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 : 1853017 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 : ['2647495'] with mtr_portfolio_ids : ['21136960'] and first list_photo_ids : [] new path : /proc/1853017/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.6698217391967773 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 Fri Mar 7 09:20:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10372 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-07 09:20:33.827635: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-07 09:20:33.855175: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-07 09:20:33.857173: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f3074000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-07 09:20:33.857217: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-07 09:20:33.861560: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-07 09:20:34.188225: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x37945560 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-07 09:20:34.188328: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-07 09:20:34.189973: 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 2025-03-07 09:20:34.191307: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 09:20:34.197608: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 09:20:34.200912: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 09:20:34.202098: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 09:20:34.206410: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 09:20:34.208689: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 09:20:34.217420: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 09:20:34.219501: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 09:20:34.219620: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 09:20:34.220643: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 09:20:34.220664: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 09:20:34.220675: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 09:20:34.222484: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9607 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. 2025-03-07 09:20:34.538687: 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 2025-03-07 09:20:34.538804: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 09:20:34.538831: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 09:20:34.538855: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 09:20:34.538877: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 09:20:34.538915: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 09:20:34.538943: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 09:20:34.538967: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 09:20:34.540641: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 09:20:34.542138: 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 2025-03-07 09:20:34.542257: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 09:20:34.542290: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 09:20:34.542317: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 09:20:34.542346: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 09:20:34.542376: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 09:20:34.542401: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 09:20:34.542426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 09:20:34.544081: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 09:20:34.544134: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 09:20:34.544149: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 09:20:34.544160: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 09:20:34.545883: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9607 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 : [] 2025-03-07 09:20:45.794737: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 09:20:46.116493: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 09:20:48.352930: 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 2025-03-07 09:20:48.353918: 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 2025-03-07 09:20:49.414191: 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 2025-03-07 09:20:49.414638: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-03-07 09:20:49.494922: 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 2025-03-07 09:20:49.495054: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 09:20:49.496143: 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 2025-03-07 09:20:49.496174: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 09:20:49.504034: 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 2025-03-07 09:20:49.504113: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 09:20:49.504921: 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 2025-03-07 09:20:49.504948: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 09:20:49.573073: 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 2025-03-07 09:20:49.573221: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 09:20:49.574459: 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 2025-03-07 09:20:49.574487: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 09:20:49.575680: 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 2025-03-07 09:20:49.575703: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB 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. 2025-03-07 09:20:49.576865: 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 2025-03-07 09:20:49.576889: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB 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. 2025-03-07 09:20:49.587728: 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 2025-03-07 09:20:49.587800: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 417.62MiB 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. 2025-03-07 09:20:49.588684: 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 2025-03-07 09:20:49.588717: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 417.62MiB 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. 2025-03-07 09:20:49.613241: 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 2025-03-07 09:20:49.614197: 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 2025-03-07 09:20:49.615063: 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 2025-03-07 09:20:49.615937: 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 2025-03-07 09:20:49.620399: 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 2025-03-07 09:20:49.621290: 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 2025-03-07 09:20:49.622175: 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 2025-03-07 09:20:49.623091: 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 2025-03-07 09:20:49.625735: 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 2025-03-07 09:20:49.625786: 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. 