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 : 2599970 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 : ['2648133'] with mtr_portfolio_ids : ['21140153'] and first list_photo_ids : [] new path : /proc/2599970/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.6097042560577393 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 12:20:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3957 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-07 12:20:33.358878: 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 12:20:33.387181: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-07 12:20:33.389793: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f3dc0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-07 12:20:33.389846: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-07 12:20:33.393900: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-07 12:20:33.673326: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x11885540 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-07 12:20:33.673373: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-07 12:20:33.674466: 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 12:20:33.675011: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 12:20:33.678382: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 12:20:33.681159: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 12:20:33.681680: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 12:20:33.686056: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 12:20:33.688011: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 12:20:33.693792: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 12:20:33.695145: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 12:20:33.695227: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 12:20:33.695859: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 12:20:33.695879: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 12:20:33.695891: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 12:20:33.697030: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3505 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 12:20:34.032563: 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 12:20:34.032669: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 12:20:34.032691: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 12:20:34.032711: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 12:20:34.032729: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 12:20:34.032748: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 12:20:34.032765: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 12:20:34.032784: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 12:20:34.033950: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 12:20:34.035142: 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 12:20:34.035187: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 12:20:34.035208: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 12:20:34.035227: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 12:20:34.035245: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 12:20:34.035262: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 12:20:34.035281: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 12:20:34.035302: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 12:20:34.036407: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 12:20:34.036443: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 12:20:34.036454: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 12:20:34.036463: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 12:20:34.037634: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3505 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 12:20:43.871518: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 12:20:44.107192: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 12:20:45.754308: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.754951: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.63G (2826318592 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.755550: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.37G (2543686656 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.756142: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.13G (2289317888 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.756178: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.756770: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.756790: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.763971: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.763996: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.764555: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.764570: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.771159: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.771182: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.771740: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.771756: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.803682: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.803723: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.804319: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.804339: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.810203: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.810232: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.810787: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.810804: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-07 12:20:45.845312: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.845895: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.847863: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.848475: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.893630: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.894268: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.896564: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.897177: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.929873: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.930842: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.932982: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.933906: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.941575: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.942561: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.945031: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.945960: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.953390: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.954361: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.956492: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.957704: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.988049: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.988655: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.989246: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.989864: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.993583: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:45.994206: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.010228: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.010875: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.011518: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.012128: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.024710: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.025340: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.025923: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.026486: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.031054: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.031708: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.036682: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.037302: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.049698: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.050266: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.054435: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.055025: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.055610: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.056193: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.056967: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.057540: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.068260: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.068851: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.069523: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.070109: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.070689: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.071293: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.071875: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.072453: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.087640: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.088360: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.121024: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.121101: 