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 : 2108438 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 : ['2647768'] with mtr_portfolio_ids : ['21137973'] and first list_photo_ids : [] new path : /proc/2108438/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.35822415351867676 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 10:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10372 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-07 10:20:31.651319: 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 10:20:31.679114: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-07 10:20:31.681511: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f3000000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-07 10:20:31.681545: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-07 10:20:31.685469: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-07 10:20:31.849523: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x353bdbb0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-07 10:20:31.849594: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-07 10:20:31.851141: 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 10:20:31.851626: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 10:20:31.854734: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 10:20:31.858235: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 10:20:31.858998: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 10:20:31.862568: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 10:20:31.864024: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 10:20:31.872687: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 10:20:31.875226: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 10:20:31.875338: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 10:20:31.876447: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 10:20:31.876463: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 10:20:31.876472: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 10:20:31.877862: 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 10:20:32.183859: 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 10:20:32.183950: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 10:20:32.183967: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 10:20:32.183983: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 10:20:32.183998: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 10:20:32.184012: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 10:20:32.184026: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 10:20:32.184041: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 10:20:32.185355: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 10:20:32.186736: 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 10:20:32.186775: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 10:20:32.186792: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 10:20:32.186807: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 10:20:32.186822: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 10:20:32.186838: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 10:20:32.186854: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 10:20:32.186867: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 10:20:32.188195: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 10:20:32.188239: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 10:20:32.188249: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 10:20:32.188256: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 10:20:32.189657: 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 10:20:42.401335: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 10:20:42.726605: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 10:20:44.738292: 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 10:20:44.739158: 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 10:20:45.602794: 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 10:20:45.602890: 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 10:20:45.686729: 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 10:20:45.686824: 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 10:20:45.687799: 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 10:20:45.687823: 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 10:20:45.697624: 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 10:20:45.697737: 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 10:20:45.698557: 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 10:20:45.698580: 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 10:20:45.761912: 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 10:20:45.761989: 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 10:20:45.763279: 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 10:20:45.763327: 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 10:20:45.776106: 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 10:20:45.776182: 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 10:20:45.777462: 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 10:20:45.777522: 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 10:20:45.801797: 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 10:20:45.801879: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 188.27MiB 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 10:20:45.803232: 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 10:20:45.803299: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 188.27MiB 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 10:20:45.804650: 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 10:20:45.806008: 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 10:20:45.812006: 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 10:20:45.813310: 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 10:20:45.814574: 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 10:20:45.815824: 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 10:20:45.818134: 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 10:20:45.818175: 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 10:20:45.829403: 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 10:20:45.830718: 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 10:20:45.843272: 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 10:20:45.844675: 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 10:20:45.846005: 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 10:20:45.847312: 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 10:20:45.848759: 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 