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 : 2755758 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 : ['2598497'] with mtr_portfolio_ids : ['20662767'] and first list_photo_ids : [] new path : /proc/2755758/ 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 : 0.6787374019622803 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 Wed Feb 19 06:20:29 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3618 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-19 06:20:32.198478: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-19 06:20:32.223140: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-19 06:20:32.225080: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fd79c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-19 06:20:32.225127: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-19 06:20:32.228811: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-19 06:20:32.466642: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x18fab5f0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-19 06:20:32.466682: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-19 06:20:32.467289: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-19 06:20:32.467603: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-19 06:20:32.469693: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-19 06:20:32.471893: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-19 06:20:32.472444: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-19 06:20:32.475341: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-19 06:20:32.476861: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-19 06:20:32.481696: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-19 06:20:32.482962: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-19 06:20:32.483058: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-19 06:20:32.483677: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-19 06:20:32.483695: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-19 06:20:32.483703: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-19 06:20:32.484768: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3166 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-02-19 06:20:32.883046: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-19 06:20:32.883146: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-19 06:20:32.883175: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-19 06:20:32.883202: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-19 06:20:32.883227: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-19 06:20:32.883252: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-19 06:20:32.883277: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-19 06:20:32.883302: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-19 06:20:32.884436: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-19 06:20:32.885416: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-19 06:20:32.885462: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-19 06:20:32.885480: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-19 06:20:32.885497: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-19 06:20:32.885513: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-19 06:20:32.885530: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-19 06:20:32.885546: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-19 06:20:32.885563: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-19 06:20:32.886436: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-19 06:20:32.886467: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-19 06:20:32.886477: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-19 06:20:32.886487: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-19 06:20:32.887490: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3166 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-19 06:20:43.532079: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-19 06:20:43.707988: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-19 06:20:45.249508: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.250133: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2506397952 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.250720: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.10G (2255758080 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.250759: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.251377: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.251395: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.259074: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.259120: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.259733: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.259752: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.266714: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.266768: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.267425: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.267452: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.301955: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.302108: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.303180: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.303224: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.310267: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.310312: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.311359: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.311392: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-19 06:20:45.347108: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.347736: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.349654: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.350201: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.396118: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.396787: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.399242: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.399879: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.431461: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.432092: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.433952: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.434561: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.441594: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.442206: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.444231: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.444808: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.452412: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.453013: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.454868: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.455504: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.490596: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.491191: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.491785: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.492367: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.496476: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.497083: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.514058: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.514643: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.515226: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.515797: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.528350: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.528933: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.529483: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.530055: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.534533: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.535159: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.539926: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.540539: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.552385: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.552922: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.556949: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.557511: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.558066: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.558651: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.559444: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.560025: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.570401: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.570944: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.571531: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.572102: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.572680: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.573297: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.588027: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.588583: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.613294: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.613350: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-02-19 