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 : 1712198 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 we have a portfolio with more photos than limit : 6>5 please execute split_portfolio.py -i 20234237 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2547951'] with mtr_portfolio_ids : ['20234237'] and first list_photo_ids : [] new path : /proc/1712198/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 0.8539552688598633 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 5 02:20:29 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10774 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-05 02:20:32.485601: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-05 02:20:32.492788: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-05 02:20:32.494179: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f38bc000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-05 02:20:32.494215: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-05 02:20:32.496560: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-05 02:20:32.705248: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x38b1d8a0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-05 02:20:32.705290: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-05 02:20:32.706645: 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 2025-02-05 02:20:32.707025: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 02:20:32.709720: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 02:20:32.712267: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 02:20:32.712707: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 02:20:32.715874: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 02:20:32.716997: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 02:20:32.720784: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 02:20:32.722117: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 02:20:32.722170: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 02:20:32.722874: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-05 02:20:32.722888: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-05 02:20:32.722904: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-05 02:20:32.724291: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-02-05 02:20:32.964623: 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 2025-02-05 02:20:32.964724: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 02:20:32.964755: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 02:20:32.964784: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 02:20:32.964812: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 02:20:32.964839: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 02:20:32.964866: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 02:20:32.964893: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 02:20:32.967070: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 02:20:32.968366: 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 2025-02-05 02:20:32.968395: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 02:20:32.968410: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 02:20:32.968424: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 02:20:32.968437: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 02:20:32.968451: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 02:20:32.968465: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 02:20:32.968478: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 02:20:32.969686: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 02:20:32.969712: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-05 02:20:32.969720: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-05 02:20:32.969728: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-05 02:20:32.971063: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-05 02:20:39.640747: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 02:20:39.833815: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 5 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.55547 max: 150.35781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0008068084716796875 length of segment : 24 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 881 time to create 1 rle with old method : 0.001611948013305664 length of segment : 39 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00030922889709472656 length of segment : 32 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.0014307498931884766 length of segment : 33 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1611 time to create 1 rle with old method : 0.0029010772705078125 length of segment : 55 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.000186920166015625 length of segment : 20 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.000225067138671875 length of segment : 35 time for calcul the mask position with numpy : 0.00017070770263671875 nb_pixel_total : 2017 time to create 1 rle with old method : 0.003040790557861328 length of segment : 96 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.13750 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 : 7.939338684082031e-05 nb_pixel_total : 2345 time to create 1 rle with old method : 0.0029256343841552734 length of segment : 48 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 2276 time to create 1 rle with old method : 0.0028307437896728516 length of segment : 51 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.02500 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 3086 time to create 1 rle with old method : 0.004187583923339844 length of segment : 122 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 941 time to create 1 rle with old method : 0.0012645721435546875 length of segment : 43 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 2465 time to create 1 rle with old method : 0.003396749496459961 length of segment : 35 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 1582 time to create 1 rle with old method : 0.0022847652435302734 length of segment : 42 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0007877349853515625 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.86406 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.00033855438232421875 length of segment : 17 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 2999 time to create 1 rle with old method : 0.003745555877685547 length of segment : 50 time for calcul the mask position with numpy : 0.00013637542724609375 nb_pixel_total : 2892 time to create 1 rle with old method : 0.004782438278198242 length of segment : 86 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.0002548694610595703 length of segment : 17 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.36172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0009453296661376953 length of segment : 17 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1412 time to create 1 rle with old