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 : 1309581 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 : ['2640172'] with mtr_portfolio_ids : ['21084501'] and first list_photo_ids : [] new path : /proc/1309581/ 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 : 4.668563604354858 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 Thu Mar 6 09:20:34 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 : 10399 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-06 09:20:37.060750: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-06 09:20:37.087146: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-06 09:20:37.088788: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f77b4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-06 09:20:37.088838: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-06 09:20:37.091421: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-06 09:20:37.231812: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xa440350 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-06 09:20:37.231856: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-06 09:20:37.232826: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-06 09:20:37.233139: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-06 09:20:37.235093: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-06 09:20:37.237280: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-06 09:20:37.237590: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-06 09:20:37.239759: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-06 09:20:37.240788: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-06 09:20:37.245201: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-06 09:20:37.246761: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-06 09:20:37.246859: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-06 09:20:37.247629: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-06 09:20:37.247645: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-06 09:20:37.247655: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-06 09:20:37.248913: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9272 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-03-06 09:20:37.500876: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-06 09:20:37.501008: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-06 09:20:37.501027: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-06 09:20:37.501044: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-06 09:20:37.501060: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-06 09:20:37.501076: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-06 09:20:37.501091: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-06 09:20:37.501107: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-06 09:20:37.502259: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-06 09:20:37.503353: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-06 09:20:37.503386: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-06 09:20:37.503400: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-06 09:20:37.503413: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-06 09:20:37.503425: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-06 09:20:37.503438: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-06 09:20:37.503450: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-06 09:20:37.503462: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-06 09:20:37.504587: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-06 09:20:37.504629: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-06 09:20:37.504638: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-06 09:20:37.504646: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-06 09:20:37.505828: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9272 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-03-06 09:20:45.299014: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-06 09:20:45.461946: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-06 09:20:47.114991: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:47.115691: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:47.895428: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:47.895544: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-03-06 09:20:47.973951: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:47.974013: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:47.995239: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:47.995281: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.001939: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.001974: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.002779: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.002793: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.033624: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.033713: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 19.91MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.033744: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-03-06 09:20:48.035336: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.035370: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 16.00MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.036960: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.036999: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 16.00MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.045248: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.045357: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.046804: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.046849: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.048198: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.048233: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-06 09:20:48.049746: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.059142: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.060480: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.077304: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.078467: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.079577: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.080432: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.084724: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.085488: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.086234: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.086987: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.088800: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.099020: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.100329: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.110362: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.112307: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.113586: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.114849: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.116143: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-06 09:20:48.117379: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 4 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.93438 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 : 0.00019216537475585938 nb_pixel_total : 3659 time to create 1 rle with old method : 0.01888895034790039 length of segment : 79 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 755 time to create 1 rle with old method : 0.0017101764678955078 length of segment : 32 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 1306 time to create 1 rle with old method : 0.0026557445526123047 length of segment : 32 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0007796287536621094 length of segment : 33 time for calcul the mask position with numpy : 0.00012826919555664062 nb_pixel_total : 2313 time to create 1 rle with old method : 0.0046045780181884766 