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 : 193920 load datou : 4234 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2609036'] with mtr_portfolio_ids : ['20759405'] and first list_photo_ids : [] new path : /proc/193920/ 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 , BFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 3 ; length of list_pids : 3 ; length of list_args : 3 time to download the photos : 0.45838189125061035 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 Mon Feb 24 03:20:28 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 2025-02-24 03:20:30.876166: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-24 03:20:30.903062: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-24 03:20:30.905352: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fef58000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-24 03:20:30.905405: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-24 03:20:30.909290: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-24 03:20:31.138005: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1536f6b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-24 03:20:31.138048: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-24 03:20:31.139380: 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 2025-02-24 03:20:31.139744: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-24 03:20:31.142389: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-24 03:20:31.144907: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-24 03:20:31.145336: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-24 03:20:31.148176: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-24 03:20:31.149170: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-24 03:20:31.153014: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-24 03:20:31.154335: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-24 03:20:31.154394: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-24 03:20:31.155105: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-24 03:20:31.155120: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-24 03:20:31.155128: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-24 03:20:31.156386: 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. 2025-02-24 03:20:31.405975: 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 2025-02-24 03:20:31.406071: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-24 03:20:31.406099: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-24 03:20:31.406125: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-24 03:20:31.406151: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-24 03:20:31.406176: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-24 03:20:31.406200: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-24 03:20:31.406225: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-24 03:20:31.408294: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-24 03:20:31.409372: 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 2025-02-24 03:20:31.409408: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-24 03:20:31.409426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-24 03:20:31.409443: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-24 03:20:31.409460: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-24 03:20:31.409476: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-24 03:20:31.409492: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-24 03:20:31.409509: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-24 03:20:31.410802: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-24 03:20:31.410828: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-24 03:20:31.410837: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-24 03:20:31.410845: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-24 03:20:31.412226: 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 : [] 2025-02-24 03:20:38.267320: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-24 03:20:38.434758: 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 : 3 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.98125 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.0004181861877441406 length of segment : 13 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1552 time to create 1 rle with old method : 0.002774477005004883 length of segment : 47 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0004680156707763672 length of segment : 20 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0012331008911132812 length of segment : 28 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0006952285766601562 length of segment : 20 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 1810 time to create 1 rle with old method : 0.0031397342681884766 length of segment : 116 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.0015609264373779297 length of segment : 41 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.00020384788513183594 length of segment : 13 time for calcul the mask position with numpy : 0.00011134147644042969 nb_pixel_total : 4285 time to create 1 rle with old method : 0.005258321762084961 length of segment : 126 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.00040149688720703125 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.12578 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0006897449493408203 length of segment : 55 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0007107257843017578 length of segment : 30 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0008873939514160156 length of segment : 26 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1853 time to create 1 rle with old method : 0.002597332000732422 length of segment : 46 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 682 time to create 1 rle with old method : 0.0008943080902099609 length of segment : 45 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0019450187683105469 length of segment : 49 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 488 time to create 1 rle with old method : 0.000659942626953125 length of segment : 27 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.00027060508728027344 length of segment : 13 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 738 time to create 1 rle with old method : 0.0010178089141845703 length of segment : 27 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0004296302795410156 length of segment : 20 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004343986511230469 length of segment : 21 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.00034117698669433594 length of segment : 10 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1792 time to create 1 rle with old method : 0.0022954940795898438 length of segment : 43 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.00044035911560058594 length of segment : 23 