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 : 2383672 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 : ['2542737'] with mtr_portfolio_ids : ['20196009'] and first list_photo_ids : [] new path : /proc/2383672/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.6371719837188721 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 Tue Feb 4 02:20:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10774 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-04 02:20:33.110126: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-04 02:20:33.135031: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-04 02:20:33.137262: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fbc68000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-04 02:20:33.137303: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-04 02:20:33.140860: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-04 02:20:33.359243: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x12afb6b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-04 02:20:33.359290: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-04 02:20:33.360650: 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 2025-02-04 02:20:33.361007: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-04 02:20:33.363680: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-04 02:20:33.366726: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-04 02:20:33.367202: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-04 02:20:33.370286: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-04 02:20:33.371916: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-04 02:20:33.375922: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-04 02:20:33.377383: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-04 02:20:33.377444: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-04 02:20:33.378239: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-04 02:20:33.378255: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-04 02:20:33.378264: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-04 02:20:33.379655: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 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. 2025-02-04 02:20:33.617551: 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 2025-02-04 02:20:33.617687: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-04 02:20:33.617715: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-04 02:20:33.617739: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-04 02:20:33.617763: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-04 02:20:33.617787: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-04 02:20:33.617809: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-04 02:20:33.617834: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-04 02:20:33.619967: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-04 02:20:33.621152: 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 2025-02-04 02:20:33.621179: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-04 02:20:33.621193: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-04 02:20:33.621205: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-04 02:20:33.621217: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-04 02:20:33.621229: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-04 02:20:33.621242: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-04 02:20:33.621254: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-04 02:20:33.622420: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-04 02:20:33.622444: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-04 02:20:33.622451: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-04 02:20:33.622458: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-04 02:20:33.623699: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 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 : [] 2025-02-04 02:20:39.794087: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-04 02:20:39.974651: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 4 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.49297 max: 149.43594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0008625984191894531 length of segment : 29 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 50 time to create 1 rle with old method : 0.00012969970703125 length of segment : 16 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 844 time to create 1 rle with old method : 0.008916616439819336 length of segment : 38 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 874 time to create 1 rle with old method : 0.0015759468078613281 length of segment : 35 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 857 time to create 1 rle with old method : 0.0015404224395751953 length of segment : 32 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.20781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 908 time to create 1 rle with old method : 0.0011086463928222656 length of segment : 41 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 2238 time to create 1 rle with old method : 0.0026416778564453125 length of segment : 41 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.00018358230590820312 length of segment : 33 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0004029273986816406 length of segment : 40 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.00030422210693359375 length of segment : 30 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 2507 time to create 1 rle with old method : 0.0030219554901123047 length of segment : 50 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.17266 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 : 0.0001354217529296875 nb_pixel_total : 6772 time to create 1 rle with old method : 0.00784611701965332 length of segment : 121 time for calcul the mask position with numpy : 0.00035452842712402344 nb_pixel_total : 24513 time to create 1 rle with old method : 0.02723073959350586 length of segment : 253 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.66875 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0005288124084472656 length of segment : 45 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1393 time to create 1 rle with old method : 0.001968860626220703 length of segment : 63 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1498 time to create 1 rle with old method : 0.0019211769104003906 length of segment : 84 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00023484230041503906 length of segment : 19 time for calcul the mask position with numpy : 0.00011277198791503906 nb_pixel_total : 2499 time to create 1 rle with old method : 0.003077983856201172 length of segment : 105 