2025-03-07 09:20:49.634766: 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 2025-03-07 09:20:49.635667: 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 2025-03-07 09:20:49.645723: 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 2025-03-07 09:20:49.646711: 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 2025-03-07 09:20:49.647559: 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 2025-03-07 09:20:49.648454: 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 2025-03-07 09:20:49.649336: 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 2025-03-07 09:20:49.650167: 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 : 4 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.17656 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 : 0.00015234947204589844 nb_pixel_total : 374 time to create 1 rle with old method : 0.0025129318237304688 length of segment : 30 time for calcul the mask position with numpy : 8.940696716308594e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0011723041534423828 length of segment : 37 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0008540153503417969 length of segment : 29 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1737 time to create 1 rle with old method : 0.0025091171264648438 length of segment : 42 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1810 time to create 1 rle with old method : 0.0024955272674560547 length of segment : 87 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 1085 time to create 1 rle with old method : 0.001621246337890625 length of segment : 74 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0007562637329101562 length of segment : 23 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.0004525184631347656 length of segment : 28 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0011909008026123047 length of segment : 57 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0005185604095458984 length of segment : 19 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0004496574401855469 length of segment : 18 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0007228851318359375 length of segment : 31 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0007314682006835938 length of segment : 39 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0008215904235839844 length of segment : 24 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1056 time to create 1 rle with old method : 0.001760721206665039 length of segment : 49 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.002085447311401367 length of segment : 35 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.17656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 0.0001270771026611328 nb_pixel_total : 461 time to create 1 rle with old method : 0.0011172294616699219 length of segment : 28 time for calcul the mask position with numpy : 0.0001678466796875 nb_pixel_total : 3716 time to create 1 rle with old method : 0.007569789886474609 length of segment : 87 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0014429092407226562 length of segment : 27 time for calcul the mask position with numpy : 0.0001666545867919922 nb_pixel_total : 3888 time to create 1 rle with old method : 0.008039236068725586 length of segment : 82 time for calcul the mask position with numpy : 0.00017833709716796875 nb_pixel_total : 2139 time to create 1 rle with old method : 0.004465341567993164 length of segment : 56 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0005514621734619141 length of segment : 13 time for calcul the mask position with numpy : 0.00010728836059570312 nb_pixel_total : 1821 time to create 1 rle with old method : 0.003907203674316406 length of segment : 41 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0005826950073242188 length of segment : 12 time for calcul the mask position with numpy : 0.00016164779663085938 nb_pixel_total : 3886 time to create 1 rle with old method : 0.007988452911376953 length of segment : 64 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0006759166717529297 length of segment : 29 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0005838871002197266 length of segment : 16 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0007088184356689453 length of segment : 18 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 1255 time to create 1 rle with old method : 0.002683877944946289 length of segment : 33 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0008747577667236328 length of segment : 25 time for calcul the mask position with numpy : 0.00010013580322265625 nb_pixel_total : 1712 time to create 1 rle with old method : 0.003758668899536133 length of segment : 33 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0005247592926025391 length of segment : 18 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 586 time to create 1 rle with old method : 0.001355886459350586 length of segment : 23 time for calcul the mask position with numpy : 0.00014472007751464844 nb_pixel_total : 3315 time to create 1 rle with old method : 0.00685882568359375 length of segment : 70 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 1102 time to create 1 rle with old method : 0.002524852752685547 length of segment : 34 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.0006780624389648438 length of segment : 25 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0013606548309326172 length of segment : 22 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0013587474822998047 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.46563 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 : 0.0001087188720703125 nb_pixel_total : 2541 time to create 1 rle with old method : 0.003520965576171875 length of segment : 51 time for calcul the mask position with numpy : 8.559226989746094e-05 nb_pixel_total : 1356 time to create 1 rle with old method : 0.002288341522216797 length of segment : 60 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1089 time to create 1 rle with old method : 0.0015180110931396484 length of segment : 36 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.0012447834014892578 length of segment : 26 time for calcul the mask position with numpy : 0.00011801719665527344 nb_pixel_total : 1804 time to create 1 rle with old method : 0.004980802536010742 length of segment : 45 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0004200935363769531 length of segment : 23 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1900 time to create 1 rle with old method : 0.0026378631591796875 length of segment : 56 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 15 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1303 time to create 1 rle with old method : 0.0018782615661621094 length of segment : 51 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.0002608299255371094 length of segment : 12 time for calcul the mask position with numpy : 0.00010013580322265625 nb_pixel_total : 1881 time to create 1 rle with old method : 0.0027294158935546875 length of segment : 43 time for calcul the mask position with numpy : 0.0001354217529296875 nb_pixel_total : 688 time to create 1 rle with old method : 0.0022728443145751953 length of segment : 24 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1814 time to create 1 rle with old method : 0.002562999725341797 length of segment : 43 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004894733428955078 length of segment : 36 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 2205 time to create 1 rle with old method : 