06:20:45.614412: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.615511: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.622740: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.623345: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.623981: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.624582: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.632570: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.633104: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.649235: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.649854: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.650442: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.651046: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.655178: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.655789: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.656367: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.656960: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.658048: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.668281: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.668894: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.678021: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.678712: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.679318: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.679901: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.680483: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-19 06:20:45.681018: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.59G (2784886784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 4 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.98906 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 9.989738464355469e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0009620189666748047 length of segment : 27 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 1315 time to create 1 rle with old method : 0.0023801326751708984 length of segment : 40 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0005729198455810547 length of segment : 7 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1873 time to create 1 rle with old method : 0.003120899200439453 length of segment : 64 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0005421638488769531 length of segment : 16 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0006337165832519531 length of segment : 19 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 669 time to create 1 rle with old method : 0.0011720657348632812 length of segment : 37 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1325 time to create 1 rle with old method : 0.002445220947265625 length of segment : 40 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.00046563148498535156 length of segment : 17 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 56 time to create 1 rle with old method : 0.0001404285430908203 length of segment : 5 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.00044846534729003906 length of segment : 32 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1785 time to create 1 rle with old method : 0.0023148059844970703 length of segment : 59 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1106 time to create 1 rle with old method : 0.0016014575958251953 length of segment : 32 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002613067626953125 length of segment : 13 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 885 time to create 1 rle with old method : 0.0011115074157714844 length of segment : 35 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0007777214050292969 length of segment : 23 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006442070007324219 length of segment : 44 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.98516 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 469 time to create 1 rle with old method : 0.0006654262542724609 length of segment : 29 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0004856586456298828 length of segment : 25 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.0007083415985107422 length of segment : 23 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.0002810955047607422 length of segment : 14 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0005548000335693359 length of segment : 18 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.0004649162292480469 length of segment : 13 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002789497375488281 length of segment : 21 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.001039743423461914 length of segment : 30 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 847 time to create 1 rle with old method : 0.0010809898376464844 length of segment : 30 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003464221954345703 length of segment : 23 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003848075866699219 length of segment : 12 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0004191398620605469 length of segment : 19 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003387928009033203 length of segment : 28 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 825 time to create 1 rle with old method : 0.00106048583984375 length of segment : 32 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0008704662322998047 length of segment : 48 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0007612705230712891 length of segment : 28 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1729 time to create 1 rle with old method : 0.002174854278564453 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.88750 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 : 7.82012939453125e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0004634857177734375 length of segment : 16 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 762 time to create 1 rle with old method : 0.001665353775024414 length of segment : 30 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 366 time to create 1 rle with old method : 0.0010342597961425781 length of segment : 22 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0008177757263183594 length of segment : 22 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 993 time to create 1 rle with old method : 0.0022802352905273438 length of segment : 43 time for calcul the mask position with numpy : 0.0001285076141357422 nb_pixel_total : 1894 time to create 1 rle with old method : 0.0029087066650390625 length of segment : 58 time for calcul the mask position with numpy : 8.559226989746094e-05 nb_pixel_total : 603 time to create 1 rle with old method : 0.0009658336639404297 length of segment : 30 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 687 time to create 1 rle with old method : 0.0010311603546142578 length of segment : 51 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 961 time to create 1 rle with old method : 0.0013246536254882812 length of segment : 31 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005633831024169922 length