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 : 2003125 load datou : 4234 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2603702'] with mtr_portfolio_ids : ['20718229'] and first list_photo_ids : [] new path : /proc/2003125/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.3856544494628906 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 Fri Feb 21 09:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 3000 l 3632 free memory gpu now : 1944 wait 20 seconds l 3637 free memory gpu now : 1944 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-21 09:20:51.406557: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-21 09:20:51.431106: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-21 09:20:51.433070: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7efc58000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-21 09:20:51.433104: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-21 09:20:51.437947: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-21 09:20:51.584828: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2a7f62f0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-21 09:20:51.584878: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-21 09:20:51.585930: 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 2025-02-21 09:20:51.586506: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-21 09:20:51.589601: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-21 09:20:51.592438: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-21 09:20:51.592946: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-21 09:20:51.596188: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-21 09:20:51.597515: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-21 09:20:51.602624: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-21 09:20:51.603579: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-21 09:20:51.603649: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-21 09:20:51.604156: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-21 09:20:51.604171: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-21 09:20:51.604180: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-21 09:20:51.605024: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1567 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. 2025-02-21 09:20:51.898205: 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 2025-02-21 09:20:51.898322: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-21 09:20:51.898360: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-21 09:20:51.898395: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-21 09:20:51.898429: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-21 09:20:51.898462: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-21 09:20:51.898523: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-21 09:20:51.898557: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-21 09:20:51.899727: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-21 09:20:51.900838: 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 2025-02-21 09:20:51.900903: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-21 09:20:51.900925: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-21 09:20:51.900943: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-21 09:20:51.900961: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-21 09:20:51.900984: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-21 09:20:51.901001: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-21 09:20:51.901018: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-21 09:20:51.901929: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-21 09:20:51.901961: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-21 09:20:51.901972: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-21 09:20:51.901981: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-21 09:20:51.902963: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1567 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 : [] 2025-02-21 09:20:59.467034: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-21 09:20:59.681047: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-21 09:21:00.900569: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:00.900618: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:00.907044: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:00.907066: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:00.955713: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:00.955753: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:00.999155: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:00.999206: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:01.044277: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:01.044330: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 09:21:01.071591: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-02-21 09:21:01.088609: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.00G (1073741824 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.089615: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 921.60M (966367744 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.090608: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 829.44M (869731072 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.091893: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 746.50M (782758144 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.255170: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-02-21 09:21:01.272687: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.273727: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.278693: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.279411: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.284447: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.285011: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.297045: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.297574: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.301647: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.302169: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.302934: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.303495: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.314105: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.314700: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.315313: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.315868: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.316423: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.316936: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.382318: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.383336: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.392891: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.394011: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.411478: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.413359: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.414353: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.415348: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.419816: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.420398: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.420949: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.421498: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.422506: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.422524: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-02-21 09:21:01.432810: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.433370: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.442401: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.442999: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.443566: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.444134: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.444692: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 09:21:01.445242: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.03G (1108213760 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 2 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.74297 max: 149.42031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 876 time to create 1 rle with old method : 0.0016620159149169922 length of segment : 31 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 761 time to create 1 rle with old method : 0.0014200210571289062 length of segment : 32 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00037932395935058594 length of segment : 21 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.00018739700317382812 length of segment : 36 length of segment : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.94609 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 : 0.00015854835510253906 