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 12:20:46.122217: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.123288: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.130455: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.131103: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.131746: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.132365: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.140537: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.141151: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.156128: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.156753: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.157369: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.157961: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.162085: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.162684: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.163276: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.163861: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.164931: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.175200: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.175799: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.184834: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.185444: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.186038: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.186635: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.187249: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-07 12:20:46.187834: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3140354048 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 4 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.21563 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 0.00010156631469726562 nb_pixel_total : 467 time to create 1 rle with old method : 0.0009584426879882812 length of segment : 29 time for calcul the mask position with numpy : 0.00015807151794433594 nb_pixel_total : 4527 time to create 1 rle with old method : 0.008079767227172852 length of segment : 94 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0011250972747802734 length of segment : 29 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 2060 time to create 1 rle with old method : 0.010792732238769531 length of segment : 57 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 1079 time to create 1 rle with old method : 0.007137775421142578 length of segment : 59 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 746 time to create 1 rle with old method : 0.0012753009796142578 length of segment : 33 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.000438690185546875 length of segment : 13 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0005092620849609375 length of segment : 24 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.00048661231994628906 length of segment : 22 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 4915 time to create 1 rle with old method : 0.0063838958740234375 length of segment : 159 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.0004210472106933594 length of segment : 37 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.00101470947265625 length of segment : 44 Processing 1 images image shape: (400, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -101.73125 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 : 9.465217590332031e-05 nb_pixel_total : 1786 time to create 1 rle with old method : 0.0030164718627929688 length of segment : 59 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1417 time to create 1 rle with old method : 0.002246379852294922 length of segment : 42 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 1952 time to create 1 rle with old method : 0.0025107860565185547 length of segment : 63 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 2075 time to create 1 rle with old method : 0.0032439231872558594 length of segment : 44 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.0011982917785644531 length of segment : 33 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 2873 time to create 1 rle with old method : 0.003553152084350586 length of segment : 44 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 982 time to create 1 rle with old method : 0.0012736320495605469 length of segment : 33 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.000865936279296875 length of segment : 17 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 2230 time to create 1 rle with old method : 0.002839326858520508 length of segment : 63 time for calcul the mask position with numpy : 0.0001461505889892578 nb_pixel_total : 6280 time to create 1 rle with old method : 0.007337093353271484 length of segment : 189 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 1017 time to create 1 rle with old method : 0.001329660415649414 length of segment : 41 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0014040470123291016 length of segment : 39 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 708 time to create 1 rle with old method : 0.0016019344329833984 length of segment : 31 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0011005401611328125 length of segment : 64 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 499 time to create 1 rle with old method : 0.0011029243469238281 length of segment : 38 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0005714893341064453 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -102.64922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0011813640594482422 length of segment : 42 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.001577138900756836 length of segment : 34 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1270 time to create 1 rle with old method : 0.0024046897888183594 length of segment : 54 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 563 time to create 1 rle with old method : 0.0010371208190917969 length of segment : 37 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0010254383087158203 length of segment : 17 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 1463 time to create 1 rle with old method : 0.0028955936431884766 length of segment : 63 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 3376 time to create 1 rle with old method : 0.0044133663177490234 length of segment : 55 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 3833 time to create 1 rle with old method : 0.004906177520751953 length of segment : 84 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002503395080566406 length of segment : 11 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 4103 time to create 1 rle with old method : 0.0053043365478515625 length of segment : 78 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0009534358978271484 length of segment : 34 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0004127025604248047 length of segment : 18 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.00027942657470703125 length of segment : 18 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 739 time to create 1 rle with old method : 0.0008940696716308594 length of segment : 120 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -104.64531 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 32 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 1919 time to create 1 rle with old method : 0.002566814422607422 length of segment : 41 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1277 time to create 1 rle with old method : 0.0017147064208984375 length of segment : 28 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0008487701416015625 length of segment : 29 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005581378936767578 length of segment : 21 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 5120 time to create 1 rle with old method : 0.0064504146575927734 length of segment : 57 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0005207061767578125 length of segment : 19 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 1572 time to create 1 rle with old method : 0.0021910667419433594 length of segment : 31 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 738 time to create 1 rle with old method : 0.0009570121765136719 length of segment : 42 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0009174346923828125 