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 : 2277874 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 : ['2605796'] with mtr_portfolio_ids : ['20733639'] and first list_photo_ids : [] new path : /proc/2277874/ 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 , BFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 3 ; length of list_pids : 3 ; length of list_args : 3 time to download the photos : 0.6045064926147461 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Sat Feb 22 05:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10814 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-22 05:20:31.622011: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-22 05:20:31.647129: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-22 05:20:31.649148: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f49d0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-22 05:20:31.649192: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-22 05:20:31.652927: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-22 05:20:31.879901: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xcc10450 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-22 05:20:31.879948: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-22 05:20:31.881207: 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 2025-02-22 05:20:31.881589: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-22 05:20:31.913827: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-22 05:20:31.916564: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-22 05:20:31.917070: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-22 05:20:31.920751: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-22 05:20:31.922328: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-22 05:20:31.928411: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-22 05:20:31.930579: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-22 05:20:31.930675: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-22 05:20:31.931869: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-22 05:20:31.931892: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-22 05:20:31.931905: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-22 05:20:31.934290: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10023 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. 2025-02-22 05:20:32.354550: 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 2025-02-22 05:20:32.354642: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-22 05:20:32.354660: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-22 05:20:32.354675: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-22 05:20:32.354690: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-22 05:20:32.354705: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-22 05:20:32.354719: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-22 05:20:32.354734: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-22 05:20:32.356066: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-22 05:20:32.357306: 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 2025-02-22 05:20:32.357367: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-22 05:20:32.357384: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-22 05:20:32.357399: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-22 05:20:32.357413: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-22 05:20:32.357428: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-22 05:20:32.357442: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-22 05:20:32.357456: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-22 05:20:32.358745: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-22 05:20:32.358773: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-22 05:20:32.358782: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-22 05:20:32.358790: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-22 05:20:32.360147: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10023 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 : [] 2025-02-22 05:20:41.708483: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-22 05:20:42.096930: 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 : 3 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: -123.14141 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 : 0.00037097930908203125 nb_pixel_total : 1709 time to create 1 rle with old method : 0.007312774658203125 length of segment : 89 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 2105 time to create 1 rle with old method : 0.0028896331787109375 length of segment : 60 time for calcul the mask position with numpy : 0.0001423358917236328 nb_pixel_total : 3198 time to create 1 rle with old method : 0.007967948913574219 length of segment : 46 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 883 time to create 1 rle with old method : 0.0011954307556152344 length of segment : 41 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002315044403076172 length of segment : 16 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.000553131103515625 length of segment : 73 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 2653 time to create 1 rle with old method : 0.0033926963806152344 length of segment : 46 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2648 time to create 1 rle with old method : 0.0035011768341064453 length of segment : 44 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0010623931884765625 length of segment : 44 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.0004458427429199219 length of segment : 29 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002579689025878906 length of segment : 15 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1033 time to create 1 rle with old method : 0.0013980865478515625 length of segment : 48 time for calcul the mask position with numpy : 0.00012063980102539062 nb_pixel_total : 2751 time to create 1 rle with old method : 0.003478527069091797 length of segment : 89 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.00041031837463378906 length of segment : 21 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 1583 time to create 1 rle with old method : 0.0021164417266845703 length of segment : 84 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1149 time to create 1 rle with old method : 0.0016026496887207031 length of segment : 32 time for calcul the mask position with numpy : 0.0001327991485595703 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003445148468017578 length of segment : 30 