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 : 102946 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 : ['2569088'] with mtr_portfolio_ids : ['20362963'] and first list_photo_ids : [] new path : /proc/102946/ 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 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.6154301166534424 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 9 20:20:30 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 : 10551 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-09 20:20:33.383380: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-09 20:20:33.411320: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-09 20:20:33.412989: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f2234000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-09 20:20:33.413011: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-09 20:20:33.415880: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-09 20:20:33.646558: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x16001470 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-09 20:20:33.646611: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-09 20:20:33.647746: 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 2025-02-09 20:20:33.648394: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-09 20:20:33.651882: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-09 20:20:33.654140: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-09 20:20:33.655429: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-09 20:20:33.657792: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-09 20:20:33.658963: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-09 20:20:33.664067: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-09 20:20:33.665638: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-09 20:20:33.665732: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-09 20:20:33.666526: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-09 20:20:33.666542: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-09 20:20:33.666551: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-09 20:20:33.667956: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9775 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. 2025-02-09 20:20:33.965881: 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 2025-02-09 20:20:33.965970: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-09 20:20:33.965994: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-09 20:20:33.966013: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-09 20:20:33.966031: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-09 20:20:33.966049: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-09 20:20:33.966076: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-09 20:20:33.966101: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-09 20:20:33.967994: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-09 20:20:33.970482: 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 2025-02-09 20:20:33.970656: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-09 20:20:33.970695: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-09 20:20:33.970729: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-09 20:20:33.970761: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-09 20:20:33.970792: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-09 20:20:33.970824: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-09 20:20:33.970857: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-09 20:20:33.979189: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-09 20:20:33.979309: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-09 20:20:33.979330: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-09 20:20:33.979348: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-09 20:20:33.981144: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9775 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 : [] 2025-02-09 20:20:41.055912: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-09 20:20:41.248599: 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 : 2 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: -114.82109 max: 149.26797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0007383823394775391 length of segment : 44 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 912 time to create 1 rle with old method : 0.0018622875213623047 length of segment : 31 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00047469139099121094 length of segment : 31 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 914 time to create 1 rle with old method : 0.0017004013061523438 length of segment : 35 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 55 time to create 1 rle with old method : 0.00012183189392089844 length of segment : 21 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 2424 time to create 1 rle with old method : 0.004110097885131836 length of segment : 78 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1937 time to create 1 rle with old method : 0.003431558609008789 length of segment : 44 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0007555484771728516 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: -117.84063 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 : 4.220008850097656e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004849433898925781 length of segment : 23 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 429 time to create 1 rle with old method : 0.0005550384521484375 length of segment : 43 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.0003197193145751953 length of segment : 22 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0007653236389160156 length of segment : 50 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 18 time to create 1 rle with old method : 3.814697265625e-05 length of segment : 15 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1738 time to create 1 rle with old method : 0.002062082290649414 length of segment : 85 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1566 time to create 1 rle with old method : 0.0018324851989746094 length of segment : 85 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.000385284423828125 length of segment : 30 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 2488 time to create 1 rle with old method : 0.002941608428955078 length of segment : 100 Processing 1 images image shape: (400, 400, 3) min: 40.