method : 0.0018873214721679688 length of segment : 49 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1435 time to create 1 rle with old method : 0.0018794536590576172 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 20.00000 max: 241.00000 molded_images shape: (1, 640, 640, 3) min: -80.18047 max: 109.00859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -105.93438 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0006647109985351562 length of segment : 25 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1669 time to create 1 rle with old method : 0.0022270679473876953 length of segment : 43 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00030422210693359375 length of segment : 18 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 677 time to create 1 rle with old method : 0.0010554790496826172 length of segment : 24 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00039458274841308594 length of segment : 17 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0004563331604003906 length of segment : 21 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 456 time to create 1 rle with old method : 0.0008056163787841797 length of segment : 19 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1085 time to create 1 rle with old method : 0.0017528533935546875 length of segment : 38 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 966 time to create 1 rle with old method : 0.00141143798828125 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: -103.90000 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 : 6.914138793945312e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.0010514259338378906 length of segment : 39 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.00016260147094726562 length of segment : 14 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00023436546325683594 length of segment : 11 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004863739013671875 length of segment : 18 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004673004150390625 length of segment : 42 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005142688751220703 length of segment : 18 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.00018644332885742188 length of segment : 10 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003337860107421875 length of segment : 17 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.0008089542388916016 length of segment : 32 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 511 time to create 1 rle with old method : 0.0008549690246582031 length of segment : 21 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0008423328399658203 length of segment : 28 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.0001990795135498047 length of segment : 13 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002319812774658203 length of segment : 10 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0009827613830566406 length of segment : 27 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002429485321044922 length of segment : 11 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00023627281188964844 length of segment : 13 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.00045800209045410156 length of segment : 56 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 39 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00017261505126953125 length of segment : 11 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 966 time to create 1 rle with old method : 0.0012786388397216797 length of segment : 48 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0004031658172607422 length of segment : 17 length of segment : 0 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.0004086494445800781 length of segment : 19 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005142688751220703 length of segment : 25 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.00026607513427734375 length of segment : 20 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002846717834472656 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: -116.02031 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 : 5.054473876953125e-05 nb_pixel_total : 782 time to create 1 rle with old method : 0.0009796619415283203 length of segment : 38 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0009245872497558594 length of segment : 47 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 454 time to create 1 rle with old method : 0.0006394386291503906 length of segment : 29 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00036025047302246094 length of segment : 17 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 584 time to create 1 rle with old method : 0.0008330345153808594 length of segment : 29 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 1202 time to create 1 rle with old method : 0.0016808509826660156 length of segment : 32 time for calcul the mask position with numpy : 0.00029754638671875 nb_pixel_total : 19956 time to create 1 rle with old method : 0.025231122970581055 length of segment : 173 time for calcul the mask position with numpy : 0.0001308917999267578 nb_pixel_total : 1759 time to create 1 rle with old method : 0.0036232471466064453 length of segment : 46 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0009081363677978516 length of segment : 28 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1098 time to create 1 rle with old method : 0.0014100074768066406 length of segment : 97 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 1958 time to create 1 rle with old method : 0.002290010452270508 length of segment : 135 time for calcul the mask position with numpy : 0.0001590251922607422 nb_pixel_total : 8120 time to create 1 rle with old method : 0.009474039077758789 length of segment : 195 time for calcul the mask position with numpy : 0.0003542900085449219 nb_pixel_total : 26765 time to create 1 rle with old method : 0.030245065689086914 length of segment : 210 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1353 time to create 1 rle with old method : 0.0017888545989990234 length of segment : 33 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1825 time to create 1 rle with old method : 0.0023064613342285156 length of segment : 46 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.00048279762268066406 length of segment : 31 time for calcul the mask position with numpy : 0.00010776519775390625 nb_pixel_total : 2831 time to create 1 rle with old method : 0.003570556640625 length of segment : 161 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1713 time to create 1 rle with old method : 0.002152681350708008 length of segment : 83 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 1046 time to create 1 rle with old method : 0.00136566162109375 length of segment : 52 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 671 time to create 1 rle with old method : 0.0008280277252197266 length of segment : 51 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1711 time to create 1 rle with old method : 0.002204418182373047 length of segment : 82 Processing 1 images image shape: (280, 400, 3) min: 20.00000 max: 216.