10:20:45.850121: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 2 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 0.00022554397583007812 nb_pixel_total : 2706 time to create 1 rle with old method : 0.005083799362182617 length of segment : 76 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 913 time to create 1 rle with old method : 0.0018792152404785156 length of segment : 55 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0009288787841796875 length of segment : 33 time for calcul the mask position with numpy : 0.0001308917999267578 nb_pixel_total : 1370 time to create 1 rle with old method : 0.002764463424682617 length of segment : 46 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.00067901611328125 length of segment : 23 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0005757808685302734 length of segment : 19 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.00054168701171875 length of segment : 19 time for calcul the mask position with numpy : 0.0003006458282470703 nb_pixel_total : 10522 time to create 1 rle with old method : 0.018470048904418945 length of segment : 142 time for calcul the mask position with numpy : 0.00012540817260742188 nb_pixel_total : 1480 time to create 1 rle with old method : 0.0029654502868652344 length of segment : 59 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0009322166442871094 length of segment : 24 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 671 time to create 1 rle with old method : 0.0014657974243164062 length of segment : 33 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 1004 time to create 1 rle with old method : 0.001967906951904297 length of segment : 30 time for calcul the mask position with numpy : 0.00010156631469726562 nb_pixel_total : 413 time to create 1 rle with old method : 0.0011188983917236328 length of segment : 31 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0007364749908447266 length of segment : 25 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.0003650188446044922 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.20000 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 : 7.486343383789062e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0003757476806640625 length of segment : 16 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0007863044738769531 length of segment : 27 time for calcul the mask position with numpy : 0.00011157989501953125 nb_pixel_total : 2474 time to create 1 rle with old method : 0.004585742950439453 length of segment : 45 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0010380744934082031 length of segment : 18 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0004642009735107422 length of segment : 21 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1173 time to create 1 rle with old method : 0.0023376941680908203 length of segment : 28 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 786 time to create 1 rle with old method : 0.0015134811401367188 length of segment : 45 time for calcul the mask position with numpy : 0.00013947486877441406 nb_pixel_total : 2817 time to create 1 rle with old method : 0.00513458251953125 length of segment : 77 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 429 time to create 1 rle with old method : 0.0009503364562988281 length of segment : 20 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0004169940948486328 length of segment : 13 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0007734298706054688 length of segment : 21 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.00045371055603027344 length of segment : 12 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.0014224052429199219 length of segment : 31 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0005791187286376953 length of segment : 19 time for calcul the mask position with numpy : 0.00011444091796875 nb_pixel_total : 1143 time to create 1 rle with old method : 0.0023097991943359375 length of segment : 52 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0006134510040283203 length of segment : 28 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0021164417266845703 length of segment : 27 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 9 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0011012554168701172 length of segment : 23 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00047397613525390625 length of segment : 21 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 2485 time to create 1 rle with old method : 0.004904508590698242 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.93047 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 : 9.036064147949219e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0030205249786376953 length of segment : 23 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 963 time to create 1 rle with old method : 0.001758575439453125 length of segment : 33 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0010051727294921875 length of segment : 31 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0005860328674316406 length of segment : 19 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0008797645568847656 length of segment : 27 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.0004889965057373047 length of segment : 33 time for calcul the mask position with numpy : 9.560585021972656e-05 nb_pixel_total : 1558 time to create 1 rle with old method : 0.002110719680786133 length of segment : 38 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.00046563148498535156 length of segment : 16 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006656646728515625 length of segment : 53 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0004069805145263672 length of segment : 15 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.00069427490234375 length of segment : 12 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 750 time to create 1 rle with old method : 0.0010256767272949219 length of segment : 38 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 1725 time to create 1 rle with old method : 0.0022385120391845703 length of segment : 41 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005950927734375 length of segment : 22 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 3696 time to create 1 rle with old method : 0.0045015811920166016 length of segment : 60 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.00033974647521972656 length of segment : 22 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 372 time to create 1 rle with old method : 0.0005447864532470703 length of segment : 30 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00041937828063964844 