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002582073211669922 length of segment : 17 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1846 time to create 1 rle with old method : 0.002220630645751953 length of segment : 155 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00019359588623046875 length of segment : 14 time for calcul the mask position with numpy : 0.00015473365783691406 nb_pixel_total : 5736 time to create 1 rle with old method : 0.006825447082519531 length of segment : 121 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00018858909606933594 length of segment : 10 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.000316619873046875 length of segment : 19 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: 138.01250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 2193 time to create 1 rle with old method : 0.002611875534057617 length of segment : 150 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.0006716251373291016 length of segment : 18 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.0004761219024658203 length of segment : 21 time for calcul the mask position with numpy : 0.0007104873657226562 nb_pixel_total : 63332 time to create 1 rle with old method : 0.0690162181854248 length of segment : 308 Processing 1 images image shape: (400, 400, 3) min: 19.00000 max: 195.00000 molded_images shape: (1, 640, 640, 3) min: -87.84844 max: 69.31484 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: -116.38750 max: 149.95156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0005249977111816406 length of segment : 27 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005338191986083984 length of segment : 38 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.00036025047302246094 length of segment : 20 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0010962486267089844 length of segment : 34 time for calcul the mask position with numpy : 0.00022673606872558594 nb_pixel_total : 13587 time to create 1 rle with old method : 0.0149078369140625 length of segment : 245 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00036334991455078125 length of segment : 19 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005192756652832031 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.70781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00042724609375 length of segment : 18 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.00024318695068359375 length of segment : 16 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 3263 time to create 1 rle with old method : 0.0038154125213623047 length of segment : 72 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1380 time to create 1 rle with old method : 0.0015377998352050781 length of segment : 32 time for calcul the mask position with numpy : 0.00027680397033691406 nb_pixel_total : 17277 time to create 1 rle with old method : 0.018697261810302734 length of segment : 147 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0005843639373779297 length of segment : 41 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 718 time to create 1 rle with old method : 0.0009493827819824219 length of segment : 40 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 570 time to create 1 rle with old method : 0.0007817745208740234 length of segment : 35 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1684 time to create 1 rle with old method : 0.002051830291748047 length of segment : 34 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0005664825439453125 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: -116.74297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 850 time to create 1 rle with old method : 0.0010526180267333984 length of segment : 37 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.00029277801513671875 length of segment : 18 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1255 time to create 1 rle with old method : 0.0016701221466064453 length of segment : 46 time for calcul the mask position with numpy : 0.00019979476928710938 nb_pixel_total : 14534 time to create 1 rle with old method : 0.015684127807617188 length of segment : 158 time for calcul the mask position with numpy : 0.00010013580322265625 nb_pixel_total : 2477 time to create 1 rle with old method : 0.002933025360107422 length of segment : 151 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 4125 time to create 1 rle with old method : 0.004640102386474609 length of segment : 114 time for calcul the mask position with numpy : 0.00020313262939453125 nb_pixel_total : 7945 time to create 1 rle with old method : 0.008777856826782227 length of segment : 229 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1288 time to create 1 rle with old method : 0.0016503334045410156 length of segment : 66 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0005571842193603516 length of segment : 21 time for calcul the mask position with numpy : 0.00010514259338378906 nb_pixel_total : 4632 time to create 1 rle with old method : 0.005398750305175781 length of segment : 106 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: 137.36016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005035400390625 length of segment : 37 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 857 time to create 1 rle with old method : 0.0010864734649658203 length of segment : 35 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1811 time to create 1 rle with old method : 0.002199888229370117 length of segment : 87 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 1269 time to create 1 rle with old method : 0.0016760826110839844 length of segment : 113 time for calcul the mask position with numpy : 0.00020956993103027344 nb_pixel_total : 1920 time to create 1 rle with old method : 0.002526998519897461 length of segment : 62 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0004525184631347656 length of segment : 29 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006475448608398438 length of segment : 27 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004379749298095703 length of segment : 30 time for calcul the mask position with numpy : 0.00019598007202148438 nb_pixel_total : 4406 time to create 1 rle with old method : 0.005315303802490234 length of segment : 216 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.0013804435729980469 length of segment : 106 time for calcul the mask position with numpy : 0.0001857280731201172 nb_pixel_total : 3436 time to create 1 rle with old method : 0.0040285587310791016 length of segment : 173 Processing 1 images image shape: (280, 400, 3) min: 15.00000 max: 180.