0.003206491470336914 length of segment : 46 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 2169 time to create 1 rle with old method : 0.0031080245971679688 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.16094 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 38 time for calcul the mask position with numpy : 0.00012421607971191406 nb_pixel_total : 1672 time to create 1 rle with old method : 0.0022559165954589844 length of segment : 33 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004737377166748047 length of segment : 25 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.00043320655822753906 length of segment : 28 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 655 time to create 1 rle with old method : 0.0010218620300292969 length of segment : 25 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 1909 time to create 1 rle with old method : 0.0026602745056152344 length of segment : 69 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 1085 time to create 1 rle with old method : 0.0015554428100585938 length of segment : 50 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 522 time to create 1 rle with old method : 0.0007576942443847656 length of segment : 35 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00041103363037109375 length of segment : 13 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 2382 time to create 1 rle with old method : 0.003409862518310547 length of segment : 41 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 850 time to create 1 rle with old method : 0.0012674331665039062 length of segment : 47 time for calcul the mask position with numpy : 0.0001468658447265625 nb_pixel_total : 4239 time to create 1 rle with old method : 0.007029533386230469 length of segment : 58 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 914 time to create 1 rle with old method : 0.001298666000366211 length of segment : 44 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.00036025047302246094 length of segment : 13 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 984 time to create 1 rle with old method : 0.0014791488647460938 length of segment : 34 time for calcul the mask position with numpy : 0.00029921531677246094 nb_pixel_total : 9033 time to create 1 rle with old method : 0.011978387832641602 length of segment : 119 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0013306140899658203 length of segment : 30 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 1187 time to create 1 rle with old method : 0.0017333030700683594 length of segment : 53 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0007119178771972656 length of segment : 23 time for calcul the mask position with numpy : 0.00019121170043945312 nb_pixel_total : 4650 time to create 1 rle with old method : 0.006055593490600586 length of segment : 107 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 1238 time to create 1 rle with old method : 0.0018568038940429688 length of segment : 30 time for calcul the mask position with numpy : 0.00016069412231445312 nb_pixel_total : 4267 time to create 1 rle with old method : 0.0061893463134765625 length of segment : 61 time for calcul the mask position with numpy : 0.00010728836059570312 nb_pixel_total : 1495 time to create 1 rle with old method : 0.0020923614501953125 length of segment : 56 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1295 time to create 1 rle with old method : 0.0018541812896728516 length of segment : 37 time for calcul the mask position with numpy : 0.0001251697540283203 nb_pixel_total : 854 time to create 1 rle with old method : 0.00138092041015625 length of segment : 43 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.0004215240478515625 length of segment : 10 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.0008072853088378906 length of segment : 24 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 2571 time to create 1 rle with old method : 0.00370025634765625 length of segment : 63 time for calcul the mask position with numpy : 0.00013518333435058594 nb_pixel_total : 1499 time to create 1 rle with old method : 0.002137422561645508 length of segment : 77 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 1166 time to create 1 rle with old method : 0.0017986297607421875 length of segment : 27 time for calcul the mask position with numpy : 0.00020766258239746094 nb_pixel_total : 4931 time to create 1 rle with old method : 0.007014274597167969 length of segment : 121 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002410411834716797 length of segment : 18 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.001253366470336914 length of segment : 26 time for calcul the mask position with numpy : 0.00017786026000976562 nb_pixel_total : 2742 time to create 1 rle with old method : 0.0037424564361572266 length of segment : 85 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 1196 time to create 1 rle with old method : 0.0017368793487548828 length of segment : 31 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 861 time to create 1 rle with old method : 0.0013096332550048828 length of segment : 28 time for calcul the mask position with numpy : 0.00024247169494628906 nb_pixel_total : 9043 time to create 1 rle with old method : 0.011916875839233398 length of segment : 121 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0006422996520996094 length of segment : 28 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 993 time to create 1 rle with old method : 0.001506805419921875 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: -121.93438 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 : 0.00010037422180175781 nb_pixel_total : 400 time to create 1 rle with old method : 0.0008153915405273438 length of segment : 22 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 690 time to create 1 rle with old method : 0.001302957534790039 length of segment : 26 time for calcul the mask position with numpy : 0.00011491775512695312 nb_pixel_total : 716 time to create 1 rle with old method : 0.0014324188232421875 length of segment : 61 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0006630420684814453 length of segment : 21 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.00045013427734375 length of segment : 20 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00041031837463378906 length of segment : 18 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0004928112030029297 length of segment : 39 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0006411075592041016 length of segment : 29 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0007953643798828125 length of segment : 19 time for calcul the mask position with numpy : 0.00012445449829101562 nb_pixel_total : 1601 time to create 1 rle with old method : 0.0029592514038085938 length of segment : 48 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.0014543533325195312 length of segment : 31 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.0003268718719482422 length of segment : 16 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 1002 time to create 1 rle with old method : 0.0020499229431152344 length of segment : 41 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 