length of segment : 24 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0007846355438232422 length of segment : 34 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0007996559143066406 length of segment : 22 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006558895111083984 length of segment : 21 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0003147125244140625 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: -118.80547 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 32 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006871223449707031 length of segment : 22 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 1721 time to create 1 rle with old method : 0.0022842884063720703 length of segment : 49 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.0005176067352294922 length of segment : 20 time for calcul the mask position with numpy : 0.00011706352233886719 nb_pixel_total : 2191 time to create 1 rle with old method : 0.003411531448364258 length of segment : 44 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007877349853515625 length of segment : 27 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0013599395751953125 length of segment : 29 time for calcul the mask position with numpy : 0.00012540817260742188 nb_pixel_total : 1257 time to create 1 rle with old method : 0.0017211437225341797 length of segment : 30 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005943775177001953 length of segment : 15 time for calcul the mask position with numpy : 8.559226989746094e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0011229515075683594 length of segment : 36 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0006902217864990234 length of segment : 21 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 574 time to create 1 rle with old method : 0.0010294914245605469 length of segment : 27 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0006008148193359375 length of segment : 23 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0009708404541015625 length of segment : 20 time for calcul the mask position with numpy : 0.00013399124145507812 nb_pixel_total : 2091 time to create 1 rle with old method : 0.002810955047607422 length of segment : 93 time for calcul the mask position with numpy : 0.00017714500427246094 nb_pixel_total : 3646 time to create 1 rle with old method : 0.004523038864135742 length of segment : 95 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 1352 time to create 1 rle with old method : 0.0018193721771240234 length of segment : 33 time for calcul the mask position with numpy : 0.0002086162567138672 nb_pixel_total : 6194 time to create 1 rle with old method : 0.007551908493041992 length of segment : 83 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0008037090301513672 length of segment : 19 time for calcul the mask position with numpy : 0.0003178119659423828 nb_pixel_total : 12593 time to create 1 rle with old method : 0.015719175338745117 length of segment : 142 time for calcul the mask position with numpy : 0.00010895729064941406 nb_pixel_total : 1256 time to create 1 rle with old method : 0.00162506103515625 length of segment : 42 time for calcul the mask position with numpy : 0.00010538101196289062 nb_pixel_total : 515 time to create 1 rle with old method : 0.0011572837829589844 length of segment : 33 time for calcul the mask position with numpy : 0.00020074844360351562 nb_pixel_total : 5640 time to create 1 rle with old method : 0.00716853141784668 length of segment : 147 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0006060600280761719 length of segment : 23 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0011456012725830078 length of segment : 36 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.00028204917907714844 length of segment : 23 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 33 time to create 1 rle with old method : 9.894371032714844e-05 length of segment : 6 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.0004127025604248047 length of segment : 12 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0005567073822021484 length of segment : 21 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0006206035614013672 length of segment : 22 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0005695819854736328 length of segment : 18 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 1493 time to create 1 rle with old method : 0.0026247501373291016 length of segment : 50 time for calcul the mask position with numpy : 0.00016689300537109375 nb_pixel_total : 6044 time to create 1 rle with old method : 0.008701801300048828 length of segment : 82 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.09063 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 : 9.703636169433594e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0009913444519042969 length of segment : 29 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.00027060508728027344 length of segment : 35 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0005533695220947266 length of segment : 24 time for calcul the mask position with numpy : 0.0001049041748046875 nb_pixel_total : 964 time to create 1 rle with old method : 0.0013003349304199219 length of segment : 61 time for calcul the mask position with numpy : 0.0002923011779785156 nb_pixel_total : 11602 time to create 1 rle with old method : 0.015112876892089844 length of segment : 124 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 1606 time to create 1 rle with old method : 0.0020399093627929688 length of segment : 33 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1436 time to create 1 rle with old method : 0.001968860626220703 length of segment : 28 time for calcul the mask position with numpy : 0.00014925003051757812 nb_pixel_total : 4798 time to create 1 rle with old method : 0.00594019889831543 length of segment : 63 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 714 time to create 1 rle with old method : 0.0010390281677246094 length of segment : 29 time for calcul the mask position with numpy : 0.00024127960205078125 nb_pixel_total : 6725 time to create 1 rle with old method : 0.008339643478393555 length of segment : 112 time for calcul the mask position with numpy : 9.703636169433594e-05 nb_pixel_total : 3916 time to create 1 rle with old method : 0.004984378814697266 length of segment : 59 time for calcul the mask position with numpy : 0.00015234947204589844 nb_pixel_total : 6365 time to create 1 rle with old method : 0.008025169372558594 length of segment : 107 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 854 time