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 93.23125 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008809566497802734 nb_pixel_total : 99658 time to create 1 rle with old method : 0.12031126022338867 length of segment : 264 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0006074905395507812 length of segment : 29 time for calcul the mask position with numpy : 0.00012993812561035156 nb_pixel_total : 3301 time to create 1 rle with old method : 0.005492210388183594 length of segment : 106 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1499 time to create 1 rle with old method : 0.002174854278564453 length of segment : 53 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002548694610595703 length of segment : 18 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0008211135864257812 length of segment : 25 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.00047898292541503906 length of segment : 24 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0008068084716796875 length of segment : 37 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 627 time to create 1 rle with old method : 0.0008566379547119141 length of segment : 44 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 608 time to create 1 rle with old method : 0.0009489059448242188 length of segment : 36 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0010306835174560547 length of segment : 32 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.0005736351013183594 length of segment : 20 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 415 time to create 1 rle with old method : 0.0006949901580810547 length of segment : 24 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.0003764629364013672 length of segment : 18 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0005292892456054688 length of segment : 21 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 133 time to create 1 rle with old method : 0.00023436546325683594 length of segment : 21 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.00048041343688964844 length of segment : 26 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00019931793212890625 length of segment : 10 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0008463859558105469 length of segment : 30 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0005502700805664062 length of segment : 20 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0004038810729980469 length of segment : 15 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 554 time to create 1 rle with old method : 0.0008211135864257812 length of segment : 27 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.00041365623474121094 length of segment : 27 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003230571746826172 length of segment : 15 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1406 time to create 1 rle with old method : 0.0020046234130859375 length of segment : 57 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.0004420280456542969 length of segment : 13 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0005288124084472656 length of segment : 17 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1227 time to create 1 rle with old method : 0.0019562244415283203 length of segment : 42 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 380 time to create 1 rle with old method : 0.0006282329559326172 length of segment : 20 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.68984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 928 time to create 1 rle with old method : 0.0012590885162353516 length of segment : 46 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 57 time to create 1 rle with old method : 0.00012731552124023438 length of segment : 17 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0004646778106689453 length of segment : 21 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.00031828880310058594 length of segment : 21 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00035190582275390625 length of segment : 51 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0006034374237060547 length of segment : 36 time for calcul the mask position with numpy : 0.00015234947204589844 nb_pixel_total : 7934 time to create 1 rle with old method : 0.010714530944824219 length of segment : 96 time for calcul the mask position with numpy : 0.00016164779663085938 nb_pixel_total : 8141 time to create 1 rle with old method : 0.010514497756958008 length of segment : 97 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0006206035614013672 length of segment : 28 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.22500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0009572505950927734 length of segment : 21 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.32891 max: 149.56484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0010704994201660156 length of segment : 27 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 861 time to create 1 rle with old method : 0.0018153190612792969 length of segment : 32 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.0002944469451904297 length of segment : 32 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0016782283782958984 length of segment : 30 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 959 time to create 1 rle with old method : 0.0023157596588134766 length of segment : 78 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.20000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 2020 time to create 1 rle with old method : 0.0026350021362304688 length of segment : 50 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 2080 time to create 1 rle with old method : 0.0026874542236328125 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.88750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 2625 time to create 1 rle with old method : 0.003444671630859375 length of segment : 102 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 961 time to create 1 rle with old method : 0.0012786388397216797 length of segment : 46 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 1045 time to create 1 rle with old method : 0.0014591217041015625 length of segment : 24 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.00012493133544921875 length of segment : 13 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.00035452842712402344 length of segment : 14 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003895759582519531 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.17656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.0003426074981689453 