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 : 4086079 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 : ['2617202'] with mtr_portfolio_ids : ['20850284'] and first list_photo_ids : [] new path : /proc/4086079/ 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 : 0.4784049987792969 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 Wed Feb 26 19:20:28 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 : 10589 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-26 19:20:30.997439: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-26 19:20:31.023173: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-26 19:20:31.025199: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f43a8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-26 19:20:31.025262: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-26 19:20:31.029423: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-26 19:20:31.274728: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3a6cd7b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-26 19:20:31.274787: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-26 19:20:31.276245: 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 2025-02-26 19:20:31.276686: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 19:20:31.279980: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 19:20:31.283078: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 19:20:31.283564: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 19:20:31.285931: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 19:20:31.287014: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 19:20:31.291746: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 19:20:31.293272: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 19:20:31.293353: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 19:20:31.294167: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-26 19:20:31.294184: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-26 19:20:31.294193: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-26 19:20:31.295616: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9811 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. 2025-02-26 19:20:31.566432: 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 2025-02-26 19:20:31.566521: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 19:20:31.566543: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 19:20:31.566562: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 19:20:31.566580: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 19:20:31.566597: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 19:20:31.566615: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 19:20:31.566633: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 19:20:31.568323: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 19:20:31.569758: 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 2025-02-26 19:20:31.569827: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 19:20:31.569850: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 19:20:31.569878: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 19:20:31.569913: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 19:20:31.569940: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 19:20:31.569983: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 19:20:31.570007: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 19:20:31.571649: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 19:20:31.571686: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-26 19:20:31.571698: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-26 19:20:31.571708: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-26 19:20:31.573473: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9811 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 : [] 2025-02-26 19:20:40.715678: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 19:20:40.927912: 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: -123.44609 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 0.00011610984802246094 nb_pixel_total : 530 time to create 1 rle with old method : 0.0012438297271728516 length of segment : 20 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 720 time to create 1 rle with old method : 0.0017223358154296875 length of segment : 29 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0008082389831542969 length of segment : 39 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.0004620552062988281 length of segment : 21 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0011250972747802734 length of segment : 12 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.000278472900390625 length of segment : 17 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.001291513442993164 length of segment : 31 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0007328987121582031 length of segment : 33 time for calcul the mask position with numpy : 9.751319885253906e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0013735294342041016 length of segment : 51 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00020003318786621094 length of segment : 26 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0008637905120849609 length of segment : 36 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0007691383361816406 length of segment : 33 time for calcul the mask position with numpy : 0.0001125335693359375 nb_pixel_total : 1066 time to create 1 rle with old method : 0.0020589828491210938 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.65313 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 637 time to create 1 rle with old method : 0.0013065338134765625 length of segment : 24 time for calcul the mask position with numpy : 0.00010228157043457031 nb_pixel_total : 1130 time to create 1 rle with old method : 0.0021593570709228516 length of segment : 39 time for calcul the mask position with numpy : 0.00013756752014160156 nb_pixel_total : 2008 time to create 1 rle with old method : 0.006087064743041992 length of segment : 40 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 889 time to create 1 rle with old method : 0.0016613006591796875 length of segment : 31 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0006701946258544922 length of segment : 20 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 704 time to create 1 rle with old method : 0.001348733901977539 length of segment : 36 time for calcul the mask position with numpy : 0.00013756752014160156 nb_pixel_total : 1669 time to create 1 rle with old method : 0.0031027793884277344 length of segment : 68 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0004787445068359375 length of segment : 37 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0012249946594238281 length of segment : 27 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 727 time to create 1 rle with old method : 0.001405954360961914 length of segment : 56 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 595 time to create 1 rle with old method : 0.0011060237884521484 length of segment : 24 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0004546642303466797 length of segment : 15 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.0002980232238769531 length of segment : 16 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0010976791381835938 length of segment : 21 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 722 time to create 1 rle with old method : 0.0015254020690917969 length of segment : 34 time for calcul the mask position with numpy : 0.00013065338134765625 nb_pixel_total : 1692 time to create 1 rle with old method : 0.003004312515258789 length of segment : 52 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 569 time to create 1 rle with old method : 0.0011622905731201172 length of segment : 26 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.0003027915954589844 