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 627 time to create 1 rle with old method : 0.0008063316345214844 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.21953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 3564 time to create 1 rle with old method : 0.0045053958892822266 length of segment : 99 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.00047397613525390625 length of segment : 16 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0004241466522216797 length of segment : 29 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003724098205566406 length of segment : 20 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.0003731250762939453 length of segment : 18 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1215 time to create 1 rle with old method : 0.0018329620361328125 length of segment : 38 time for calcul the mask position with numpy : 0.00034880638122558594 nb_pixel_total : 20886 time to create 1 rle with old method : 0.02586650848388672 length of segment : 163 time for calcul the mask position with numpy : 0.00020599365234375 nb_pixel_total : 8273 time to create 1 rle with old method : 0.009665489196777344 length of segment : 107 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00018358230590820312 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 9.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.99688 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 : 4.172325134277344e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0005831718444824219 length of segment : 28 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004355907440185547 length of segment : 30 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.0002117156982421875 length of segment : 14 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.00046825408935546875 length of segment : 30 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0005247592926025391 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 98.00000 max: 225.00000 molded_images shape: (1, 640, 640, 3) min: -25.70000 max: 116.39297 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: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.60625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00018215179443359375 nb_pixel_total : 1194 time to create 1 rle with old method : 0.001714944839477539 length of segment : 121 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 3125 time to create 1 rle with old method : 0.003995418548583984 length of segment : 84 Processing 1 images image shape: (400, 160, 3) min: 9.00000 max: 217.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 108.31094 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: -122.57891 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1080 time to create 1 rle with old method : 0.0013875961303710938 length of segment : 47 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 2417 time to create 1 rle with old method : 0.0030286312103271484 length of segment : 63 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 560 time to create 1 rle with old method : 0.0007264614105224609 length of segment : 29 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 1023 time to create 1 rle with old method : 0.0012371540069580078 length of segment : 36 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003662109375 length of segment : 22 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 2481 time to create 1 rle with old method : 0.0030269622802734375 length of segment : 62 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.0008442401885986328 length of segment : 25 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00031828880310058594 length of segment : 15 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0007069110870361328 length of segment : 41 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0006802082061767578 length of segment : 26 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1149 time to create 1 rle with old method : 0.0015015602111816406 length of segment : 46 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 538 time to create 1 rle with old method : 0.0007429122924804688 length of segment : 28 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 590 time to create 1 rle with old method : 0.0008957386016845703 length of segment : 28 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.00095367431640625 length of segment : 30 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006041526794433594 length of segment : 21 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 939 time to create 1 rle with old method : 0.0011889934539794922 length of segment : 28 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 612 time to create 1 rle with old method : 0.0007884502410888672 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.10234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003933906555175781 length of segment : 21 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005536079406738281 length of segment : 24 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1434 time to create 1 rle with old method : 0.0018153190612792969 length of segment : 55 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 611 time to create 1 rle with old method : 0.0009081363677978516 length of segment : 30 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 2521 time to create 1 rle with old method : 0.0031495094299316406 length of segment : 52 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005412101745605469 length of segment : 31 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005481243133544922 length of segment : 25 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 936 time to create 1 rle with old method : 0.0011665821075439453 length of segment : 67 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.00038933753967285156 length of segment : 22 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00025534629821777344 length of segment : 22 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1594 time to create 1 rle with old method : 0.0021283626556396484 length of segment : 37 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00030231475830078125 length of segment : 50 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00035500526428222656 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.42266 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 : 4.57763671875e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005147457122802734 length of segment : 27 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.0005636215209960938 length of segment : 30 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003447532653808594 length of segment : 18 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 2355 time to create 1 rle with old method : 0.002994060516357422 length of segment : 71 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0005824565887451172 