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 : 3842516 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 : ['2535616'] with mtr_portfolio_ids : ['20124866'] and first list_photo_ids : [] new path : /proc/3842516/ 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 : 0.7882001399993896 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 Sat Feb 1 08:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10332 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-01 08:20:31.650693: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-01 08:20:31.675704: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493020000 Hz 2025-02-01 08:20:31.677160: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fed78000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-01 08:20:31.677211: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-01 08:20:31.679878: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-01 08:20:31.815298: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x194f1120 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-01 08:20:31.815342: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-01 08:20:31.816267: 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 2025-02-01 08:20:31.816553: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 08:20:31.822759: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 08:20:31.824935: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 08:20:31.825253: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 08:20:31.827609: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 08:20:31.829088: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 08:20:31.833936: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 08:20:31.835377: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 08:20:31.835452: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 08:20:31.836198: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-01 08:20:31.836213: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-01 08:20:31.836222: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-01 08:20:31.837490: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9570 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. 2025-02-01 08:20:32.092647: 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 2025-02-01 08:20:32.092768: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 08:20:32.092786: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 08:20:32.092802: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 08:20:32.092817: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 08:20:32.092831: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 08:20:32.092846: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 08:20:32.092861: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 08:20:32.094090: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 08:20:32.095691: 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 2025-02-01 08:20:32.095754: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 08:20:32.095784: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 08:20:32.095811: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 08:20:32.095838: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 08:20:32.095865: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 08:20:32.095891: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 08:20:32.095918: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 08:20:32.098114: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 08:20:32.098161: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-01 08:20:32.098177: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-01 08:20:32.098191: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-01 08:20:32.100430: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9570 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 : [] 2025-02-01 08:20:39.406192: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 08:20:39.603278: 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: -114.34063 max: 149.52187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 49 time to create 1 rle with old method : 0.00019788742065429688 length of segment : 13 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0007669925689697266 length of segment : 24 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 57 time to create 1 rle with old method : 0.00012922286987304688 length of segment : 11 length of segment : 0 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00018596649169921875 length of segment : 24 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.00027823448181152344 length of segment : 25 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.00020623207092285156 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.34844 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 : 4.1961669921875e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007939338684082031 length of segment : 24 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 3850 time to create 1 rle with old method : 0.004812479019165039 length of segment : 116 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 3526 time to create 1 rle with old method : 0.00431370735168457 length of segment : 98 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1004 time to create 1 rle with old method : 0.0012028217315673828 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.86016 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 : 6.699562072753906e-05 nb_pixel_total : 1007 time to create 1 rle with old method : 0.0017895698547363281 length of segment : 45 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0005512237548828125 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.90313 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 : 5.53131103515625e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0005240440368652344 length of segment : 16 time for calcul the mask position with numpy : 0.00020241737365722656 nb_pixel_total : 8788 time to create 1 rle with old method : 0.01052546501159668 length of segment : 109 time for calcul the mask position with numpy : 0.00012087821960449219 nb_pixel_total : 523 time to create 1 rle with old method : 0.0009415149688720703 length of segment : 51 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.00046539306640625 length of segment : 13 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: 150.45156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 956 time to create 1 rle with old method : 0.0012423992156982422 length of segment : 32 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 511 time to create 1 rle with old method : 0.000720977783203125 length of segment : 20 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.0002167224884033203 length of segment : 11 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 2281 time to create 1 rle with old method : 0.002666950225830078 length of segment : 187 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007164478302001953 length of segment : 20 time for calcul the mask position with numpy : 0.0006093978881835938 nb_pixel_total : 41249 time to create 1 rle with old method : 0.048241615295410156 length of segment : 251 Processing 1 images image shape: (400, 400, 3) min: 23.00000 max: 231.00000 molded_images shape: (1, 640, 640, 3) min: -79.92656 max: 97.98516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.55547 max: 151.06875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 880 time to create 1 rle with old method : 0.0011539459228515625 length of segment : 36 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0003230571746826172 length of segment : 12 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003390312194824219 length of segment : 16 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00014138221740722656 length of segment : 10 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002644062042236328 length of segment : 42 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.00086212158203125 length of segment : 32 