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 : 3780418 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 : 61>5 please execute split_portfolio.py -i 20881155 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2619669'] with mtr_portfolio_ids : ['20881155'] and first list_photo_ids : [] new path : /proc/3780418/ 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 : 0.9640312194824219 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 Feb 27 14:20:28 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 : 10593 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-27 14:20:32.056876: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-27 14:20:32.083295: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-27 14:20:32.085128: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fb5a8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-27 14:20:32.085183: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-27 14:20:32.088831: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-27 14:20:32.328049: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x31dbe6c0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-27 14:20:32.328105: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-27 14:20:32.329170: 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 2025-02-27 14:20:32.329510: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-27 14:20:32.331631: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-27 14:20:32.335903: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-27 14:20:32.336279: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-27 14:20:32.344126: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-27 14:20:32.345427: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-27 14:20:32.356259: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-27 14:20:32.357734: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-27 14:20:32.357814: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-27 14:20:32.358554: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-27 14:20:32.358570: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-27 14:20:32.358578: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-27 14:20:32.360578: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9815 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. 2025-02-27 14:20:32.675864: 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 2025-02-27 14:20:32.675977: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-27 14:20:32.676002: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-27 14:20:32.676023: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-27 14:20:32.676044: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-27 14:20:32.676064: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-27 14:20:32.676084: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-27 14:20:32.676105: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-27 14:20:32.677698: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-27 14:20:32.679274: 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 2025-02-27 14:20:32.679397: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-27 14:20:32.679423: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-27 14:20:32.679447: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-27 14:20:32.679470: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-27 14:20:32.679492: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-27 14:20:32.679512: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-27 14:20:32.679534: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-27 14:20:32.681217: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-27 14:20:32.681291: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-27 14:20:32.681303: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-27 14:20:32.681314: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-27 14:20:32.683094: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9815 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 : [] 2025-02-27 14:20:41.009803: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-27 14:20:41.228006: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 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: -119.28594 max: 149.32266 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00016379356384277344 nb_pixel_total : 732 time to create 1 rle with old method : 0.0042531490325927734 length of segment : 58 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 937 time to create 1 rle with old method : 0.0033473968505859375 length of segment : 35 time for calcul the mask position with numpy : 0.0002760887145996094 nb_pixel_total : 5949 time to create 1 rle with old method : 0.01989889144897461 length of segment : 107 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1 time to create 1 rle with old method : 2.7894973754882812e-05 length of segment : 1 time for calcul the mask position with numpy : 0.0001895427703857422 nb_pixel_total : 6210 time to create 1 rle with old method : 0.00778651237487793 length of segment : 118 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.08281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0011668205261230469 length of segment : 57 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 2176 time to create 1 rle with old method : 0.004202127456665039 length of segment : 54 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 2342 time to create 1 rle with old method : 0.004385709762573242 length of segment : 51 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 2719 time to create 1 rle with old method : 0.004895210266113281 length of segment : 97 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.00015163421630859375 length of segment : 19 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 39 time to create 1 rle with old method : 0.00010228157043457031 length of segment : 7 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.46563 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 5734 time to create 1 rle with old method : 0.0075190067291259766 length of segment : 100 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 545 time to create 1 rle with old method : 0.0008020401000976562 length of segment : 34 time for calcul the mask position with numpy : 0.0003650188446044922 nb_pixel_total : 18372 time to create 1 rle with old method : 0.024318695068359375 length of segment : 359 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.60234 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 : 6.532669067382812e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0013659000396728516 length