length of segment : 24 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002791881561279297 length of segment : 17 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 2296 time to create 1 rle with old method : 0.003951072692871094 length of segment : 69 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.0002734661102294922 length of segment : 11 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0006949901580810547 length of segment : 39 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00040650367736816406 length of segment : 17 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0007333755493164062 length of segment : 25 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 1131 time to create 1 rle with old method : 0.0020809173583984375 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.84063 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 435 time to create 1 rle with old method : 0.0006320476531982422 length of segment : 18 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 955 time to create 1 rle with old method : 0.001241922378540039 length of segment : 42 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.000335693359375 length of segment : 32 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 659 time to create 1 rle with old method : 0.0008897781372070312 length of segment : 29 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1791 time to create 1 rle with old method : 0.0023658275604248047 length of segment : 37 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1173 time to create 1 rle with old method : 0.0015926361083984375 length of segment : 36 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005552768707275391 length of segment : 34 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.0002853870391845703 length of segment : 11 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 703 time to create 1 rle with old method : 0.0010695457458496094 length of segment : 29 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0008876323699951172 length of segment : 33 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0008797645568847656 length of segment : 20 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 792 time to create 1 rle with old method : 0.001043081283569336 length of segment : 52 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0006439685821533203 length of segment : 20 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 800 time to create 1 rle with old method : 0.0010437965393066406 length of segment : 36 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0006573200225830078 length of segment : 47 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005440711975097656 length of segment : 22 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005810260772705078 length of segment : 22 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0003998279571533203 length of segment : 15 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0006194114685058594 length of segment : 22 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003833770751953125 length of segment : 20 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00029158592224121094 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 39.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -73.98906 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1527 time to create 1 rle with old method : 0.0022382736206054688 length of segment : 63 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.07109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 972 time to create 1 rle with old method : 0.0011730194091796875 length of segment : 112 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.0003254413604736328 length of segment : 18 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1103 time to create 1 rle with old method : 0.0013954639434814453 length of segment : 50 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 133 time to create 1 rle with old method : 0.0002548694610595703 length of segment : 22 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00038123130798339844 length of segment : 19 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004305839538574219 length of segment : 24 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0007648468017578125 length of segment : 34 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1174 time to create 1 rle with old method : 0.001522064208984375 length of segment : 50 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 21 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00021314620971679688 length of segment : 13 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.45547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0006206035614013672 length of segment : 21 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005991458892822266 length of segment : 32 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 805 time to create 1 rle with old method : 0.0011014938354492188 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.14141 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004982948303222656 length of segment : 27 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1016 time to create 1 rle with old method : 0.0013298988342285156 length of segment : 36 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 1115 time to create 1 rle with old method : 0.0014066696166992188 length of segment : 49 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.0007174015045166016 length of segment : 45 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.000537872314453125 length of segment : 30 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003540515899658203 length of segment : 21 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005445480346679688 length of segment : 35 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1300 time to create 1 rle with old method : 0.0016930103302001953 length of segment : 74 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 863 time to create 1 rle with old method : 0.0010554790496826172 length of segment : 30 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 1794 time to create 1 rle with old method : 0.0022864341735839844 length of segment : 144 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 2915 time to create 1 rle with old method : 0.0032935142517089844 length of segment : 78 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1267 time to create 1 rle with old method : 0.0015788078308105469 length of segment : 55 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 2180 time to create 1 rle with old method : 0.002569913864135742 length of segment : 78 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 2111 time to create 1 rle with old method : 0.0024423599243164062 length of segment : 73 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 2901 time