463 time to create 1 rle with old method : 0.0009281635284423828 length of segment : 35 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00036978721618652344 length of segment : 12 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.0002601146697998047 length of segment : 17 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.0003292560577392578 length of segment : 22 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1268 time to create 1 rle with old method : 0.0017960071563720703 length of segment : 39 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 1537 time to create 1 rle with old method : 0.002201557159423828 length of segment : 55 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0007433891296386719 length of segment : 29 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 1457 time to create 1 rle with old method : 0.002863645553588867 length of segment : 46 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 609 time to create 1 rle with old method : 0.0012865066528320312 length of segment : 21 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0007929801940917969 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.33672 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 : 8.034706115722656e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0009772777557373047 length of segment : 24 time for calcul the mask position with numpy : 0.0001385211944580078 nb_pixel_total : 858 time to create 1 rle with old method : 0.0018684864044189453 length of segment : 44 time for calcul the mask position with numpy : 0.0004360675811767578 nb_pixel_total : 14480 time to create 1 rle with old method : 0.02677750587463379 length of segment : 178 Processing 1 images image shape: (400, 160, 3) min: 5.00000 max: 215.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 103.17812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00028395652770996094 nb_pixel_total : 7742 time to create 1 rle with old method : 0.019333362579345703 length of segment : 255 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.11406 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 : 0.00013208389282226562 nb_pixel_total : 1410 time to create 1 rle with old method : 0.002973318099975586 length of segment : 57 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 686 time to create 1 rle with old method : 0.0015976428985595703 length of segment : 24 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.0006966590881347656 length of segment : 24 time for calcul the mask position with numpy : 0.0003075599670410156 nb_pixel_total : 5044 time to create 1 rle with old method : 0.009509563446044922 length of segment : 138 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0008404254913330078 length of segment : 18 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 1668 time to create 1 rle with old method : 0.0033299922943115234 length of segment : 73 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 642 time to create 1 rle with old method : 0.0013492107391357422 length of segment : 24 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 372 time to create 1 rle with old method : 0.0009169578552246094 length of segment : 19 time for calcul the mask position with numpy : 0.00019407272338867188 nb_pixel_total : 494 time to create 1 rle with old method : 0.002362489700317383 length of segment : 25 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0004935264587402344 length of segment : 21 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.0003108978271484375 length of segment : 14 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0013287067413330078 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.27813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 0.00011277198791503906 nb_pixel_total : 2772 time to create 1 rle with old method : 0.0037322044372558594 length of segment : 86 time for calcul the mask position with numpy : 0.0001308917999267578 nb_pixel_total : 2276 time to create 1 rle with old method : 0.0031158924102783203 length of segment : 62 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.000690460205078125 length of segment : 34 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.00040221214294433594 length of segment : 20 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 612 time to create 1 rle with old method : 0.0009267330169677734 length of segment : 35 time for calcul the mask position with numpy : 0.00010037422180175781 nb_pixel_total : 2011 time to create 1 rle with old method : 0.009566307067871094 length of segment : 54 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0007951259613037109 length of segment : 29 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0007102489471435547 length of segment : 20 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 821 time to create 1 rle with old method : 0.0012276172637939453 length of segment : 51 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.000335693359375 length of segment : 23 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.00024247169494628906 length of segment : 17 time for calcul the mask position with numpy : 0.00011277198791503906 nb_pixel_total : 3028 time to create 1 rle with old method : 0.004146575927734375 length of segment : 119 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0014598369598388672 length of segment : 54 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1074 time to create 1 rle with old method : 0.0015058517456054688 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.73125 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 : 8.821487426757812e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0005373954772949219 length of segment : 45 time for calcul the mask position with numpy : 0.00012826919555664062 nb_pixel_total : 4503 time to create 1 rle with old method : 0.0060100555419921875 length of segment : 83 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1181 time to create 1 rle with old method : 0.0016372203826904297 length of segment : 41 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1198 time to create 1 rle with old method : 0.001703500747680664 length of segment : 92 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.0003924369812011719 length of segment : 11 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 1772 time to create 1 rle with old method : 0.0023698806762695312 length of segment : 52 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0009257793426513672 length of segment : 26 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1174 time to create 1 rle with old method : 0.001588582992553711 length of segment : 78 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004944801330566406 length of segment : 26 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0008616447448730469 length of segment : 25 time for calcul the mask position with numpy : 0.0001289844512939453 nb_pixel_total : 3318 time to create 1 rle with old method : 0.005538225173950195 length of segment : 63 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0006630420684814453 length of segment : 17 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1122 time to create 1 rle with old method : 0.0015850067138671875 length of