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003733634948730469 length of segment : 26 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1367 time to create 1 rle with old method : 0.0019958019256591797 length of segment : 46 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1355 time to create 1 rle with old method : 0.001967191696166992 length of segment : 37 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 1290 time to create 1 rle with old method : 0.0019559860229492188 length of segment : 58 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 992 time to create 1 rle with old method : 0.0013546943664550781 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: -123.24297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 37 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0009055137634277344 length of segment : 29 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1061 time to create 1 rle with old method : 0.002081155776977539 length of segment : 40 time for calcul the mask position with numpy : 0.00012946128845214844 nb_pixel_total : 2121 time to create 1 rle with old method : 0.003968715667724609 length of segment : 66 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0006964206695556641 length of segment : 21 time for calcul the mask position with numpy : 0.0002052783966064453 nb_pixel_total : 4297 time to create 1 rle with old method : 0.006671428680419922 length of segment : 100 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004763603210449219 length of segment : 23 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1646 time to create 1 rle with old method : 0.002080202102661133 length of segment : 47 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.000576019287109375 length of segment : 30 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1164 time to create 1 rle with old method : 0.0015239715576171875 length of segment : 80 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 2400 time to create 1 rle with old method : 0.0030660629272460938 length of segment : 78 time for calcul the mask position with numpy : 0.00012922286987304688 nb_pixel_total : 2476 time to create 1 rle with old method : 0.003041982650756836 length of segment : 81 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1625 time to create 1 rle with old method : 0.0019927024841308594 length of segment : 56 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1089 time to create 1 rle with old method : 0.0014941692352294922 length of segment : 46 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2680 time to create 1 rle with old method : 0.0034973621368408203 length of segment : 58 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.000152587890625 length of segment : 11 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0005609989166259766 length of segment : 23 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0006036758422851562 length of segment : 25 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 876 time to create 1 rle with old method : 0.0011982917785644531 length of segment : 47 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1166 time to create 1 rle with old method : 0.0015726089477539062 length of segment : 37 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 1647 time to create 1 rle with old method : 0.0025713443756103516 length of segment : 71 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 252 time to create 1 rle with old method : 0.0003819465637207031 length of segment : 15 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0009109973907470703 length of segment : 70 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1320 time to create 1 rle with old method : 0.002202749252319336 length of segment : 47 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 1848 time to create 1 rle with old method : 0.0025026798248291016 length of segment : 126 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1854 time to create 1 rle with old method : 0.0022499561309814453 length of segment : 61 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 2233 time to create 1 rle with old method : 0.002895355224609375 length of segment : 97 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 761 time to create 1 rle with old method : 0.0009908676147460938 length of segment : 33 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 3624 time to create 1 rle with old method : 0.00455021858215332 length of segment : 132 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 2007 time to create 1 rle with old method : 0.002553224563598633 length of segment : 53 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 29 time to create 1 rle with old method : 6.67572021484375e-05 length of segment : 8 time for calcul the mask position with numpy : 0.00019216537475585938 nb_pixel_total : 3456 time to create 1 rle with old method : 0.004369497299194336 length of segment : 88 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 1947 time to create 1 rle with old method : 0.0025894641876220703 length of segment : 78 time for calcul the mask position with numpy : 0.0001423358917236328 nb_pixel_total : 3247 time to create 1 rle with old method : 0.003951072692871094 length of segment : 62 time for calcul the mask position with numpy : 0.000179290771484375 nb_pixel_total : 5831 time to create 1 rle with old method : 0.006985664367675781 length of segment : 108 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0003466606140136719 length of segment : 24 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 1475 time to create 1 rle with old method : 0.0018854141235351562 length of segment : 65 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.0010409355163574219 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.19219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 46 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 1026 time to create 1 rle with old method : 0.0014696121215820312 length of segment : 50 time for calcul the mask position with numpy : 0.00021529197692871094 nb_pixel_total : 5704 time to create 1 rle with old method : 0.010443925857543945 length of segment : 76 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 499 time to create 1 rle with old method : 0.0006570816040039062 length of segment : 43 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0007092952728271484 length of segment : 22 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0006549358367919922 length of segment : 19 time for calcul the mask position with numpy : 9.846687316894531e-05 nb_pixel_total : 2198 time to create 1 