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -75.20391 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 : 7.033348083496094e-05 nb_pixel_total : 1404 time to create 1 rle with old method : 0.002156972885131836 length of segment : 73 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 308 time to create 1 rle with old method : 0.0005006790161132812 length of segment : 34 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1325 time to create 1 rle with old method : 0.002499103546142578 length of segment : 67 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 2412 time to create 1 rle with old method : 0.0031321048736572266 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 16.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -101.90703 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0008955001831054688 length of segment : 19 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 488 time to create 1 rle with old method : 0.0007920265197753906 length of segment : 28 time for calcul the mask position with numpy : 0.00036978721618652344 nb_pixel_total : 25513 time to create 1 rle with old method : 0.028434276580810547 length of segment : 290 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.00022864341735839844 length of segment : 13 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 579 time to create 1 rle with old method : 0.0007905960083007812 length of segment : 94 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 982 time to create 1 rle with old method : 0.0012691020965576172 length of segment : 49 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003218650817871094 length of segment : 20 time for calcul the mask position with numpy : 9.989738464355469e-05 nb_pixel_total : 3573 time to create 1 rle with old method : 0.0044841766357421875 length of segment : 61 time for calcul the mask position with numpy : 0.0006589889526367188 nb_pixel_total : 40147 time to create 1 rle with old method : 0.05078411102294922 length of segment : 192 Processing 1 images image shape: (400, 400, 3) min: 51.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -67.84063 max: 141.15859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012340545654296875 nb_pixel_total : 153578 time to create 1 rle with new method : 0.0018939971923828125 length of segment : 407 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.44219 max: 150.83047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 784 time to create 1 rle with old method : 0.0010242462158203125 length of segment : 24 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.000629425048828125 length of segment : 18 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 570 time to create 1 rle with old method : 0.0007865428924560547 length of segment : 22 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 836 time to create 1 rle with old method : 0.0010986328125 length of segment : 34 time for calcul the mask position with numpy : 0.00012373924255371094 nb_pixel_total : 2302 time to create 1 rle with old method : 0.0030930042266845703 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.02813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006544589996337891 length of segment : 24 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0006110668182373047 length of segment : 21 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 968 time to create 1 rle with old method : 0.0013225078582763672 length of segment : 41 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 734 time to create 1 rle with old method : 0.0009527206420898438 length of segment : 47 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.0011959075927734375 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -107.79375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 2182 time to create 1 rle with old method : 0.002859830856323242 length of segment : 48 time for calcul the mask position with numpy : 0.00017499923706054688 nb_pixel_total : 9203 time to create 1 rle with old method : 0.010674238204956055 length of segment : 217 time for calcul the mask position with numpy : 0.00018262863159179688 nb_pixel_total : 1332 time to create 1 rle with old method : 0.002399444580078125 length of segment : 138 time for calcul the mask position with numpy : 0.0007822513580322266 nb_pixel_total : 61258 time to create 1 rle with old method : 0.08253049850463867 length of segment : 334 time for calcul the mask position with numpy : 0.0009140968322753906 nb_pixel_total : 73355 time to create 1 rle with old method : 0.08227658271789551 length of segment : 422 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0010755062103271484 length of segment : 38 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 231.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 120.36953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.000293731689453125 length of segment : 26 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 592 time to create 1 rle with old method : 0.0007531642913818359 length of segment : 45 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 773 time to create 1 rle with old method : 0.0010769367218017578 length of segment : 30 time for calcul the mask position with numpy : 0.0001354217529296875 nb_pixel_total : 477 time to create 1 rle with old method : 0.0008206367492675781 length of segment : 64 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 642 time to create 1 rle with old method : 0.0008368492126464844 length of segment : 42 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00035309791564941406 length of segment : 28 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.00057220458984375 length of segment : 38 time for calcul the mask position with numpy : 0.0002582073211669922 nb_pixel_total : 4227 time to create 1 rle with old method : 0.004909038543701172 length of segment : 224 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 1219 time to create 1 rle with old method : 0.0015358924865722656 length of segment : 65 time for calcul the mask position with numpy : 0.0001380443572998047 nb_pixel_total : 1646 time to create 1 rle with old method : 0.002132415771484375 length of segment : 82 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 1259 time to create 1 rle with old method : 0.0016238689422607422 length of segment : 79 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003409385681152344 length of segment : 26 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0010530948638916016 length of segment : 41 time for calcul the mask position with numpy : 0.0003025531768798828 nb_pixel_total : 3408 time to create 1 rle with old method : 0.0042383670806884766 length of segment : 181 Processing 1 images image shape: (280, 400, 3) min: 51.00000 max: 230.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 119.