segment : 41 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1334 time to create 1 rle with old method : 0.0019538402557373047 length of segment : 79 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0011587142944335938 length of segment : 62 time for calcul the mask position with numpy : 0.00013303756713867188 nb_pixel_total : 1612 time to create 1 rle with old method : 0.002791166305541992 length of segment : 58 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00028204917907714844 length of segment : 11 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1651 time to create 1 rle with old method : 0.002317667007446289 length of segment : 51 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 30 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 617 time to create 1 rle with old method : 0.0009019374847412109 length of segment : 38 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 1624 time to create 1 rle with old method : 0.0023543834686279297 length of segment : 39 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0008080005645751953 length of segment : 43 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0006971359252929688 length of segment : 31 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00019979476928710938 length of segment : 15 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0006270408630371094 length of segment : 31 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 894 time to create 1 rle with old method : 0.001300811767578125 length of segment : 74 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.00037407875061035156 length of segment : 34 time for calcul the mask position with numpy : 0.00012183189392089844 nb_pixel_total : 631 time to create 1 rle with old method : 0.0009953975677490234 length of segment : 28 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 1110 time to create 1 rle with old method : 0.0017147064208984375 length of segment : 56 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00037407875061035156 length of segment : 18 time for calcul the mask position with numpy : 0.00014400482177734375 nb_pixel_total : 2248 time to create 1 rle with old method : 0.003225564956665039 length of segment : 83 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 275 time to create 1 rle with old method : 0.0007765293121337891 length of segment : 14 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0006420612335205078 length of segment : 12 time for calcul the mask position with numpy : 0.00021386146545410156 nb_pixel_total : 2558 time to create 1 rle with old method : 0.004535198211669922 length of segment : 68 time for calcul the mask position with numpy : 0.00013589859008789062 nb_pixel_total : 800 time to create 1 rle with old method : 0.0016963481903076172 length of segment : 62 time for calcul the mask position with numpy : 0.00016164779663085938 nb_pixel_total : 2570 time to create 1 rle with old method : 0.005106449127197266 length of segment : 68 time for calcul the mask position with numpy : 0.00024580955505371094 nb_pixel_total : 3332 time to create 1 rle with old method : 0.0065059661865234375 length of segment : 69 time for calcul the mask position with numpy : 0.00019550323486328125 nb_pixel_total : 3311 time to create 1 rle with old method : 0.00635981559753418 length of segment : 62 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.01641 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 : 0.00012946128845214844 nb_pixel_total : 1870 time to create 1 rle with old method : 0.0026292800903320312 length of segment : 52 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0006198883056640625 length of segment : 20 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 2251 time to create 1 rle with old method : 0.003009319305419922 length of segment : 63 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.00020241737365722656 length of segment : 26 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0005233287811279297 length of segment : 26 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.0006301403045654297 length of segment : 37 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1040 time to create 1 rle with old method : 0.001955747604370117 length of segment : 43 time for calcul the mask position with numpy : 0.0001494884490966797 nb_pixel_total : 3932 time to create 1 rle with old method : 0.005809783935546875 length of segment : 77 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.00077056884765625 length of segment : 23 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.000640869140625 length of segment : 13 time for calcul the mask position with numpy : 0.0001456737518310547 nb_pixel_total : 4631 time to create 1 rle with old method : 0.006967782974243164 length of segment : 105 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 725 time to create 1 rle with old method : 0.0010280609130859375 length of segment : 37 time for calcul the mask position with numpy : 0.0003421306610107422 nb_pixel_total : 2207 time to create 1 rle with old method : 0.003445863723754883 length of segment : 116 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 788 time to create 1 rle with old method : 0.001168966293334961 length of segment : 31 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006735324859619141 length of segment : 34 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003726482391357422 length of segment : 16 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 909 time to create 1 rle with old method : 0.0013785362243652344 length of segment : 50 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0006897449493408203 length of segment : 24 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.0004343986511230469 length of segment : 21 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 1014 time to create 1 rle with old method : 0.0015399456024169922 length of segment : 42 time for calcul the mask position with numpy : 0.0001938343048095703 nb_pixel_total : 5959 time to create 1 rle with old method : 0.00853872299194336 length of segment : 90 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 1480 time to create 1 rle with old method : 0.0019769668579101562 length of segment : 57 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 1806 time to create 1 rle with old method : 0.0024497509002685547 length of segment : 46 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.00043010711669921875 length of segment : 13 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 538 time to create 1 rle with old method : 0.0009157657623291016 length of segment : 26 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.0003495216369628906 length of segment : 16 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.0002219676971435547 length of segment : 14 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1225 time to create 1 rle with old method : 0.0019512176513671875 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.15313 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 : 9.202957153320312e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0009613037109375 length of segment : 25 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 940 time to create 1 rle