length of segment : 29 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 959 time to create 1 rle with old method : 0.0013818740844726562 length of segment : 28 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0004711151123046875 length of segment : 18 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0007927417755126953 length of segment : 25 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1453 time to create 1 rle with old method : 0.0018153190612792969 length of segment : 46 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 790 time to create 1 rle with old method : 0.0010433197021484375 length of segment : 56 time for calcul the mask position with numpy : 0.00016498565673828125 nb_pixel_total : 8234 time to create 1 rle with old method : 0.01035928726196289 length of segment : 96 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1656 time to create 1 rle with old method : 0.002869129180908203 length of segment : 39 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0012023448944091797 length of segment : 23 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007905960083007812 length of segment : 30 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.00025081634521484375 length of segment : 28 time for calcul the mask position with numpy : 0.00011134147644042969 nb_pixel_total : 5118 time to create 1 rle with old method : 0.0064165592193603516 length of segment : 53 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0006084442138671875 length of segment : 25 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1145 time to create 1 rle with old method : 0.0017778873443603516 length of segment : 33 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006864070892333984 length of segment : 27 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.00042939186096191406 length of segment : 26 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 2202 time to create 1 rle with old method : 0.0030846595764160156 length of segment : 70 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006382465362548828 length of segment : 26 time for calcul the mask position with numpy : 0.00011920928955078125 nb_pixel_total : 2826 time to create 1 rle with old method : 0.0045108795166015625 length of segment : 55 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0007359981536865234 length of segment : 22 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 3238 time to create 1 rle with old method : 0.00496220588684082 length of segment : 61 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1404 time to create 1 rle with old method : 0.0023365020751953125 length of segment : 45 time for calcul the mask position with numpy : 0.00011301040649414062 nb_pixel_total : 3703 time to create 1 rle with old method : 0.006232500076293945 length of segment : 70 time for calcul the mask position with numpy : 0.00013399124145507812 nb_pixel_total : 3869 time to create 1 rle with old method : 0.006918430328369141 length of segment : 67 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.17266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 0.00010895729064941406 nb_pixel_total : 2213 time to create 1 rle with old method : 0.002711057662963867 length of segment : 89 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0009372234344482422 length of segment : 19 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 819 time to create 1 rle with old method : 0.001123189926147461 length of segment : 23 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1378 time to create 1 rle with old method : 0.00176239013671875 length of segment : 40 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0005059242248535156 length of segment : 22 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0008170604705810547 length of segment : 16 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.00035452842712402344 length of segment : 16 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 785 time to create 1 rle with old method : 0.0011456012725830078 length of segment : 35 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0008957386016845703 length of segment : 36 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1268 time to create 1 rle with old method : 0.0016829967498779297 length of segment : 72 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1424 time to create 1 rle with old method : 0.001984834671020508 length of segment : 51 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0007560253143310547 length of segment : 21 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 824 time to create 1 rle with old method : 0.0014040470123291016 length of segment : 42 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 3072 time to create 1 rle with old method : 0.004374980926513672 length of segment : 71 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007915496826171875 length of segment : 31 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00017714500427246094 length of segment : 20 time for calcul the mask position with numpy : 0.00022649765014648438 nb_pixel_total : 12641 time to create 1 rle with old method : 0.015355348587036133 length of segment : 129 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1175 time to create 1 rle with old method : 0.0014770030975341797 length of segment : 35 time for calcul the mask position with numpy : 0.00020742416381835938 nb_pixel_total : 12122 time to create 1 rle with old method : 0.014373064041137695 length of segment : 133 Processing 1 images image shape: (400, 400, 3) min: 22.00000 max: 213.00000 molded_images shape: (1, 640, 640, 3) min: -95.56719 max: 100.63516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00019288063049316406 nb_pixel_total : 11527 time to create 1 rle with old method : 0.013441085815429688 length of segment : 257 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.0011718273162841797 length of segment : 54 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00031256675720214844 length of segment : 28 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.0010824203491210938 length of segment : 54 Processing 1 images image shape: (400, 160, 3) min: 19.00000 max: 157.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 42.16641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 1760 time to create 1 rle with old method : 0.0033609867095947266 length of segment : 71 Processing 1 images image shape: (400, 400, 3) min: 17.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -90.44609 max: 151.06094 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 2476 time to create 1 rle with old method : 0.0030465126037597656 length of segment : 102 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 511 time to create 1 rle with old method : 0.0007648468017578125 length of segment : 30 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1549 time to create 1 rle with old method : 0.0019135475158691406 length of segment : 59 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0005624294281005859 length of segment : 47 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 1838 time to create 1 rle with old method : 0.002725839614868164 length of segment : 53 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.0011038780212402344 length of segment : 52 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 58 time to create 1 rle with old method : 0.00011181831359863281 length of segment : 18 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.0001430511474609375 length of segment : 13 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003190040588378906 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.77422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 30 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.000579833984375 length of segment : 28 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 2767 time to create 1 rle with old method : 0.003584623336791992 length of segment : 87 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 1946 time to create 1 rle with old method : 0.002847909927368164 length of segment : 60 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 2533 time to create 1 rle with old method : 0.004191875457763672 length of segment : 53 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 2473 time to create 1 rle with old method : 0.0035529136657714844 length of segment : 90 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 574 time to create 1 rle with old method : 0.0009410381317138672 length of segment : 31 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1298 time to create 1 rle with old method : 0.0019071102142333984 length of segment : 