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008833408355712891 nb_pixel_total : 104775 time to create 1 rle with old method : 0.11990642547607422 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: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 27 time for calcul the mask position with numpy : 0.0001251697540283203 nb_pixel_total : 5206 time to create 1 rle with old method : 0.006311893463134766 length of segment : 69 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 541 time to create 1 rle with old method : 0.0007026195526123047 length of segment : 31 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.00023555755615234375 length of segment : 18 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.00035643577575683594 length of segment : 20 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00023508071899414062 length of segment : 13 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0004558563232421875 length of segment : 24 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005083084106445312 length of segment : 40 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 67 time to create 1 rle with old method : 0.00012564659118652344 length of segment : 8 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.012340545654296875 length of segment : 18 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0008571147918701172 length of segment : 40 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0008006095886230469 length of segment : 39 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 419 time to create 1 rle with old method : 0.0007452964782714844 length of segment : 41 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.00030517578125 length of segment : 44 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0006175041198730469 length of segment : 40 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 579 time to create 1 rle with old method : 0.0007815361022949219 length of segment : 22 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006587505340576172 length of segment : 33 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002295970916748047 length of segment : 16 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.0001251697540283203 length of segment : 18 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001461505889892578 length of segment : 21 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00025725364685058594 length of segment : 13 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1396 time to create 1 rle with old method : 0.0017333030700683594 length of segment : 59 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 757 time to create 1 rle with old method : 0.000993967056274414 length of segment : 43 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003933906555175781 length of segment : 9 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00034046173095703125 length of segment : 22 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 855 time to create 1 rle with old method : 0.0010478496551513672 length of segment : 50 time for calcul the mask position with numpy : 0.000164031982421875 nb_pixel_total : 8488 time to create 1 rle with old method : 0.010387659072875977 length of segment : 77 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 814 time to create 1 rle with old method : 0.0010464191436767578 length of segment : 30 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.98281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0005040168762207031 length of segment : 12 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.0003063678741455078 length of segment : 16 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0006997585296630859 length of segment : 16 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.0003771781921386719 length of segment : 16 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0008635520935058594 length of segment : 26 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0010843276977539062 length of segment : 41 time for calcul the mask position with numpy : 0.0001342296600341797 nb_pixel_total : 451 time to create 1 rle with old method : 0.008902788162231445 length of segment : 29 time for calcul the mask position with numpy : 0.00010228157043457031 nb_pixel_total : 540 time to create 1 rle with old method : 0.001695871353149414 length of segment : 31 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1134 time to create 1 rle with old method : 0.0023407936096191406 length of segment : 30 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: 150.06875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 997 time to create 1 rle with old method : 0.001165628433227539 length of segment : 47 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003864765167236328 length of segment : 31 time for calcul the mask position with numpy : 0.00044989585876464844 nb_pixel_total : 41775 time to create 1 rle with old method : 0.044823408126831055 length of segment : 232 time for calcul the mask position with numpy : 0.0004520416259765625 nb_pixel_total : 42633 time to create 1 rle with old method : 0.04555487632751465 length of segment : 233 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 12 time to create 1 rle with old method : 4.172325134277344e-05 length of segment : 7 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 920 time to create 1 rle with old method : 0.0011081695556640625 length of segment : 39 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: 141.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 0.00020599365234375 nb_pixel_total : 7615 time to create 1 rle with old method : 0.009316205978393555 length of segment : 251 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 16 time to create 1 rle with old method : 6.103515625e-05 length of segment : 4 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00040721893310546875 length of segment : 53 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0006158351898193359 length of segment : 30 time for calcul the mask position with numpy : 0.0002880096435546875 nb_pixel_total : 13968 time to create 1 rle with old method : 0.017260313034057617 length of segment : 422 time for calcul the mask position with numpy : 0.0004570484161376953 nb_pixel_total : 21435 time to create 1 rle with old method : 0.029194116592407227 length of segment : 331 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: -114.82109 max: 149.26797 2025-02-09 20:20:47.277034: F tensorflow/core/kernels/bias_op_gpu.cu.cc:97] Non-OK-status: GpuLaunchKernel(BiasNCHWKernel, config.block_count, config.thread_per_block, 0, d.stream(), config.virtual_thread_count, input, bias, output, bias_size, image_size) status: Internal: an illegal memory access was encountered 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 ! 14.83user 10.18system 1:00:06elapsed 0%CPU (0avgtext+0avgdata 2487104maxresident)k 5112inputs+1048outputs (84major+683093minor)pagefaults 0swaps