length of segment : 15 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 862 time to create 1 rle with old method : 0.001089334487915039 length of segment : 53 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 2992 time to create 1 rle with old method : 0.003819704055786133 length of segment : 51 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 3746 time to create 1 rle with old method : 0.004799604415893555 length of segment : 105 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.36172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0007009506225585938 length of segment : 18 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 7264 time to create 1 rle with old method : 0.009092569351196289 length of segment : 76 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1644 time to create 1 rle with old method : 0.0021657943725585938 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 30.00000 max: 239.00000 molded_images shape: (1, 640, 640, 3) min: -77.89531 max: 104.77813 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.75156 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0003981590270996094 length of segment : 31 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.00033092498779296875 length of segment : 17 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1534 time to create 1 rle with old method : 0.0021049976348876953 length of segment : 39 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1956 time to create 1 rle with old method : 0.0025491714477539062 length of segment : 53 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002846717834472656 length of segment : 25 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003571510314941406 length of segment : 21 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 1236 time to create 1 rle with old method : 0.0018241405487060547 length of segment : 71 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 2432 time to create 1 rle with old method : 0.0032143592834472656 length of segment : 50 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.27031 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 : 5.5789947509765625e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.0002377033233642578 length of segment : 9 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.0005228519439697266 length of segment : 18 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0005383491516113281 length of segment : 18 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0003719329833984375 length of segment : 13 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0009660720825195312 length of segment : 34 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003600120544433594 length of segment : 19 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.00023317337036132812 length of segment : 17 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 678 time to create 1 rle with old method : 0.0010304450988769531 length of segment : 67 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0005991458892822266 length of segment : 27 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00020885467529296875 length of segment : 13 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 655 time to create 1 rle with old method : 0.0008740425109863281 length of segment : 28 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00024509429931640625 length of segment : 10 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00018525123596191406 length of segment : 13 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 2607 time to create 1 rle with old method : 0.0033409595489501953 length of segment : 107 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005552768707275391 length of segment : 23 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00022792816162109375 length of segment : 10 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004937648773193359 length of segment : 42 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 803 time to create 1 rle with old method : 0.001186370849609375 length of segment : 41 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 743 time to create 1 rle with old method : 0.0009627342224121094 length of segment : 31 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0008585453033447266 length of segment : 21 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0002713203430175781 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: -103.90000 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 : 5.078315734863281e-05 nb_pixel_total : 725 time to create 1 rle with old method : 0.0010399818420410156 length of segment : 48 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.0002193450927734375 length of segment : 7 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1242 time to create 1 rle with old method : 0.0017545223236083984 length of segment : 31 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1731 time to create 1 rle with old method : 0.002179384231567383 length of segment : 54 time for calcul the mask position with numpy : 0.0002593994140625 nb_pixel_total : 17978 time to create 1 rle with old method : 0.021049976348876953 length of segment : 147 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0007560253143310547 length of segment : 34 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0007991790771484375 length of segment : 28 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0004107952117919922 length of segment : 17 time for calcul the mask position with numpy : 0.00011014938354492188 nb_pixel_total : 1963 time to create 1 rle with old method : 0.0024929046630859375 length of segment : 141 time for calcul the mask position with numpy : 0.00015664100646972656 nb_pixel_total : 6370 time to create 1 rle with old method : 0.007963180541992188 length of segment : 172 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007083415985107422 length of segment : 28 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1801 time to create 1 rle with old method : 0.0023946762084960938 length of segment : 45 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 685 time to create 1 rle with old method : 0.0010044574737548828 length of segment : 97 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1740 time to create 1 rle with old method : 0.00232696533203125 length of segment : 46 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0006148815155029297 length of segment : 20 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 0.0001266002655029297 nb_pixel_total : 2162 time to create 1 rle with old method : 0.003407716751098633 length of segment : 158 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.00044417381286621094 length of segment : 28 time for calcul the mask position with numpy : 0.00013828277587890625 nb_pixel_total : 2015 time to create 1 rle with old method : 0.0026984214782714844 length of segment : 152 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1755 time to create 1 rle with old method : 0.002252340316772461 length of segment : 82 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 941 time to create 1 rle with old method : 0.0013158321380615234 length of segment : 51 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 661 time to create 1 rle with old method : 0.0008502006530761719 length of segment : 52 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1589 time to create 1 rle with old method : 0.0020477771759033203 length of segment : 75 Processing 1 images image shape: (280, 400, 3) min: 20.00000 max: 217.