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 : 1638842 load datou : 4234 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 we have a portfolio with more photos than limit : 64>5 please execute split_portfolio.py -i 21130880 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2646439'] with mtr_portfolio_ids : ['21130880'] and first list_photo_ids : [] new path : /proc/1638842/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 0.6288599967956543 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 Fri Mar 7 08:20:30 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 : 10814 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-07 08:20:33.114104: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-07 08:20:33.143126: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-07 08:20:33.145064: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fcb10000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-07 08:20:33.145097: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-07 08:20:33.149669: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-07 08:20:33.309311: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xbef5950 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-07 08:20:33.309364: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-07 08:20:33.310202: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-07 08:20:33.310559: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 08:20:33.312728: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 08:20:33.315009: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 08:20:33.315384: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 08:20:33.317705: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 08:20:33.318794: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 08:20:33.324289: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 08:20:33.326270: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 08:20:33.326385: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 08:20:33.327400: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 08:20:33.327423: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 08:20:33.327434: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 08:20:33.328875: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9879 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-03-07 08:20:33.613167: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-07 08:20:33.613281: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 08:20:33.613313: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 08:20:33.613340: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 08:20:33.613366: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 08:20:33.613393: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 08:20:33.613419: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 08:20:33.613446: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 08:20:33.615265: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 08:20:33.616785: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-07 08:20:33.616854: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-07 08:20:33.616884: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 08:20:33.616910: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-07 08:20:33.616936: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-07 08:20:33.616960: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-07 08:20:33.616987: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-07 08:20:33.617015: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-07 08:20:33.618758: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-07 08:20:33.618818: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-07 08:20:33.618832: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-07 08:20:33.618842: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-07 08:20:33.620685: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9879 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-03-07 08:20:42.194395: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-07 08:20:42.401768: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 5 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.22344 max: 146.08047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00033974647521972656 length of segment : 23 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00041604042053222656 length of segment : 27 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.001425027847290039 length of segment : 53 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.0002532005310058594 length of segment : 13 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.0014679431915283203 length of segment : 55 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 817 time to create 1 rle with old method : 0.0014171600341796875 length of segment : 51 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.35625 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 : 0.00026226043701171875 nb_pixel_total : 3830 time to create 1 rle with old method : 0.006289958953857422 length of segment : 412 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 672 time to create 1 rle with old method : 0.0009758472442626953 length of segment : 33 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 2866 time to create 1 rle with old method : 0.003732919692993164 length of segment : 54 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 958 time to create 1 rle with old method : 0.001226186752319336 length of segment : 58 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0007734298706054688 length of segment : 40 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 937 time to create 1 rle with old method : 0.0015859603881835938 length of segment : 59 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 736 time to create 1 rle with old method : 0.0010423660278320312 length of segment : 36 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 3161 time to create 1 rle with old method : 0.004471778869628906 length of segment : 57 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 40 time to create 1 rle with old method : 0.00010347366333007812 length of segment : 8 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 40 time to create 1 rle with old method : 9.632110595703125e-05 length of segment : 7 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.06719 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 : 0.0003085136413574219 nb_pixel_total : 7129 time to create 1 rle with old method : 0.012211799621582031 length of segment : 135 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0008480548858642578 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.52031 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 : 7.867813110351562e-05 nb_pixel_total : 435 time to create 1 rle with old method : 0.0009765625 length of segment : 26 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003299713134765625 length of segment : 22 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0006327629089355469 length of segment : 23 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0006477832794189453 length of segment : 25 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0007636547088623047 length of segment : 23 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 198.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 65.63516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0007233619689941406 length of segment : 17 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 813 time to create 1 rle with old method : 0.0010685920715332031 length of segment : 55 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1488 time to create 1 rle with old method : 0.0018200874328613281 length of segment : 92 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0004105567932128906 length of segment : 26 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 636 time to create 1 rle with old method : 0.0008325576782226562 length of segment : 33 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 672 time to create 1 rle with old method : 0.0008931159973144531 length of segment : 34 time for calcul the mask position with numpy : 0.0005497932434082031 nb_pixel_total : 46661 time to create 1 rle with old method : 0.05317997932434082 length of segment : 298 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 165.00000 molded_images shape: (1, 640, 640, 3) min: -99.68828 max: 47.16641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0013015270233154297 nb_pixel_total : 153123 time to create 1 rle with new method : 0.0019192695617675781 length of segment : 404 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.15703 max: 150.84609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 2287 time to create 1 rle with old method : 0.0028846263885498047 length of segment : 48 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1214 time to create 1 rle with old method : 0.0016067028045654297 length of segment : 36 time for calcul the mask position with numpy : 0.0001544952392578125 nb_pixel_total : 9415 time to create 1 rle with old method : 0.011339902877807617 length of segment : 123 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005624294281005859 length of segment : 21 time for calcul the mask position with numpy : 0.0001246929168701172 nb_pixel_total : 8559 time to create 1 rle with old method : 0.01032567024230957 length of segment : 103 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004062652587890625 length of segment : 20 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.0006101131439208984 