56 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0010192394256591797 length of segment : 22 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0005004405975341797 length of segment : 27 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 877 time to create 1 rle with old method : 0.0011298656463623047 length of segment : 40 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 3167 time to create 1 rle with old method : 0.004601716995239258 length of segment : 52 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1026 time to create 1 rle with old method : 0.0013203620910644531 length of segment : 33 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1151 time to create 1 rle with old method : 0.0015230178833007812 length of segment : 60 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 3112 time to create 1 rle with old method : 0.003945350646972656 length of segment : 51 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1503 time to create 1 rle with old method : 0.0030868053436279297 length of segment : 46 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0009303092956542969 length of segment : 39 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.0004916191101074219 length of segment : 20 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 2834 time to create 1 rle with old method : 0.003735780715942383 length of segment : 54 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006821155548095703 length of segment : 33 time for calcul the mask position with numpy : 0.00011754035949707031 nb_pixel_total : 3076 time to create 1 rle with old method : 0.00394439697265625 length of segment : 81 time for calcul the mask position with numpy : 0.00010776519775390625 nb_pixel_total : 3106 time to create 1 rle with old method : 0.0037469863891601562 length of segment : 80 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1554 time to create 1 rle with old method : 0.0020759105682373047 length of segment : 42 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0006358623504638672 length of segment : 23 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0005967617034912109 length of segment : 24 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0007159709930419922 length of segment : 24 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 1144 time to create 1 rle with old method : 0.0014524459838867188 length of segment : 93 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1407 time to create 1 rle with old method : 0.0019559860229492188 length of segment : 42 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004601478576660156 length of segment : 20 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.0013356208801269531 length of segment : 32 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006670951843261719 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: -114.79375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 47 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 1506 time to create 1 rle with old method : 0.0020537376403808594 length of segment : 51 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 753 time to create 1 rle with old method : 0.0011191368103027344 length of segment : 30 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 3185 time to create 1 rle with old method : 0.004434823989868164 length of segment : 59 time for calcul the mask position with numpy : 0.00015592575073242188 nb_pixel_total : 3473 time to create 1 rle with old method : 0.005702018737792969 length of segment : 92 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0005183219909667969 length of segment : 31 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 2685 time to create 1 rle with old method : 0.003259897232055664 length of segment : 76 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 2577 time to create 1 rle with old method : 0.003136873245239258 length of segment : 51 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 984 time to create 1 rle with old method : 0.0013098716735839844 length of segment : 38 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006916522979736328 length of segment : 20 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 945 time to create 1 rle with old method : 0.0013000965118408203 length of segment : 49 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 2088 time to create 1 rle with old method : 0.0027284622192382812 length of segment : 57 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005915164947509766 length of segment : 20 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0006036758422851562 length of segment : 22 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 2771 time to create 1 rle with old method : 0.00362396240234375 length of segment : 80 time for calcul the mask position with numpy : 0.00015497207641601562 nb_pixel_total : 4018 time to create 1 rle with old method : 0.004907131195068359 length of segment : 96 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 3199 time to create 1 rle with old method : 0.004129171371459961 length of segment : 66 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0005042552947998047 length of segment : 26 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003330707550048828 length of segment : 23 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 2015 time to create 1 rle with old method : 0.0025424957275390625 length of segment : 57 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0005238056182861328 length of segment : 22 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 2285 time to create 1 rle with old method : 0.003545999526977539 length of segment : 58 time for calcul the mask position with numpy : 0.00011420249938964844 nb_pixel_total : 652 time to create 1 rle with old method : 0.0013930797576904297 length of segment : 37 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0005326271057128906 length of segment : 31 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 669 time to create 1 rle with old method : 0.0013384819030761719 length of segment : 16 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.001285552978515625 length of segment : 25 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 671 time to create 1 rle with old method : 0.0011827945709228516 length of segment : 49 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 670 time to create 1 rle with old method : 0.001111745834350586 length of segment : 21 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1628 time to create 1 rle with old method : 0.0026869773864746094 length of segment : 56 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 720 time to create 1 rle with old method : 0.0009624958038330078 length of segment : 32 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0005664825439453125 length of segment : 26 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0007736682891845703 length of segment : 27 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0015234947204589844 length of segment : 32 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0006582736968994141 length of segment : 18 time for calcul the mask position with numpy : 0.0001819133758544922 nb_pixel_total : 5238 time to create 1 rle with old method : 0.007124185562133789 length of segment : 132 time for calcul the mask position with numpy : 0.0001614093780517578 nb_pixel_total : 3865 time to create 1 rle with old method : 0.007243633270263672 length of segment : 107 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 579 time to create 1 rle with old method : 0.0008139610290527344 length of segment : 39 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0008080005645751953 length of segment : 21 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 638 time to create 1 rle with old method : 0.001043558120727539 length of segment : 38 time for calcul the mask position with numpy : 0.0002105236053466797 nb_pixel_total : 5299 time to create 1 rle with old method : 0.007828474044799805 length of segment : 105 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 737 time to create 1 rle with old method : 0.0011959075927734375 length of segment : 16 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0007340908050537109 length of segment : 16 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 615 time to create 1 rle with old method : 0.0008504390716552734 length of segment : 22 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.00026154518127441406 length of segment : 15 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0005719661712646484 length of segment : 17 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0005004405975341797 length