of segment : 19 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.000247955322265625 length of segment : 6 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 957 time to create 1 rle with old method : 0.0013151168823242188 length of segment : 41 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1062 time to create 1 rle with old method : 0.0014007091522216797 length of segment : 40 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1103 time to create 1 rle with old method : 0.0014300346374511719 length of segment : 39 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1853 time to create 1 rle with old method : 0.002289295196533203 length of segment : 61 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0005478858947753906 length of segment : 32 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004787445068359375 length of segment : 14 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 992 time to create 1 rle with old method : 0.0012848377227783203 length of segment : 38 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00039887428283691406 length of segment : 18 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004935264587402344 length of segment : 23 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006926059722900391 length of segment : 34 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1499 time to create 1 rle with old method : 0.0020389556884765625 length of segment : 51 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 810 time to create 1 rle with old method : 0.0011358261108398438 length of segment : 37 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0010538101196289062 length of segment : 23 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 812 time to create 1 rle with old method : 0.0010788440704345703 length of segment : 38 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0009484291076660156 length of segment : 25 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0006794929504394531 length of segment : 23 time for calcul the mask position with numpy : 0.00017523765563964844 nb_pixel_total : 2705 time to create 1 rle with old method : 0.004412174224853516 length of segment : 61 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 672 time to create 1 rle with old method : 0.0011167526245117188 length of segment : 21 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002872943878173828 length of segment : 10 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.11797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 1319 time to create 1 rle with old method : 0.002767324447631836 length of segment : 38 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 772 time to create 1 rle with old method : 0.0016489028930664062 length of segment : 37 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0006971359252929688 length of segment : 29 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 1541 time to create 1 rle with old method : 0.0031766891479492188 length of segment : 46 time for calcul the mask position with numpy : 0.0001316070556640625 nb_pixel_total : 3338 time to create 1 rle with old method : 0.00712275505065918 length of segment : 55 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 1069 time to create 1 rle with old method : 0.0017092227935791016 length of segment : 53 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1344 time to create 1 rle with old method : 0.0017461776733398438 length of segment : 87 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 612 time to create 1 rle with old method : 0.0008900165557861328 length of segment : 27 time for calcul the mask position with numpy : 0.0004172325134277344 nb_pixel_total : 27680 time to create 1 rle with old method : 0.029656648635864258 length of segment : 211 time for calcul the mask position with numpy : 0.0002872943878173828 nb_pixel_total : 17648 time to create 1 rle with old method : 0.019171476364135742 length of segment : 217 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0007767677307128906 length of segment : 23 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006501674652099609 length of segment : 23 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.0001468658447265625 length of segment : 11 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004680156707763672 length of segment : 29 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005781650543212891 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 92.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -31.70000 max: 147.93594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00022792816162109375 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 23.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -100.70000 max: 150.11562 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 1536 time to create 1 rle with old method : 0.0021016597747802734 length of segment : 47 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.0002460479736328125 length of segment : 17 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 208.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 85.72891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 718 time to create 1 rle with old method : 0.0013659000396728516 length of segment : 31 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0003478527069091797 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.20000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 27 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 703 time to create 1 rle with old method : 0.0010192394256591797 length of segment : 32 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 774 time to create 1 rle with old method : 0.0010662078857421875 length of segment : 40 time for calcul the mask position with numpy : 0.00016236305236816406 nb_pixel_total : 4992 time to create 1 rle with old method : 0.006657123565673828 length of segment : 82 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 1353 time to create 1 rle with old method : 0.0020830631256103516 length of segment : 51 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 644 time to create 1 rle with old method : 0.001544952392578125 length of segment : 26 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 2180 time to create 1 rle with old method : 0.005663156509399414 length of segment : 63 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.000980377197265625 length of segment : 35 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.001668691635131836 length of segment : 35 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.0009701251983642578 length of segment : 27 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002715587615966797 length of segment : 17 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 4087 time to create 1 rle with old method : 0.006688117980957031 length of segment : 84 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0005125999450683594 length of segment : 26 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 807 time to create 1 rle with old method : 0.0015311241149902344 length of segment : 48 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 840 time to create 1 rle with old method : 0.0010204315185546875 length of segment : 29 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0008819103240966797 length of segment : 33 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0004467964172363281 length of segment : 19 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0005688667297363281 length of segment : 22 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1035 time to create 1 rle with old method : 0.0013697147369384766 length of segment : 49 time for calcul the mask position with numpy : 0.00011444091796875 nb_pixel_total : 1454 time to create 1 rle with old method : 0.0019118785858154297 length of segment : 60 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.00042247772216796875 length of segment : 21 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.0010919570922851562 