with old method : 0.0013022422790527344 length of segment : 71 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0004131793975830078 length of segment : 18 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0006160736083984375 length of segment : 23 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.00048041343688964844 length of segment : 33 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 737 time to create 1 rle with old method : 0.0010683536529541016 length of segment : 41 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0011000633239746094 length of segment : 26 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0007524490356445312 length of segment : 24 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0004801750183105469 length of segment : 16 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0004889965057373047 length of segment : 26 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0007474422454833984 length of segment : 23 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00026345252990722656 length of segment : 21 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.000957489013671875 length of segment : 29 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0008265972137451172 length of segment : 17 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 2039 time to create 1 rle with old method : 0.0028645992279052734 length of segment : 128 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0005228519439697266 length of segment : 24 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00033473968505859375 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: -121.22734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 0.00012969970703125 nb_pixel_total : 406 time to create 1 rle with old method : 0.0008361339569091797 length of segment : 36 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 651 time to create 1 rle with old method : 0.0014264583587646484 length of segment : 59 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0006306171417236328 length of segment : 30 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 405 time to create 1 rle with old method : 0.0007407665252685547 length of segment : 28 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0006053447723388672 length of segment : 24 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00030994415283203125 length of segment : 20 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002734661102294922 length of segment : 20 time for calcul the mask position with numpy : 0.0002052783966064453 nb_pixel_total : 8183 time to create 1 rle with old method : 0.010909080505371094 length of segment : 208 time for calcul the mask position with numpy : 0.00018715858459472656 nb_pixel_total : 3613 time to create 1 rle with old method : 0.0048542022705078125 length of segment : 258 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 334 time to create 1 rle with old method : 0.0005099773406982422 length of segment : 34 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00017881393432617188 length of segment : 12 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 1277 time to create 1 rle with old method : 0.0019030570983886719 length of segment : 91 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0009715557098388672 length of segment : 51 Processing 1 images image shape: (400, 160, 3) min: 5.00000 max: 236.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 112.06875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 57 time to create 1 rle with old method : 0.00020360946655273438 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.37578 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.0009610652923583984 length of segment : 55 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0006794929504394531 length of segment : 21 time for calcul the mask position with numpy : 0.00014781951904296875 nb_pixel_total : 1646 time to create 1 rle with old method : 0.0029821395874023438 length of segment : 73 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 480 time to create 1 rle with old method : 0.000682830810546875 length of segment : 37 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0005199909210205078 length of segment : 26 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1435 time to create 1 rle with old method : 0.002004384994506836 length of segment : 60 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1386 time to create 1 rle with old method : 0.0022056102752685547 length of segment : 20 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 2057 time to create 1 rle with old method : 0.002766132354736328 length of segment : 56 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 2087 time to create 1 rle with old method : 0.0030059814453125 length of segment : 52 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 729 time to create 1 rle with old method : 0.0013117790222167969 length of segment : 33 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 3146 time to create 1 rle with old method : 0.005120515823364258 length of segment : 66 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0006892681121826172 length of segment : 29 time for calcul the mask position with numpy : 8.940696716308594e-05 nb_pixel_total : 2876 time to create 1 rle with old method : 0.003989696502685547 length of segment : 74 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 829 time to create 1 rle with old method : 0.0010972023010253906 length of segment : 40 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 2547 time to create 1 rle with old method : 0.0036079883575439453 length of segment : 62 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004596710205078125 length of segment : 26 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 1389 time to create 1 rle with old method : 0.002401113510131836 length of segment : 56 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006985664367675781 length of segment : 35 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 718 time to create 1 rle with old method : 0.0010428428649902344 length of segment : 34 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.000274658203125 length of segment : 18 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1320 time to create 1 rle with old method : 0.001917123794555664 length of segment : 48 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 1742 time to create 1 rle with old method : 0.0024557113647460938 length of segment : 57 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 723 time to create 1 rle with old method : 0.0010821819305419922 length of segment : 38 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.00026702880859375 length of segment : 17 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0010192394256591797 length of segment : 41 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 1592 time to create 1 rle with old method : 0.002272367477416992 length of segment : 50 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0010755062103271484 length of segment : 18 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005974769592285156 length of segment : 35 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1108 time to create 