rle with old method : 0.002844095230102539 length of segment : 64 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 2855 time to create 1 rle with old method : 0.003640890121459961 length of segment : 119 time for calcul the mask position with numpy : 0.0001773834228515625 nb_pixel_total : 5156 time to create 1 rle with old method : 0.008095026016235352 length of segment : 66 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.0002982616424560547 length of segment : 19 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0004363059997558594 length of segment : 17 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0009682178497314453 length of segment : 30 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0007615089416503906 length of segment : 41 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1636 time to create 1 rle with old method : 0.00316619873046875 length of segment : 68 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.00043392181396484375 length of segment : 31 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 1667 time to create 1 rle with old method : 0.002402782440185547 length of segment : 78 time for calcul the mask position with numpy : 0.00011014938354492188 nb_pixel_total : 2665 time to create 1 rle with old method : 0.0037131309509277344 length of segment : 54 time for calcul the mask position with numpy : 0.00022530555725097656 nb_pixel_total : 5381 time to create 1 rle with old method : 0.008298873901367188 length of segment : 87 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.00042510032653808594 length of segment : 27 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0009434223175048828 length of segment : 30 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1648 time to create 1 rle with old method : 0.0024263858795166016 length of segment : 45 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 1682 time to create 1 rle with old method : 0.002225637435913086 length of segment : 87 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.0003719329833984375 length of segment : 9 time for calcul the mask position with numpy : 0.00012874603271484375 nb_pixel_total : 3493 time to create 1 rle with old method : 0.004499673843383789 length of segment : 104 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 2094 time to create 1 rle with old method : 0.003221750259399414 length of segment : 55 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0005338191986083984 length of segment : 41 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.00041794776916503906 length of segment : 19 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 699 time to create 1 rle with old method : 0.0011260509490966797 length of segment : 46 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00023627281188964844 length of segment : 14 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 788 time to create 1 rle with old method : 0.0011076927185058594 length of segment : 34 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 743 time to create 1 rle with old method : 0.0009906291961669922 length of segment : 36 time for calcul the mask position with numpy : 0.00012493133544921875 nb_pixel_total : 5105 time to create 1 rle with old method : 0.006081819534301758 length of segment : 76 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0003597736358642578 length of segment : 26 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 2659 time to create 1 rle with old method : 0.003715038299560547 length of segment : 54 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0009737014770507812 length of segment : 47 time for calcul the mask position with numpy : 0.0003116130828857422 nb_pixel_total : 10596 time to create 1 rle with old method : 0.013474702835083008 length of segment : 177 time for calcul the mask position with numpy : 0.00033664703369140625 nb_pixel_total : 18901 time to create 1 rle with old method : 0.022283077239990234 length of segment : 183 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.00035691261291503906 length of segment : 19 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 2051 time to create 1 rle with old method : 0.00251007080078125 length of segment : 83 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0010688304901123047 length of segment : 35 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1083 time to create 1 rle with old method : 0.0014674663543701172 length of segment : 37 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0011434555053710938 length of segment : 41 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 655 time to create 1 rle with old method : 0.0009477138519287109 length of segment : 27 time for calcul the mask position with numpy : 0.00014448165893554688 nb_pixel_total : 5112 time to create 1 rle with old method : 0.006372213363647461 length of segment : 75 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 1917 time to create 1 rle with old method : 0.003192424774169922 length of segment : 79 time for calcul the mask position with numpy : 0.0005269050598144531 nb_pixel_total : 26836 time to create 1 rle with old method : 0.03417611122131348 length of segment : 212 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1963 time to create 1 rle with old method : 0.002562284469604492 length of segment : 75 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.23906 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 30 time for calcul the mask position with numpy : 0.0002586841583251953 nb_pixel_total : 12685 time to create 1 rle with old method : 0.014810800552368164 length of segment : 224 time for calcul the mask position with numpy : 0.00012683868408203125 nb_pixel_total : 3760 time to create 1 rle with old method : 0.0046749114990234375 length of segment : 66 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 2711 time to create 1 rle with old method : 0.0035851001739501953 length of segment : 45 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003457069396972656 length of segment : 21 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 971 time to create 1 rle with old method : 0.0013260841369628906 length of segment : 29 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 735 time to create 1 rle with old method : 0.0011203289031982422 length of segment : 19 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 4287 time to create 1 rle with old method : 0.005233049392700195 length of segment : 93 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 693 time to create 1 rle with old method : 0.0010218620300292969 