to create 1 rle with old method : 0.0012235641479492188 length of segment : 52 time for calcul the mask position with numpy : 0.00011754035949707031 nb_pixel_total : 290 time to create 1 rle with old method : 0.0006513595581054688 length of segment : 24 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 1533 time to create 1 rle with old method : 0.0027780532836914062 length of segment : 27 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0006225109100341797 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: -116.33672 max: 150.19766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0003826618194580078 nb_pixel_total : 17867 time to create 1 rle with old method : 0.028285503387451172 length of segment : 176 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.00668644905090332 length of segment : 23 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 662 time to create 1 rle with old method : 0.0014526844024658203 length of segment : 49 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 139.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0001823902130126953 nb_pixel_total : 6330 time to create 1 rle with old method : 0.026799917221069336 length of segment : 248 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 1307 time to create 1 rle with old method : 0.001957416534423828 length of segment : 92 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1412 time to create 1 rle with old method : 0.0019230842590332031 length of segment : 89 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.79375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 0.00016260147094726562 nb_pixel_total : 666 time to create 1 rle with old method : 0.0012934207916259766 length of segment : 31 time for calcul the mask position with numpy : 0.00011515617370605469 nb_pixel_total : 1944 time to create 1 rle with old method : 0.003527402877807617 length of segment : 41 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0011906623840332031 length of segment : 28 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.0003509521484375 length of segment : 15 time for calcul the mask position with numpy : 0.0001499652862548828 nb_pixel_total : 2172 time to create 1 rle with old method : 0.003919124603271484 length of segment : 90 time for calcul the mask position with numpy : 0.00014662742614746094 nb_pixel_total : 632 time to create 1 rle with old method : 0.00144195556640625 length of segment : 27 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 327 time to create 1 rle with old method : 0.0008718967437744141 length of segment : 33 time for calcul the mask position with numpy : 0.000156402587890625 nb_pixel_total : 1811 time to create 1 rle with old method : 0.0038459300994873047 length of segment : 43 time for calcul the mask position with numpy : 0.00012087821960449219 nb_pixel_total : 1522 time to create 1 rle with old method : 0.0026085376739501953 length of segment : 44 time for calcul the mask position with numpy : 0.00011706352233886719 nb_pixel_total : 1079 time to create 1 rle with old method : 0.0019893646240234375 length of segment : 37 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.0003566741943359375 length of segment : 32 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0009050369262695312 length of segment : 30 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006515979766845703 length of segment : 34 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00030684471130371094 length of segment : 19 time for calcul the mask position with numpy : 0.00025725364685058594 nb_pixel_total : 6922 time to create 1 rle with old method : 0.008282899856567383 length of segment : 119 time for calcul the mask position with numpy : 0.00015044212341308594 nb_pixel_total : 861 time to create 1 rle with old method : 0.0019214153289794922 length of segment : 49 time for calcul the mask position with numpy : 0.00014519691467285156 nb_pixel_total : 947 time to create 1 rle with old method : 0.0017521381378173828 length of segment : 56 time for calcul the mask position with numpy : 0.000156402587890625 nb_pixel_total : 1313 time to create 1 rle with old method : 0.002641439437866211 length of segment : 49 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0011553764343261719 length of segment : 33 time for calcul the mask position with numpy : 0.0001914501190185547 nb_pixel_total : 6961 time to create 1 rle with old method : 0.008571386337280273 length of segment : 120 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.39531 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 : 8.58306884765625e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0009262561798095703 length of segment : 34 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0005664825439453125 length of segment : 25 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0005376338958740234 length of segment : 18 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 687 time to create 1 rle with old method : 0.0012807846069335938 length of segment : 41 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0007467269897460938 length of segment : 32 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 2086 time to create 1 rle with old method : 0.0038077831268310547 length of segment : 59 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 1421 time to create 1 rle with old method : 0.00270843505859375 length of segment : 56 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 1326 time to create 1 rle with old method : 0.0025374889373779297 length of segment : 54 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 861 time to create 1 rle with old method : 0.0016531944274902344 length of segment : 39 time for calcul the mask position with numpy : 9.989738464355469e-05 nb_pixel_total : 1804 time to create 1 rle with old method : 0.003139019012451172 length of segment : 81 time for calcul the mask position with numpy : 0.0001735687255859375 nb_pixel_total : 899 time to create 1 rle with old method : 0.0012514591217041016 length of segment : 29 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.000762939453125 length of segment : 42 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 482 time to create 1 rle with old method : 0.0006308555603027344 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.51250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0007262229919433594 length of segment : 32 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1179 time to create 1 rle with old method : 0.0015380382537841797 length of segment : 39 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1474 time to create 1 rle with old method : 