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.74297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.0001747608184814453 nb_pixel_total : 11763 time to create 1 rle with old method : 0.016233444213867188 length of segment : 144 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0003299713134765625 length of segment : 12 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 692 time to create 1 rle with old method : 0.0012443065643310547 length of segment : 33 time for calcul the mask position with numpy : 0.0003294944763183594 nb_pixel_total : 12311 time to create 1 rle with old method : 0.020938396453857422 length of segment : 154 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.18047 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 : 5.841255187988281e-05 nb_pixel_total : 1760 time to create 1 rle with old method : 0.002266407012939453 length of segment : 40 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1344 time to create 1 rle with old method : 0.0017194747924804688 length of segment : 43 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 752 time to create 1 rle with old method : 0.00095367431640625 length of segment : 36 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.00044155120849609375 length of segment : 20 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 631 time to create 1 rle with old method : 0.0008246898651123047 length of segment : 50 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1983 time to create 1 rle with old method : 0.0026116371154785156 length of segment : 58 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1305 time to create 1 rle with old method : 0.0016770362854003906 length of segment : 43 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0005214214324951172 length of segment : 21 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 171.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 56.19766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 2157 time to create 1 rle with old method : 0.0025954246520996094 length of segment : 130 time for calcul the mask position with numpy : 0.00015687942504882812 nb_pixel_total : 3352 time to create 1 rle with old method : 0.004050731658935547 length of segment : 192 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 2390 time to create 1 rle with old method : 0.002936124801635742 length of segment : 145 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005347728729248047 length of segment : 40 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005757808685302734 length of segment : 28 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 858 time to create 1 rle with old method : 0.0011680126190185547 length of segment : 55 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0007274150848388672 length of segment : 34 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 683 time to create 1 rle with old method : 0.0009303092956542969 length of segment : 41 Processing 1 images image shape: (280, 400, 3) min: 11.00000 max: 165.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 50.32656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009472370147705078 nb_pixel_total : 105341 time to create 1 rle with old method : 0.11702871322631836 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0006854534149169922 length of segment : 27 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.00043702125549316406 length of segment : 41 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.00042700767517089844 length of segment : 27 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 3752 time to create 1 rle with old method : 0.004584789276123047 length of segment : 66 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.0008139610290527344 length of segment : 29 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1130 time to create 1 rle with old method : 0.0014643669128417969 length of segment : 46 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0007357597351074219 length of segment : 32 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1450 time to create 1 rle with old method : 0.0018911361694335938 length of segment : 40 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0016205310821533203 length of segment : 38 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.0008444786071777344 length of segment : 30 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0005142688751220703 length of segment : 16 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 228.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 110.61953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.00016307830810546875 length of segment : 13 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.00023126602172851562 length of segment : 14 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0009951591491699219 length of segment : 35 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005023479461669922 length of segment : 20 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.00046753883361816406 length of segment : 21 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.00014853477478027344 length of segment : 13 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002529621124267578 length of segment : 20 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003769397735595703 length of segment : 21 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004353523254394531 length of segment : 18 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006053447723388672 length of segment : 32 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.00042629241943359375 length of segment : 21 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007493495941162109 length of segment : 49 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004189014434814453 length of segment : 18 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004999637603759766 length of segment : 21 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: 148.86172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.00063323974609375 length of segment : 34 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00028395652770996094 length of segment : 20 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 522 time to create 1 rle with old method : 0.0007085800170898438 length of segment : 33 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0007431507110595703 length of segment : 25 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.0006437301635742188 length of segment : 40 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.00035643577575683594 length of segment : 25 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00036597251892089844 length of segment : 31 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.35000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0005097389221191406 nb_pixel_total : 37479 time to create 1 rle with old method : 0.04220128059387207 length of segment : 216 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: -118.89141 max: 145.55703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00030875205993652344 length of segment : 28 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 678 time to create 1 rle with old method : 0.0009605884552001953 length of segment : 46 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0005230903625488281 length of segment : 37 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.0002090930938720703 length of segment : 20 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.0001468658447265625 length of segment : 22 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 743 time to create 1 rle with old method : 0.001035928726196289 length of segment : 49 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003380775451660156 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.36016 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 : 0.00024390220642089844 nb_pixel_total : 1449 time to create 1 rle with old method : 0.0019221305847167969 length of segment : 167 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 2675 time to create 1 rle with old method : 0.003234386444091797 length of segment : 48 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 682 time to create 1 rle with old method : 0.0013158321380615234 length of segment : 63 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0008111000061035156 length of segment : 45 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 885 time to create 1 rle with old method : 0.0011289119720458984 length of segment : 57 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 988 time to create 1 rle with old method : 0.0013184547424316406 length of segment : 26 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 61 time to create 1 rle with old method : 0.00013971328735351562 length of segment : 22 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 833 time to create 1 rle with old method : 0.0010919570922851562 length of segment : 29 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 2636 2025-03-07 08:20:49.158151: E tensorflow/stream_executor/cuda/cuda_event.cc:29] Error polling for event status: failed to query event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered 2025-03-07 08:20:49.158212: F tensorflow/core/common_runtime/gpu/gpu_event_mgr.cc:273] Unexpected Event status: 1 max_time_sub_proc : 3600 Catched exception ! Connect or reconnect ! in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 16.34user 12.04system 1:00:08elapsed 0%CPU (0avgtext+0avgdata 2508680maxresident)k 617904inputs+2320outputs (11067major+684009minor)pagefaults 0swaps