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 67.05703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.84609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 845 time to create 1 rle with old method : 0.001079559326171875 length of segment : 53 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007796287536621094 length of segment : 23 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0006036758422851562 length of segment : 43 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0006852149963378906 length of segment : 24 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0006537437438964844 length of segment : 26 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.000629425048828125 length of segment : 27 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00026726722717285156 length of segment : 16 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: 151.08828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 32 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00035262107849121094 length of segment : 15 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011396408081054688 length of segment : 11 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0003685951232910156 length of segment : 28 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00031566619873046875 length of segment : 21 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.0002810955047607422 length of segment : 15 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00018596649169921875 length of segment : 8 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0004987716674804688 length of segment : 29 time for calcul the mask position with numpy : 2.7418136596679688e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.00017189979553222656 length of segment : 9 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00035858154296875 length of segment : 16 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004584789276123047 length of segment : 31 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002028942108154297 length of segment : 20 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002918243408203125 length of segment : 18 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003256797790527344 length of segment : 20 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 58 time to create 1 rle with old method : 0.00012111663818359375 length of segment : 8 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.00033974647521972656 length of segment : 17 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0006690025329589844 length of segment : 25 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 32 time to create 1 rle with old method : 7.390975952148438e-05 length of segment : 7 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006513595581054688 length of segment : 41 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.00043463706970214844 length of segment : 25 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 19 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0006277561187744141 length of segment : 39 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003247261047363281 length of segment : 25 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.00043511390686035156 length of segment : 16 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001499652862548828 length of segment : 13 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.000431060791015625 length of segment : 14 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.00039196014404296875 length of segment : 17 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 1625 time to create 1 rle with old method : 0.0023679733276367188 length of segment : 142 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0005030632019042969 length of segment : 24 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.00023937225341796875 length of segment : 18 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.00036215782165527344 length of segment : 26 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005803108215332031 length of segment : 38 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00017452239990234375 length of segment : 14 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: 150.76797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 788 time to create 1 rle with old method : 0.0009846687316894531 length of segment : 42 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0005118846893310547 length of segment : 49 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.00031447410583496094 length of segment : 17 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 848 time to create 1 rle with old method : 0.0010449886322021484 length of segment : 49 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0009446144104003906 length of segment : 24 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002701282501220703 length of segment : 48 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004000663757324219 length of segment : 34 time for calcul the mask position with numpy : 2.6226043701171875e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.00010895729064941406 length of segment : 12 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002734661102294922 length of segment : 24 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 2323 time to create 1 rle with old method : 0.0027532577514648438 length of segment : 40 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.0002262592315673828 length of segment : 14 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0003674030303955078 length of segment : 16 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002980232238769531 length of segment : 21 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003516674041748047 length of segment : 16 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 654 time to create 1 rle with old method : 0.0008389949798583984 length of segment : 51 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0005843639373779297 length of segment : 24 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: 138.97500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 57 time to create 1 rle with old method : 0.00012683868408203125 length of segment : 26 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004010200500488281 length of segment : 18 time for calcul the mask position with numpy : 0.0004322528839111328 nb_pixel_total : 36832 time to create 1 rle with old method : 0.038985252380371094 length of segment : 232 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: -117.80547 max: 149.81875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0005955696105957031 length of segment : 28 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 810 time to create 1 rle with old method : 0.0010383129119873047 