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 : 3157065 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 : ['2559148'] with mtr_portfolio_ids : ['20296450'] and first list_photo_ids : [] new path : /proc/3157065/ 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 : 0.31688857078552246 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 Thu Feb 6 11:20:29 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10998 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-06 11:20:32.175951: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-06 11:20:32.203120: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-06 11:20:32.204970: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fb8ac000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-06 11:20:32.205035: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-06 11:20:32.209195: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-06 11:20:32.515015: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3c29b610 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-06 11:20:32.515073: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-06 11:20:32.515998: 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 2025-02-06 11:20:32.516319: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-06 11:20:32.518306: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-06 11:20:32.520455: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-06 11:20:32.520775: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-06 11:20:32.523073: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-06 11:20:32.524187: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-06 11:20:32.528714: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-06 11:20:32.530158: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-06 11:20:32.530234: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-06 11:20:32.530987: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-06 11:20:32.531005: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-06 11:20:32.531015: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-06 11:20:32.532406: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-02-06 11:20:32.789172: 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 2025-02-06 11:20:32.789276: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-06 11:20:32.789304: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-06 11:20:32.789323: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-06 11:20:32.789341: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-06 11:20:32.789359: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-06 11:20:32.789376: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-06 11:20:32.789394: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-06 11:20:32.791003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-06 11:20:32.792326: 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 2025-02-06 11:20:32.792373: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-06 11:20:32.792392: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-06 11:20:32.792409: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-06 11:20:32.792426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-06 11:20:32.792443: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-06 11:20:32.792460: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-06 11:20:32.792477: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-06 11:20:32.794172: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-06 11:20:32.794207: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-06 11:20:32.794218: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-06 11:20:32.794228: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-06 11:20:32.795926: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-06 11:20:39.939216: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-06 11:20:40.087980: 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: -120.07109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 0.00012493133544921875 nb_pixel_total : 1140 time to create 1 rle with old method : 0.011409997940063477 length of segment : 42 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 1772 time to create 1 rle with old method : 0.0030002593994140625 length of segment : 41 time for calcul the mask position with numpy : 9.465217590332031e-05 nb_pixel_total : 1816 time to create 1 rle with old method : 0.0031092166900634766 length of segment : 53 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 2264 time to create 1 rle with old method : 0.003907203674316406 length of segment : 66 time for calcul the mask position with numpy : 0.0001614093780517578 nb_pixel_total : 2022 time to create 1 rle with old method : 0.002521991729736328 length of segment : 155 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 669 time to create 1 rle with old method : 0.0008323192596435547 length of segment : 41 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 994 time to create 1 rle with old method : 0.0011937618255615234 length of segment : 43 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002956390380859375 length of segment : 15 time for calcul the mask position with numpy : 0.0001575946807861328 nb_pixel_total : 2363 time to create 1 rle with old method : 0.002797365188598633 length of segment : 169 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002956390380859375 length of segment : 15 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003781318664550781 length of segment : 21 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 1875 time to create 1 rle with old method : 0.0023636817932128906 length of segment : 52 time for calcul the mask position with numpy : 0.00012040138244628906 nb_pixel_total : 984 time to create 1 rle with old method : 0.0013475418090820312 length of segment : 72 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 788 time to create 1 rle with old method : 0.0009808540344238281 length of segment : 39 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 786 time to create 1 rle with old method : 0.000965118408203125 length of segment : 38 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 1833 time to create 1 rle with old method : 0.002189159393310547 length of segment : 42 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002734661102294922 length of segment : 15 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 2039 time to create 1 rle with old method : 0.0024902820587158203 length of segment : 81 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003204345703125 length of segment : 17 time for calcul the mask position with numpy : 0.000148773193359375 nb_pixel_total : 2973 time to create 1 rle with old method : 0.003547191619873047 length of segment : 75 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 1738 time to create 1 rle with old method : 0.0021371841430664062 length of segment : 68 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1062 time to create 1 rle with old method : 0.0014109611511230469 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.09453 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 1577 time to create 1 rle with old method : 0.0019068717956542969 length of segment : 58 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0006754398345947266 length of segment : 31 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006589889526367188 length of segment : 23 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 2825 time to create 1 rle with old method : 0.0034894943237304688 length of segment : 72 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.0002892017364501953 length of segment : 8 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0007750988006591797 length of segment : 26 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0006201267242431641 length of segment : 26 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.00046634674072265625 length of segment : 27 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0007486343383789062 length of segment : 39 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002410411834716797 length of segment : 16 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0007369518280029297 length of segment : 46 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0005216598510742188 length of segment : 20 