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 84.33281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009126663208007812 nb_pixel_total : 106710 time to create 1 rle with old method : 0.11797571182250977 length of segment : 278 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1483 time to create 1 rle with old method : 0.001895904541015625 length of segment : 52 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 8032 time to create 1 rle with old method : 0.009428024291992188 length of segment : 88 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00022268295288085938 length of segment : 17 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 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 : 5.245208740234375e-05 nb_pixel_total : 606 time to create 1 rle with old method : 0.0008196830749511719 length of segment : 42 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006899833679199219 length of segment : 36 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.0004558563232421875 length of segment : 19 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0012631416320800781 length of segment : 35 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.000667572021484375 length of segment : 21 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 660 time to create 1 rle with old method : 0.0012669563293457031 length of segment : 32 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0007102489471435547 length of segment : 23 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0007967948913574219 length of segment : 27 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.000545501708984375 length of segment : 20 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0005733966827392578 length of segment : 25 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0006940364837646484 length of segment : 17 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0009036064147949219 length of segment : 25 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0006833076477050781 length of segment : 21 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0010612010955810547 length of segment : 27 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.0002377033233642578 length of segment : 13 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.00026702880859375 length of segment : 18 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 609 time to create 1 rle with old method : 0.0009453296661376953 length of segment : 27 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0008549690246582031 length of segment : 28 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003445148468017578 length of segment : 15 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 1013 time to create 1 rle with old method : 0.00136566162109375 length of segment : 39 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.68984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 842 time to create 1 rle with old method : 0.001051187515258789 length of segment : 73 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0006940364837646484 length of segment : 39 time for calcul the mask position with numpy : 0.00013113021850585938 nb_pixel_total : 8207 time to create 1 rle with old method : 0.010125875473022461 length of segment : 96 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0003952980041503906 length of segment : 18 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004839897155761719 length of segment : 28 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 1070 time to create 1 rle with old method : 0.001352071762084961 length of segment : 49 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.00018072128295898438 length of segment : 25 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.00038814544677734375 length of segment : 32 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 896 time to create 1 rle with old method : 0.001165151596069336 length of segment : 86 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00038814544677734375 length of segment : 48 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 405 time to create 1 rle with old method : 0.0005576610565185547 length of segment : 35 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0006628036499023438 length of segment : 23 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0005612373352050781 length of segment : 73 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.52813 max: 149.74062 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006778240203857422 length of segment : 26 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 841 time to create 1 rle with old method : 0.0011889934539794922 length of segment : 41 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002567768096923828 length of segment : 34 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 2692 time to create 1 rle with old method : 0.003448963165283203 length of segment : 87 time for calcul the mask position with numpy : 0.00030517578125 nb_pixel_total : 18378 time to create 1 rle with old method : 0.022114992141723633 length of segment : 268 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1125 time to create 1 rle with old method : 0.0016810894012451172 length of segment : 67 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 640 time to create 1 rle with old method : 0.0009629726409912109 length of segment : 36 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0005841255187988281 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: -117.70781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1507 time to create 1 rle with old method : 0.0020394325256347656 length of segment : 32 time for calcul the mask position with numpy : 0.0001201629638671875 nb_pixel_total : 2564 time to create 1 rle with old method : 0.0033080577850341797 length of segment : 55 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0013580322265625 length of segment : 47 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.61797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 2302 time to create 1 rle with old method : 0.003012418746948242 length of segment : 97 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 943 time to create 1 rle with old method : 0.001249551773071289 length