0.0019519329071044922 length of segment : 92 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0008244514465332031 length of segment : 41 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005452632904052734 length of segment : 22 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00018334388732910156 length of segment : 12 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 838 time to create 1 rle with old method : 0.001051187515258789 length of segment : 87 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004963874816894531 length of segment : 22 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.00034880638122558594 length of segment : 18 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 1679 time to create 1 rle with old method : 0.0021810531616210938 length of segment : 53 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.00032830238342285156 length of segment : 25 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001533031463623047 length of segment : 17 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00037360191345214844 length of segment : 14 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.00052642822265625 length of segment : 14 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0007486343383789062 length of segment : 24 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1040 time to create 1 rle with old method : 0.0013878345489501953 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: -114.27422 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 : 0.0001461505889892578 nb_pixel_total : 1557 time to create 1 rle with old method : 0.0019774436950683594 length of segment : 42 time for calcul the mask position with numpy : 0.00012087821960449219 nb_pixel_total : 941 time to create 1 rle with old method : 0.001750946044921875 length of segment : 80 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0005869865417480469 length of segment : 24 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0010535717010498047 length of segment : 21 time for calcul the mask position with numpy : 0.00014019012451171875 nb_pixel_total : 1736 time to create 1 rle with old method : 0.0032806396484375 length of segment : 45 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0008399486541748047 length of segment : 25 time for calcul the mask position with numpy : 0.00013780593872070312 nb_pixel_total : 1470 time to create 1 rle with old method : 0.01800084114074707 length of segment : 41 time for calcul the mask position with numpy : 0.00015091896057128906 nb_pixel_total : 1697 time to create 1 rle with old method : 0.0023355484008789062 length of segment : 47 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 667 time to create 1 rle with old method : 0.0009505748748779297 length of segment : 33 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 731 time to create 1 rle with old method : 0.001043081283569336 length of segment : 21 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0003504753112792969 length of segment : 33 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 1919 time to create 1 rle with old method : 0.002536296844482422 length of segment : 50 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 1125 time to create 1 rle with old method : 0.0014319419860839844 length of segment : 53 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 769 time to create 1 rle with old method : 0.0011358261108398438 length of segment : 37 time for calcul the mask position with numpy : 0.00024580955505371094 nb_pixel_total : 5329 time to create 1 rle with old method : 0.0066149234771728516 length of segment : 189 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 859 time to create 1 rle with old method : 0.00115203857421875 length of segment : 38 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.0003936290740966797 length of segment : 23 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001919269561767578 length of segment : 12 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0010485649108886719 length of segment : 32 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 592 time to create 1 rle with old method : 0.0008831024169921875 length of segment : 76 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00023603439331054688 length of segment : 9 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005164146423339844 length of segment : 44 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00017976760864257812 length of segment : 14 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0006394386291503906 length of segment : 27 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0004112720489501953 length of segment : 14 time for calcul the mask position with numpy : 0.00011301040649414062 nb_pixel_total : 399 time to create 1 rle with old method : 0.0007660388946533203 length of segment : 25 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 1113 time to create 1 rle with old method : 0.0014247894287109375 length of segment : 51 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 1289 time to create 1 rle with old method : 0.00165557861328125 length of segment : 48 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 1800 time to create 1 rle with old method : 0.0024394989013671875 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: -120.80547 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 : 0.00011801719665527344 nb_pixel_total : 662 time to create 1 rle with old method : 0.0011987686157226562 length of segment : 33 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.00038504600524902344 length of segment : 15 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0006177425384521484 length of segment : 26 time for calcul the mask position with numpy : 0.00013756752014160156 nb_pixel_total : 1282 time to create 1 rle with old method : 0.0028319358825683594 length of segment : 73 time for calcul the mask position with numpy : 0.00010180473327636719 nb_pixel_total : 1805 time to create 1 rle with old method : 0.0023386478424072266 length of segment : 46 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 674 time to create 1 rle with old method : 0.0009832382202148438 length of segment : 24 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1478 time to create 1 rle with old method : 0.0018763542175292969 length of segment : 46 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 931 time to create 1 rle with old method : 0.001322031021118164 length of segment : 46 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 803 time to create 1 rle with old method : 0.0011262893676757812 length of segment : 39 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 