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0008046627044677734 length of segment : 35 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.00046133995056152344 length of segment : 26 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 668 time to create 1 rle with old method : 0.0008502006530761719 length of segment : 42 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 652 time to create 1 rle with old method : 0.0008757114410400391 length of segment : 35 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 777 time to create 1 rle with old method : 0.0010504722595214844 length of segment : 59 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 854 time to create 1 rle with old method : 0.0011589527130126953 length of segment : 62 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.94609 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 : 9.608268737792969e-05 nb_pixel_total : 1843 time to create 1 rle with old method : 0.0020983219146728516 length of segment : 94 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.00040435791015625 length of segment : 34 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0003809928894042969 length of segment : 24 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0010001659393310547 length of segment : 27 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 872 time to create 1 rle with old method : 0.001085042953491211 length of segment : 118 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0007977485656738281 length of segment : 28 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1055 time to create 1 rle with old method : 0.00140380859375 length of segment : 40 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0004894733428955078 length of segment : 22 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002741813659667969 length of segment : 9 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0009558200836181641 length of segment : 71 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0004088878631591797 length of segment : 24 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.001004934310913086 length of segment : 40 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001976490020751953 length of segment : 13 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 372 time to create 1 rle with old method : 0.0005581378936767578 length of segment : 22 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005321502685546875 length of segment : 34 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1027 time to create 1 rle with old method : 0.0013663768768310547 length of segment : 42 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0006151199340820312 length of segment : 33 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0005848407745361328 length of segment : 23 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00038313865661621094 length of segment : 24 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 165 time to create 1 rle with old method : 0.000240325927734375 length of segment : 21 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0007815361022949219 length of segment : 46 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0003924369812011719 length of segment : 27 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1420 time to create 1 rle with old method : 0.0018663406372070312 length of segment : 57 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.00021600723266601562 length of segment : 20 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0006811618804931641 length of segment : 25 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0007936954498291016 length of segment : 28 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0003914833068847656 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -101.59453 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 : 6.747245788574219e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004699230194091797 length of segment : 14 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.0012516975402832031 length of segment : 41 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003509521484375 length of segment : 23 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 2415 time to create 1 rle with old method : 0.002771615982055664 length of segment : 112 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0010268688201904297 length of segment : 38 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1428 time to create 1 rle with old method : 0.0018360614776611328 length of segment : 52 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0014960765838623047 length of segment : 46 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.00041222572326660156 length of segment : 29 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005373954772949219 length of segment : 20 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003647804260253906 length of segment : 20 time for calcul the mask position with numpy : 0.0002384185791015625 nb_pixel_total : 2019 time to create 1 rle with old method : 0.003400087356567383 length of segment : 119 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0005524158477783203 length of segment : 15 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 694 time to create 1 rle with old method : 0.0012431144714355469 length of segment : 41 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0006806850433349609 length of segment : 43 time for calcul the mask position with numpy : 0.00011014938354492188 nb_pixel_total : 1607 time to create 1 rle with old method : 0.002746105194091797 length of segment : 54 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0010635852813720703 length of segment : 33 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0005347728729248047 length of segment : 18 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 2954 time to create 1 rle with old method : 0.0035276412963867188 length of segment : 55 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1572 time to create 1 rle with old method : 0.0018401145935058594 length of segment : 68 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 691 time to create 1 rle with old method : 0.0009431838989257812 length of segment : 36 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 606 time to create 1 rle with old method : 0.0007519721984863281 length of segment : 34 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1166 time to create 1 rle with old method : 0.0015082359313964844 length of segment : 51 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.001104116439819336 length of segment : 37 time for calcul the mask position with numpy : 0.0001327991485595703 nb_pixel_total : 2282 time to create 1 rle with old method : 0.0027618408203125 length of segment : 163 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1034 time to create 1 rle with old method : 0.0014913082122802734 length of segment : 15 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 2572 time to create 1 rle with old method : 0.0030260086059570312 length of segment : 66 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 2564 time to create 1 rle with old method : 0.0029892921447753906 length of segment : 57 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 419 time to create 1 rle with old method : 0.0006287097930908203 length of segment : 33 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004203319549560547 length of segment : 25 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 2446 time to create 1 rle with old method : 0.002865314483642578 length of segment : 71 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 544 time to create 1 rle with old method : 0.0007090568542480469 length of segment : 33 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1236 time to create 1 rle with old method : 0.001552581787109375 length of segment : 48 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2623 time to create 1 rle with old method : 0.003234386444091797 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.80938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006849765777587891 length of segment : 25 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00041484832763671875 length of segment : 22 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002913475036621094 length of segment : 13 