length of segment : 12 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00034356117248535156 length of segment : 32 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 568 time to create 1 rle with old method : 0.0010478496551513672 length of segment : 31 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 1214 time to create 1 rle with old method : 0.002191305160522461 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.20781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0010378360748291016 length of segment : 21 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.001344442367553711 length of segment : 25 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1170 time to create 1 rle with old method : 0.0014770030975341797 length of segment : 51 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.00026726722717285156 length of segment : 23 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.00036454200744628906 length of segment : 35 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 617 time to create 1 rle with old method : 0.003854990005493164 length of segment : 23 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.0012097358703613281 length of segment : 57 time for calcul the mask position with numpy : 0.00013136863708496094 nb_pixel_total : 3010 time to create 1 rle with old method : 0.0036497116088867188 length of segment : 97 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.00032520294189453125 length of segment : 16 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 974 time to create 1 rle with old method : 0.0012230873107910156 length of segment : 43 length of segment : 0 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0010399818420410156 length of segment : 26 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1465 time to create 1 rle with old method : 0.0019118785858154297 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.37578 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 2510 time to create 1 rle with old method : 0.0031681060791015625 length of segment : 50 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 752 time to create 1 rle with old method : 0.0010385513305664062 length of segment : 36 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.001027822494506836 length of segment : 34 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 4774 time to create 1 rle with old method : 0.0061664581298828125 length of segment : 56 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 747 time to create 1 rle with old method : 0.0009832382202148438 length of segment : 29 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 725 time to create 1 rle with old method : 0.0009779930114746094 length of segment : 31 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0004420280456542969 length of segment : 28 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1737 time to create 1 rle with old method : 0.002240419387817383 length of segment : 54 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0007562637329101562 length of segment : 25 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1527 time to create 1 rle with old method : 0.0018815994262695312 length of segment : 49 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0005819797515869141 length of segment : 19 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005693435668945312 length of segment : 33 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.0007102489471435547 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 91.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -32.70000 max: 145.39687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 609 time to create 1 rle with old method : 0.0011448860168457031 length of segment : 33 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 951 time to create 1 rle with old method : 0.0017914772033691406 length of segment : 29 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 804 time to create 1 rle with old method : 0.0015082359313964844 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 26.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -87.06328 max: 150.74844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 545 time to create 1 rle with old method : 0.0007433891296386719 length of segment : 31 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0005066394805908203 length of segment : 16 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 2111 time to create 1 rle with old method : 0.0027005672454833984 length of segment : 66 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.00040340423583984375 length of segment : 43 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003287792205810547 length of segment : 10 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003674030303955078 length of segment : 26 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0007269382476806641 length of segment : 19 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1398 time to create 1 rle with old method : 0.0019268989562988281 length of segment : 29 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1055 time to create 1 rle with old method : 0.0014507770538330078 length of segment : 35 Processing 1 images image shape: (400, 160, 3) min: 52.00000 max: 222.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 105.59219 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 : 162 time to create 1 rle with old method : 0.00025153160095214844 length of segment : 15 time for calcul the mask position with numpy : 0.0001971721649169922 nb_pixel_total : 12159 time to create 1 rle with old method : 0.014251708984375 length of segment : 226 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.14922 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 : 0.00012564659118652344 nb_pixel_total : 433 time to create 1 rle with old method : 0.0012509822845458984 length of segment : 27 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0007081031799316406 length of segment : 15 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0009980201721191406 length of segment : 28 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0003757476806640625 length of segment : 17 time for calcul the mask position with numpy : 0.00011205673217773438 nb_pixel_total : 1099 time to create 1 rle with old method : 0.0018000602722167969 length of segment : 58 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0005564689636230469 length of segment : 34 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 681 time to create 1 rle with old method : 0.0012030601501464844 length of segment : 40 time for calcul the mask position with numpy : 0.00018835067749023438 nb_pixel_total : 4119 time to create 1 rle with old method : 0.0071277618408203125 length of segment : 77 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0011484622955322266 length of segment : 27 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0007238388061523438 length of segment : 52 time for calcul the mask position with numpy : 0.00018143653869628906 nb_pixel_total : 6215 time to create 1 rle with old method : 0.00803995132446289 length of segment : 159 time for calcul the mask position with numpy : 0.00011277198791503906 nb_pixel_total : 438 time to create 1 rle with old method : 0.0008256435394287109 length of segment : 35 time for calcul the mask position with numpy : 0.00017333030700683594 nb_pixel_total : 2748 time to create 1 rle with old method : 0.005037069320678711 length of segment : 129 time for calcul the mask position with numpy : 0.0001220703125 nb_pixel_total : 1113 time to create 1 rle with old method : 0.0019626617431640625 length of segment : 40 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 2206 time to create 1 rle with old method : 0.0037806034088134766 length of segment : 38 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0004374980926513672 