length of segment : 36 time for calcul the mask position with numpy : 0.0002644062042236328 nb_pixel_total : 7847 time to create 1 rle with old method : 0.00954294204711914 length of segment : 92 time for calcul the mask position with numpy : 0.00011944770812988281 nb_pixel_total : 4011 time to create 1 rle with old method : 0.004927396774291992 length of segment : 62 time for calcul the mask position with numpy : 0.00013494491577148438 nb_pixel_total : 4198 time to create 1 rle with old method : 0.005202770233154297 length of segment : 106 time for calcul the mask position with numpy : 0.00013756752014160156 nb_pixel_total : 3068 time to create 1 rle with old method : 0.003795146942138672 length of segment : 105 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0008518695831298828 length of segment : 55 time for calcul the mask position with numpy : 0.00012993812561035156 nb_pixel_total : 3138 time to create 1 rle with old method : 0.003942966461181641 length of segment : 88 time for calcul the mask position with numpy : 0.00013971328735351562 nb_pixel_total : 2446 time to create 1 rle with old method : 0.0030226707458496094 length of segment : 105 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004990100860595703 length of segment : 18 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 896 time to create 1 rle with old method : 0.0012478828430175781 length of segment : 34 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0007839202880859375 length of segment : 46 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 920 time to create 1 rle with old method : 0.001222848892211914 length of segment : 45 time for calcul the mask position with numpy : 0.00011467933654785156 nb_pixel_total : 5199 time to create 1 rle with old method : 0.006048679351806641 length of segment : 69 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1045 time to create 1 rle with old method : 0.001352071762084961 length of segment : 46 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0004038810729980469 length of segment : 20 time for calcul the mask position with numpy : 2.8133392333984375e-05 nb_pixel_total : 133 time to create 1 rle with old method : 0.00019979476928710938 length of segment : 15 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1580 time to create 1 rle with old method : 0.0019283294677734375 length of segment : 52 time for calcul the mask position with numpy : 0.00010180473327636719 nb_pixel_total : 4053 time to create 1 rle with old method : 0.004971027374267578 length of segment : 63 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0004055500030517578 length of segment : 16 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 4039 time to create 1 rle with old method : 0.005005598068237305 length of segment : 94 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 2649 time to create 1 rle with old method : 0.0034198760986328125 length of segment : 45 time for calcul the mask position with numpy : 0.00015306472778320312 nb_pixel_total : 4464 time to create 1 rle with old method : 0.0055735111236572266 length of segment : 94 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0003757476806640625 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.76641 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 : 0.00010633468627929688 nb_pixel_total : 628 time to create 1 rle with old method : 0.0008852481842041016 length of segment : 22 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005571842193603516 length of segment : 40 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0006127357482910156 length of segment : 22 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 2489 time to create 1 rle with old method : 0.003156423568725586 length of segment : 73 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1021 time to create 1 rle with old method : 0.0012853145599365234 length of segment : 61 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 822 time to create 1 rle with old method : 0.0010399818420410156 length of segment : 45 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1468 time to create 1 rle with old method : 0.0019257068634033203 length of segment : 45 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005509853363037109 length of segment : 21 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0008001327514648438 length of segment : 29 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 2500 time to create 1 rle with old method : 0.003222942352294922 length of segment : 74 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00021076202392578125 length of segment : 19 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1140 time to create 1 rle with old method : 0.0015294551849365234 length of segment : 41 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 839 time to create 1 rle with old method : 0.0010836124420166016 length of segment : 68 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.00069427490234375 length of segment : 20 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0006580352783203125 length of segment : 17 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1177 time to create 1 rle with old method : 0.0015475749969482422 length of segment : 41 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1200 time to create 1 rle with old method : 0.0017199516296386719 length of segment : 37 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 619 time to create 1 rle with old method : 0.000934600830078125 length of segment : 39 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 1214 time to create 1 rle with old method : 0.0014584064483642578 length of segment : 63 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.07109 max: 148.31094 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 0.0001494884490966797 nb_pixel_total : 512 time to create 1 rle with old method : 0.0010380744934082031 length of segment : 33 time for calcul the mask position with numpy : 0.00017786026000976562 nb_pixel_total : 263 time to create 1 rle with old method : 0.0006530284881591797 length of segment : 22 time for calcul the mask position with numpy : 0.00011396408081054688 nb_pixel_total : 584 time to create 1 rle with old method : 0.001222848892211914 length of segment : 27 time for calcul the mask position with numpy : 0.00031948089599609375 nb_pixel_total : 201 time to create 1 rle with old method : 0.0005640983581542969 length of segment : 25 time for calcul the mask position with numpy : 0.00015735626220703125 nb_pixel_total : 1289 time to create 1 rle with old method : 