length of segment : 29 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006058216094970703 length of segment : 32 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 786 time to create 1 rle with old method : 0.0009715557098388672 length of segment : 37 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00033473968505859375 length of segment : 18 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0008280277252197266 length of segment : 35 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 2331 time to create 1 rle with old method : 0.0026960372924804688 length of segment : 88 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0009276866912841797 length of segment : 35 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.14531 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 973 time to create 1 rle with old method : 0.001148223876953125 length of segment : 96 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005853176116943359 length of segment : 36 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1034 time to create 1 rle with old method : 0.0012998580932617188 length of segment : 56 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 40 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005402565002441406 length of segment : 30 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.00046753883361816406 length of segment : 19 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.000469207763671875 length of segment : 21 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005292892456054688 length of segment : 20 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0003085136413574219 length of segment : 14 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 934 time to create 1 rle with old method : 0.0012111663818359375 length of segment : 80 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1247 time to create 1 rle with old method : 0.0017178058624267578 length of segment : 29 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 529 time to create 1 rle with old method : 0.0007274150848388672 length of segment : 30 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00024247169494628906 length of segment : 19 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.00040030479431152344 length of segment : 20 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0006272792816162109 length of segment : 21 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00029206275939941406 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.23359 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 997 time to create 1 rle with old method : 0.0014388561248779297 length of segment : 30 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1313 time to create 1 rle with old method : 0.0017135143280029297 length of segment : 52 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005280971527099609 length of segment : 26 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0013267993927001953 length of segment : 35 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0007028579711914062 length of segment : 24 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0007061958312988281 length of segment : 20 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 2486 time to create 1 rle with old method : 0.0032033920288085938 length of segment : 56 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 876 time to create 1 rle with old method : 0.001087188720703125 length of segment : 50 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.0005171298980712891 length of segment : 17 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0010044574737548828 length of segment : 30 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 977 time to create 1 rle with old method : 0.0012536048889160156 length of segment : 57 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0009372234344482422 length of segment : 34 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.00042700767517089844 length of segment : 22 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005445480346679688 length of segment : 21 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0005841255187988281 length of segment : 37 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 679 time to create 1 rle with old method : 0.0009226799011230469 length of segment : 47 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1168 time to create 1 rle with old method : 0.001519918441772461 length of segment : 55 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1056 time to create 1 rle with old method : 0.001520395278930664 length of segment : 36 time for calcul the mask position with numpy : 0.0001068115234375 nb_pixel_total : 3573 time to create 1 rle with old method : 0.0052700042724609375 length of segment : 65 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 380 time to create 1 rle with old method : 0.0005297660827636719 length of segment : 27 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 1020 time to create 1 rle with old method : 0.0014128684997558594 length of segment : 40 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.00046324729919433594 length of segment : 24 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 686 time to create 1 rle with old method : 0.0008845329284667969 length of segment : 44 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0007350444793701172 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.78594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0006406307220458984 length of segment : 32 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 898 time to create 1 rle with old method : 0.0011682510375976562 length of segment : 36 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1756 time to create 1 rle with old method : 0.0022444725036621094 length of segment : 47 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0007228851318359375 length of segment : 33 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 1037 time to create 1 rle with old method : 0.0016632080078125 length of segment : 31 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 670 time to create 1 rle with old method : 0.0009136199951171875 length of segment : 27 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003230571746826172 length of segment : 22 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00031757354736328125 length of segment : 23 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.0003802776336669922 length of segment : 28 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0008001327514648438 length of segment : 28 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005552768707275391 length of segment : 23 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 4143 time to create 1 rle with old method : 0.005215167999267578 length of segment : 64 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 4169 time to create 1 rle with old method : 0.005303621292114258 length of segment : 65 Processing 1 images image shape: (400, 400, 3) min: 52.