length of segment : 80 time for calcul the mask position with numpy : 0.0001327991485595703 nb_pixel_total : 1364 time to create 1 rle with old method : 0.0030670166015625 length of segment : 36 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 717 time to create 1 rle with old method : 0.0018951892852783203 length of segment : 22 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 165 time to create 1 rle with old method : 0.000457763671875 length of segment : 16 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0007572174072265625 length of segment : 18 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.0004000663757324219 length of segment : 16 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0008218288421630859 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: -122.33281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 310 time to create 1 rle with old method : 0.0008244514465332031 length of segment : 27 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005941390991210938 length of segment : 30 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 2133 time to create 1 rle with old method : 0.003210783004760742 length of segment : 66 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1357 time to create 1 rle with old method : 0.002002239227294922 length of segment : 40 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 653 time to create 1 rle with old method : 0.0009398460388183594 length of segment : 25 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0006382465362548828 length of segment : 22 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0012063980102539062 length of segment : 31 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 1939 time to create 1 rle with old method : 0.0025665760040283203 length of segment : 46 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1480 time to create 1 rle with old method : 0.0019845962524414062 length of segment : 51 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 1484 time to create 1 rle with old method : 0.002048969268798828 length of segment : 51 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0006642341613769531 length of segment : 27 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 714 time to create 1 rle with old method : 0.0012919902801513672 length of segment : 28 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0006456375122070312 length of segment : 28 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1504 time to create 1 rle with old method : 0.002216339111328125 length of segment : 34 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0005388259887695312 length of segment : 23 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002892017364501953 length of segment : 12 time for calcul the mask position with numpy : 0.00017642974853515625 nb_pixel_total : 2387 time to create 1 rle with old method : 0.0037336349487304688 length of segment : 67 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0005624294281005859 length of segment : 22 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0007266998291015625 length of segment : 28 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 631 time to create 1 rle with old method : 0.0008788108825683594 length of segment : 35 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 820 time to create 1 rle with old method : 0.0012161731719970703 length of segment : 45 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0005834102630615234 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: -119.46953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 1480 time to create 1 rle with old method : 0.002005338668823242 length of segment : 63 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 930 time to create 1 rle with old method : 0.0014340877532958984 length of segment : 32 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 991 time to create 1 rle with old method : 0.0014553070068359375 length of segment : 41 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0008046627044677734 length of segment : 50 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003981590270996094 length of segment : 20 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00038695335388183594 length of segment : 22 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0006361007690429688 length of segment : 23 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.00045037269592285156 length of segment : 31 time for calcul the mask position with numpy : 0.00014519691467285156 nb_pixel_total : 6065 time to create 1 rle with old method : 0.008656501770019531 length of segment : 99 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 969 time to create 1 rle with old method : 0.001355886459350586 length of segment : 29 time for calcul the mask position with numpy : 0.00016498565673828125 nb_pixel_total : 7249 time to create 1 rle with old method : 0.009852170944213867 length of segment : 108 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0004475116729736328 length of segment : 23 time for calcul the mask position with numpy : 0.00010156631469726562 nb_pixel_total : 1220 time to create 1 rle with old method : 0.0022127628326416016 length of segment : 39 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0006103515625 length of segment : 22 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 2056 time to create 1 rle with old method : 0.003149271011352539 length of segment : 63 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00041866302490234375 length of segment : 32 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 2127 time to create 1 rle with old method : 0.002842426300048828 length of segment : 53 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 976 time to create 1 rle with old method : 0.001386880874633789 length of segment : 28 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0007688999176025391 length of segment : 25 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1030 time to create 1 rle with old method : 0.0014781951904296875 length of segment : 30 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 2862 time to create 1 rle with old method : 0.004513263702392578 length of segment : 49 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 2816 time to create 1 rle with old method : 0.003573179244995117 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.20781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 0.0001068115234375 nb_pixel_total : 1335 time to create 1 rle with old method : 0.0018658638000488281 length of segment : 34 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0007824897766113281 length of segment : 39 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 1361 time to create 1 rle with old method : 0.0018274784088134766 length of segment : 30 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0006175041198730469 length of segment : 21 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005893707275390625 length of segment : 25 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 2234 time to create 1 rle with old method : 0.003183603286743164 length of segment : 53 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 616 time to create 1 rle with old method : 0.00092315673828125 length of segment : 27 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0004010200500488281 length of segment : 18 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0006976127624511719 length of segment : 22 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 1654 time to create 1 rle with old method : 0.002149343490600586 length of segment : 44 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001838207244873047 length of segment : 8 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 1045 time to create 1 rle with