length of segment : 33 time for calcul the mask position with numpy : 0.0002994537353515625 nb_pixel_total : 18373 time to create 1 rle with old method : 0.020559310913085938 length of segment : 181 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 892 time to create 1 rle with old method : 0.001138448715209961 length of segment : 35 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 11 time to create 1 rle with old method : 8.153915405273438e-05 length of segment : 7 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 1134 time to create 1 rle with old method : 0.0013206005096435547 length of segment : 55 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 22 time to create 1 rle with old method : 5.793571472167969e-05 length of segment : 20 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003972053527832031 length of segment : 30 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1383 time to create 1 rle with old method : 0.001737833023071289 length of segment : 86 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.68047 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 : 4.482269287109375e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.0009748935699462891 length of segment : 37 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 2215 time to create 1 rle with old method : 0.0025186538696289062 length of segment : 44 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.12969 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 : 9.989738464355469e-05 nb_pixel_total : 5827 time to create 1 rle with old method : 0.0067365169525146484 length of segment : 136 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1491 time to create 1 rle with old method : 0.0019676685333251953 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: -118.85234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00012993812561035156 nb_pixel_total : 6754 time to create 1 rle with old method : 0.007931947708129883 length of segment : 114 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.00031566619873046875 length of segment : 21 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005116462707519531 length of segment : 78 time for calcul the mask position with numpy : 0.00014495849609375 nb_pixel_total : 7750 time to create 1 rle with old method : 0.008860111236572266 length of segment : 128 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: 135.55937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 852 time to create 1 rle with old method : 0.0010662078857421875 length of segment : 119 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004229545593261719 length of segment : 15 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0004029273986816406 length of segment : 22 time for calcul the mask position with numpy : 0.0007529258728027344 nb_pixel_total : 70785 time to create 1 rle with old method : 0.0831747055053711 length of segment : 278 Processing 1 images image shape: (400, 400, 3) min: 16.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -92.82109 max: 70.57656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.001298666000366211 nb_pixel_total : 152375 time to create 1 rle with new method : 0.001956462860107422 length of segment : 398 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.12188 max: 148.22891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004088878631591797 length of segment : 19 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0005443096160888672 length of segment : 36 time for calcul the mask position with numpy : 0.00028896331787109375 nb_pixel_total : 18772 time to create 1 rle with old method : 0.020655155181884766 length of segment : 235 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.00037384033203125 length of segment : 20 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002570152282714844 length of segment : 12 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.0002930164337158203 length of segment : 15 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.0002052783966064453 length of segment : 10 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0010373592376708984 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.11016 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.00024366378784179688 length of segment : 16 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.0002551078796386719 length of segment : 8 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0008337497711181641 length of segment : 28 time for calcul the mask position with numpy : 0.00023031234741210938 nb_pixel_total : 16056 time to create 1 rle with old method : 0.01791834831237793 length of segment : 164 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.00040841102600097656 length of segment : 17 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0009067058563232422 length of segment : 29 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.00045490264892578125 length of segment : 47 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006642341613769531 length of segment : 42 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004458427429199219 length of segment : 17 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005791187286376953 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.64141 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 842 time to create 1 rle with old method : 0.0010764598846435547 length of segment : 38 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.00030350685119628906 length of segment : 19 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 997 time to create 1 rle with old method : 0.0012264251708984375 length of segment : 59 time for calcul the mask position with numpy : 0.0001990795135498047 nb_pixel_total : 14571 time to create 1 rle with old method : 0.016113758087158203 length of segment : 147 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 2114 time to create 1 rle with old method : 0.0026111602783203125 length of segment : 148 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1220 time to create 1 rle with old method : 0.0016219615936279297 length of segment : 42 time for calcul the mask position with numpy : 0.0002238750457763672 nb_pixel_total : 14811 time to create 1 rle with old method : 0.016987085342407227 length of segment : 142 time for calcul the mask position with numpy : 0.0002796649932861328 nb_pixel_total : 11001 time to create 1 rle with old method : 0.012162208557128906 length of segment : 333 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 2078 time to create 1 rle with old method : 0.0025506019592285156 length of segment : 59 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 2293 time to create 1 rle with old