of segment : 29 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0014472007751464844 length of segment : 38 time for calcul the mask position with numpy : 9.560585021972656e-05 nb_pixel_total : 4073 time to create 1 rle with old method : 0.005185127258300781 length of segment : 104 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -101.02813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 33 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.00043964385986328125 length of segment : 18 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1522 time to create 1 rle with old method : 0.0020487308502197266 length of segment : 43 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 715 time to create 1 rle with old method : 0.0009391307830810547 length of segment : 37 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0004723072052001953 length of segment : 22 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 557 time to create 1 rle with old method : 0.0007226467132568359 length of segment : 40 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 768 time to create 1 rle with old method : 0.001110076904296875 length of segment : 58 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 2259 time to create 1 rle with old method : 0.0029332637786865234 length of segment : 85 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 415 time to create 1 rle with old method : 0.0006723403930664062 length of segment : 28 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 1785 time to create 1 rle with old method : 0.0023314952850341797 length of segment : 74 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1423 time to create 1 rle with old method : 0.0018055438995361328 length of segment : 58 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 2389 time to create 1 rle with old method : 0.0030570030212402344 length of segment : 66 time for calcul the mask position with numpy : 0.00013017654418945312 nb_pixel_total : 3040 time to create 1 rle with old method : 0.00421905517578125 length of segment : 62 time for calcul the mask position with numpy : 0.00016307830810546875 nb_pixel_total : 3845 time to create 1 rle with old method : 0.004695415496826172 length of segment : 145 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1487 time to create 1 rle with old method : 0.0018463134765625 length of segment : 61 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002932548522949219 length of segment : 13 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0005793571472167969 length of segment : 22 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0002181529998779297 length of segment : 7 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0006055831909179688 length of segment : 25 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 456 time to create 1 rle with old method : 0.0007433891296386719 length of segment : 37 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0008423328399658203 length of segment : 27 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0004937648773193359 length of segment : 28 time for calcul the mask position with numpy : 0.0001068115234375 nb_pixel_total : 1792 time to create 1 rle with old method : 0.0032749176025390625 length of segment : 61 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1206 time to create 1 rle with old method : 0.001552581787109375 length of segment : 41 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0008199214935302734 length of segment : 28 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.0006117820739746094 length of segment : 41 time for calcul the mask position with numpy : 0.0001518726348876953 nb_pixel_total : 2875 time to create 1 rle with old method : 0.0036025047302246094 length of segment : 116 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0002715587615966797 length of segment : 24 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 3873 time to create 1 rle with old method : 0.004818439483642578 length of segment : 75 time for calcul the mask position with numpy : 9.751319885253906e-05 nb_pixel_total : 838 time to create 1 rle with old method : 0.0022029876708984375 length of segment : 27 time for calcul the mask position with numpy : 0.0001423358917236328 nb_pixel_total : 1045 time to create 1 rle with old method : 0.0016045570373535156 length of segment : 40 time for calcul the mask position with numpy : 0.00016355514526367188 nb_pixel_total : 1394 time to create 1 rle with old method : 0.0019307136535644531 length of segment : 55 time for calcul the mask position with numpy : 0.00017547607421875 nb_pixel_total : 1976 time to create 1 rle with old method : 0.0027463436126708984 length of segment : 50 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0007550716400146484 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -102.47344 max: 150.66641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.0011129379272460938 length of segment : 33 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0006306171417236328 length of segment : 22 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 823 time to create 1 rle with old method : 0.0010151863098144531 length of segment : 46 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 700 time to create 1 rle with old method : 0.0009531974792480469 length of segment : 45 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0005080699920654297 length of segment : 11 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001976490020751953 length of segment : 12 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.0002033710479736328 length of segment : 12 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.000762939453125 length of segment : 21 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1071 time to create 1 rle with old method : 0.0013837814331054688 length of segment : 60 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 1645 time to create 1 rle with old method : 0.0021600723266601562 length of segment : 55 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0006704330444335938 length of segment : 43 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0007331371307373047 length of segment : 25 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.00046133995056152344 length of segment : 35 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0008797645568847656 length of segment : 24 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006086826324462891 length of segment : 28 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1655 time to create 1 rle with old method : 0.0020842552185058594 length of segment : 42 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0007572174072265625 length of segment : 19 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1169 time to create 1 rle with old method : 0.0015032291412353516 length of segment : 52 Processing 1 images image shape: (400, 400, 3) min: 9.00000 max: 245.00000 molded_images shape: (1, 640, 640, 3) min: -107.80547 max: 128.39687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1829 time to create 1 rle with old method : 0.002256631851196289 length of segment : 63 Processing 1 images image shape: (400, 160, 3) min: 29.00000 max: 152.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 42.84219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -91.50469 max: 150.83828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00034928321838378906 length of segment : 20 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 682 time to create 1 rle with old method : 0.0009579658508300781 length of segment : 46 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1174 time to create 1 rle with old method : 0.0015277862548828125 length of segment : 62 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007023811340332031 length of segment : 24 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1357 time to create 1 rle with old method : 0.001764059066772461 length of segment : 29 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1483 time to create 1 rle with old method : 0.0020101070404052734 length of segment : 34 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1244 time to create 1 rle with old method : 0.0016810894012451172 length of segment : 63 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.94453 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 43 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0007734298706054688 length of segment : 39 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 928 time to create 1 rle with old method : 0.0016641616821289062 length of segment : 40 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.0017478466033935547 