length of segment : 16 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0004227161407470703 length of segment : 38 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 1037 time to create 1 rle with old method : 0.0018749237060546875 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: -120.50078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009355545043945312 length of segment : 20 time for calcul the mask position with numpy : 0.0001475811004638672 nb_pixel_total : 2346 time to create 1 rle with old method : 0.0037670135498046875 length of segment : 55 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 599 time to create 1 rle with old method : 0.0011973381042480469 length of segment : 28 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.00047469139099121094 length of segment : 24 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 728 time to create 1 rle with old method : 0.0009500980377197266 length of segment : 38 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006556510925292969 length of segment : 24 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 1323 time to create 1 rle with old method : 0.0018334388732910156 length of segment : 48 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 667 time to create 1 rle with old method : 0.0009069442749023438 length of segment : 26 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1033 time to create 1 rle with old method : 0.0013473033905029297 length of segment : 42 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1596 time to create 1 rle with old method : 0.0019447803497314453 length of segment : 49 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 2041 time to create 1 rle with old method : 0.0025620460510253906 length of segment : 44 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 2159 time to create 1 rle with old method : 0.0026712417602539062 length of segment : 85 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0008616447448730469 length of segment : 51 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.00107574462890625 length of segment : 50 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 686 time to create 1 rle with old method : 0.0008463859558105469 length of segment : 63 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 1359 time to create 1 rle with old method : 0.002126455307006836 length of segment : 43 time for calcul the mask position with numpy : 0.00012302398681640625 nb_pixel_total : 3274 time to create 1 rle with old method : 0.003988742828369141 length of segment : 71 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00019788742065429688 length of segment : 8 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 2497 time to create 1 rle with old method : 0.0030951499938964844 length of segment : 60 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.0005335807800292969 length of segment : 22 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002961158752441406 length of segment : 11 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0003943443298339844 length of segment : 22 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 553 time to create 1 rle with old method : 0.0007028579711914062 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: -116.43828 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 : 0.0001201629638671875 nb_pixel_total : 663 time to create 1 rle with old method : 0.0009601116180419922 length of segment : 34 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1118 time to create 1 rle with old method : 0.00141143798828125 length of segment : 54 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 1534 time to create 1 rle with old method : 0.0019068717956542969 length of segment : 47 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005209445953369141 length of segment : 32 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 955 time to create 1 rle with old method : 0.001272439956665039 length of segment : 46 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.00033783912658691406 length of segment : 19 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0005831718444824219 length of segment : 22 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0008630752563476562 length of segment : 33 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005183219909667969 length of segment : 20 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 719 time to create 1 rle with old method : 0.0009059906005859375 length of segment : 53 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1390 time to create 1 rle with old method : 0.0018146038055419922 length of segment : 40 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 572 time to create 1 rle with old method : 0.0007953643798828125 length of segment : 25 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.00045752525329589844 length of segment : 27 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1574 time to create 1 rle with old method : 0.002030611038208008 length of segment : 42 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1784 time to create 1 rle with old method : 0.002225637435913086 length of segment : 37 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 730 time to create 1 rle with old method : 0.000978708267211914 length of segment : 84 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002455711364746094 length of segment : 27 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 927 time to create 1 rle with old method : 0.0012516975402832031 length of segment : 43 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 931 time to create 1 rle with old method : 0.001500844955444336 length of segment : 42 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 854 time to create 1 rle with old method : 0.0014646053314208984 length of segment : 37 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.0002543926239013672 length of segment : 14 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.00025534629821777344 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -102.43516 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00032639503479003906 length of segment : 21 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 28 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0007562637329101562 length of segment : 27 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002593994140625 length of segment : 20 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1041 time to create 1 rle with old method : 0.001300811767578125 length of segment : 48 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 2844 time to create 1 rle with old method : 0.003458261489868164 length of segment : 66 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.00023937225341796875 length of segment : 15 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.00025200843811035156 length of segment : 15 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.00045490264892578125 length of segment : 24 time for calcul the mask position with numpy : 0.00014829635620117188 nb_pixel_total : 3189 time to create 1 rle with old method : 0.004502296447753906 length of segment : 80 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1507 time to create 1 rle with old method : 0.001917123794555664 length of segment : 39 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005521774291992188 length of segment : 31 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1508 time to create 1 rle with old method : 0.001947641372680664 length of segment : 35 Processing 1 images image shape: (400, 400, 3) min: 27.