1 rle with old method : 0.0016362667083740234 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: -122.57109 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 : 8.702278137207031e-05 nb_pixel_total : 747 time to create 1 rle with old method : 0.0010771751403808594 length of segment : 40 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0018453598022460938 length of segment : 41 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.0007109642028808594 length of segment : 56 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.001066446304321289 length of segment : 20 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0007925033569335938 length of segment : 43 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 869 time to create 1 rle with old method : 0.0012810230255126953 length of segment : 41 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1253 time to create 1 rle with old method : 0.0016787052154541016 length of segment : 49 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 801 time to create 1 rle with old method : 0.001138448715209961 length of segment : 50 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 2421 time to create 1 rle with old method : 0.0034227371215820312 length of segment : 58 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1200 time to create 1 rle with old method : 0.0017075538635253906 length of segment : 28 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 848 time to create 1 rle with old method : 0.0013043880462646484 length of segment : 36 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0007596015930175781 length of segment : 24 time for calcul the mask position with numpy : 0.00012612342834472656 nb_pixel_total : 476 time to create 1 rle with old method : 0.0010380744934082031 length of segment : 32 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0009028911590576172 length of segment : 26 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0007185935974121094 length of segment : 41 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.0013175010681152344 length of segment : 34 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 615 time to create 1 rle with old method : 0.0011556148529052734 length of segment : 38 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 574 time to create 1 rle with old method : 0.0008845329284667969 length of segment : 36 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 1589 time to create 1 rle with old method : 0.002155780792236328 length of segment : 73 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002510547637939453 length of segment : 11 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 881 time to create 1 rle with old method : 0.0012326240539550781 length of segment : 48 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 52 time to create 1 rle with old method : 0.00012254714965820312 length of segment : 11 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004482269287109375 length of segment : 23 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 831 time to create 1 rle with old method : 0.0012123584747314453 length of segment : 27 time for calcul the mask position with numpy : 0.00020194053649902344 nb_pixel_total : 2296 time to create 1 rle with old method : 0.0034742355346679688 length of segment : 61 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00032019615173339844 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.99688 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 45 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 1104 time to create 1 rle with old method : 0.0016205310821533203 length of segment : 43 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0007064342498779297 length of segment : 40 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0005304813385009766 length of segment : 23 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.0011546611785888672 length of segment : 39 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 1761 time to create 1 rle with old method : 0.002546072006225586 length of segment : 52 time for calcul the mask position with numpy : 0.00011467933654785156 nb_pixel_total : 2399 time to create 1 rle with old method : 0.0032491683959960938 length of segment : 89 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0007102489471435547 length of segment : 47 time for calcul the mask position with numpy : 0.00010895729064941406 nb_pixel_total : 2039 time to create 1 rle with old method : 0.002908945083618164 length of segment : 89 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004546642303466797 length of segment : 25 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 915 time to create 1 rle with old method : 0.0013251304626464844 length of segment : 43 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 822 time to create 1 rle with old method : 0.0012302398681640625 length of segment : 39 time for calcul the mask position with numpy : 9.465217590332031e-05 nb_pixel_total : 1111 time to create 1 rle with old method : 0.0020389556884765625 length of segment : 45 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 752 time to create 1 rle with old method : 0.0010695457458496094 length of segment : 32 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1136 time to create 1 rle with old method : 0.0016095638275146484 length of segment : 53 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.0011987686157226562 length of segment : 35 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.00030612945556640625 length of segment : 35 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.0013895034790039062 length of segment : 34 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0004904270172119141 length of segment : 19 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 1126 time to create 1 rle with old method : 0.0016236305236816406 length of segment : 37 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00021886825561523438 length of segment : 16 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1897 time to create 1 rle with old method : 0.0031251907348632812 length of segment : 62 time for calcul the mask position with numpy : 0.00010037422180175781 nb_pixel_total : 1136 time to create 1 rle with old method : 0.0017771720886230469 length of segment : 36 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 1718 time to create 1 rle with old method : 0.0025870800018310547 length of segment : 47 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0005095005035400391 length of segment : 17 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0004572868347167969 length of segment : 22 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0011909008026123047 length of segment : 30 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.000835418701171875 length of segment : 40 time for calcul the mask position with numpy : 0.0001201629638671875 nb_pixel_total : 528 time to create 1 rle with old method : 0.0008449554443359375 length of segment : 40 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0004544258117675781 length of segment : 22 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 833 time to create 1 rle with old method : 0.001210927963256836 length