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 : 2346561 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 : ['2537648'] with mtr_portfolio_ids : ['20142790'] and first list_photo_ids : [] new path : /proc/2346561/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.5713355541229248 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 Sun Feb 2 04:20:27 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 : 10998 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-02 04:20:30.426933: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-02 04:20:30.451471: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493020000 Hz 2025-02-02 04:20:30.453237: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fd818000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-02 04:20:30.453300: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-02 04:20:30.457191: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-02 04:20:30.764711: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x299fb6a0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-02 04:20:30.764769: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-02 04:20:30.766075: 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 2025-02-02 04:20:30.766521: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-02 04:20:30.773141: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-02 04:20:30.775672: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-02 04:20:30.776079: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-02 04:20:30.778919: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-02 04:20:30.780284: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-02 04:20:30.785651: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-02 04:20:30.787084: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-02 04:20:30.787160: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-02 04:20:30.787975: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-02 04:20:30.787993: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-02 04:20:30.788003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-02 04:20:30.789369: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 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. 2025-02-02 04:20:31.047272: 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 2025-02-02 04:20:31.047443: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-02 04:20:31.047475: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-02 04:20:31.047501: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-02 04:20:31.047526: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-02 04:20:31.047550: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-02 04:20:31.047574: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-02 04:20:31.047599: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-02 04:20:31.049454: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-02 04:20:31.050841: 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 2025-02-02 04:20:31.050877: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-02 04:20:31.050895: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-02 04:20:31.050912: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-02 04:20:31.050929: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-02 04:20:31.050946: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-02 04:20:31.050963: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-02 04:20:31.050980: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-02 04:20:31.052530: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-02 04:20:31.052570: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-02 04:20:31.052581: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-02 04:20:31.052590: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-02 04:20:31.054187: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 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 : [] 2025-02-02 04:20:38.458698: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-02 04:20:38.650757: 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 : 4 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.34063 max: 149.66641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0008897781372070312 length of segment : 34 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 32 time to create 1 rle with old method : 9.179115295410156e-05 length of segment : 10 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.0002510547637939453 length of segment : 30 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 825 time to create 1 rle with old method : 0.0015404224395751953 length of segment : 39 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 865 time to create 1 rle with old method : 0.0016338825225830078 length of segment : 35 length of segment : 0 time for calcul the mask position with numpy : 0.00014710426330566406 nb_pixel_total : 1923 time to create 1 rle with old method : 0.003344297409057617 length of segment : 47 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 526 time to create 1 rle with old method : 0.0006923675537109375 length of segment : 35 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.30938 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 : 5.412101745605469e-05 nb_pixel_total : 683 time to create 1 rle with old method : 0.0009217262268066406 length of segment : 76 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 2354 time to create 1 rle with old method : 0.0029144287109375 length of segment : 49 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 955 time to create 1 rle with old method : 0.0012581348419189453 length of segment : 41 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1671 time to create 1 rle with old method : 0.002137899398803711 length of segment : 35 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 4078 time to create 1 rle with old method : 0.005033731460571289 length of segment : 44 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 2722 time to create 1 rle with old method : 0.0033533573150634766 length of segment : 56 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 2027 time to create 1 rle with old method : 0.0025517940521240234 length of segment : 45 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 966 time to create 1 rle with old method : 0.0012822151184082031 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: -116.19219 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 : 0.00015616416931152344 nb_pixel_total : 5665 time to create 1 rle with old method : 0.007890939712524414 length of segment : 139 Processing 1 images image shape: (400, 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 : 7 time for calcul the mask position with numpy : 0.00011968612670898438 nb_pixel_total : 6181 time to create 1 rle with old method : 0.00763392448425293 length of segment : 132 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1150 time to create 1 rle with old method : 0.0013890266418457031 length of segment : 60 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003230571746826172 length of segment : 23 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1234 time to create 1 rle with old method : 0.0016353130340576172 length of segment : 83 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0008502006530761719 length of segment : 38 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00013327598571777344 length of segment : 15 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.0008018016815185547 length of segment : 39 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 244.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 116.97891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.0001895427703857422 length of segment : 13 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006861686706542969 length of segment : 20 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.0002338886260986328 length of segment : 21 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 1033 time to create 1 rle with old method : 0.0012958049774169922 length of segment : 32 time for calcul the mask position with numpy : 0.0005927085876464844 nb_pixel_total : 60229 time to create 1 rle with old method : 0.06852555274963379 length of segment : 280 Processing 1 images image shape: (400, 400, 3) min: 4.00000 max: 203.00000 molded_images shape: (1, 640, 640, 3) min: -94.35313 max: 66.65937 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: -108.77422 max: 150.86172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0003066062927246094 length of segment : 14 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1352 time to create 1 rle with old method : 0.0016021728515625 length of segment : 47 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.00061798095703125 length of segment : 18 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 1231 time to create 1 rle with old method : 0.0015475749969482422 length of segment : 44 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.0003681182861328125 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.11797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0006172657012939453 length of segment : 30 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00019407272338867188 length of segment : 13 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0011172294616699219 length of segment : 36 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.00047397613525390625 length of segment : 23 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003151893615722656 length of segment : 18 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004057884216308594 length of segment : 23 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 779 time to create 1 rle with old method : 0.0009799003601074219 