with old method : 0.0012738704681396484 length of segment : 27 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003414154052734375 length of segment : 21 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.00017571449279785156 length of segment : 24 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 415 time to create 1 rle with old method : 0.0006022453308105469 length of segment : 24 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00022649765014648438 length of segment : 14 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0007214546203613281 nb_pixel_total : 40914 time to create 1 rle with old method : 0.05604219436645508 length of segment : 353 time for calcul the mask position with numpy : 0.00012159347534179688 nb_pixel_total : 3326 time to create 1 rle with old method : 0.00547027587890625 length of segment : 51 time for calcul the mask position with numpy : 0.0002624988555908203 nb_pixel_total : 14257 time to create 1 rle with old method : 0.022740602493286133 length of segment : 103 Processing 1 images image shape: (240, 160, 3) min: 0.00000 max: 229.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 120.17019 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.00041794776916503906 length of segment : 19 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: -122.27813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1568 time to create 1 rle with old method : 0.0018801689147949219 length of segment : 45 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.00039505958557128906 length of segment : 18 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00030159950256347656 length of segment : 17 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1007 time to create 1 rle with old method : 0.0012054443359375 length of segment : 54 time for calcul the mask position with numpy : 0.00012540817260742188 nb_pixel_total : 3569 time to create 1 rle with old method : 0.004186868667602539 length of segment : 140 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1756 time to create 1 rle with old method : 0.002405405044555664 length of segment : 64 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1738 time to create 1 rle with old method : 0.002162456512451172 length of segment : 62 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 387 time to create 1 rle with old method : 0.0007266998291015625 length of segment : 23 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0009417533874511719 length of segment : 35 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0006968975067138672 length of segment : 27 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0006546974182128906 length of segment : 30 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0007607936859130859 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -107.01250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0007083415985107422 length of segment : 16 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.00022649765014648438 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 13.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -96.17656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 1040 time to create 1 rle with old method : 0.0019440650939941406 length of segment : 36 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00030517578125 length of segment : 8 Processing 1 images image shape: (400, 400, 3) min: 23.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -88.57891 max: 149.37734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0003960132598876953 length of segment : 16 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0005028247833251953 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -98.22344 max: 150.85391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.0002541542053222656 length of segment : 14 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1543 time to create 1 rle with old method : 0.003092050552368164 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 227.00000 molded_images shape: (1, 640, 640, 3) min: -110.98125 max: 113.49844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 161.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 55.64297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00016069412231445312 nb_pixel_total : 8624 time to create 1 rle with old method : 0.009727716445922852 length of segment : 230 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.86406 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1332 time to create 1 rle with old method : 0.0016019344329833984 length of segment : 48 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 3768 time to create 1 rle with old method : 0.004580497741699219 length of segment : 69 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 986 time to create 1 rle with old method : 0.001306772232055664 length of segment : 47 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 857 time to create 1 rle with old method : 0.0011856555938720703 length of segment : 23 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0003020763397216797 length of segment : 20 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1761 time to create 1 rle with old method : 0.0020291805267333984 length of segment : 64 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003590583801269531 length of segment : 28 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0004894733428955078 length of segment : 25 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0007214546203613281 length of segment : 52 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0004730224609375 length of segment : 34 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0007407665252685547 length of segment : 29 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 763 time to create 1 rle with old method : 0.000949859619140625 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.59063 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0006501674652099609 length of segment : 33 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.00037789344787597656 length of segment : 19 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003693103790283203 length of segment : 24 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 599 time to create 1 rle with old method : 0.0007233619689941406 length of segment : 34 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1520 time to create 1 rle with old method : 0.0019192695617675781 length of segment : 41 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0004165172576904297 length of segment : 21 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00024080276489257812 length of segment : 14 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 662 time to create 1 rle with old method : 0.0008828639984130859 length of segment : 33 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005929470062255859 length of segment : 35 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004329681396484375 length of segment : 24 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006868839263916016 length of segment : 28 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 586 time to create 1 rle with old method : 0.0008268356323242188 length of segment : 41 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002543926239013672 length of segment : 16 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.00046372413635253906 length of segment : 22 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1088 time to create 1 rle with old method : 0.0014216899871826172 length of segment : 35 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0004661083221435547 length of segment : 36 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.00044345855712890625 length of segment : 22 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0004949569702148438 length of segment : 27 time for calcul the mask position with numpy : 0.00011754035949707031 nb_pixel_total : 1867 time to create 1 rle with old method : 0.0023827552795410156 length of segment : 38 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00027370452880859375 length of segment : 22 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 785 time to create 1 rle with old method : 0.0009813308715820312 