of segment : 34 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0007767677307128906 length of segment : 20 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 684 time to create 1 rle with old method : 0.0010089874267578125 length of segment : 37 time for calcul the mask position with numpy : 0.0001876354217529297 nb_pixel_total : 5856 time to create 1 rle with old method : 0.008112907409667969 length of segment : 107 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 1300 time to create 1 rle with old method : 0.0018048286437988281 length of segment : 45 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0006146430969238281 length of segment : 21 time for calcul the mask position with numpy : 0.00016021728515625 nb_pixel_total : 3456 time to create 1 rle with old method : 0.0048105716705322266 length of segment : 65 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0004899501800537109 length of segment : 19 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0006234645843505859 length of segment : 26 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 29 time to create 1 rle with old method : 8.130073547363281e-05 length of segment : 5 time for calcul the mask position with numpy : 0.00024890899658203125 nb_pixel_total : 10427 time to create 1 rle with old method : 0.018350601196289062 length of segment : 145 time for calcul the mask position with numpy : 0.0001251697540283203 nb_pixel_total : 970 time to create 1 rle with old method : 0.001855611801147461 length of segment : 33 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0006022453308105469 length of segment : 21 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.001641988754272461 length of segment : 32 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 1834 time to create 1 rle with old method : 0.002966642379760742 length of segment : 53 time for calcul the mask position with numpy : 0.0002589225769042969 nb_pixel_total : 10084 time to create 1 rle with old method : 0.01504063606262207 length of segment : 139 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.19219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0007541179656982422 length of segment : 28 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0009303092956542969 length of segment : 44 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0007460117340087891 length of segment : 36 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0008339881896972656 length of segment : 31 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 2120 time to create 1 rle with old method : 0.003032207489013672 length of segment : 63 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 1708 time to create 1 rle with old method : 0.002276897430419922 length of segment : 49 time for calcul the mask position with numpy : 0.00010323524475097656 nb_pixel_total : 3506 time to create 1 rle with old method : 0.004714250564575195 length of segment : 66 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0005800724029541016 length of segment : 20 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 1678 time to create 1 rle with old method : 0.0023441314697265625 length of segment : 68 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.00020265579223632812 length of segment : 11 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.000621795654296875 length of segment : 28 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0003123283386230469 length of segment : 12 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0010530948638916016 length of segment : 39 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.00043201446533203125 length of segment : 31 time for calcul the mask position with numpy : 0.0001068115234375 nb_pixel_total : 2761 time to create 1 rle with old method : 0.0039026737213134766 length of segment : 51 time for calcul the mask position with numpy : 0.00010037422180175781 nb_pixel_total : 1902 time to create 1 rle with old method : 0.0027952194213867188 length of segment : 49 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1418 time to create 1 rle with old method : 0.002531290054321289 length of segment : 44 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00022530555725097656 length of segment : 11 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 2179 time to create 1 rle with old method : 0.0031507015228271484 length of segment : 42 time for calcul the mask position with numpy : 9.703636169433594e-05 nb_pixel_total : 2626 time to create 1 rle with old method : 0.0036830902099609375 length of segment : 56 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 2156 time to create 1 rle with old method : 0.0030679702758789062 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: -121.44219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003590583801269531 length of segment : 28 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.00039386749267578125 length of segment : 29 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0008065700531005859 length of segment : 51 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0003142356872558594 length of segment : 18 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00031685829162597656 length of segment : 20 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 499 time to create 1 rle with old method : 0.0007426738739013672 length of segment : 28 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00032019615173339844 length of segment : 16 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 435 time to create 1 rle with old method : 0.0006482601165771484 length of segment : 28 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0009245872497558594 length of segment : 53 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005834102630615234 length of segment : 20 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 1601 time to create 1 rle with old method : 0.0024721622467041016 length of segment : 111 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.00017142295837402344 length of segment : 33 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.000751495361328125 length of segment : 35 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0006055831909179688 length of segment : 22 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00023651123046875 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 246.00000 molded_images shape: (1, 640, 640, 3) min: -117.21172 max: 133.75625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2158 time to create 1 rle with old method : 0.004163265228271484 length of segment : 73 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 541 time to create 1 rle with old method : 0.0010867118835449219 length of segment : 42 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0004887580871582031 length of segment : 14 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0010936260223388672 length of segment : 49 2025-03-07 09:20:56.226277: 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 2025-03-07 09:20:56.226351: 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 ! 21.07user 14.68system 1:00:07elapsed 0%CPU (0avgtext+0avgdata 2472640maxresident)k 913032inputs+4920outputs (13990major+784624minor)pagefaults 0swaps