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 : 4069000 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 we have a portfolio with more photos than limit : 11>5 please execute split_portfolio.py -i 20672520 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2599317'] with mtr_portfolio_ids : ['20672520'] and first list_photo_ids : [] new path : /proc/4069000/ 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 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 0.607335090637207 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 12:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 4952 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-19 12:20:31.474097: 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 12:20:31.499173: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-19 12:20:31.501572: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f90f4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-19 12:20:31.501647: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-19 12:20:31.505664: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-19 12:20:31.671754: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x13e1d730 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-19 12:20:31.671814: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-19 12:20:31.672985: 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 12:20:31.673389: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-19 12:20:31.676225: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-19 12:20:31.679117: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-19 12:20:31.679596: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-19 12:20:31.682184: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-19 12:20:31.683446: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-19 12:20:31.688514: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-19 12:20:31.689504: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-19 12:20:31.689579: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-19 12:20:31.690100: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-19 12:20:31.690114: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-19 12:20:31.690123: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-19 12:20:31.690975: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2400 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 12:20:31.942691: 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 12:20:31.942779: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-19 12:20:31.942802: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-19 12:20:31.942822: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-19 12:20:31.942842: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-19 12:20:31.942861: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-19 12:20:31.942881: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-19 12:20:31.942919: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-19 12:20:31.943926: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-19 12:20:31.944916: 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 12:20:31.944953: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-19 12:20:31.944972: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-19 12:20:31.944989: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-19 12:20:31.945007: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-19 12:20:31.945024: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-19 12:20:31.945041: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-19 12:20:31.945059: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-19 12:20:31.946086: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-19 12:20:31.946115: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-19 12:20:31.946125: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-19 12:20:31.946135: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-19 12:20:31.947200: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2400 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 12:20:40.096843: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-19 12:20:40.299546: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-19 12:20:41.690162: 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 12:20:41.690394: 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 12:20:41.696920: 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 12:20:41.696945: 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 12:20:41.749752: 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 12:20:41.749827: 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 12:20:41.792246: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB 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 12:20:41.792291: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB 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 12:20:41.843759: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB 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 12:20:41.843797: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB 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 12:20:42.203786: 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. 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 : 5 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: -117.20391 max: 147.42031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 908 time to create 1 rle with old method : 0.0017044544219970703 length of segment : 36 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.0003287792205810547 length of segment : 14 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.0002002716064453125 length of segment : 28 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 780 time to create 1 rle with old method : 0.001566171646118164 length of segment : 34 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.0001583099365234375 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: -119.99297 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 : 0.00013971328735351562 nb_pixel_total : 2412 time to create 1 rle with old method : 0.004624366760253906 length of segment : 52 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 786 time to create 1 rle with old method : 0.0010464191436767578 length of segment : 55 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 825 time to create 1 rle with old method : 0.0010676383972167969 length of segment : 49 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 915 time to create 1 rle with old method : 0.001184701919555664 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: -116.68828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.0001614093780517578 nb_pixel_total : 6917 time to create 1 rle with old method : 0.009279489517211914 length of segment : 117 time for calcul the mask position with numpy : 0.00016880035400390625 nb_pixel_total : 3391 time to create 1 rle with old method : 0.004519224166870117 length of segment : 112 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 1272 time to create 1 rle with old method : 0.002088785171508789 length of segment : 51 time for calcul the mask position with numpy : 0.00011420249938964844 nb_pixel_total : 1771 time to create 1 rle with old method : 0.0028502941131591797 