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -62.46172 max: 151.01797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00022149085998535156 length of segment : 15 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006532669067382812 length of segment : 28 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.00034117698669433594 length of segment : 13 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0007460117340087891 length of segment : 27 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.00043129920959472656 length of segment : 31 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1314 time to create 1 rle with old method : 0.0015730857849121094 length of segment : 37 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.00024962425231933594 length of segment : 16 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0010704994201660156 length of segment : 23 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1426 time to create 1 rle with old method : 0.0018377304077148438 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.11797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1188 time to create 1 rle with old method : 0.001512289047241211 length of segment : 34 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005984306335449219 length of segment : 27 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0005238056182861328 length of segment : 21 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.00035190582275390625 length of segment : 25 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1061 time to create 1 rle with old method : 0.0013573169708251953 length of segment : 44 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0005514621734619141 length of segment : 32 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0003552436828613281 length of segment : 24 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00026607513427734375 length of segment : 16 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0005705356597900391 length of segment : 24 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.0001583099365234375 length of segment : 16 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.00018286705017089844 length of segment : 13 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004165172576904297 length of segment : 20 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005862712860107422 length of segment : 17 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 584 time to create 1 rle with old method : 0.0007905960083007812 length of segment : 57 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005922317504882812 length of segment : 27 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.000335693359375 length of segment : 22 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0003743171691894531 length of segment : 21 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.0001437664031982422 length of segment : 9 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003902912139892578 length of segment : 30 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.0002751350402832031 length of segment : 17 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.000762939453125 length of segment : 51 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001437664031982422 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.46563 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 820 time to create 1 rle with old method : 0.001050710678100586 length of segment : 47 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 895 time to create 1 rle with old method : 0.0011394023895263672 length of segment : 43 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0007908344268798828 length of segment : 34 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.0011386871337890625 length of segment : 31 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 846 time to create 1 rle with old method : 0.0011453628540039062 length of segment : 26 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0014913082122802734 length of segment : 59 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.0003161430358886719 length of segment : 13 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 419 time to create 1 rle with old method : 0.0006339550018310547 length of segment : 34 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005347728729248047 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.05156 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.00032639503479003906 length of segment : 21 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 985 time to create 1 rle with old method : 0.0012929439544677734 length of segment : 36 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 1042 time to create 1 rle with old method : 0.002088785171508789 length of segment : 30 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0002779960632324219 length of segment : 16 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.00017261505126953125 length of segment : 14 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 1289 time to create 1 rle with old method : 0.002554178237915039 length of segment : 44 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 2886 time to create 1 rle with old method : 0.004250049591064453 length of segment : 66 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.34844 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.00046181678771972656 length of segment : 31 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0008840560913085938 length of segment : 32 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0004534721374511719 length of segment : 40 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 1145 time to create 1 rle with old method : 0.0015168190002441406 length of segment : 44 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0006060600280761719 length of segment : 25 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005352497100830078 length of segment : 33 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.00037670135498046875 length of segment : 14 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1365 time to create 1 rle with old method : 0.0017118453979492188 length of segment : 79 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001838207244873047 length of segment : 10 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0006966590881347656 length of segment : 32 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00036072731018066406 length of segment : 20 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.00015592575073242188 length of segment : 11 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0004811286926269531 length of segment : 40 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.00025463104248046875 length of segment : 21 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.00025200843811035156 length of segment : 20 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.000247955322265625 length of segment : 22 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 1307 time to create 1 rle with old method : 0.0015349388122558594 length of segment : 62 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003457069396972656 length of segment : 19 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 1081 time to create 1 rle with old method : 0.0014061927795410156 length of segment : 47 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1357 time to create 1 rle with old method : 0.0017740726470947266 length of segment : 32 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1270 time to create 1 rle with old method : 0.0015611648559570312 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.58672 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 : 4.57763671875e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.00033974647521972656 length of segment : 23 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 929 time to create 1 rle with old method : 0.001180887222290039 length of segment : 38 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.00022149085998535156 length of segment : 17 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.00020575523376464844 length of segment : 16 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.000576019287109375 length of segment : 32 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0007562637329101562 length of segment : 26 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003993511199951172 length of segment : 42 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.00039649009704589844 length of segment : 34 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003311634063720703 length of segment : 29 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 722 time to create 1 rle with old method : 0.000885009765625 length of segment : 61 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003230571746826172 length of segment : 14 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 