0.0024514198303222656 length of segment : 53 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 1185 time to create 1 rle with old method : 0.0023822784423828125 length of segment : 47 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0008122920989990234 length of segment : 30 time for calcul the mask position with numpy : 0.0002543926239013672 nb_pixel_total : 7862 time to create 1 rle with old method : 0.013399124145507812 length of segment : 124 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0007817745208740234 length of segment : 40 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.0002505779266357422 length of segment : 11 time for calcul the mask position with numpy : 0.00020575523376464844 nb_pixel_total : 915 time to create 1 rle with old method : 0.0014171600341796875 length of segment : 67 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.0002143383026123047 length of segment : 19 time for calcul the mask position with numpy : 0.0002124309539794922 nb_pixel_total : 2510 time to create 1 rle with old method : 0.0035049915313720703 length of segment : 106 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 737 time to create 1 rle with old method : 0.0016009807586669922 length of segment : 55 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 228.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 113.18203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.00045418739318847656 length of segment : 19 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1409 time to create 1 rle with old method : 0.0018105506896972656 length of segment : 47 time for calcul the mask position with numpy : 0.00030612945556640625 nb_pixel_total : 11973 time to create 1 rle with old method : 0.015956401824951172 length of segment : 257 time for calcul the mask position with numpy : 0.00011444091796875 nb_pixel_total : 603 time to create 1 rle with old method : 0.0012388229370117188 length of segment : 54 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 70 time to create 1 rle with old method : 0.00012803077697753906 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.02813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0006825923919677734 length of segment : 40 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0007643699645996094 length of segment : 18 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 4042 time to create 1 rle with old method : 0.005269527435302734 length of segment : 76 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 3273 time to create 1 rle with old method : 0.0043065547943115234 length of segment : 112 time for calcul the mask position with numpy : 0.0005362033843994141 nb_pixel_total : 31264 time to create 1 rle with old method : 0.0364680290222168 length of segment : 320 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0003159046173095703 length of segment : 48 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 2164 time to create 1 rle with old method : 0.0030791759490966797 length of segment : 103 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 841 time to create 1 rle with old method : 0.0012331008911132812 length of segment : 44 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 1416 time to create 1 rle with old method : 0.0018558502197265625 length of segment : 32 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0010995864868164062 length of segment : 61 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 2115 time to create 1 rle with old method : 0.0034368038177490234 length of segment : 55 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0009157657623291016 length of segment : 25 time for calcul the mask position with numpy : 0.0002009868621826172 nb_pixel_total : 2060 time to create 1 rle with old method : 0.004194736480712891 length of segment : 146 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0007796287536621094 length of segment : 24 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0006117820739746094 length of segment : 31 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 2376 time to create 1 rle with old method : 0.004710197448730469 length of segment : 48 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0005986690521240234 length of segment : 31 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 2055 time to create 1 rle with old method : 0.0037398338317871094 length of segment : 55 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0009031295776367188 length of segment : 25 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1848 time to create 1 rle with old method : 0.0037994384765625 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.05547 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 36 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0006444454193115234 length of segment : 19 time for calcul the mask position with numpy : 0.0002856254577636719 nb_pixel_total : 14317 time to create 1 rle with old method : 0.01772904396057129 length of segment : 156 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00039458274841308594 length of segment : 17 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.0009210109710693359 length of segment : 40 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1427 time to create 1 rle with old method : 0.0017731189727783203 length of segment : 59 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 2562 time to create 1 rle with old method : 0.00313568115234375 length of segment : 70 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.00083160400390625 length of segment : 39 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.000469207763671875 length of segment : 10 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006427764892578125 length of segment : 36 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 836 time to create 1 rle with old method : 0.0011456012725830078 length of segment : 25 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.000553131103515625 length of segment : 34 time for calcul the mask position with numpy : 0.00028967857360839844 nb_pixel_total : 11975 time to create 1 rle with old method : 0.01691722869873047 length of segment : 137 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 644 time to create 1 rle with old method : 0.0008678436279296875 length of segment : 29 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003845691680908203 length of segment : 21 time for calcul the mask position with numpy : 0.00010013580322265625 nb_pixel_total : 2282 time to create 1 rle with old method : 0.003255605697631836 length of