of segment : 40 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1102 time to create 1 rle with old method : 0.001501321792602539 length of segment : 67 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 63 time to create 1 rle with old method : 0.00010704994201660156 length of segment : 12 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.0005433559417724609 length of segment : 15 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 807 time to create 1 rle with old method : 0.0011703968048095703 length of segment : 21 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 890 time to create 1 rle with old method : 0.0011396408081054688 length of segment : 42 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.0003936290740966797 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -99.88828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003447532653808594 length of segment : 15 time for calcul the mask position with numpy : 9.846687316894531e-05 nb_pixel_total : 3307 time to create 1 rle with old method : 0.004195451736450195 length of segment : 107 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 2877 time to create 1 rle with old method : 0.003768444061279297 length of segment : 49 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 829 time to create 1 rle with old method : 0.0010695457458496094 length of segment : 56 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002613067626953125 length of segment : 17 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.34219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0007448196411132812 length of segment : 19 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 948 time to create 1 rle with old method : 0.0012781620025634766 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 30.00000 max: 241.00000 molded_images shape: (1, 640, 640, 3) min: -77.18438 max: 110.08672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0014159679412841797 nb_pixel_total : 151693 time to create 1 rle with new method : 0.0019173622131347656 length of segment : 395 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -98.05156 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 : 4.1961669921875e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.0003437995910644531 length of segment : 18 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0014307498931884766 length of segment : 39 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0003457069396972656 length of segment : 18 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1837 time to create 1 rle with old method : 0.002449512481689453 length of segment : 43 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 738 time to create 1 rle with old method : 0.0010979175567626953 length of segment : 21 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1113 time to create 1 rle with old method : 0.0016171932220458984 length of segment : 39 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 2109 time to create 1 rle with old method : 0.002725362777709961 length of segment : 59 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 672 time to create 1 rle with old method : 0.0009667873382568359 length of segment : 37 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 895 time to create 1 rle with old method : 0.001275777816772461 length of segment : 75 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.00035071372985839844 length of segment : 21 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00024271011352539062 length of segment : 9 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0006122589111328125 length of segment : 17 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 866 time to create 1 rle with old method : 0.001219034194946289 length of segment : 35 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.24297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 27 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 718 time to create 1 rle with old method : 0.0009865760803222656 length of segment : 35 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00024580955505371094 length of segment : 10 length of segment : 0 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0005238056182861328 length of segment : 18 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002551078796386719 length of segment : 19 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.0008847713470458984 length of segment : 28 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005092620849609375 length of segment : 18 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.0002110004425048828 length of segment : 14 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.000316619873046875 length of segment : 19 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00026154518127441406 length of segment : 11 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0007505416870117188 length of segment : 18 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0004673004150390625 length of segment : 23 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00020575523376464844 length of segment : 10 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 659 time to create 1 rle with old method : 0.0008721351623535156 length of segment : 27 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004439353942871094 length of segment : 15 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0007708072662353516 length of segment : 25 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00039839744567871094 length of segment : 19 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.0007801055908203125 length of segment : 27 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 722 time to create 1 rle with old method : 0.00099945068359375 length of segment : 42 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.00030303001403808594 length of segment : 16 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001571178436279297 length of segment : 13 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.00039005279541015625 length of segment : 34 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005943775177001953 length of segment : 25 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0009114742279052734 length of segment : 23 time for calcul the mask position with numpy : 2.765655517578125e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00021791458129882812 length of segment : 18 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.00025177001953125 length of segment : 15 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002980232238769531 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.72344 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 0.0003025531768798828 nb_pixel_total : 18977 time to create 1 rle with old method : 0.023493289947509766 length of segment : 159 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.000782012939453125 