old method : 0.0015461444854736328 length of segment : 57 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0007810592651367188 length of segment : 39 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0006539821624755859 length of segment : 23 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 58 time to create 1 rle with old method : 0.000194549560546875 length of segment : 9 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 1472 time to create 1 rle with old method : 0.00189971923828125 length of segment : 42 time for calcul the mask position with numpy : 0.00011205673217773438 nb_pixel_total : 2220 time to create 1 rle with old method : 0.0030531883239746094 length of segment : 84 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002589225769042969 length of segment : 19 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 732 time to create 1 rle with old method : 0.0010805130004882812 length of segment : 24 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.0010688304901123047 length of segment : 33 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0008106231689453125 length of segment : 39 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0005576610565185547 length of segment : 19 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.00034689903259277344 length of segment : 25 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 1754 time to create 1 rle with old method : 0.0023927688598632812 length of segment : 56 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003554821014404297 length of segment : 15 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0010654926300048828 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.45781 max: 149.37734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0009970664978027344 length of segment : 32 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 1153 time to create 1 rle with old method : 0.002386808395385742 length of segment : 59 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 1134 time to create 1 rle with old method : 0.0020401477813720703 length of segment : 28 time for calcul the mask position with numpy : 0.00015807151794433594 nb_pixel_total : 3880 time to create 1 rle with old method : 0.005336761474609375 length of segment : 71 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.00032329559326171875 length of segment : 14 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1475 time to create 1 rle with old method : 0.0019011497497558594 length of segment : 44 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0007138252258300781 length of segment : 29 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 3090 time to create 1 rle with old method : 0.0038030147552490234 length of segment : 91 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1738 time to create 1 rle with old method : 0.0021834373474121094 length of segment : 82 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1295 time to create 1 rle with old method : 0.0017015933990478516 length of segment : 63 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0006172657012939453 length of segment : 31 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0006330013275146484 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 4.00000 max: 238.00000 molded_images shape: (1, 640, 640, 3) min: -107.95000 max: 114.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 160, 3) min: 4.00000 max: 170.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 44.61953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1635 time to create 1 rle with old method : 0.0019507408142089844 length of segment : 110 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.00043964385986328125 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.99297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 42 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004303455352783203 length of segment : 23 time for calcul the mask position with numpy : 0.00012087821960449219 nb_pixel_total : 2347 time to create 1 rle with old method : 0.002979755401611328 length of segment : 52 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005831718444824219 length of segment : 40 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0005509853363037109 length of segment : 29 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004506111145019531 length of segment : 15 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1190 time to create 1 rle with old method : 0.001451730728149414 length of segment : 53 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00035071372985839844 length of segment : 16 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 900 time to create 1 rle with old method : 0.0013165473937988281 length of segment : 49 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 1397 time to create 1 rle with old method : 0.0016026496887207031 length of segment : 56 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0009920597076416016 length of segment : 39 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 521 time to create 1 rle with old method : 0.0006711483001708984 length of segment : 42 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1435 time to create 1 rle with old method : 0.001796722412109375 length of segment : 40 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 807 time to create 1 rle with old method : 0.0011031627655029297 length of segment : 23 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00043392181396484375 length of segment : 12 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 788 time to create 1 rle with old method : 0.0010139942169189453 length of segment : 36 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.001089334487915039 length of segment : 60 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0007982254028320312 length of segment : 26 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1406 time to create 1 rle with old method : 0.0021126270294189453 length of segment : 46 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1673 time to create 1 rle with old method : 0.002697467803955078 length of segment : 48 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00023293495178222656 length of segment : 20 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 936 time to create 1 rle with old method : 0.001153707504272461 length of segment : 41 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005679130554199219 length of segment : 17 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 592 time to create 1 rle with old method : 0.0007405281066894531 length of segment : 35 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 2196 time to create 1 rle with old method : 0.002582073211669922 length of segment : 64 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1708 time to create 1 rle with old method : 0.002102375030517578 length of segment : 59 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1171 time to create 1 rle with old method : 0.0015246868133544922 length of segment : 76 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 4629 time to create 1 rle with old method : 0.005438804626464844 length of segment : 111 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 724 time to create 1 rle with old method : 0.0009195804595947266 length of segment : 71 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 2025-03-06 09:20:50.292190: E tensorflow/stream_executor/cuda/cuda_event.cc:29] Error polling for event status: failed to query event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered 2025-03-06 09:20:50.292249: 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 ! 14.10user 8.16system 1:00:11elapsed 0%CPU (0avgtext+0avgdata 2494524maxresident)k 119128inputs+3888outputs (9134major+669663minor)pagefaults 0swaps