to create 1 rle with old method : 0.003591775894165039 length of segment : 77 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.30938 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 : 3.933906555175781e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002987384796142578 length of segment : 29 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 1020 time to create 1 rle with old method : 0.0013279914855957031 length of segment : 48 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1511 time to create 1 rle with old method : 0.0018723011016845703 length of segment : 43 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1564 time to create 1 rle with old method : 0.0019397735595703125 length of segment : 43 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0018846988677978516 length of segment : 30 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.0001888275146484375 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.36797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.0012049674987792969 length of segment : 44 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00040984153747558594 length of segment : 19 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0008227825164794922 length of segment : 31 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0013306140899658203 length of segment : 34 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 973 time to create 1 rle with old method : 0.0012166500091552734 length of segment : 32 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 126 time to create 1 rle with old method : 0.00020503997802734375 length of segment : 13 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00017452239990234375 length of segment : 11 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 1047 time to create 1 rle with old method : 0.0012836456298828125 length of segment : 36 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 2859 time to create 1 rle with old method : 0.003391265869140625 length of segment : 66 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002925395965576172 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.03203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005261898040771484 length of segment : 20 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005338191986083984 length of segment : 32 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.00037980079650878906 length of segment : 21 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2079 time to create 1 rle with old method : 0.0026319026947021484 length of segment : 72 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0007627010345458984 length of segment : 57 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.00038361549377441406 length of segment : 15 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005140304565429688 length of segment : 29 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 885 time to create 1 rle with old method : 0.0011322498321533203 length of segment : 40 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 6 time to create 1 rle with old method : 3.910064697265625e-05 length of segment : 1 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.0009899139404296875 length of segment : 39 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.91484 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 : 3.814697265625e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.000324249267578125 length of segment : 21 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00036144256591796875 length of segment : 23 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.00045299530029296875 length of segment : 20 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002865791320800781 length of segment : 15 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00031638145446777344 length of segment : 16 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 802 time to create 1 rle with old method : 0.0009317398071289062 length of segment : 71 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 780 time to create 1 rle with old method : 0.0009746551513671875 length of segment : 29 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0007100105285644531 length of segment : 36 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 1121 time to create 1 rle with old method : 0.0014338493347167969 length of segment : 38 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004971027374267578 length of segment : 21 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00024580955505371094 length of segment : 17 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0007538795471191406 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.39922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0005123615264892578 length of segment : 20 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003814697265625 length of segment : 24 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.0002148151397705078 length of segment : 24 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0005125999450683594 length of segment : 15 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0006029605865478516 length of segment : 36 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00022554397583007812 length of segment : 21 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.0005614757537841797 length of segment : 48 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0005846023559570312 length of segment : 49 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 18 time to create 1 rle with old method : 5.507469177246094e-05 length of segment : 4 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005068778991699219 length of segment : 25 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003407001495361328 length of segment : 16 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0004165172576904297 length of segment : 54 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.0002257823944091797 length of segment : 20 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0007739067077636719 length of segment : 61 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 3094 time to create 1 rle with old method : 0.0037529468536376953 length of segment : 64 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.59609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0008745193481445312 length of segment : 26 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003380775451660156 length of segment : 22 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003933906555175781 length of segment : 20 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 850 time to create 1 rle with old method : 0.0010650157928466797 length of segment : 45 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0009202957153320312 length of segment : 30 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00020384788513183594 