nb_pixel_total : 3958 time to create 1 rle with old method : 0.004936933517456055 length of segment : 191 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 2667 time to create 1 rle with old method : 0.0034177303314208984 length of segment : 55 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 937 time to create 1 rle with old method : 0.001272439956665039 length of segment : 68 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 742 time to create 1 rle with old method : 0.0009846687316894531 length of segment : 45 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 2604 time to create 1 rle with old method : 0.0033745765686035156 length of segment : 87 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.39922 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 : 8.702278137207031e-05 nb_pixel_total : 2732 time to create 1 rle with old method : 0.0035037994384765625 length of segment : 106 time for calcul the mask position with numpy : 0.0004000663757324219 nb_pixel_total : 19601 time to create 1 rle with old method : 0.026972532272338867 length of segment : 206 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.001092672348022461 length of segment : 80 time for calcul the mask position with numpy : 0.00012421607971191406 nb_pixel_total : 5011 time to create 1 rle with old method : 0.006407260894775391 length of segment : 115 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 2641 time to create 1 rle with old method : 0.003387928009033203 length of segment : 99 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.87578 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 : 5.1975250244140625e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.001039266586303711 length of segment : 27 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 67 time to create 1 rle with old method : 0.00016736984252929688 length of segment : 11 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00023627281188964844 length of segment : 17 time for calcul the mask position with numpy : 0.00017023086547851562 nb_pixel_total : 8239 time to create 1 rle with old method : 0.015496969223022461 length of segment : 128 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1037 time to create 1 rle with old method : 0.0013566017150878906 length of segment : 40 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004513263702392578 length of segment : 30 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.000362396240234375 length of segment : 32 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 233.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 111.94766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 570 time to create 1 rle with old method : 0.0008327960968017578 length of segment : 20 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 3562 time to create 1 rle with old method : 0.004475116729736328 length of segment : 89 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00019931793212890625 length of segment : 12 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 4150 time to create 1 rle with old method : 0.005307674407958984 length of segment : 84 time for calcul the mask position with numpy : 0.0006010532379150391 nb_pixel_total : 55778 time to create 1 rle with old method : 0.06603574752807617 length of segment : 269 time for calcul the mask position with numpy : 0.0007722377777099609 nb_pixel_total : 67731 time to create 1 rle with old method : 0.07818818092346191 length of segment : 300 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 181.00000 molded_images shape: (1, 640, 640, 3) min: -96.61406 max: 64.49062 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: -120.45000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 25 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.00016951560974121094 length of segment : 17 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.00031185150146484375 length of segment : 25 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00040435791015625 length of segment : 24 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.0008437633514404297 length of segment : 17 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 54 time to create 1 rle with old method : 0.00010442733764648438 length of segment : 18 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0006330013275146484 length of segment : 27 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002493858337402344 length of segment : 12 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0008158683776855469 length of segment : 27 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 872 time to create 1 rle with old method : 0.0012934207916259766 length of segment : 26 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 586 time to create 1 rle with old method : 0.0008070468902587891 length of segment : 39 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0009772777557373047 length of segment : 25 time for calcul the mask position with numpy : 0.00022459030151367188 nb_pixel_total : 10315 time to create 1 rle with old method : 0.013158082962036133 length of segment : 167 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0005137920379638672 length of segment : 22 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006527900695800781 length of segment : 17 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 2836 time to create 1 rle with old method : 0.0036542415618896484 length of segment : 56 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0009632110595703125 length of segment : 31 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003154277801513672 length of segment : 17 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 661 time to create 1 rle with old method : 0.0010066032409667969 length of segment : 29 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 852 time to create 1 rle with old method : 0.0015327930450439453 length of segment : 22 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00023651123046875 length of segment : 17 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00030803680419921875 length of segment : 16 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 712 time to create 1 rle with old method : 0.0009598731994628906 length of segment : 33 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0003151893615722656 length of segment : 15 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.0003063678741455078 length of segment : 23 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003228187561035156 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.75859 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 1155 time to create 1 rle with old method : 0.0023660659790039062 length of segment : 42 time for calcul the mask position with numpy : 0.00010919570922851562 nb_pixel_total : 1985 time to create 1 rle with old method : 0.003791332244873047 length of segment : 54 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0006730556488037109 length of segment : 23 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0008633136749267578 length of segment : 18 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 807 time to create 1 rle with old method : 0.001415252685546875 length of segment : 34 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0008137226104736328 length of segment : 36 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003261566162109375 length of segment : 26 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0008051395416259766 length of segment : 30 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0006036758422851562 length of segment : 20 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.0007538795471191406 length of segment : 22 time for calcul the mask position with numpy : 0.00012946128845214844 nb_pixel_total : 3990 time to create 1 rle with old method : 0.00501251220703125 length of segment : 99 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0006723403930664062 length of segment : 32 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0006268024444580078 length of segment : 36 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 768 time to create 1 rle with old method : 0.0009441375732421875 length of segment : 33 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0008373260498046875 length of segment : 22 time for calcul the mask position with numpy : 2.8133392333984375e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.0002231597900390625 length of segment : 13 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00025081634521484375 length of segment : 19 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1262 time to create 1 rle with old method : 0.001499176025390625 length of segment : 58 