627 time to create 1 rle with old method : 0.000911712646484375 length of segment : 60 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0004687309265136719 length of segment : 31 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 626 time to create 1 rle with old method : 0.000823974609375 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.27422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0007281303405761719 length of segment : 25 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 1339 time to create 1 rle with old method : 0.0017392635345458984 length of segment : 76 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 697 time to create 1 rle with old method : 0.0009253025054931641 length of segment : 30 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.000339508056640625 length of segment : 16 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003628730773925781 length of segment : 18 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0008225440979003906 length of segment : 16 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0005772113800048828 length of segment : 31 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002682209014892578 length of segment : 19 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.0002791881561279297 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.53984 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 0.00010728836059570312 nb_pixel_total : 2126 time to create 1 rle with old method : 0.002521991729736328 length of segment : 131 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0006630420684814453 length of segment : 59 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1345 time to create 1 rle with old method : 0.0017271041870117188 length of segment : 35 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.00035643577575683594 length of segment : 46 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.000997304916381836 length of segment : 34 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005943775177001953 length of segment : 22 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0008337497711181641 length of segment : 32 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1646 time to create 1 rle with old method : 0.0020699501037597656 length of segment : 56 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1172 time to create 1 rle with old method : 0.0014538764953613281 length of segment : 32 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 572 time to create 1 rle with old method : 0.0008084774017333984 length of segment : 25 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0006420612335205078 length of segment : 32 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0005681514739990234 length of segment : 38 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 651 time to create 1 rle with old method : 0.0008463859558105469 length of segment : 22 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004673004150390625 length of segment : 22 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 672 time to create 1 rle with old method : 0.0009016990661621094 length of segment : 22 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.00033974647521972656 length of segment : 30 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003662109375 length of segment : 27 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 633 time to create 1 rle with old method : 0.0008718967437744141 length of segment : 33 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003490447998046875 length of segment : 23 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 681 time to create 1 rle with old method : 0.0009715557098388672 length of segment : 49 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007877349853515625 length of segment : 24 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 539 time to create 1 rle with old method : 0.0008502006530761719 length of segment : 19 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.0002899169921875 length of segment : 26 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.75625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005502700805664062 length of segment : 40 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 1337 time to create 1 rle with old method : 0.0016984939575195312 length of segment : 55 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004253387451171875 length of segment : 19 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0006554126739501953 length of segment : 60 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 549 time to create 1 rle with old method : 0.0007419586181640625 length of segment : 28 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003631114959716797 length of segment : 18 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00034999847412109375 length of segment : 16 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1223 time to create 1 rle with old method : 0.0016214847564697266 length of segment : 60 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002765655517578125 length of segment : 20 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.0011439323425292969 length of segment : 40 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1361 time to create 1 rle with old method : 0.0016469955444335938 length of segment : 52 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1145 time to create 1 rle with old method : 0.001402139663696289 length of segment : 43 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.00030684471130371094 length of segment : 16 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.000545501708984375 length of segment : 26 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006628036499023438 length of segment : 37 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003495216369628906 length of segment : 18 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.00021123886108398438 length of segment : 11 time for calcul the mask position with numpy : 0.00042748451232910156 nb_pixel_total : 25387 time to create 1 rle with old method : 0.030676841735839844 length of segment : 294 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 3537 time to create 1 rle with old method : 0.004164934158325195 length of segment : 50 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 3436 time to create 1 rle with old method : 0.0040590763092041016 length of segment : 48 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00049591064453125 nb_pixel_total : 44120 time to create 1 rle with old method : 0.04970669746398926 length of segment : 146 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.00017452239990234375 length of segment : 8 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004665851593017578 length of segment : 19 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 4186 time to create 1 rle with old method : 0.004998683929443359 length of segment : 85 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.000331878662109375 length of segment : 14 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003943443298339844 length of segment : 22 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00015544891357421875 length of segment : 13 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.000507354736328125 length of segment : 29 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.00044608116149902344 length of segment : 19 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.00033855438232421875 length of segment : 21 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0003845691680908203 length of segment : 20 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0006086826324462891 length of segment : 20 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.0001633167266845703 length of segment : 12 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00031876564025878906 length of segment : 19 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1361 