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -86.78203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 1291 time to create 1 rle with old method : 0.002181529998779297 length of segment : 48 time for calcul the mask position with numpy : 0.00013303756713867188 nb_pixel_total : 3748 time to create 1 rle with old method : 0.006254434585571289 length of segment : 54 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 1819 time to create 1 rle with old method : 0.002290964126586914 length of segment : 94 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 2054 time to create 1 rle with old method : 0.002599000930786133 length of segment : 124 time for calcul the mask position with numpy : 0.00012612342834472656 nb_pixel_total : 3833 time to create 1 rle with old method : 0.00474095344543457 length of segment : 122 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0005371570587158203 length of segment : 28 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.0012614727020263672 length of segment : 46 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0002872943878173828 length of segment : 21 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 761 time to create 1 rle with old method : 0.0011119842529296875 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 16.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -94.04375 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 : 6.747245788574219e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0004658699035644531 length of segment : 13 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 821 time to create 1 rle with old method : 0.0014929771423339844 length of segment : 42 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0008635520935058594 length of segment : 29 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0008406639099121094 length of segment : 26 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1286 time to create 1 rle with old method : 0.0023322105407714844 length of segment : 49 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0005605220794677734 length of segment : 37 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00046539306640625 length of segment : 29 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0007491111755371094 length of segment : 50 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.0014791488647460938 length of segment : 40 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0008885860443115234 length of segment : 18 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.90078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0008754730224609375 length of segment : 28 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.004205942153930664 length of segment : 50 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0005412101745605469 length of segment : 32 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0004165172576904297 length of segment : 23 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.00028204917907714844 length of segment : 18 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00025963783264160156 length of segment : 19 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0034003257751464844 length of segment : 60 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004143714904785156 length of segment : 34 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011515617370605469 length of segment : 13 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 777 time to create 1 rle with old method : 0.0010535717010498047 length of segment : 52 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00025463104248046875 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.68047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 1094 time to create 1 rle with old method : 0.0019268989562988281 length of segment : 46 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 989 time to create 1 rle with old method : 0.0017826557159423828 length of segment : 38 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 458 time to create 1 rle with old method : 0.0008957386016845703 length of segment : 37 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0010917186737060547 length of segment : 40 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0006036758422851562 length of segment : 25 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 1674 time to create 1 rle with old method : 0.002908468246459961 length of segment : 56 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 469 time to create 1 rle with old method : 0.0008313655853271484 length of segment : 27 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.000270843505859375 length of segment : 33 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 499 time to create 1 rle with old method : 0.0006775856018066406 length of segment : 28 time for calcul the mask position with numpy : 0.00019860267639160156 nb_pixel_total : 5959 time to create 1 rle with old method : 0.0072972774505615234 length of segment : 135 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005867481231689453 length of segment : 24 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.00047588348388671875 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: -121.36797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 491 time to create 1 rle with old method : 0.0007200241088867188 length of segment : 22 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0010228157043457031 length of segment : 23 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.0002522468566894531 length of segment : 13 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1961 time to create 1 rle with old method : 0.0024220943450927734 length of segment : 50 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.00031256675720214844 length of segment : 31 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0005726814270019531 length of segment : 34 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0007023811340332031 length of segment : 31 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005693435668945312 length of segment : 41 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0009319782257080078 length of segment : 35 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1055 time to create 1 rle with old method : 0.001377105712890625 length of segment : 43 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003712177276611328 length of segment : 39 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 1984 time to create 1 rle with old method : 0.002506732940673828 length of segment : 71 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0011320114135742188 length of segment : 30 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.0004067420959472656 length of segment : 27 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0003020763397216797 length of segment : 22 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0004553794860839844 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: -120.43828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 0.0001480579376220703 nb_pixel_total : 405 time to create 1 rle with old method : 0.0005788803100585938 length of segment : 36 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0005216598510742188 length of segment : 23 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0008521080017089844 length of segment : 17 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00026488304138183594 length of segment : 27 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003552436828613281 length of segment : 13 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003387928009033203 length of segment : 20 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1741 time to create 1 rle with old method : 0.0023660659790039062 length of segment : 41 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002956390380859375 length of segment : 13 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001709461212158203 length of segment : 12 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 714 time to create 1 rle with old method : 0.0009682178497314453 length of segment : 