segment : 52 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 549 time to create 1 rle with old method : 0.0007617473602294922 length of segment : 35 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 960 time to create 1 rle with old method : 0.0013797283172607422 length of segment : 39 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 852 time to create 1 rle with old method : 0.0013687610626220703 length of segment : 47 time for calcul the mask position with numpy : 0.00020647048950195312 nb_pixel_total : 4705 time to create 1 rle with old method : 0.008537769317626953 length of segment : 87 time for calcul the mask position with numpy : 0.00013685226440429688 nb_pixel_total : 2699 time to create 1 rle with old method : 0.003587961196899414 length of segment : 74 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 741 time to create 1 rle with old method : 0.001085519790649414 length of segment : 38 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 736 time to create 1 rle with old method : 0.0010027885437011719 length of segment : 78 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004913806915283203 length of segment : 33 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002338886260986328 length of segment : 12 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 873 time to create 1 rle with old method : 0.001241445541381836 length of segment : 24 time for calcul the mask position with numpy : 0.00016641616821289062 nb_pixel_total : 4679 time to create 1 rle with old method : 0.00589442253112793 length of segment : 90 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 912 time to create 1 rle with old method : 0.001184701919555664 length of segment : 89 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 1543 time to create 1 rle with old method : 0.0020470619201660156 length of segment : 72 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004317760467529297 length of segment : 27 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.00031638145446777344 length of segment : 12 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1138 time to create 1 rle with old method : 0.0015053749084472656 length of segment : 44 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 887 time to create 1 rle with old method : 0.0011458396911621094 length of segment : 53 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0003674030303955078 length of segment : 24 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.00029158592224121094 length of segment : 25 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 943 time to create 1 rle with old method : 0.0013370513916015625 length of segment : 26 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 864 time to create 1 rle with old method : 0.0012466907501220703 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.16094 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 : 9.202957153320312e-05 nb_pixel_total : 1333 time to create 1 rle with old method : 0.0017080307006835938 length of segment : 71 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 599 time to create 1 rle with old method : 0.0007872581481933594 length of segment : 39 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 875 time to create 1 rle with old method : 0.001192331314086914 length of segment : 23 time for calcul the mask position with numpy : 0.00014543533325195312 nb_pixel_total : 5088 time to create 1 rle with old method : 0.006299018859863281 length of segment : 84 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1375 time to create 1 rle with old method : 0.0018832683563232422 length of segment : 35 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0015835762023925781 length of segment : 74 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1786 time to create 1 rle with old method : 0.002380847930908203 length of segment : 34 time for calcul the mask position with numpy : 0.00036597251892089844 nb_pixel_total : 19873 time to create 1 rle with old method : 0.0242617130279541 length of segment : 168 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002772808074951172 length of segment : 16 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005173683166503906 length of segment : 33 time for calcul the mask position with numpy : 0.0005862712860107422 nb_pixel_total : 29783 time to create 1 rle with old method : 0.035292625427246094 length of segment : 266 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002894401550292969 length of segment : 24 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.00025653839111328125 length of segment : 26 time for calcul the mask position with numpy : 0.00010371208190917969 nb_pixel_total : 4794 time to create 1 rle with old method : 0.006524324417114258 length of segment : 93 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0007574558258056641 length of segment : 28 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005474090576171875 length of segment : 19 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1676 time to create 1 rle with old method : 0.002111196517944336 length of segment : 59 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 1484 time to create 1 rle with old method : 0.0019805431365966797 length of segment : 67 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.12969 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 35 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 924 time to create 1 rle with old method : 0.001245737075805664 length of segment : 34 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1995 time to create 1 rle with old method : 0.0024907588958740234 length of segment : 39 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005090236663818359 length of segment : 42 time for calcul the mask position with numpy : 0.00014209747314453125 nb_pixel_total : 5409 time to create 1 rle with old method : 0.00705409049987793 length of segment : 77 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 570 time to create 1 rle with old method : 0.0008161067962646484 length of segment : 50 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.0003185272216796875 length of segment : 14 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 877 time to create 1 rle with old method : 0.0012350082397460938 length of segment : 32 time for calcul the mask position with numpy : 0.00025534629821777344 nb_pixel_total : 9228 time to create 1 rle with old method : 0.011223077774047852 length of segment : 118 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002760887145996094 length of