method : 0.002918720245361328 length of segment : 62 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: 135.63750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1708 time to create 1 rle with old method : 0.0019817352294921875 length of segment : 82 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0004754066467285156 length of segment : 32 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1455 time to create 1 rle with old method : 0.0017337799072265625 length of segment : 55 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 1436 time to create 1 rle with old method : 0.0016858577728271484 length of segment : 128 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0005662441253662109 length of segment : 38 time for calcul the mask position with numpy : 0.0001475811004638672 nb_pixel_total : 3755 time to create 1 rle with old method : 0.0042035579681396484 length of segment : 181 time for calcul the mask position with numpy : 0.0002200603485107422 nb_pixel_total : 2643 time to create 1 rle with old method : 0.0032944679260253906 length of segment : 63 time for calcul the mask position with numpy : 0.00019049644470214844 nb_pixel_total : 4904 time to create 1 rle with old method : 0.005467891693115234 length of segment : 221 time for calcul the mask position with numpy : 0.00017023086547851562 nb_pixel_total : 4858 time to create 1 rle with old method : 0.005750417709350586 length of segment : 220 Processing 1 images image shape: (280, 400, 3) min: 16.00000 max: 178.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 56.91641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0010600090026855469 nb_pixel_total : 106449 time to create 1 rle with old method : 0.11241006851196289 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.37344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1037 time to create 1 rle with old method : 0.0013651847839355469 length of segment : 54 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 40 time to create 1 rle with old method : 0.00011134147644042969 length of segment : 17 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.00033926963806152344 length of segment : 23 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.0007250308990478516 length of segment : 23 time for calcul the mask position with numpy : 0.0003325939178466797 nb_pixel_total : 25297 time to create 1 rle with old method : 0.027308940887451172 length of segment : 255 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003628730773925781 length of segment : 21 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 49 time to create 1 rle with old method : 9.799003601074219e-05 length of segment : 9 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006368160247802734 length of segment : 22 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 56 time to create 1 rle with old method : 0.00010418891906738281 length of segment : 10 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0007026195526123047 length of segment : 41 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: 151.08828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 34 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.00032806396484375 length of segment : 14 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00014638900756835938 length of segment : 11 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.0002930164337158203 length of segment : 23 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0004150867462158203 length of segment : 31 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003342628479003906 length of segment : 21 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.00024271011352539062 length of segment : 19 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.00034737586975097656 length of segment : 18 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003476142883300781 length of segment : 21 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002758502960205078 length of segment : 21 time for calcul the mask position with numpy : 2.6941299438476562e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.000125885009765625 length of segment : 9 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1201 time to create 1 rle with old method : 0.0014357566833496094 length of segment : 41 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0004208087921142578 length of segment : 14 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004248619079589844 length of segment : 31 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0006070137023925781 length of segment : 22 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00024437904357910156 length of segment : 13 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 868 time to create 1 rle with old method : 0.0010614395141601562 length of segment : 47 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0004246234893798828 length of segment : 27 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0001957416534423828 length of segment : 10 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 65 time to create 1 rle with old method : 0.00012111663818359375 length of segment : 9 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00028228759765625 length of segment : 15 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003657341003417969 length of segment : 16 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 70 time to create 1 rle with old method : 0.00010514259338378906 length of segment : 16 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 911 time to create 1 rle with old method : 0.0011820793151855469 length of segment : 79 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003612041473388672 length of segment : 24 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 413 time to create 1 rle with old method : 0.0005748271942138672 length of segment : 23 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.0003581047058105469 length of segment : 19 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 779 time to create 1 rle with old method : 0.0010209083557128906 length of segment : 74 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004875659942626953 length of segment : 25 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.0002498626708984375 length of segment : 24 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 925 time to create 1 rle with old method : 0.0011255741119384766 length of segment : 41 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004451274871826172 length of segment : 25 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 739 time to create 1 rle with old method : 0.0009450912475585938 length of segment : 34 