26 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0006475448608398438 length of segment : 38 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0006017684936523438 length of segment : 28 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0005002021789550781 length of segment : 22 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 972 time to create 1 rle with old method : 0.001425027847290039 length of segment : 44 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0007300376892089844 length of segment : 27 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005254745483398438 length of segment : 33 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 1710 time to create 1 rle with old method : 0.0026674270629882812 length of segment : 42 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003733634948730469 length of segment : 19 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.0004940032958984375 length of segment : 25 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.000579833984375 length of segment : 29 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 1482 time to create 1 rle with old method : 0.001954793930053711 length of segment : 87 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.24297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 726 time to create 1 rle with old method : 0.0009829998016357422 length of segment : 31 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00031280517578125 length of segment : 12 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003914833068847656 length of segment : 17 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.0007641315460205078 length of segment : 28 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003609657287597656 length of segment : 16 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0008933544158935547 length of segment : 54 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0006630420684814453 length of segment : 23 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003838539123535156 length of segment : 23 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 366 time to create 1 rle with old method : 0.000499725341796875 length of segment : 24 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0007343292236328125 length of segment : 33 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0007231235504150391 length of segment : 22 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 192 time to create 1 rle with old method : 0.0004165172576904297 length of segment : 31 time for calcul the mask position with numpy : 0.0002219676971435547 nb_pixel_total : 1669 time to create 1 rle with old method : 0.0031054019927978516 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.70391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0005624294281005859 length of segment : 32 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0006556510925292969 length of segment : 20 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003757476806640625 length of segment : 27 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.00027298927307128906 length of segment : 21 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0004305839538574219 length of segment : 23 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1045 time to create 1 rle with old method : 0.0037267208099365234 length of segment : 76 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 1621 time to create 1 rle with old method : 0.002210855484008789 length of segment : 44 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1699 time to create 1 rle with old method : 0.002260923385620117 length of segment : 51 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.0003337860107421875 length of segment : 19 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.001043558120727539 length of segment : 28 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1253 time to create 1 rle with old method : 0.0015866756439208984 length of segment : 48 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.0006473064422607422 length of segment : 29 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0005283355712890625 length of segment : 26 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0006742477416992188 length of segment : 16 time for calcul the mask position with numpy : 0.00013637542724609375 nb_pixel_total : 1993 time to create 1 rle with old method : 0.002603292465209961 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: -119.91875 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 1052 time to create 1 rle with old method : 0.0014176368713378906 length of segment : 47 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0006043910980224609 length of segment : 30 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1469 time to create 1 rle with old method : 0.0019223690032958984 length of segment : 54 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0010638236999511719 length of segment : 44 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0005896091461181641 length of segment : 41 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.0002238750457763672 length of segment : 13 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006566047668457031 length of segment : 39 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.000152587890625 length of segment : 8 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0003006458282470703 length of segment : 19 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002377033233642578 length of segment : 21 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1191 time to create 1 rle with old method : 0.0014755725860595703 length of segment : 47 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0007812976837158203 length of segment : 55 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.92422 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.0003204345703125 length of segment : 42 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0005691051483154297 length of segment : 25 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 840 time to create 1 rle with old method : 0.0015401840209960938 length of segment : 30 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0006177425384521484 length of segment : 35 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0005009174346923828 length of segment : 19 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.0002582073211669922 length of segment : 22 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 2905 time to create 1 rle with old method : 0.005459308624267578 length of segment : 81 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 2622 time to create 1 rle with old method : 0.006268739700317383 length of segment : 66 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005366802215576172 length of segment : 24 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005540847778320312 length of segment : 47 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003399848937988281 length of segment : 17 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 634 time to create 1 rle with old method : 0.0008988380432128906 length of segment : 30 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0008578300476074219 length of segment : 31 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006716251373291016 length of segment : 41 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0008032321929931641 length of segment : 23 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00018525123596191406 length of segment : 5 2025-02-26 19:20:50.409984: 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 2025-02-26 19:20:50.410052: 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 ! 18.49user 15.89system 1:00:05elapsed 0%CPU (0avgtext+0avgdata 2508060maxresident)k 622776inputs+3920outputs (12959major+736277minor)pagefaults 0swaps