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.99297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1897 time to create 1 rle with old method : 0.0021698474884033203 length of segment : 128 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005068778991699219 length of segment : 23 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 936 time to create 1 rle with old method : 0.0012204647064208984 length of segment : 42 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.000370025634765625 length of segment : 19 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0003032684326171875 length of segment : 18 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 766 time to create 1 rle with old method : 0.0009818077087402344 length of segment : 31 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 854 time to create 1 rle with old method : 0.0010881423950195312 length of segment : 37 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1333 time to create 1 rle with old method : 0.0016415119171142578 length of segment : 43 time for calcul the mask position with numpy : 0.0005118846893310547 nb_pixel_total : 28011 time to create 1 rle with old method : 0.03193068504333496 length of segment : 325 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 2108 time to create 1 rle with old method : 0.0026149749755859375 length of segment : 60 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1391 time to create 1 rle with old method : 0.0017724037170410156 length of segment : 43 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 236.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 117.50625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 1927 time to create 1 rle with old method : 0.0024175643920898438 length of segment : 88 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.00043892860412597656 length of segment : 28 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2225 time to create 1 rle with old method : 0.002814769744873047 length of segment : 142 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 1601 time to create 1 rle with old method : 0.003609895706176758 length of segment : 121 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0006661415100097656 length of segment : 40 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.0009531974792480469 length of segment : 46 Processing 1 images image shape: (280, 400, 3) min: 7.00000 max: 181.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 60.01250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.0012545585632324219 length of segment : 63 time for calcul the mask position with numpy : 0.0012331008911132812 nb_pixel_total : 106539 time to create 1 rle with old method : 0.13360023498535156 length of segment : 284 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: 147.76797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 1740 time to create 1 rle with old method : 0.0030517578125 length of segment : 75 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 1639 time to create 1 rle with old method : 0.0020339488983154297 length of segment : 91 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1720 time to create 1 rle with old method : 0.0021355152130126953 length of segment : 46 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 75 time to create 1 rle with old method : 0.00014972686767578125 length of segment : 10 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006165504455566406 length of segment : 31 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.0004305839538574219 length of segment : 30 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1642 time to create 1 rle with old method : 0.002295255661010742 length of segment : 38 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 419 time to create 1 rle with old method : 0.0009121894836425781 length of segment : 28 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1683 time to create 1 rle with old method : 0.002191781997680664 length of segment : 43 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: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 39 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0003457069396972656 length of segment : 10 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0016357898712158203 length of segment : 39 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.0001811981201171875 length of segment : 13 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.0001590251922607422 length of segment : 12 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1467 time to create 1 rle with old method : 0.002317190170288086 length of segment : 51 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00031185150146484375 length of segment : 15 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.0010080337524414062 length of segment : 30 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.00037789344787597656 length of segment : 18 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00024080276489257812 length of segment : 16 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0004398822784423828 length of segment : 22 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005257129669189453 length of segment : 23 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 859 time to create 1 rle with old method : 0.0012066364288330078 length of segment : 17 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005486011505126953 length of segment : 23 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00030493736267089844 length of segment : 16 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 696 time to create 1 rle with old method : 0.0009207725524902344 length of segment : 35 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.0001933574676513672 length of segment : 11 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1281 time to create 1 rle with old method : 0.001596689224243164 length of segment : 49 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 865 time to create 1 rle with old method : 0.0011718273162841797 length of segment : 17 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002789497375488281 length of segment : 24 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00012254714965820312 length of segment : 8 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002684593200683594 length of segment : 20 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 671 time to create 1 rle with old method : 0.0008587837219238281 length of segment : 34 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 712 time to create 1 rle with old method : 0.0009145736694335938 length of segment : 33 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1675 time to create 1 rle with old method : 0.0020356178283691406 length of segment : 70 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002243518829345703 length of segment : 18 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 63 time to create 1 rle with old method : 9.942054748535156e-05 length of segment : 12 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004115104675292969 length of segment : 17 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0002734661102294922 length of segment : 32 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00040149688720703125 length of segment : 17 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00030231475830078125 length of segment : 14 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0004987716674804688 length of segment : 30 time for calcul the mask position with numpy : 2.6702880859375e-05 nb_pixel_total : 57 time to create 1 rle with old method : 0.00010466575622558594 length of segment : 9 time for calcul the mask position with numpy : 2.7179718017578125e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.00013947486877441406 length of segment : 16 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.0004553794860839844 length of segment : 23 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 2141 time to create 1 rle with old method : 0.0024213790893554688 length of segment : 135 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.00043964385986328125 length of segment : 23 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 898 time to create 1 rle with old method : 0.001123189926147461 length of segment : 41 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00032210350036621094 length of segment : 17 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003752708435058594 length of segment : 18 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.23281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0009870529174804688 length of segment : 38 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0003752708435058594 length of segment : 27 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 629 time to create 1 rle with old method : 0.0010690689086914062 length of segment : 20 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00017023086547851562 length of segment : 19 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 2834 time to create 1 rle with old method : 0.0034301280975341797 length of segment : 78 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 3197 time to create 1 rle with old method : 0.003764629364013672 length of segment : 87 2025-02-02 04:20:44.767814: 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 2025-02-02 04:20:44.767867: F tensorflow/core/common_runtime/gpu/gpu_event_mgr.cc:273] Unexpected Event status: 1 max_time_sub_proc : 3600 Catched exception ! Connect or reconnect ! in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 14.63user 11.76system 1:00:05elapsed 0%CPU (0avgtext+0avgdata 2506964maxresident)k 618568inputs+2192outputs (12154major+676428minor)pagefaults 0swaps