length of segment : 27 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 964 time to create 1 rle with old method : 0.0013899803161621094 length of segment : 24 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0007092952728271484 length of segment : 26 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0007061958312988281 length of segment : 25 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 1821 time to create 1 rle with old method : 0.0023109912872314453 length of segment : 129 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.00029659271240234375 length of segment : 17 time for calcul the mask position with numpy : 0.00011229515075683594 nb_pixel_total : 2236 time to create 1 rle with old method : 0.00274658203125 length of segment : 147 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1179 time to create 1 rle with old method : 0.0015311241149902344 length of segment : 28 time for calcul the mask position with numpy : 0.00012040138244628906 nb_pixel_total : 1516 time to create 1 rle with old method : 0.0020673274993896484 length of segment : 145 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1686 time to create 1 rle with old method : 0.0023152828216552734 length of segment : 53 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1560 time to create 1 rle with old method : 0.002065896987915039 length of segment : 38 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0008325576782226562 length of segment : 32 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1462 time to create 1 rle with old method : 0.001958608627319336 length of segment : 32 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1303 time to create 1 rle with old method : 0.0017189979553222656 length of segment : 29 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1689 time to create 1 rle with old method : 0.002012014389038086 length of segment : 55 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1637 time to create 1 rle with old method : 0.002007007598876953 length of segment : 37 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00011992454528808594 nb_pixel_total : 2713 time to create 1 rle with old method : 0.0035147666931152344 length of segment : 167 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004737377166748047 length of segment : 30 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1680 time to create 1 rle with old method : 0.002184629440307617 length of segment : 81 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1672 time to create 1 rle with old method : 0.0021560192108154297 length of segment : 78 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 2689 time to create 1 rle with old method : 0.003362417221069336 length of segment : 182 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 680 time to create 1 rle with old method : 0.0009038448333740234 length of segment : 52 time for calcul the mask position with numpy : 0.00017714500427246094 nb_pixel_total : 4038 time to create 1 rle with old method : 0.00519251823425293 length of segment : 123 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1045 time to create 1 rle with old method : 0.0013859272003173828 length of segment : 48 Processing 1 images image shape: (280, 400, 3) min: 16.00000 max: 225.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 94.03594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009434223175048828 nb_pixel_total : 107105 time to create 1 rle with old method : 0.12105774879455566 length of segment : 279 Processing 1 images image shape: (280, 400, 3) min: 1.00000 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 : 4 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1418 time to create 1 rle with old method : 0.0018286705017089844 length of segment : 53 time for calcul the mask position with numpy : 0.00010561943054199219 nb_pixel_total : 5315 time to create 1 rle with old method : 0.006714582443237305 length of segment : 137 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 138 time to create 1 rle with old method : 0.0002167224884033203 length of segment : 17 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004413127899169922 length of segment : 18 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0007121562957763672 length of segment : 36 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0006456375122070312 length of segment : 25 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00037598609924316406 length of segment : 20 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007579326629638672 length of segment : 26 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0004937648773193359 length of segment : 22 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0008032321929931641 length of segment : 36 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0006723403930664062 length of segment : 31 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.0004775524139404297 length of segment : 21 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1370 time to create 1 rle with old method : 0.0017545223236083984 length of segment : 54 time for calcul the mask position with numpy : 2.7894973754882812e-05 nb_pixel_total : 38 time to create 1 rle with old method : 8.821487426757812e-05 length of segment : 7 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0008270740509033203 length of segment : 32 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0007102489471435547 length of segment : 25 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.0008332729339599609 length of segment : 34 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001723766326904297 length of segment : 10 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0005278587341308594 length of segment : 15 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.00048279762268066406 length of segment : 26 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005245208740234375 length of segment : 22 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003063678741455078 length of segment : 23 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0008053779602050781 length of segment : 31 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.001178741455078125 length of segment : 34 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003428459167480469 length of segment : 16 2025-02-05 02:20:51.533725: F ./tensorflow/core/kernels/conv_2d_gpu.h:453] Non-OK-status: GpuLaunchKernel(ShuffleInTensor3Simple, config.block_count, config.thread_per_block, 0, d.stream(), config.virtual_thread_count, in.data(), combined_dims, out.data()) status: Internal: an illegal memory access was encountered max_time_sub_proc : 3600 Catched exception ! Connect or reconnect ! in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 20.85user 16.77system 1:00:07elapsed 1%CPU (0avgtext+0avgdata 2522940maxresident)k 117208inputs+3024outputs (10128major+652210minor)pagefaults 0swaps