length of segment : 29 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.000255584716796875 length of segment : 16 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1857 time to create 1 rle with old method : 0.0022389888763427734 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.96563 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 : 5.7220458984375e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.00045108795166015625 length of segment : 29 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.00029778480529785156 length of segment : 24 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 774 time to create 1 rle with old method : 0.0010232925415039062 length of segment : 24 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002884864807128906 length of segment : 19 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1124 time to create 1 rle with old method : 0.0013623237609863281 length of segment : 47 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005636215209960938 length of segment : 18 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0003039836883544922 length of segment : 19 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.0009131431579589844 length of segment : 36 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00020933151245117188 length of segment : 14 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004248619079589844 length of segment : 20 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 526 time to create 1 rle with old method : 0.0006985664367675781 length of segment : 23 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006146430969238281 length of segment : 32 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0007331371307373047 length of segment : 28 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006277561187744141 length of segment : 29 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.0002079010009765625 length of segment : 7 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002295970916748047 length of segment : 16 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00023674964904785156 length of segment : 12 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1747 time to create 1 rle with old method : 0.0020475387573242188 length of segment : 68 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.00048160552978515625 length of segment : 34 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0004258155822753906 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 38 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 1801 time to create 1 rle with old method : 0.0029494762420654297 length of segment : 57 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005812644958496094 length of segment : 20 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 1122 time to create 1 rle with old method : 0.0019047260284423828 length of segment : 39 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 488 time to create 1 rle with old method : 0.0006439685821533203 length of segment : 35 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 937 time to create 1 rle with old method : 0.0012631416320800781 length of segment : 36 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 680 time to create 1 rle with old method : 0.0009019374847412109 length of segment : 78 time for calcul the mask position with numpy : 0.00019478797912597656 nb_pixel_total : 3699 time to create 1 rle with old method : 0.004742622375488281 length of segment : 74 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0013713836669921875 length of segment : 36 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 982 time to create 1 rle with old method : 0.0013685226440429688 length of segment : 27 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0007035732269287109 length of segment : 13 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0007927417755126953 length of segment : 24 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0003001689910888672 length of segment : 19 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0006437301635742188 length of segment : 25 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0006394386291503906 length of segment : 21 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.0016846656799316406 length of segment : 51 time for calcul the mask position with numpy : 0.00012302398681640625 nb_pixel_total : 3640 time to create 1 rle with old method : 0.0051729679107666016 length of segment : 68 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 1930 time to create 1 rle with old method : 0.002316713333129883 length of segment : 67 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005364418029785156 length of segment : 25 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 584 time to create 1 rle with old method : 0.0007727146148681641 length of segment : 27 time for calcul the mask position with numpy : 0.0001513957977294922 nb_pixel_total : 2384 time to create 1 rle with old method : 0.0030438899993896484 length of segment : 73 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 649 time to create 1 rle with old method : 0.0012145042419433594 length of segment : 53 time for calcul the mask position with numpy : 0.00020384788513183594 nb_pixel_total : 4174 time to create 1 rle with old method : 0.006993293762207031 length of segment : 76 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0016248226165771484 length of segment : 34 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 3077 time to create 1 rle with old method : 0.003751039505004883 length of segment : 55 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007355213165283203 length of segment : 29 time for calcul the mask position with numpy : 0.000133514404296875 nb_pixel_total : 3446 time to create 1 rle with old method : 0.004179239273071289 length of segment : 66 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.0002818107604980469 length of segment : 15 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.0009257793426513672 length of segment : 38 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1266 time to create 1 rle with old method : 0.0015103816986083984 length of segment : 38 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 793 time to create 1 rle with old method : 0.0010139942169189453 length of segment : 29 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 503 time to create 1 rle with old method : 0.0006663799285888672 length of segment : 23 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00025200843811035156 length of segment : 16 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 2122 time to create 1 rle with old method : 0.002492666244506836 length of segment : 57 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002727508544921875 length of segment : 18 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 674 time to create 1 rle with old method : 0.0008971691131591797 length of segment : 42 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 389 time to create 1 rle with old method : 0.00051116943359375 length of segment : 27 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0005278587341308594 length of segment : 31 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005421638488769531 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.37969 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0009436607360839844 length of segment : 33 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 677 time to create 1 rle with old method : 0.00093841552734375 length of segment : 37 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.00047850608825683594 length of segment : 17 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0006387233734130859 length of segment : 23 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0010712146759033203 length of segment : 26 time for calcul the mask position with numpy : 5.626678466796875e-05 2025-02-18 10:20:54.208026: 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 2025-02-18 10:20:54.208084: 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 ! 22.32user 17.24system 1:00:07elapsed 1%CPU (0avgtext+0avgdata 2360868maxresident)k 614024inputs+2536outputs (8745major+771141minor)pagefaults 0swaps