length of segment : 8 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 49 2025-02-24 03:20:45.783116: E tensorflow/stream_executor/cuda/cuda_driver.cc:939] could not synchronize on CUDA context: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered :: *** Begin stack trace *** tensorflow::CurrentStackTrace() stream_executor::gpu::GpuDriver::SynchronizeContext(stream_executor::gpu::GpuContext*) stream_executor::StreamExecutor::SynchronizeAllActivity() tensorflow::GPUUtil::SyncAll(tensorflow::Device*) tensorflow::BaseGPUDevice::Sync() tensorflow::TensorHandle::CopyToDevice(tensorflow::EagerContext const&, tensorflow::Device*, tensorflow::Tensor*) tensorflow::TensorHandleInterface::Resolve(tensorflow::Status*) TFE_TensorHandleResolve _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall PyObject_Call _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName PyEval_EvalCode PyRun_SimpleFileExFlags Py_RunMain Py_BytesMain __libc_start_main _start *** End stack trace *** time to create 1 rle with old method : 0.00010156631469726562 length of segment : 9 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1353 time to create 1 rle with old method : 0.0016834735870361328 length of segment : 54 time for calcul the mask position with numpy : 0.0004143714904785156 nb_pixel_total : 27832 time to create 1 rle with old method : 0.03274726867675781 length of segment : 223 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1739 time to create 1 rle with old method : 0.0022351741790771484 length of segment : 45 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.88125 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00025534629821777344 length of segment : 15 length of segment : 0 time for calcul the mask position with numpy : 0.0004980564117431641 nb_pixel_total : 41565 time to create 1 rle with old method : 0.04648947715759277 length of segment : 188 length of segment : 0 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.00028634071350097656 length of segment : 32 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 662 time to create 1 rle with old method : 0.0008194446563720703 length of segment : 58 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 133 time to create 1 rle with old method : 0.00021505355834960938 length of segment : 15 time for calcul the mask position with numpy : 0.0006144046783447266 nb_pixel_total : 51304 time to create 1 rle with old method : 0.05798220634460449 length of segment : 301 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002880096435546875 length of segment : 18 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00024819374084472656 length of segment : 13 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.0003352165222167969 length of segment : 15 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 909 time to create 1 rle with old method : 0.0011305809020996094 length of segment : 32 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0006122589111328125 length of segment : 26 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001709461212158203 length of segment : 13 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0004756450653076172 length of segment : 23 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.00018024444580078125 length of segment : 8 time for calcul the mask position with numpy : 0.00019121170043945312 nb_pixel_total : 9843 time to create 1 rle with old method : 0.011467456817626953 length of segment : 70 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 825 time to create 1 rle with old method : 0.0009899139404296875 length of segment : 38 time for calcul the mask position with numpy : 2.7179718017578125e-05 nb_pixel_total : 62 time to create 1 rle with old method : 0.00010561943054199219 length of segment : 11 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003879070281982422 length of segment : 20 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004220008850097656 length of segment : 19 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.00020956993103027344 length of segment : 19 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1676 time to create 1 rle with old method : 0.002010822296142578 length of segment : 46 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00020456314086914062 length of segment : 17 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.07656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 25 time to create 1 rle with old method : 6.556510925292969e-05 length of segment : 5 time for calcul the mask position with numpy : 0.0001461505889892578 nb_pixel_total : 8858 time to create 1 rle with old method : 0.010207176208496094 length of segment : 93 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 47 time to create 1 rle with old method : 0.00011229515075683594 length of segment : 6 time for calcul the mask position with numpy : 0.0004181861877441406 nb_pixel_total : 27542 time to create 1 rle with old method : 0.03143501281738281 length of segment : 172 time for calcul the mask position with numpy : 0.0001437664031982422 nb_pixel_total : 8281 time to create 1 rle with old method : 0.009799480438232422 length of segment : 92 time for calcul the mask position with numpy : 0.00014138221740722656 nb_pixel_total : 9134 time to create 1 rle with old method : 0.009988069534301758 length of segment : 96 time for calcul the mask position with numpy : 0.00014090538024902344 nb_pixel_total : 8739 time to create 1 rle with old method : 0.00969552993774414 length of segment : 94 Processing 1 images image shape: (240, 160, 3) min: 0.00000 max: 234.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 120.48144 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.45781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 error in detect the image : temp/1740363627_193920_1339269032_dc7fdc7c9fae364d38dd1ca64102927f.jpg GPU sync failed NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images 2025-02-24 03:20:45.828577: E tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:725] failed to record completion event; therefore, failed to create inter-stream dependency 2025-02-24 03:20:45.828631: I tensorflow/stream_executor/stream.cc:4938] [stream=0x166ee2b0,impl=0x166ecf40] did not memcpy host-to-device; source: 0x41957a00 2025-02-24 03:20:45.828657: E tensorflow/stream_executor/stream.cc:334] Error recording event in stream: Error recording CUDA event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered; not marking stream as bad, as the Event object may be at fault. Monitor for further errors. 2025-02-24 03:20:45.828678: 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 2025-02-24 03:20:45.828693: 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 ! 15.63user 13.53system 1:00:05elapsed 0%CPU (0avgtext+0avgdata 2546456maxresident)k 116448inputs+3488outputs (9590major+665294minor)pagefaults 0swaps