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005314350128173828 length of segment : 41 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 2797 time to create 1 rle with old method : 0.0033910274505615234 length of segment : 65 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.00016260147094726562 length of segment : 16 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 790 time to create 1 rle with old method : 0.0009260177612304688 length of segment : 63 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.00040531158447265625 length of segment : 27 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 660 time to create 1 rle with old method : 0.0008471012115478516 length of segment : 28 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.00032401084899902344 length of segment : 19 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005426406860351562 length of segment : 25 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0009675025939941406 length of segment : 49 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 1349 time to create 1 rle with old method : 0.0016584396362304688 length of segment : 54 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1383 time to create 1 rle with old method : 0.0017290115356445312 length of segment : 54 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 1545 time to create 1 rle with old method : 0.001895904541015625 length of segment : 39 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005199909210205078 length of segment : 30 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 2075 time to create 1 rle with old method : 0.0023245811462402344 length of segment : 110 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.000164031982421875 length of segment : 9 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 853 time to create 1 rle with old method : 0.0010056495666503906 length of segment : 64 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.32891 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 : 7.700920104980469e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0003688335418701172 length of segment : 23 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0008492469787597656 length of segment : 41 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0003604888916015625 length of segment : 17 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0008344650268554688 length of segment : 27 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 701 time to create 1 rle with old method : 0.001771688461303711 length of segment : 55 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 976 time to create 1 rle with old method : 0.0011487007141113281 length of segment : 57 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 920 time to create 1 rle with old method : 0.001130819320678711 length of segment : 52 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0008270740509033203 length of segment : 44 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0004987716674804688 length of segment : 40 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 2177 time to create 1 rle with old method : 0.002669811248779297 length of segment : 44 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.00042748451232910156 length of segment : 16 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0003898143768310547 length of segment : 13 Processing 1 images image shape: (400, 160, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.24062 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0010976791381835938 length of segment : 36 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.00022125244140625 length of segment : 26 time for calcul the mask position with numpy : 0.00015282630920410156 nb_pixel_total : 2061 time to create 1 rle with old method : 0.002808094024658203 length of segment : 132 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.00014901161193847656 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.73906 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 : 5.817413330078125e-05 nb_pixel_total : 1022 time to create 1 rle with old method : 0.001222372055053711 length of segment : 44 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005223751068115234 length of segment : 24 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 42 time to create 1 rle with old method : 0.00011658668518066406 length of segment : 6 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.00045037269592285156 length of segment : 20 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005636215209960938 length of segment : 17 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005621910095214844 length of segment : 16 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.000614166259765625 length of segment : 35 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00018858909606933594 length of segment : 15 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.0010225772857666016 length of segment : 54 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.97734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0009183883666992188 length of segment : 51 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1318 time to create 1 rle with old method : 0.002250194549560547 length of segment : 50 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 2671 time to create 1 rle with old method : 0.0044596195220947266 length of segment : 63 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0005114078521728516 length of segment : 18 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004589557647705078 length of segment : 18 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 366 time to create 1 rle with old method : 0.0005075931549072266 length of segment : 31 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002741813659667969 length of segment : 15 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0006103515625 length of segment : 22 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1559 time to create 1 rle with old method : 0.0017955303192138672 length of segment : 81 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0004673004150390625 length of segment : 20 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00021123886108398438 length of segment : 10 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1733 time to create 1 rle with old method : 0.0035932064056396484 length of segment : 40 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 4268 time to create 1 rle with old method : 0.0048449039459228516 length of segment : 84 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.0002200603485107422 length of segment : 19 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007989406585693359 length of segment : 41 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1635 time to create 1 rle with old method : 0.0020449161529541016 length of segment : 54 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 684 time to create 1 rle with old method : 0.0008432865142822266 length of segment : 28 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.00033593177795410156 length of segment : 59 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00019860267639160156 length of segment : 15 time for calcul the mask position with numpy : 0.00011849403381347656 nb_pixel_total : 3161 time to create 1 rle with old method : 0.003955364227294922 length of segment : 104 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1641 time to create 1 rle with old method : 0.0018711090087890625 length of segment : 83 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0004131793975830078 length of segment : 20 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 2484 time to create 1 rle with old method : 0.0027151107788085938 length of segment : 111 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.22734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 2025-02-06 11:20:45.486382: F ./tensorflow/core/kernels/conv_2d_gpu.h:453] Non-OK-status: GpuLaunchKernel(ShuffleInTensor3Simple, config.block_count, config.thread_per_block, 0, d.stream(), config.virtual_thread_count, in.data(), combined_dims, out.data()) 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 ! 14.14user 8.46system 1:00:06elapsed 0%CPU (0avgtext+0avgdata 2487272maxresident)k 124232inputs+2872outputs (11826major+590167minor)pagefaults 0swaps