segment : 39 time for calcul the mask position with numpy : 0.00023627281188964844 nb_pixel_total : 4638 time to create 1 rle with old method : 0.0073354244232177734 length of segment : 83 time for calcul the mask position with numpy : 0.00015401840209960938 nb_pixel_total : 4566 time to create 1 rle with old method : 0.005663871765136719 length of segment : 100 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0004119873046875 length of segment : 33 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1749 time to create 1 rle with old method : 0.0021331310272216797 length of segment : 66 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0006444454193115234 length of segment : 21 time for calcul the mask position with numpy : 0.00017023086547851562 nb_pixel_total : 6016 time to create 1 rle with old method : 0.007162570953369141 length of segment : 202 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.0003027915954589844 length of segment : 14 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0009298324584960938 length of segment : 28 time for calcul the mask position with numpy : 0.0001220703125 nb_pixel_total : 1581 time to create 1 rle with old method : 0.002015352249145508 length of segment : 66 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0011074542999267578 length of segment : 49 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0007977485656738281 length of segment : 20 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 429 time to create 1 rle with old method : 0.0006659030914306641 length of segment : 19 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005705356597900391 length of segment : 24 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 844 time to create 1 rle with old method : 0.00115203857421875 length of segment : 33 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1597 time to create 1 rle with old method : 0.0021848678588867188 length of segment : 45 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1517 time to create 1 rle with old method : 0.0019421577453613281 length of segment : 61 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1432 time to create 1 rle with old method : 0.0018529891967773438 length of segment : 48 time for calcul the mask position with numpy : 0.00016617774963378906 nb_pixel_total : 5838 time to create 1 rle with old method : 0.007356405258178711 length of segment : 111 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0005011558532714844 length of segment : 19 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1138 time to create 1 rle with old method : 0.0014257431030273438 length of segment : 47 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006566047668457031 length of segment : 28 time for calcul the mask position with numpy : 0.00014781951904296875 nb_pixel_total : 5490 time to create 1 rle with old method : 0.006796360015869141 length of segment : 76 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.0002002716064453125 length of segment : 34 time for calcul the mask position with numpy : 0.00015354156494140625 nb_pixel_total : 3567 time to create 1 rle with old method : 0.004491567611694336 length of segment : 146 time for calcul the mask position with numpy : 0.00018715858459472656 nb_pixel_total : 1748 time to create 1 rle with old method : 0.0023565292358398438 length of segment : 122 time for calcul the mask position with numpy : 0.0001380443572998047 nb_pixel_total : 1584 time to create 1 rle with old method : 0.0021066665649414062 length of segment : 72 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.07891 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0005145072937011719 length of segment : 27 time for calcul the mask position with numpy : 0.00010561943054199219 nb_pixel_total : 680 time to create 1 rle with old method : 0.0011417865753173828 length of segment : 47 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0007684230804443359 length of segment : 19 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.0011396408081054688 length of segment : 43 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 803 time to create 1 rle with old method : 0.0015490055084228516 length of segment : 67 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0005552768707275391 length of segment : 16 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1983 time to create 1 rle with old method : 0.0023949146270751953 length of segment : 98 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 2795 time to create 1 rle with old method : 0.0036742687225341797 length of segment : 56 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 593 time to create 1 rle with old method : 0.0008642673492431641 length of segment : 29 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0006756782531738281 length of segment : 31 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 926 time to create 1 rle with old method : 0.0012645721435546875 length of segment : 36 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 18 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1311 time to create 1 rle with old method : 0.0017867088317871094 length of segment : 36 time for calcul the mask position with numpy : 0.00017547607421875 nb_pixel_total : 8379 time to create 1 rle with old method : 0.010510444641113281 length of segment : 126 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 1804 time to create 1 rle with old method : 0.002287149429321289 length of segment : 43 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0003292560577392578 length of segment : 21 time for calcul the mask position with numpy : 0.00034427642822265625 nb_pixel_total : 22688 time to create 1 rle with old method : 0.02736663818359375 length of segment : 134 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0005564689636230469 length of segment : 25 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 553 time to create 1 rle with old method : 0.0007369518280029297 length of segment : 45 time for calcul the mask position with numpy : 0.00019621849060058594 nb_pixel_total : 8284 time to create 1 rle with old method : 0.010580778121948242 length of segment : 111 time for calcul the mask position with numpy : 0.00010919570922851562 nb_pixel_total : 2237 2025-02-22 05:20:52.488674: 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 2025-02-22 05:20:52.488743: 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 ! 17.66user 17.37system 1:00:06elapsed 0%CPU (0avgtext+0avgdata 2524832maxresident)k 1509080inputs+3480outputs (16553major+724796minor)pagefaults 0swaps