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00037860870361328125 length of segment : 16 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1431 time to create 1 rle with old method : 0.001863241195678711 length of segment : 63 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006556510925292969 length of segment : 24 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0007257461547851562 length of segment : 31 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0007076263427734375 length of segment : 37 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0006198883056640625 length of segment : 21 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0004093647003173828 length of segment : 17 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0004467964172363281 length of segment : 11 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00022077560424804688 length of segment : 18 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007708072662353516 length of segment : 24 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 703 time to create 1 rle with old method : 0.0008566379547119141 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.84063 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 : 5.030632019042969e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0004889965057373047 length of segment : 18 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0004892349243164062 length of segment : 12 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0014772415161132812 length of segment : 39 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0010006427764892578 length of segment : 79 time for calcul the mask position with numpy : 0.00023174285888671875 nb_pixel_total : 13764 time to create 1 rle with old method : 0.017002344131469727 length of segment : 267 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1360 time to create 1 rle with old method : 0.0018475055694580078 length of segment : 48 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 1715 time to create 1 rle with old method : 0.0021288394927978516 length of segment : 117 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 243.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 122.65469 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 1815 time to create 1 rle with old method : 0.003347158432006836 length of segment : 146 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 2320 time to create 1 rle with old method : 0.0030188560485839844 length of segment : 147 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.0010807514190673828 length of segment : 73 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1951 time to create 1 rle with old method : 0.002680063247680664 length of segment : 47 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1865 time to create 1 rle with old method : 0.002457141876220703 length of segment : 44 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1508 time to create 1 rle with old method : 0.0019762516021728516 length of segment : 70 time for calcul the mask position with numpy : 0.00021338462829589844 nb_pixel_total : 4855 time to create 1 rle with old method : 0.006030082702636719 length of segment : 234 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 184.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 58.35781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008723735809326172 nb_pixel_total : 106071 time to create 1 rle with old method : 0.11718225479125977 length of segment : 281 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 : 25 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 2053 time to create 1 rle with old method : 0.0025467872619628906 length of segment : 46 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 3480 time to create 1 rle with old method : 0.004045724868774414 length of segment : 73 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.00037407875061035156 length of segment : 35 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.000476837158203125 length of segment : 30 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 662 time to create 1 rle with old method : 0.0008955001831054688 length of segment : 35 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0010273456573486328 length of segment : 36 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 864 time to create 1 rle with old method : 0.00113677978515625 length of segment : 27 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0005514621734619141 length of segment : 25 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0005218982696533203 length of segment : 22 time for calcul the mask position with numpy : 0.00042819976806640625 nb_pixel_total : 29732 time to create 1 rle with old method : 0.03413987159729004 length of segment : 182 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0006206035614013672 length of segment : 41 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.000400543212890625 length of segment : 19 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0012001991271972656 length of segment : 56 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0008728504180908203 length of segment : 60 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00026869773864746094 length of segment : 23 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004303455352783203 length of segment : 30 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0004589557647705078 length of segment : 36 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004801750183105469 length of segment : 42 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 979 time to create 1 rle with old method : 0.0013632774353027344 length of segment : 39 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 681 time to create 1 rle with old method : 0.0007750988006591797 length of segment : 50 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1084 time to create 1 rle with old method : 0.001621246337890625 length of segment : 48 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005686283111572266 length of segment : 32 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0006105899810791016 length of segment : 27 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006012916564941406 length of segment : 28 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1115 time to create 1 rle with old method : 0.0015192031860351562 length of segment : 51 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: 150.05703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 38 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 2555 time to create 1 rle with old method : 0.003065347671508789 length of segment : 57 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.00025773048400878906 length of segment : 38 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 668 time to create 1 rle with old method : 0.0008985996246337891 length of segment : 35 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.00027251243591308594 length of segment : 17 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1645 time to create 1 rle with old method : 0.002130270004272461 length of segment : 49 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00039768218994140625 length of segment : 20 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1224 time to create 1 rle with old method : 0.0016009807586669922 length of segment : 55 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1227 time to create 1 rle with old method : 0.0016062259674072266 length of segment : 53 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1176 time to create 1 rle with old method : 0.0016205310821533203 length of segment : 50 time for calcul the mask position with numpy : 0.00013017654418945312 nb_pixel_total : 5196 time to create 1 rle with old method : 0.006711006164550781 length of segment : 201 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0008597373962402344 length of segment : 36 time for calcul the mask position with numpy : 0.00011324882507324219 nb_pixel_total : 4168 time to create 1 rle with old method : 0.00501704216003418 length of segment : 137 time for calcul the mask position with numpy : 0.00011086463928222656 nb_pixel_total : 1962 time to create 1 rle with old method : 0.002621889114379883 length of segment : 87 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0005078315734863281 length of segment : 23 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.00022673606872558594 length of segment : 10 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002980232238769531 length of segment : 24 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.00022721290588378906 length of segment : 14 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006279945373535156 