922 time to create 1 rle with old method : 0.0015308856964111328 length of segment : 54 time for calcul the mask position with numpy : 0.00018525123596191406 nb_pixel_total : 4950 time to create 1 rle with old method : 0.007060527801513672 length of segment : 83 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 1278 time to create 1 rle with old method : 0.001600027084350586 length of segment : 62 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1162 time to create 1 rle with old method : 0.0017986297607421875 length of segment : 50 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 860 time to create 1 rle with old method : 0.0010807514190673828 length of segment : 54 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00021982192993164062 length of segment : 12 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 4257 time to create 1 rle with old method : 0.005185127258300781 length of segment : 75 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.60625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 909 time to create 1 rle with old method : 0.001760721206665039 length of segment : 54 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0004107952117919922 length of segment : 24 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 3321 time to create 1 rle with old method : 0.006117820739746094 length of segment : 144 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.001285552978515625 length of segment : 45 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0007321834564208984 length of segment : 21 time for calcul the mask position with numpy : 0.00017499923706054688 nb_pixel_total : 3089 time to create 1 rle with old method : 0.0056035518646240234 length of segment : 108 time for calcul the mask position with numpy : 0.0001418590545654297 nb_pixel_total : 312 time to create 1 rle with old method : 0.0010166168212890625 length of segment : 30 time for calcul the mask position with numpy : 0.0003361701965332031 nb_pixel_total : 4073 time to create 1 rle with old method : 0.007413387298583984 length of segment : 196 Processing 1 images image shape: (400, 160, 3) min: 4.00000 max: 204.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 97.27969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0002353191375732422 nb_pixel_total : 9018 time to create 1 rle with old method : 0.01091623306274414 length of segment : 403 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.56328 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 0.00021314620971679688 nb_pixel_total : 4759 time to create 1 rle with old method : 0.00568389892578125 length of segment : 127 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 607 time to create 1 rle with old method : 0.0008244514465332031 length of segment : 39 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00040841102600097656 length of segment : 12 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003604888916015625 length of segment : 26 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005924701690673828 length of segment : 31 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1721 time to create 1 rle with old method : 0.002209901809692383 length of segment : 56 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1344 time to create 1 rle with old method : 0.0017066001892089844 length of segment : 44 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0006473064422607422 length of segment : 24 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.0002429485321044922 length of segment : 11 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006465911865234375 length of segment : 28 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0010890960693359375 length of segment : 40 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.0002799034118652344 length of segment : 20 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.00054931640625 length of segment : 20 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1322 time to create 1 rle with old method : 0.0017361640930175781 length of segment : 48 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0004634857177734375 length of segment : 27 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1371 time to create 1 rle with old method : 0.001773834228515625 length of segment : 51 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1378 time to create 1 rle with old method : 0.0017974376678466797 length of segment : 55 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1058 time to create 1 rle with old method : 0.0013442039489746094 length of segment : 38 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 943 time to create 1 rle with old method : 0.0012161731719970703 length of segment : 57 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0006501674652099609 length of segment : 30 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00022530555725097656 length of segment : 12 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 1704 time to create 1 rle with old method : 0.002139568328857422 length of segment : 60 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005753040313720703 length of segment : 27 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1688 time to create 1 rle with old method : 0.002192974090576172 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 50 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 586 time to create 1 rle with old method : 0.0008051395416259766 length of segment : 36 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 606 time to create 1 rle with old method : 0.0008368492126464844 length of segment : 38 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 616 time to create 1 rle with old method : 0.0009372234344482422 length of segment : 38 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004296302795410156 length of segment : 29 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006387233734130859 length of segment : 39 time for calcul the mask position with numpy : 0.00010013580322265625 nb_pixel_total : 2601 time to create 1 rle with old method : 0.0035750865936279297 length of segment : 54 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0008454322814941406 length of segment : 40 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 1105 time to create 1 rle with old method : 0.0015106201171875 length of segment : 44 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.00063323974609375 length of segment : 34 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0008022785186767578 length of segment : 21 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1949 time to create 1 rle with old method : 