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0002911090850830078 length of segment : 17 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0002856254577636719 length of segment : 17 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: 150.60391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 819 time to create 1 rle with old method : 0.001028299331665039 length of segment : 43 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004076957702636719 length of segment : 57 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004162788391113281 length of segment : 25 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 2261 time to create 1 rle with old method : 0.0025856494903564453 length of segment : 43 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00037288665771484375 length of segment : 49 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003662109375 length of segment : 15 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0013616085052490234 length of segment : 76 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.00042891502380371094 length of segment : 33 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00022101402282714844 length of segment : 17 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.0002410411834716797 length of segment : 23 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003552436828613281 length of segment : 21 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 1125 time to create 1 rle with old method : 0.0012955665588378906 length of segment : 67 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 16 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 51 time to create 1 rle with old method : 0.00010156631469726562 length of segment : 10 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 1318 time to create 1 rle with old method : 0.001535654067993164 length of segment : 50 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0003635883331298828 length of segment : 22 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.00040531158447265625 length of segment : 23 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: 140.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.00046324729919433594 length of segment : 20 time for calcul the mask position with numpy : 0.0003986358642578125 nb_pixel_total : 29362 time to create 1 rle with old method : 0.03159451484680176 length of segment : 247 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: -117.31328 max: 148.18203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0006661415100097656 length of segment : 31 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 859 time to create 1 rle with old method : 0.0015475749969482422 length of segment : 32 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 29 time to create 1 rle with old method : 6.890296936035156e-05 length of segment : 12 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 742 time to create 1 rle with old method : 0.0009577274322509766 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.79766 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 21 time to create 1 rle with old method : 6.914138793945312e-05 length of segment : 4 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 811 time to create 1 rle with old method : 0.0009224414825439453 length of segment : 36 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 54 time to create 1 rle with old method : 9.298324584960938e-05 length of segment : 11 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 2708 time to create 1 rle with old method : 0.0031425952911376953 length of segment : 56 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 3450 time to create 1 rle with old method : 0.004026651382446289 length of segment : 64 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 2546 time to create 1 rle with old method : 0.0031838417053222656 length of segment : 57 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.07891 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 5049 time to create 1 rle with old method : 0.005736112594604492 length of segment : 141 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 3063 time to create 1 rle with old method : 0.003510713577270508 length of segment : 107 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 1126 time to create 1 rle with old method : 0.001499176025390625 length of segment : 34 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 972 time to create 1 rle with old method : 0.0013172626495361328 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.59453 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00013971328735351562 nb_pixel_total : 7853 time to create 1 rle with old method : 0.008886575698852539 length of segment : 107 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003020763397216797 length of segment : 22 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 934 2025-02-04 02:20:49.804848: E tensorflow/stream_executor/cuda/cuda_driver.cc:939] could not synchronize on CUDA context: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered :: *** Begin stack trace *** tensorflow::CurrentStackTrace() stream_executor::gpu::GpuDriver::SynchronizeContext(stream_executor::gpu::GpuContext*) stream_executor::StreamExecutor::SynchronizeAllActivity() tensorflow::GPUUtil::SyncAll(tensorflow::Device*) tensorflow::BaseGPUDevice::Sync() tensorflow::TensorHandle::CopyToDevice(tensorflow::EagerContext const&, tensorflow::Device*, tensorflow::Tensor*) tensorflow::TensorHandleInterface::Resolve(tensorflow::Status*) TFE_TensorHandleResolve _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall PyObject_Call _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName PyEval_EvalCode PyRun_SimpleFileExFlags Py_RunMain Py_BytesMain __libc_start_main _start *** End stack trace *** 2025-02-04 02:20:49.853389: E tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:725] failed to record completion event; therefore, failed to create inter-stream dependency 2025-02-04 02:20:49.853445: I tensorflow/stream_executor/stream.cc:4938] [stream=0x1402b6a0,impl=0x1402a330] did not memcpy host-to-device; source: 0x3e845740 2025-02-04 02:20:49.853458: E tensorflow/stream_executor/stream.cc:334] Error recording event in stream: Error recording CUDA event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered; not marking stream as bad, as the Event object may be at fault. Monitor for further errors. 2025-02-04 02:20:49.853475: 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 2025-02-04 02:20:49.853486: 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 ! 18.22user 15.12system 1:00:08elapsed 0%CPU (0avgtext+0avgdata 2550900maxresident)k 119336inputs+2272outputs (7544major+675758minor)pagefaults 0swaps