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 1924 time to create 1 rle with old method : 0.0023686885833740234 length of segment : 62 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004432201385498047 length of segment : 14 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.00022220611572265625 length of segment : 17 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.00045990943908691406 length of segment : 18 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1598 time to create 1 rle with old method : 0.0021889209747314453 length of segment : 36 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 1470 time to create 1 rle with old method : 0.0027544498443603516 length of segment : 57 time for calcul the mask position with numpy : 0.0003688335418701172 nb_pixel_total : 20844 time to create 1 rle with old method : 0.02441263198852539 length of segment : 139 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004417896270751953 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.03594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003447532653808594 length of segment : 19 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 817 time to create 1 rle with old method : 0.0010676383972167969 length of segment : 35 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.00026535987854003906 length of segment : 11 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0008020401000976562 length of segment : 20 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00027751922607421875 length of segment : 12 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0004565715789794922 length of segment : 9 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0009865760803222656 length of segment : 41 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002892017364501953 length of segment : 32 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0004436969757080078 length of segment : 12 time for calcul the mask position with numpy : 0.00034737586975097656 nb_pixel_total : 11570 time to create 1 rle with old method : 0.013721227645874023 length of segment : 201 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.00036597251892089844 length of segment : 35 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.00016379356384277344 length of segment : 10 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.000993490219116211 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: -122.35625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.001032114028930664 length of segment : 35 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002827644348144531 length of segment : 11 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1309 time to create 1 rle with old method : 0.00165557861328125 length of segment : 40 time for calcul the mask position with numpy : 0.0002205371856689453 nb_pixel_total : 7750 time to create 1 rle with old method : 0.009255409240722656 length of segment : 150 time for calcul the mask position with numpy : 0.0004305839538574219 nb_pixel_total : 18682 time to create 1 rle with old method : 0.021373510360717773 length of segment : 208 time for calcul the mask position with numpy : 0.00013446807861328125 nb_pixel_total : 1880 time to create 1 rle with old method : 0.0022661685943603516 length of segment : 139 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0009300708770751953 length of segment : 27 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 687 time to create 1 rle with old method : 0.0014765262603759766 length of segment : 38 time for calcul the mask position with numpy : 0.00019788742065429688 nb_pixel_total : 5311 time to create 1 rle with old method : 0.009244680404663086 length of segment : 159 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0013158321380615234 length of segment : 35 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0007309913635253906 length of segment : 50 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 778 time to create 1 rle with old method : 0.0013966560363769531 length of segment : 35 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: 150.74844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0002617835998535156 length of segment : 21 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0013442039489746094 length of segment : 41 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.0009944438934326172 length of segment : 46 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1220 time to create 1 rle with old method : 0.0015277862548828125 length of segment : 47 time for calcul the mask position with numpy : 0.00018477439880371094 nb_pixel_total : 3786 time to create 1 rle with old method : 0.004457712173461914 length of segment : 198 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1583 time to create 1 rle with old method : 0.0019354820251464844 length of segment : 82 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 990 time to create 1 rle with old method : 0.0013158321380615234 length of segment : 27 time for calcul the mask position with numpy : 0.00025963783264160156 nb_pixel_total : 6046 time to create 1 rle with old method : 0.007361173629760742 length of segment : 156 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1034 time to create 1 rle with old method : 0.0013840198516845703 length of segment : 27 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.0002541542053222656 length of segment : 14 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.0009353160858154297 length of segment : 53 Processing 1 images image shape: (280, 400, 3) min: 13.00000 max: 209.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 79.21953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.000997781753540039 nb_pixel_total : 106481 time to create 1 rle with old method : 0.11911439895629883 length of segment : 281 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 : 14 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 1587 time to create 1 rle with old method : 0.0019989013671875 length of segment : 85 time for calcul the mask position with numpy : 0.0001480579376220703 nb_pixel_total : 2993 time to create 1 rle with old method : 0.003701925277709961 length of segment : 92 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 1168 time to create 1 rle with old method : 0.001514434814453125 length of segment : 34 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1274 time to create 1 rle with old method : 0.001661062240600586 length of segment : 36 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002727508544921875 length of segment : 14 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0002689361572265625 length of segment : 39 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.00047659873962402344 length of segment : 24 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1096 time to create 1 rle with old method : 0.0013303756713867188 length of segment : 31 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 2139 time to create 1 rle with old method : 0.0026350021362304688 length of segment : 100 time for calcul the mask position with numpy : 0.00011873245239257812 nb_pixel_total : 3169 time to create 1 rle with old method : 0.00411677360534668 length of segment : 94 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00017762184143066406 length of segment : 44 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1258 time to create 1 rle with old method : 0.0016155242919921875 length of segment : 36 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.0007214546203613281 length of segment : 33 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006818771362304688 length of segment : 32 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 : 33 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003676414489746094 length of segment : 19 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 675 time to create 1 rle with old method : 0.0008516311645507812 length of segment : 39 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.0005826950073242188 