0.002424478530883789 length of segment : 61 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1141 time to create 1 rle with old method : 0.001474142074584961 length of segment : 36 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 1396 time to create 1 rle with old method : 0.0019299983978271484 length of segment : 41 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 1028 time to create 1 rle with old method : 0.0013589859008789062 length of segment : 53 time for calcul the mask position with numpy : 9.560585021972656e-05 nb_pixel_total : 1681 time to create 1 rle with old method : 0.0022268295288085938 length of segment : 49 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0005443096160888672 length of segment : 30 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00023293495178222656 length of segment : 15 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0005161762237548828 length of segment : 26 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.00048542022705078125 length of segment : 27 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 1564 time to create 1 rle with old method : 0.0020568370819091797 length of segment : 68 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 60 time to create 1 rle with old method : 0.0001266002655029297 length of segment : 8 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 970 time to create 1 rle with old method : 0.0013189315795898438 length of segment : 31 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001723766326904297 length of segment : 27 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007781982421875 length of segment : 26 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0004291534423828125 length of segment : 12 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 690 time to create 1 rle with old method : 0.0013685226440429688 length of segment : 32 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1179 time to create 1 rle with old method : 0.0015494823455810547 length of segment : 43 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 1529 time to create 1 rle with old method : 0.002027750015258789 length of segment : 36 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0007328987121582031 length of segment : 39 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0006089210510253906 length of segment : 24 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 563 time to create 1 rle with old method : 0.0007970333099365234 length of segment : 25 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0008597373962402344 length of segment : 26 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00023055076599121094 length of segment : 17 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 585 time to create 1 rle with old method : 0.0008599758148193359 length of segment : 25 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006208419799804688 length of segment : 29 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 674 time to create 1 rle with old method : 0.001161813735961914 length of segment : 37 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 782 time to create 1 rle with old method : 0.0010042190551757812 length of segment : 47 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.0006260871887207031 length of segment : 36 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0008003711700439453 length of segment : 58 time for calcul the mask position with numpy : 0.00013327598571777344 nb_pixel_total : 1960 time to create 1 rle with old method : 0.00252532958984375 length of segment : 55 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0004112720489501953 length of segment : 16 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 58 time to create 1 rle with old method : 0.00011777877807617188 length of segment : 9 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0006029605865478516 length of segment : 29 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005590915679931641 length of segment : 18 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0006084442138671875 length of segment : 16 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 883 time to create 1 rle with old method : 0.0011436939239501953 length of segment : 81 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.00061798095703125 length of segment : 44 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 522 time to create 1 rle with old method : 0.0007538795471191406 length of segment : 28 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1093 time to create 1 rle with old method : 0.0015642642974853516 length of segment : 49 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.0007922649383544922 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: -123.09063 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 42 time for calcul the mask position with numpy : 0.00021886825561523438 nb_pixel_total : 3017 time to create 1 rle with old method : 0.005939960479736328 length of segment : 72 time for calcul the mask position with numpy : 0.00011324882507324219 nb_pixel_total : 1856 time to create 1 rle with old method : 0.002450704574584961 length of segment : 67 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 616 time to create 1 rle with old method : 0.0008409023284912109 length of segment : 32 time for calcul the mask position with numpy : 0.00016069412231445312 nb_pixel_total : 2953 time to create 1 rle with old method : 0.003707408905029297 length of segment : 81 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.00083160400390625 length of segment : 27 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0008208751678466797 length of segment : 26 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003402233123779297 length of segment : 21 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003457069396972656 length of segment : 25 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.00045037269592285156 length of segment : 20 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006649494171142578 length of segment : 19 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 576 time to create 1 rle with old method : 0.0008871555328369141 length of segment : 22 time for calcul the mask position with numpy : 0.00015044212341308594 nb_pixel_total : 3372 time to create 1 rle with old method : 0.004251003265380859 length of segment : 130 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007565021514892578 length of segment : 32 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0006334781646728516 length of segment : 30 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1419 time to create 1 rle with old