length of segment : 26 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 2895 time to create 1 rle with old method : 0.00414276123046875 length of segment : 108 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1099 time to create 1 rle with old method : 0.0014314651489257812 length of segment : 66 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0010237693786621094 length of segment : 43 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 2191 time to create 1 rle with old method : 0.0028481483459472656 length of segment : 67 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.0012969970703125 length of segment : 60 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0009410381317138672 length of segment : 36 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1149 time to create 1 rle with old method : 0.0017287731170654297 length of segment : 41 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003993511199951172 length of segment : 20 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005726814270019531 length of segment : 22 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005838871002197266 length of segment : 29 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0005280971527099609 length of segment : 27 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0009472370147705078 length of segment : 42 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1993 time to create 1 rle with old method : 0.0030221939086914062 length of segment : 98 time for calcul the mask position with numpy : 0.00011944770812988281 nb_pixel_total : 1476 time to create 1 rle with old method : 0.002144336700439453 length of segment : 51 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 1134 time to create 1 rle with old method : 0.001798868179321289 length of segment : 54 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 1356 time to create 1 rle with old method : 0.0018622875213623047 length of segment : 44 time for calcul the mask position with numpy : 0.00011920928955078125 nb_pixel_total : 3663 time to create 1 rle with old method : 0.004796743392944336 length of segment : 98 time for calcul the mask position with numpy : 0.000125885009765625 nb_pixel_total : 5174 time to create 1 rle with old method : 0.006261110305786133 length of segment : 93 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 2523 time to create 1 rle with old method : 0.0032587051391601562 length of segment : 48 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 404 time to create 1 rle with old method : 0.0005645751953125 length of segment : 31 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 736 time to create 1 rle with old method : 0.0018458366394042969 length of segment : 26 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 1831 time to create 1 rle with old method : 0.0032510757446289062 length of segment : 55 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 2652 time to create 1 rle with old method : 0.003676891326904297 length of segment : 89 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 892 time to create 1 rle with old method : 0.0011339187622070312 length of segment : 34 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 818 time to create 1 rle with old method : 0.0011909008026123047 length of segment : 30 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1107 time to create 1 rle with old method : 0.0014643669128417969 length of segment : 79 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1006 time to create 1 rle with old method : 0.0013227462768554688 length of segment : 53 time for calcul the mask position with numpy : 0.0001232624053955078 nb_pixel_total : 2741 time to create 1 rle with old method : 0.0034630298614501953 length of segment : 103 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1470 time to create 1 rle with old method : 0.0018231868743896484 length of segment : 59 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 2883 time to create 1 rle with old method : 0.0034630298614501953 length of segment : 72 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 616 time to create 1 rle with old method : 0.0008113384246826172 length of segment : 38 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0006775856018066406 length of segment : 33 time for calcul the mask position with numpy : 0.00013971328735351562 nb_pixel_total : 7787 time to create 1 rle with old method : 0.009691953659057617 length of segment : 83 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 1956 time to create 1 rle with old method : 0.0024139881134033203 length of segment : 61 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003757476806640625 length of segment : 13 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 1976 time to create 1 rle with old method : 0.0025339126586914062 length of segment : 51 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.00041747093200683594 length of segment : 14 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1487 time to create 1 rle with old method : 0.0018270015716552734 length of segment : 56 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 880 time to create 1 rle with old method : 0.001190185546875 length of segment : 32 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0008490085601806641 length of segment : 39 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.95391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 60 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00038170814514160156 length of segment : 18 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 570 time to create 1 rle with old method : 0.0008008480072021484 length of segment : 18 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 1582 time to create 1 rle with old method : 0.0020575523376464844 length of segment : 35 time for calcul the mask position with numpy : 0.0001232624053955078 nb_pixel_total : 3118 time to create 1 rle with old method : 0.003948211669921875 length of segment : 86 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1534 time to create 1 rle with old method : 0.0019485950469970703 length of segment : 40 time for calcul the mask position with numpy : 0.00015807151794433594 nb_pixel_total : 5563 time to create 1 rle with old method : 0.006575345993041992 length of segment : 108 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 1628 time to create 1 rle with old method : 0.002133607864379883 length of segment : 51 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 2098 time to create 1 rle with old method : 0.0025568008422851562 length of segment : 107 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 856 time to create 1 rle with old method : 0.0011670589447021484 length of segment : 31 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1681 time to create 1 rle with old method : 0.0021364688873291016 length of segment : 44 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0017724037170410156 length of segment : 52 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003833770751953125 length of segment : 18 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 3214 time to create 1 rle with old method : 0.0039920806884765625 length of segment : 59 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 745 time to create 1 rle with old method : 0.001065969467163086 length of segment : 32 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 1304 time to create 1 rle with old method : 0.001692056655883789 length of segment : 32 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 1567 time to create 1 rle with old method : 0.002084016799926758 length of segment : 89 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0007159709930419922 length of segment : 19 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 1561 time to create 1 rle with old method : 0.0019736289978027344 length of segment : 63 time for calcul the mask position with numpy : 0.00010704994201660156 nb_pixel_total : 2428 time to create 1 rle with old method : 0.003274202346801758 length of segment : 112 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 480 time to create 1 rle with old method : 0.0006768703460693359 length of segment : 19 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004780292510986328 length of segment : 27 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0007963180541992188 length of segment : 48 time for calcul the mask position with numpy : 9.846687316894531e-05 nb_pixel_total : 3380 time to create 1 rle with old method : 0.004109859466552734 length of segment : 107 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003707408905029297 length of segment : 26 