length of segment : 42 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0006303787231445312 length of segment : 31 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004773139953613281 length of segment : 21 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001838207244873047 length of segment : 10 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.000522613525390625 length of segment : 32 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0006270408630371094 length of segment : 27 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00032401084899902344 length of segment : 17 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 684 time to create 1 rle with old method : 0.0008699893951416016 length of segment : 34 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00023412704467773438 length of segment : 15 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.000179290771484375 length of segment : 11 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0004241466522216797 length of segment : 25 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004239082336425781 length of segment : 23 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0007293224334716797 length of segment : 32 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001773834228515625 length of segment : 12 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.0006461143493652344 length of segment : 16 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002989768981933594 length of segment : 18 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 529 time to create 1 rle with old method : 0.0006957054138183594 length of segment : 25 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 682 time to create 1 rle with old method : 0.000873565673828125 length of segment : 35 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.000415802001953125 length of segment : 27 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.00040149688720703125 length of segment : 14 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 2586 time to create 1 rle with old method : 0.003177165985107422 length of segment : 35 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.00024390220642089844 length of segment : 21 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 981 time to create 1 rle with old method : 0.0012857913970947266 length of segment : 32 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.000274658203125 length of segment : 23 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00033020973205566406 length of segment : 14 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1187 time to create 1 rle with old method : 0.00147247314453125 length of segment : 39 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 429 time to create 1 rle with old method : 0.0005710124969482422 length of segment : 27 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 1830 time to create 1 rle with old method : 0.002187490463256836 length of segment : 98 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 3006 time to create 1 rle with old method : 0.00359344482421875 length of segment : 42 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00021457672119140625 length of segment : 24 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1818 time to create 1 rle with old method : 0.0022039413452148438 length of segment : 103 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: 150.12734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 986 time to create 1 rle with old method : 0.0013267993927001953 length of segment : 34 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.0004210472106933594 length of segment : 34 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.000335693359375 length of segment : 17 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.0001621246337890625 length of segment : 20 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.00020647048950195312 length of segment : 27 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001857280731201172 length of segment : 19 time for calcul the mask position with numpy : 0.00028204917907714844 nb_pixel_total : 968 time to create 1 rle with old method : 0.0014908313751220703 length of segment : 73 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005054473876953125 length of segment : 22 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 75 time to create 1 rle with old method : 0.00014972686767578125 length of segment : 6 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.00022292137145996094 length of segment : 28 time for calcul the mask position with numpy : 0.0002620220184326172 nb_pixel_total : 1896 time to create 1 rle with old method : 0.0026748180389404297 length of segment : 114 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004968643188476562 length of segment : 22 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: 134.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.0004477500915527344 length of segment : 30 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1703 time to create 1 rle with old method : 0.0021698474884033203 length of segment : 52 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005886554718017578 length of segment : 28 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.0003409385681152344 length of segment : 18 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0009932518005371094 length of segment : 98 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0006289482116699219 length of segment : 55 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001628398895263672 length of segment : 10 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: -117.10234 max: 148.24453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 51 time to create 1 rle with old method : 0.0001342296600341797 length of segment : 16 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0006840229034423828 length of segment : 28 time for calcul the mask position with numpy : 0.00019860267639160156 nb_pixel_total : 3746 time to create 1 rle with old method : 0.00855565071105957 length of segment : 141 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 52 time to create 1 rle with old method : 9.441375732421875e-05 length of segment : 12 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011372566223144531 length of segment : 18 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 62 time to create 1 rle with old method : 0.00011444091796875 length of segment : 28 length of segment : 0 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1632 time to create 1 rle with old method : 0.002121448516845703 length of segment : 51 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.00014710426330566406 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.40703 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 : 9.512901306152344e-05 nb_pixel_total : 2469 time to create 1 rle with old method : 0.003083467483520508 length of segment : 53 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0009121894836425781 length of segment : 63 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.29375 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 : 0.00010752677917480469 nb_pixel_total : 6228 time to create 1 rle with old method : 0.007387638092041016 length of segment : 122 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0005106925964355469 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 2025-02-01 08:20:46.699218: E tensorflow/stream_executor/cuda/cuda_event.cc:29] Error polling for event status: failed to query event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered 2025-02-01 08:20:46.699268: F tensorflow/core/common_runtime/gpu/gpu_event_mgr.cc:273] Unexpected Event status: 1 max_time_sub_proc : 3600 Catched exception ! Connect or reconnect ! in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 15.97user 12.08system 1:00:05elapsed 0%CPU (0avgtext+0avgdata 2522816maxresident)k 140976inputs+2984outputs (12531major+649199minor)pagefaults 0swaps