method : 0.001924276351928711 length of segment : 31 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00043487548828125 length of segment : 23 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.0008342266082763672 length of segment : 50 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1518 time to create 1 rle with old method : 0.0020210742950439453 length of segment : 42 time for calcul the mask position with numpy : 0.00013399124145507812 nb_pixel_total : 2635 time to create 1 rle with old method : 0.0030901432037353516 length of segment : 112 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005881786346435547 length of segment : 24 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 994 time to create 1 rle with old method : 0.0014529228210449219 length of segment : 48 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006480216979980469 length of segment : 39 time for calcul the mask position with numpy : 0.00011944770812988281 nb_pixel_total : 2160 time to create 1 rle with old method : 0.0026862621307373047 length of segment : 89 time for calcul the mask position with numpy : 0.00010824203491210938 nb_pixel_total : 1853 time to create 1 rle with old method : 0.002360820770263672 length of segment : 48 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.00033736228942871094 length of segment : 30 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0003254413604736328 length of segment : 17 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00022077560424804688 length of segment : 12 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0009520053863525391 length of segment : 35 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.00026416778564453125 length of segment : 14 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 1372 time to create 1 rle with old method : 0.0017604827880859375 length of segment : 37 time for calcul the mask position with numpy : 0.00017189979553222656 nb_pixel_total : 759 time to create 1 rle with old method : 0.0011932849884033203 length of segment : 35 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 133 time to create 1 rle with old method : 0.00028896331787109375 length of segment : 12 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.0002808570861816406 length of segment : 18 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0006971359252929688 length of segment : 33 time for calcul the mask position with numpy : 0.0001220703125 nb_pixel_total : 602 time to create 1 rle with old method : 0.0008571147918701172 length of segment : 25 time for calcul the mask position with numpy : 0.00010037422180175781 nb_pixel_total : 411 time to create 1 rle with old method : 0.0006201267242431641 length of segment : 25 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002684593200683594 length of segment : 15 time for calcul the mask position with numpy : 0.0001251697540283203 nb_pixel_total : 556 time to create 1 rle with old method : 0.0008449554443359375 length of segment : 33 time for calcul the mask position with numpy : 0.00013136863708496094 nb_pixel_total : 429 time to create 1 rle with old method : 0.0006346702575683594 length of segment : 26 time for calcul the mask position with numpy : 0.0001506805419921875 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006365776062011719 length of segment : 36 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0007009506225585938 length of segment : 31 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0006804466247558594 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.87969 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 35 time for calcul the mask position with numpy : 0.00015211105346679688 nb_pixel_total : 962 time to create 1 rle with old method : 0.001249074935913086 length of segment : 61 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.00048470497131347656 length of segment : 19 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 2246 time to create 1 rle with old method : 0.002988576889038086 length of segment : 53 time for calcul the mask position with numpy : 0.00012874603271484375 nb_pixel_total : 595 time to create 1 rle with old method : 0.0008504390716552734 length of segment : 26 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0007712841033935547 length of segment : 31 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 1232 time to create 1 rle with old method : 0.0015938282012939453 length of segment : 31 time for calcul the mask position with numpy : 0.00025343894958496094 nb_pixel_total : 3596 time to create 1 rle with old method : 0.005365610122680664 length of segment : 70 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 938 time to create 1 rle with old method : 0.0013158321380615234 length of segment : 49 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 184 2025-03-07 10:20:52.564458: E tensorflow/stream_executor/cuda/cuda_driver.cc:939] could not synchronize on CUDA context: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered :: *** Begin stack trace *** tensorflow::CurrentStackTrace() stream_executor::gpu::GpuDriver::SynchronizeContext(stream_executor::gpu::GpuContext*) stream_executor::StreamExecutor::SynchronizeAllActivity() tensorflow::GPUUtil::SyncAll(tensorflow::Device*) tensorflow::BaseGPUDevice::Sync() tensorflow::TensorHandle::CopyToDevice(tensorflow::EagerContext const&, tensorflow::Device*, tensorflow::Tensor*) tensorflow::TensorHandleInterface::Resolve(tensorflow::Status*) TFE_TensorHandleResolve _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall PyObject_Call _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName PyEval_EvalCode PyRun_SimpleFileExFlags Py_RunMain Py_BytesMain __libc_start_main _start *** End stack trace *** 2025-03-07 10:20:52.642174: E tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:725] failed to record completion event; therefore, failed to create inter-stream dependency 2025-03-07 10:20:52.642464: I tensorflow/stream_executor/stream.cc:4938] [stream=0x368edc40,impl=0x368ec8d0] did not memcpy host-to-device; source: 0x5fe182c0 2025-03-07 10:20:52.642487: E tensorflow/stream_executor/stream.cc:334] Error recording event in stream: Error recording CUDA event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered; not marking stream as bad, as the Event object may be at fault. Monitor for further errors. 2025-03-07 10:20:52.642523: 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 10:20:52.642538: 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 ! 20.26user 13.12system 1:00:06elapsed 0%CPU (0avgtext+0avgdata 2413668maxresident)k 689816inputs+2472outputs (13483major+736539minor)pagefaults 0swaps