length of segment : 49 time for calcul the mask position with numpy : 0.00010824203491210938 nb_pixel_total : 1301 time to create 1 rle with old method : 0.0020287036895751953 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: -121.11016 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 : 0.00013971328735351562 nb_pixel_total : 7286 time to create 1 rle with old method : 0.009344100952148438 length of segment : 145 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 820 time to create 1 rle with old method : 0.0011060237884521484 length of segment : 79 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0004496574401855469 length of segment : 18 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 415 time to create 1 rle with old method : 0.0007126331329345703 length of segment : 24 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0015263557434082031 length of segment : 39 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0008463859558105469 length of segment : 24 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.91641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 511 time to create 1 rle with old method : 0.0007221698760986328 length of segment : 18 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003285408020019531 length of segment : 25 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.00016379356384277344 length of segment : 9 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007228851318359375 length of segment : 20 time for calcul the mask position with numpy : 0.0006737709045410156 nb_pixel_total : 44512 time to create 1 rle with old method : 0.06839919090270996 length of segment : 349 Processing 1 images image shape: (400, 400, 3) min: 22.00000 max: 206.00000 molded_images shape: (1, 640, 640, 3) min: -90.79375 max: 78.10781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.17656 max: 147.62344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 0.0003037452697753906 nb_pixel_total : 10840 time to create 1 rle with old method : 0.02003622055053711 length of segment : 149 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.00029778480529785156 length of segment : 10 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 2522 time to create 1 rle with old method : 0.005344390869140625 length of segment : 42 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1097 time to create 1 rle with old method : 0.0021369457244873047 length of segment : 25 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 585 time to create 1 rle with old method : 0.000885009765625 length of segment : 20 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 387 time to create 1 rle with old method : 0.0006718635559082031 length of segment : 16 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0007588863372802734 length of segment : 21 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.0007753372192382812 length of segment : 21 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1041 time to create 1 rle with old method : 0.0014731884002685547 length of segment : 24 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 841 time to create 1 rle with old method : 0.0012497901916503906 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: -115.97734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.00044274330139160156 length of segment : 16 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0006899833679199219 length of segment : 30 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0004165172576904297 length of segment : 14 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0004417896270751953 length of segment : 33 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00038361549377441406 length of segment : 11 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 549 time to create 1 rle with old method : 0.0010514259338378906 length of segment : 31 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 1432 time to create 1 rle with old method : 0.0026731491088867188 length of segment : 42 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0011932849884033203 length of segment : 15 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.0002903938293457031 length of segment : 8 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0010633468627929688 length of segment : 34 time for calcul the mask position with numpy : 0.00022721290588378906 nb_pixel_total : 7963 time to create 1 rle with old method : 0.013583183288574219 length of segment : 120 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001857280731201172 length of segment : 12 time for calcul the mask position with numpy : 0.0002300739288330078 nb_pixel_total : 9126 time to create 1 rle with old method : 0.011754512786865234 length of segment : 233 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.0002391338348388672 length of segment : 15 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002834796905517578 length of segment : 18 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1042 time to create 1 rle with old method : 0.001348733901977539 length of segment : 29 time for calcul the mask position with numpy : 0.0002002716064453125 nb_pixel_total : 8567 time to create 1 rle with old method : 0.010336160659790039 length of segment : 154 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00032258033752441406 length of segment : 11 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.00038933753967285156 length of segment : 15 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.0001876354217529297 length of segment : 6 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003871917724609375 length of segment : 12 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002722740173339844 length of segment : 20 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 26 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0005383491516113281 length of segment : 24 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0005872249603271484 length of segment : 32 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 46 time to create 1 rle with old method : 9.083747863769531e-05 length of segment : 13 time for calcul the mask position with numpy : 0.00018453598022460938 nb_pixel_total : 9791 time to create 1 rle with old method : 0.013874530792236328 length of segment : 129 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 456 time to create 1 rle with old method : 0.0006377696990966797 length of segment : 32 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 458 time to create 1 rle with old method : 0.0007395744323730469 length of segment : 15 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.18047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 613 time to create 1 rle with old method : 0.0008749961853027344 length of segment : 19 time for calcul the mask position with numpy : 0.00011181831359863281 nb_pixel_total : 3310 time to create 1 rle with old method : 0.004142045974731445 length of segment : 172 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1658 time to create 1 rle with old method : 0.002180814743041992 length of segment : 38 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 912 time to create 1 rle with old method : 0.0012676715850830078 