time to create 1 rle with old method : 0.00159454345703125 length of segment : 38 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002510547637939453 length of segment : 18 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1674 time to create 1 rle with old method : 0.002127408981323242 length of segment : 44 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005288124084472656 length of segment : 29 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 727 time to create 1 rle with old method : 0.0010263919830322266 length of segment : 39 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004630088806152344 length of segment : 24 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00037932395935058594 length of segment : 23 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1208 time to create 1 rle with old method : 0.0016281604766845703 length of segment : 50 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003726482391357422 length of segment : 14 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.000370025634765625 length of segment : 15 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 3690 time to create 1 rle with old method : 0.006395816802978516 length of segment : 75 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0002434253692626953 length of segment : 21 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.0014755725860595703 length of segment : 22 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00024366378784179688 length of segment : 15 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0006542205810546875 length of segment : 26 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0004456043243408203 length of segment : 23 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0005726814270019531 length of segment : 21 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0005056858062744141 length of segment : 19 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0003459453582763672 length of segment : 14 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0013730525970458984 length of segment : 35 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.0006673336029052734 length of segment : 17 time for calcul the mask position with numpy : 0.00032520294189453125 nb_pixel_total : 18344 time to create 1 rle with old method : 0.02175116539001465 length of segment : 87 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.00037932395935058594 length of segment : 19 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006935596466064453 length of segment : 28 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0005538463592529297 length of segment : 18 Processing 1 images image shape: (240, 160, 3) min: 0.00000 max: 248.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 129.64764 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 39 time to create 1 rle with old method : 0.0001761913299560547 length of segment : 9 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1167 time to create 1 rle with old method : 0.0015494823455810547 length of segment : 24 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.95781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006430149078369141 length of segment : 25 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0011014938354492188 length of segment : 31 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 1128 time to create 1 rle with old method : 0.0014836788177490234 length of segment : 34 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 43 time to create 1 rle with old method : 0.0001392364501953125 length of segment : 5 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.0003247261047363281 length of segment : 7 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003426074981689453 length of segment : 17 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0004909038543701172 length of segment : 26 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003497600555419922 length of segment : 17 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006034374237060547 length of segment : 44 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003247261047363281 length of segment : 30 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0019085407257080078 length of segment : 42 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0004780292510986328 length of segment : 20 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1861 time to create 1 rle with old method : 0.0024590492248535156 length of segment : 74 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 674 time to create 1 rle with old method : 0.0014791488647460938 length of segment : 41 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004150867462158203 length of segment : 22 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0010406970977783203 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.79375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0008037090301513672 length of segment : 27 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 569 time to create 1 rle with old method : 0.0008776187896728516 length of segment : 24 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0005466938018798828 length of segment : 28 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001926422119140625 length of segment : 17 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 804 time to create 1 rle with old method : 0.001046895980834961 length of segment : 29 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0003647804260253906 length of segment : 27 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0005106925964355469 length of segment : 12 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0007915496826171875 length of segment : 47 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0006258487701416016 length of segment : 21 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 388 2025-02-19 06:20:52.883110: E tensorflow/stream_executor/cuda/cuda_driver.cc:939] could not synchronize on CUDA context: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered :: *** Begin stack trace *** tensorflow::CurrentStackTrace() stream_executor::gpu::GpuDriver::SynchronizeContext(stream_executor::gpu::GpuContext*) stream_executor::StreamExecutor::SynchronizeAllActivity() tensorflow::GPUUtil::SyncAll(tensorflow::Device*) tensorflow::BaseGPUDevice::Sync() tensorflow::TensorHandle::CopyToDevice(tensorflow::EagerContext const&, tensorflow::Device*, tensorflow::Tensor*) tensorflow::TensorHandleInterface::Resolve(tensorflow::Status*) TFE_TensorHandleResolve _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall PyObject_Call _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName PyEval_EvalCode PyRun_SimpleFileExFlags Py_RunMain Py_BytesMain __libc_start_main _start *** End stack trace *** 2025-02-19 06:20:52.933235: E tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:725] failed to record completion event; therefore, failed to create inter-stream dependency 2025-02-19 06:20:52.933292: I tensorflow/stream_executor/stream.cc:4938] [stream=0x1a59af20,impl=0x1a599a00] did not memcpy host-to-device; source: 0x45b41d40 2025-02-19 06:20:52.933316: E tensorflow/stream_executor/stream.cc:334] Error recording event in stream: Error recording CUDA event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered; not marking stream as bad, as the Event object may be at fault. Monitor for further errors. 2025-02-19 06:20:52.933345: E tensorflow/stream_executor/cuda/cuda_event.cc:29] Error polling for event status: failed to query event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered 2025-02-19 06:20:52.933366: F tensorflow/core/common_runtime/gpu/gpu_event_mgr.cc:273] Unexpected Event status: 1 max_time_sub_proc : 3600 Catched exception ! Connect or reconnect ! in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 18.81user 17.03system 1:00:07elapsed 0%CPU (0avgtext+0avgdata 2448252maxresident)k 126856inputs+5248outputs (11314major+682630minor)pagefaults 0swaps