of segment : 45 time for calcul the mask position with numpy : 0.00017833709716796875 nb_pixel_total : 10223 time to create 1 rle with old method : 0.012783288955688477 length of segment : 86 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 1687 time to create 1 rle with old method : 0.0021750926971435547 length of segment : 107 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1133 time to create 1 rle with old method : 0.001497507095336914 length of segment : 48 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: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 863 time to create 1 rle with old method : 0.0018124580383300781 length of segment : 30 time for calcul the mask position with numpy : 0.00012159347534179688 nb_pixel_total : 2499 time to create 1 rle with old method : 0.004683494567871094 length of segment : 217 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00023651123046875 length of segment : 9 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 173.00000 molded_images shape: (1, 640, 640, 3) min: -100.97344 max: 54.75625 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: -122.57500 max: 131.20937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00027179718017578125 nb_pixel_total : 15967 time to create 1 rle with old method : 0.02103900909423828 length of segment : 229 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.000274658203125 length of segment : 21 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 2429 time to create 1 rle with old method : 0.003107309341430664 length of segment : 84 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003516674041748047 length of segment : 13 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 2843 time to create 1 rle with old method : 0.003810882568359375 length of segment : 55 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.10234 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 : 0.00042128562927246094 nb_pixel_total : 14803 time to create 1 rle with old method : 0.018524646759033203 length of segment : 144 time for calcul the mask position with numpy : 0.0001652240753173828 nb_pixel_total : 8972 time to create 1 rle with old method : 0.011470317840576172 length of segment : 82 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 47 time to create 1 rle with old method : 0.00010418891906738281 length of segment : 7 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1171 time to create 1 rle with old method : 0.0016641616821289062 length of segment : 39 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0006315708160400391 length of segment : 11 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.28203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1021 time to create 1 rle with old method : 0.0014874935150146484 length of segment : 38 time for calcul the mask position with numpy : 0.00011205673217773438 nb_pixel_total : 1527 time to create 1 rle with old method : 0.0020220279693603516 length of segment : 114 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0005681514739990234 length of segment : 18 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1100 time to create 1 rle with old method : 0.0014941692352294922 length of segment : 38 time for calcul the mask position with numpy : 0.0001399517059326172 nb_pixel_total : 307 time to create 1 rle with old method : 0.000507354736328125 length of segment : 74 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 719 time to create 1 rle with old method : 0.0010256767272949219 length of segment : 96 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0010635852813720703 length of segment : 37 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: 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 : 8.082389831542969e-05 nb_pixel_total : 1257 time to create 1 rle with old method : 0.0017821788787841797 length of segment : 142 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.0012478828430175781 length of segment : 79 time for calcul the mask position with numpy : 0.0001995563507080078 nb_pixel_total : 3605 time to create 1 rle with old method : 0.004553079605102539 length of segment : 218 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1505 time to create 1 rle with old method : 0.0019922256469726562 length of segment : 79 Processing 1 images image shape: (280, 400, 3) min: 8.00000 max: 176.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 53.51797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009410381317138672 nb_pixel_total : 105209 time to create 1 rle with old method : 0.1267235279083252 length of segment : 282 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: 146.99844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1273 time to create 1 rle with old method : 0.002411365509033203 length of segment : 36 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0005593299865722656 length of segment : 17 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1090 time to create 1 rle with old method : 0.002230405807495117 length of segment : 43 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 2984 time to create 1 rle with old method : 0.0056684017181396484 length of segment : 47 time for calcul the mask position with numpy : 0.00013113021850585938 nb_pixel_total : 3239 time to create 1 rle with old method : 0.007001638412475586 length of segment : 108 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 1316 time to create 1 rle with old method : 0.0024843215942382812 length of segment : 51 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0009746551513671875 length of segment : 50 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0003082752227783203 length of segment : 15 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.0002167224884033203 length of segment : 15 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1034 time to create 1 rle with old method : 0.0014553070068359375 length of segment : 31 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: 141.23281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003676414489746094 length of segment : 20 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003440380096435547 length of segment : 20 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0005056858062744141 length of segment : 22 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0008263587951660156 length of segment : 34 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0008671283721923828 length of segment : 28 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0003101825714111328 length of segment : 12 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005602836608886719 length of segment : 34 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00043010711669921875 length of segment : 18 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0002639293670654297 length of segment : 13 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0009722709655761719 length of segment : 27 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 793 time to create 1 rle with old method : 0.001115560531616211 length of segment : 33 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: 144.