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 4379 time to create 1 rle with old method : 0.005701303482055664 length of segment : 60 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 831 time to create 1 rle with old method : 0.0011081695556640625 length of segment : 33 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.00039887428283691406 length of segment : 21 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1019 time to create 1 rle with old method : 0.0013129711151123047 length of segment : 34 time for calcul the mask position with numpy : 0.00011014938354492188 nb_pixel_total : 2916 time to create 1 rle with old method : 0.0037164688110351562 length of segment : 67 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1619 time to create 1 rle with old method : 0.0019245147705078125 length of segment : 96 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1111 time to create 1 rle with old method : 0.0013773441314697266 length of segment : 53 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 3206 time to create 1 rle with old method : 0.004117727279663086 length of segment : 60 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003185272216796875 length of segment : 13 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 711 time to create 1 rle with old method : 0.0009865760803222656 length of segment : 34 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0004169940948486328 length of segment : 15 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 2158 time to create 1 rle with old method : 0.0026819705963134766 length of segment : 68 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.00046324729919433594 length of segment : 29 time for calcul the mask position with numpy : 0.00021123886108398438 nb_pixel_total : 7107 time to create 1 rle with old method : 0.008353233337402344 length of segment : 123 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1612 time to create 1 rle with old method : 0.0018396377563476562 length of segment : 99 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1083 time to create 1 rle with old method : 0.0013470649719238281 length of segment : 51 time for calcul the mask position with numpy : 0.00010967254638671875 nb_pixel_total : 4465 time to create 1 rle with old method : 0.0050923824310302734 length of segment : 58 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 3158 time to create 1 rle with old method : 0.003734111785888672 length of segment : 64 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006773471832275391 length of segment : 26 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1392 time to create 1 rle with old method : 0.0016956329345703125 length of segment : 38 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 910 time to create 1 rle with old method : 0.0011754035949707031 length of segment : 54 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002722740173339844 length of segment : 17 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 499 time to create 1 rle with old method : 0.0006420612335205078 length of segment : 66 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 3127 time to create 1 rle with old method : 0.003686666488647461 length of segment : 60 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1457 time to create 1 rle with old method : 0.001837015151977539 length of segment : 70 time for calcul the mask position with numpy : 0.00015497207641601562 nb_pixel_total : 5984 time to create 1 rle with old method : 0.0074803829193115234 length of segment : 116 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005829334259033203 length of segment : 38 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 18 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004391670227050781 length of segment : 32 time for calcul the mask position with numpy : 0.00015473365783691406 nb_pixel_total : 6358 time to create 1 rle with old method : 0.007384777069091797 length of segment : 119 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0006260871887207031 length of segment : 19 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 3190 time to create 1 rle with old method : 0.003909587860107422 length of segment : 62 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1573 time to create 1 rle with old method : 0.001956462860107422 length of segment : 77 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0006618499755859375 length of segment : 28 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00027251243591308594 length of segment : 30 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 2113 time to create 1 rle with old method : 0.002663135528564453 length of segment : 65 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.60625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 52 time for calcul the mask position with numpy : 0.00017762184143066406 nb_pixel_total : 1057 time to create 1 rle with old method : 0.0039751529693603516 length of segment : 43 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0007085800170898438 length of segment : 25 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 577 time to create 1 rle with old method : 0.0011816024780273438 length of segment : 25 time for calcul the mask position with numpy : 0.00012993812561035156 nb_pixel_total : 2087 time to create 1 rle with old method : 0.003652334213256836 length of segment : 69 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.00036454200744628906 length of segment : 26 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 1009 time to create 1 rle with old method : 0.001331329345703125 length of segment : 58 time for calcul the mask position with numpy : 0.00011086463928222656 nb_pixel_total : 2260 time to create 1 rle with old method : 0.003125905990600586 length of segment : 40 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0005381107330322266 length of segment : 18 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004019737243652344 length of segment : 20 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 939 time to create 1 rle with old method : 0.001317739486694336 length of segment : 35 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 2813 time to create 1 rle with old method : 0.0035414695739746094 length of segment : 79 time for calcul the mask position with numpy : 0.00033020973205566406 nb_pixel_total : 10483 time to create 1 rle with old method : 0.012253761291503906 length of segment : 174 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1333 time to create 1 rle with old method : 0.0017511844635009766 length of segment : 47 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0006265640258789062 length of segment : 40 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 2981 time to create 1 rle with old method : 0.003848552703857422 length of segment : 56 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 715 time to create 1 rle with old method : 0.001168966293334961 length of segment : 32 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.00027823448181152344 length of segment : 19 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0005393028259277344 length of segment : 22 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 874 time to create 1 rle with old method : 0.0018029212951660156 length of segment : 28 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0007491111755371094 length of segment : 35 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 860 time to create 1 rle with old method : 0.0012280941009521484 length of segment : 38 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 1469 time to create 1 rle with old method : 0.0021288394927978516 length of segment : 48 time for calcul the mask position with numpy : 0.00020456314086914062 nb_pixel_total : 6456 time to create 1 rle with old method : 0.009557485580444336 length of segment : 127 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 627 time to create 1 rle with old method : 0.0011813640594482422 length of segment : 39 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 836 time to create 1 rle with old method : 0.0011906623840332031 length of segment : 50 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 906 time to create 1 rle with old method : 0.0014333724975585938 length of segment : 35 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 935 time to create 1 rle with old method : 0.0014350414276123047 length of segment : 45 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.001096487045288086 length of segment : 37 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 837 time to create 1 rle with old method : 0.0011506080627441406 length of segment : 51 time for calcul the mask position with numpy : 0.00014543533325195312 nb_pixel_total : 5505 time to create 1 rle with old method : 0.006899833679199219 length of segment : 80 time for calcul the mask position with numpy : 0.00011897087097167969 nb_pixel_total : 3890 time to create 1 rle with old method : 0.00482177734375 length of segment : 66 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 2888 time to create 1 rle with old method : 0.003731966018676758 length of segment : 49 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 2110 time to create 1 rle with old method : 0.002714872360229492 length of segment : 60 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1004 time to create 1 rle with old method : 0.0014336109161376953 length of segment : 34 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0011188983917236328 length of segment : 39 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0007228851318359375 length of segment : 33 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1349 time to create 1 rle with old method : 0.0019576549530029297 length of segment : 30 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003535747528076172 length of segment : 19 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1348 time to create 1 rle with old method : 0.002060413360595703 length of segment : 41 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 909 time to create 1 rle with old method : 0.0012161731719970703 length of segment : 27 time for calcul the mask position with numpy : 0.0001246929168701172 nb_pixel_total : 5791 time to create 1 rle with old method : 0.007178783416748047 length of segment : 84 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0016300678253173828 length of segment : 74 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 2498 time to create 1 rle with old method : 0.0031995773315429688 length of segment : 65 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 608 time to create 1 rle with old method : 0.0009472370147705078 length of segment : 18 time for calcul the mask position with numpy : 0.000339508056640625 nb_pixel_total : 10931 time to create 1 rle with old method : 0.012931585311889648 length of segment : 177 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1006 time to create 1 rle with old method : 0.0012612342834472656 length of segment : 45 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0008273124694824219 length of segment : 53 time for calcul the mask position with numpy : 0.00025582313537597656 nb_pixel_total : 6685 time to create 1 rle with old method : 0.008045434951782227 length of segment : 198 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 3186 time to create 1 rle with old method : 0.0038115978240966797 length of segment : 87 time for calcul the mask position with numpy : 0.00010776519775390625 nb_pixel_total : 2082 time to create 1 rle with old method : 0.002688884735107422 length of segment : 61 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 1929 time to create 1 rle with old method : 0.002421855926513672 length of segment : 60 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1445 time to create 1 rle with old method : 0.0018768310546875 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.72734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 38 time for calcul the mask position with numpy : 0.00012302398681640625 nb_pixel_total : 1282 time to create 1 rle with old method : 0.0023391246795654297 length of segment : 42 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 2095 time to create 1 rle with old method : 0.0037369728088378906 length of segment : 49 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0007803440093994141 length of segment : 23 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 1069 time to create 1 rle with old method : 0.0019898414611816406 length of segment : 35 time for calcul the mask position with numpy : 0.00021147727966308594 nb_pixel_total : 6449 time to create 1 rle with old method : 0.009497642517089844 length of segment : 112 time for calcul the mask position with numpy : 0.00010228157043457031 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003447532653808594 length of segment : 23 time for calcul the mask position with numpy : 0.0001780986785888672 nb_pixel_total : 942 time to create 1 rle with old method : 0.002357959747314453 length of segment : 45 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 126 time to create 1 rle with old method : 0.0002276897430419922 length of segment : 13 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0006270408630371094 length of segment : 25 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1378 time to create 1 rle with old method : 0.0017731189727783203 length of segment : 49 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0008990764617919922 length of segment : 29 time for calcul the mask position with numpy : 0.00019240379333496094 nb_pixel_total : 3680 time to create 1 rle with old method : 0.0048482418060302734 length of segment : 97 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 404 time to create 1 rle with old method : 0.0005862712860107422 length of segment : 20 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 976 time to create 1 rle with old method : 0.0013108253479003906 length of segment : 33 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 586 time to create 1 rle with old method : 0.0007998943328857422 length of segment : 35 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 908 time to create 1 rle with old method : 0.0012106895446777344 length of segment : 45 time for calcul the mask position with numpy : 0.00016570091247558594 nb_pixel_total : 2023 time to create 1 rle with old method : 0.004528522491455078 length of segment : 104 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 1788 time to create 1 rle with old method : 0.003093242645263672 length of segment : 59 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 911 time to create 1 rle with old method : 0.001644134521484375 length of segment : 38 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 1151 time to create 1 rle with old method : 0.0020384788513183594 length of segment : 48 time for calcul the mask position with numpy : 0.0001277923583984375 nb_pixel_total : 2448 time to create 1 rle with old method : 0.004380464553833008 length of segment : 55 time for calcul the mask position with numpy : 0.00017547607421875 nb_pixel_total : 3422 time to create 1 rle with old method : 0.006102323532104492 length of segment : 89 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1738 time to create 1 rle with old method : 0.002122163772583008 length of segment : 58 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.00031256675720214844 length of segment : 17 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0004391670227050781 length of segment : 25 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 2499 time to create 1 rle with old method : 0.003195524215698242 length of segment : 73 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 736 time to create 1 rle with old method : 0.0010080337524414062 length of segment : 36 time for calcul the mask position with numpy : 0.00013303756713867188 nb_pixel_total : 1660 time to create 1 rle with old method : 0.002074003219604492 length of segment : 66 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1152 time to create 1 rle with old method : 0.001470804214477539 length of segment : 33 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1285 time to create 1 rle with old method : 0.0016584396362304688 length of segment : 44 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 1140 time to create 1 rle with old method : 0.002198457717895508 length of segment : 32 time for calcul the mask position with numpy : 0.00012493133544921875 nb_pixel_total : 2748 time to create 1 rle with old method : 0.003328084945678711 length of segment : 71 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 389 time to create 1 rle with old method : 0.0005693435668945312 2025-03-07 12:20:53.031750: F tensorflow/core/kernels/bias_op_gpu.cu.cc:97] Non-OK-status: GpuLaunchKernel(BiasNCHWKernel, config.block_count, config.thread_per_block, 0, d.stream(), config.virtual_thread_count, input, bias, output, bias_size, image_size) status: Internal: an illegal memory access was encountered max_time_sub_proc : 3600 Catched exception ! Connect or reconnect ! in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 18.97user 13.43system 1:00:08elapsed 0%CPU (0avgtext+0avgdata 2380088maxresident)k 645248inputs+4248outputs (9685major+730215minor)pagefaults 0swaps