length of segment : 28 time for calcul the mask position with numpy : 0.00025963783264160156 nb_pixel_total : 9451 time to create 1 rle with old method : 0.014452695846557617 length of segment : 237 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004596710205078125 length of segment : 19 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1197 time to create 1 rle with old method : 0.0015594959259033203 length of segment : 39 time for calcul the mask position with numpy : 0.0004534721374511719 nb_pixel_total : 20176 time to create 1 rle with old method : 0.02311229705810547 length of segment : 316 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 1334 time to create 1 rle with old method : 0.0017161369323730469 length of segment : 45 time for calcul the mask position with numpy : 0.00011992454528808594 nb_pixel_total : 4657 time to create 1 rle with old method : 0.005712270736694336 length of segment : 154 time for calcul the mask position with numpy : 0.0004885196685791016 nb_pixel_total : 19570 time to create 1 rle with old method : 0.02585625648498535 length of segment : 276 time for calcul the mask position with numpy : 0.0001544952392578125 nb_pixel_total : 5122 time to create 1 rle with old method : 0.007658481597900391 length of segment : 131 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.26797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.00042819976806640625 length of segment : 30 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 469 time to create 1 rle with old method : 0.0006263256072998047 length of segment : 55 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1813 time to create 1 rle with old method : 0.0023894309997558594 length of segment : 44 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 1759 time to create 1 rle with old method : 0.002270221710205078 length of segment : 84 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 865 time to create 1 rle with old method : 0.001285552978515625 length of segment : 85 Processing 1 images image shape: (280, 400, 3) min: 8.00000 max: 200.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 73.89687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0014388561248779297 nb_pixel_total : 105999 time to create 1 rle with old method : 0.12434172630310059 length of segment : 283 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.69766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 636 time to create 1 rle with old method : 0.0008521080017089844 length of segment : 34 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 3339 time to create 1 rle with old method : 0.0040051937103271484 length of segment : 57 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 910 time to create 1 rle with old method : 0.0012788772583007812 length of segment : 26 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 2520 time to create 1 rle with old method : 0.0033986568450927734 length of segment : 57 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1185 time to create 1 rle with old method : 0.0015337467193603516 length of segment : 54 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1747 time to create 1 rle with old method : 0.002324819564819336 length of segment : 61 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004181861877441406 length of segment : 29 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 569 time to create 1 rle with old method : 0.0007436275482177734 length of segment : 45 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.00012683868408203125 length of segment : 14 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.00015544891357421875 length of segment : 9 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1301 time to create 1 rle with old method : 0.001847982406616211 length of segment : 44 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1852 time to create 1 rle with old method : 0.002410888671875 length of segment : 68 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.0003445148468017578 length of segment : 15 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.00022029876708984375 length of segment : 10 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003895759582519531 length of segment : 25 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.05703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 36 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 407 time to create 1 rle with old method : 0.0008153915405273438 length of segment : 31 time for calcul the mask position with numpy : 0.00015354156494140625 nb_pixel_total : 658 time to create 1 rle with old method : 0.0012664794921875 length of segment : 32 time for calcul the mask position with numpy : 0.0001747608184814453 nb_pixel_total : 305 time to create 1 rle with old method : 0.0006561279296875 length of segment : 22 time for calcul the mask position with numpy : 0.00011801719665527344 nb_pixel_total : 268 time to create 1 rle with old method : 0.0005733966827392578 length of segment : 27 time for calcul the mask position with numpy : 0.00013184547424316406 nb_pixel_total : 495 time to create 1 rle with old method : 0.000997781753540039 length of segment : 24 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 232 time to create 1 rle with old method : 0.0005061626434326172 length of segment : 20 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 403 time to create 1 rle with old method : 0.0008249282836914062 length of segment : 26 time for calcul the mask position with numpy : 0.00012731552124023438 nb_pixel_total : 64 time to create 1 rle with old method : 0.00019693374633789062 length of segment : 10 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 755 time to create 1 rle with old method : 0.0014324188232421875 length of segment : 34 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 131 time to create 1 rle with old method : 0.00035572052001953125 length of segment : 12 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 373 time to create 1 rle with old method : 0.0007407665252685547 length of segment : 36 time for calcul the mask position with numpy : 0.0001418590545654297 nb_pixel_total : 377 time to create 1 rle with old method : 0.0007481575012207031 length of segment : 27 time for calcul the mask position with numpy : 0.00017905235290527344 nb_pixel_total : 942 time to create 1 rle with old method : 0.0017697811126708984 length of segment : 53 time for calcul the mask position with numpy : 9.751319885253906e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.00041413307189941406 length of segment : 20 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.0004088878631591797 length of segment : 19 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0004000663757324219 length of segment : 16 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.000949859619140625 length of segment : 24 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 234 2025-02-19 12:20:46.433455: 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 12:20:46.433524: 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 ! 15.48user 10.83system 1:00:06elapsed 0%CPU (0avgtext+0avgdata 2483344maxresident)k 132184inputs+2824outputs (10522major+683358minor)pagefaults 0swaps