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007898807525634766 length of segment : 44 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.0002815723419189453 length of segment : 34 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005881786346435547 length of segment : 26 time for calcul the mask position with numpy : 0.00013518333435058594 nb_pixel_total : 7353 time to create 1 rle with old method : 0.010078907012939453 length of segment : 65 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 34 time to create 1 rle with old method : 9.584426879882812e-05 length of segment : 14 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 757 time to create 1 rle with old method : 0.0011129379272460938 length of segment : 26 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0005772113800048828 length of segment : 36 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.0002193450927734375 length of segment : 17 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003695487976074219 length of segment : 27 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: -119.36797 max: 149.00625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 906 time to create 1 rle with old method : 0.0012371540069580078 length of segment : 36 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 938 time to create 1 rle with old method : 0.0014066696166992188 length of segment : 40 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 12 time to create 1 rle with old method : 0.0001010894775390625 length of segment : 4 time for calcul the mask position with numpy : 0.00021529197692871094 nb_pixel_total : 4887 time to create 1 rle with old method : 0.007066488265991211 length of segment : 134 time for calcul the mask position with numpy : 0.00017213821411132812 nb_pixel_total : 5282 time to create 1 rle with old method : 0.006905078887939453 length of segment : 119 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.87188 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 37 time to create 1 rle with old method : 8.559226989746094e-05 length of segment : 7 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 2387 time to create 1 rle with old method : 0.003403186798095703 length of segment : 60 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 380 time to create 1 rle with old method : 0.0005273818969726562 length of segment : 35 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2389 time to create 1 rle with old method : 0.003270864486694336 length of segment : 75 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 22 time to create 1 rle with old method : 7.081031799316406e-05 length of segment : 5 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1120 time to create 1 rle with old method : 0.001688241958618164 length of segment : 34 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1093 time to create 1 rle with old method : 0.0014405250549316406 length of segment : 33 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1372 time to create 1 rle with old method : 0.0019562244415283203 length of segment : 49 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 3079 time to create 1 rle with old method : 0.0041294097900390625 length of segment : 68 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00028324127197265625 length of segment : 30 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 2730 time to create 1 rle with old method : 0.003393888473510742 length of segment : 89 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1132 time to create 1 rle with old method : 0.0015938282012939453 length of segment : 33 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1564 time to create 1 rle with old method : 0.002199888229370117 length of segment : 32 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 2798 time to create 1 rle with old method : 0.0035910606384277344 length of segment : 65 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.58672 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00011157989501953125 nb_pixel_total : 5656 time to create 1 rle with old method : 0.009213685989379883 length of segment : 98 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0008711814880371094 length of segment : 33 time for calcul the mask position with numpy : 0.0004639625549316406 nb_pixel_total : 17754 time to create 1 rle with old method : 0.024566650390625 length of segment : 386 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.21563 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 : 0.0002033710479736328 nb_pixel_total : 9144 time to create 1 rle with old method : 0.015879154205322266 length of segment : 113 time for calcul the mask position with numpy : 0.00010156631469726562 nb_pixel_total : 586 time to create 1 rle with old method : 0.0011920928955078125 length of segment : 84 time for calcul the mask position with numpy : 0.00010967254638671875 nb_pixel_total : 624 time to create 1 rle with old method : 0.0012142658233642578 length of segment : 82 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1519 time to create 1 rle with old method : 0.0027709007263183594 length of segment : 41 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: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 830 time to create 1 rle with old method : 0.0010614395141601562 length of segment : 27 time for calcul the mask position with numpy : 0.0006487369537353516 nb_pixel_total : 57886 time to create 1 rle with old method : 0.07241940498352051 length of segment : 292 time for calcul the mask position with numpy : 0.0001552104949951172 nb_pixel_total : 1884 time to create 1 rle with old method : 0.002866029739379883 length of segment : 172 time for calcul the mask position with numpy : 8.273124694824219e-05 2025-02-27 14:20:48.149377: 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 2025-02-27 14:20:48.149437: 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 ! 16.18user 13.09system 1:00:06elapsed 0%CPU (0avgtext+0avgdata 2526856maxresident)k 762528inputs+2736outputs (5754major+697290minor)pagefaults 0swaps