length of segment : 42 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004508495330810547 length of segment : 30 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003209114074707031 length of segment : 23 time for calcul the mask position with numpy : 2.6464462280273438e-05 nb_pixel_total : 45 time to create 1 rle with old method : 6.985664367675781e-05 length of segment : 19 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 816 time to create 1 rle with old method : 0.0010025501251220703 length of segment : 71 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0006237030029296875 length of segment : 31 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 1972 time to create 1 rle with old method : 0.002386808395385742 length of segment : 59 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0008275508880615234 length of segment : 36 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0009310245513916016 length of segment : 29 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0006928443908691406 length of segment : 41 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1013 time to create 1 rle with old method : 0.0012545585632324219 length of segment : 49 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006463527679443359 length of segment : 28 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1970 time to create 1 rle with old method : 0.0025637149810791016 length of segment : 60 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005955696105957031 length of segment : 19 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.00047135353088378906 length of segment : 29 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00036835670471191406 length of segment : 20 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 889 time to create 1 rle with old method : 0.0011262893676757812 length of segment : 59 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0005488395690917969 length of segment : 13 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 1142 time to create 1 rle with old method : 0.0013878345489501953 length of segment : 46 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2659 time to create 1 rle with old method : 0.003117084503173828 length of segment : 66 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.0005071163177490234 length of segment : 21 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: 145.87344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0006134510040283203 length of segment : 27 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0005774497985839844 length of segment : 30 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 640 time to create 1 rle with old method : 0.0008833408355712891 length of segment : 29 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 2523 time to create 1 rle with old method : 0.0032682418823242188 length of segment : 64 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005826950073242188 length of segment : 22 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.00042557716369628906 length of segment : 28 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.00028014183044433594 length of segment : 22 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 480 time to create 1 rle with old method : 0.0006430149078369141 length of segment : 36 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0004057884216308594 length of segment : 16 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.00040435791015625 length of segment : 25 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0004572868347167969 nb_pixel_total : 44886 time to create 1 rle with old method : 0.05751681327819824 length of segment : 243 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: -118.44609 max: 149.29531 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 : 113 time to create 1 rle with old method : 0.0001976490020751953 length of segment : 11 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 790 time to create 1 rle with old method : 0.001138448715209961 length of segment : 37 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 755 time to create 1 rle with old method : 0.0011179447174072266 length of segment : 34 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.00024771690368652344 length of segment : 33 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00014925003051757812 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.94219 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 : 5.745887756347656e-05 nb_pixel_total : 876 time to create 1 rle with old method : 0.001138925552368164 length of segment : 40 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 2665 time to create 1 rle with old method : 0.003544330596923828 length of segment : 52 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0008831024169921875 length of segment : 84 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1170 time to create 1 rle with old method : 0.001556396484375 length of segment : 76 time for calcul the mask position with numpy : 0.00018286705017089844 nb_pixel_total : 1153 time to create 1 rle with old method : 0.0015344619750976562 length of segment : 88 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00012826919555664062 length of segment : 22 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 2977 time to create 1 rle with old method : 0.003789186477661133 length of segment : 57 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.80938 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 : 0.00011658668518066406 nb_pixel_total : 5423 time to create 1 rle with old method : 0.00682520866394043 length of segment : 101 time for calcul the mask position with numpy : 0.00014662742614746094 nb_pixel_total : 3032 time to create 1 rle with old method : 0.003860950469970703 length of segment : 115 time for calcul the mask position with numpy : 0.0001316070556640625 nb_pixel_total : 6079 time to create 1 rle with old method : 0.007576942443847656 length of segment : 117 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0007503032684326172 length of segment : 20 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 988 time to create 1 rle with old method : 0.0012819766998291016 length of segment : 46 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 2687 time to create 1 rle with old method : 0.0034906864166259766 length of segment : 97 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.87578 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 : 4.673004150390625e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0007147789001464844 length of segment : 26 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002830028533935547 length of segment : 17 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 1056 time to create 1 rle with old method : 0.0013179779052734375 length of segment : 42 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00015854835510253906 length of segment : 16 time for calcul the mask position with numpy : 0.0001442432403564453 nb_pixel_total : 9078 time to create 1 rle with old method : 0.011029720306396484 length of segment : 127 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 237.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 114.13516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 3317 time to create 1 rle with old method : 0.004073619842529297 length of segment : 93 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0007345676422119141 length of segment : 21 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0002694129943847656 length of segment : 10 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 953 time to create 1 rle with old method : 0.0012235641479492188 length of segment : 119 time for calcul the mask position with numpy : 0.0006132125854492188 nb_pixel_total : 61798 time to create 1 rle with old method : 0.07129836082458496 length of segment : 379 time for calcul the mask position with numpy : 0.0006618499755859375 nb_pixel_total : 58536 time to create 1 rle with old method : 0.07219624519348145 length of segment : 290 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 184.00000 molded_images shape: (1, 640, 640, 3) min: -94.18828 max: 66.24062 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: -120.45000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001761913299560547 length of segment : 16 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005044937133789062 length of segment : 32 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.0003509521484375 length of segment : 26 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0003159046173095703 length of segment : 18 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 962 time to create 1 rle with old method : 0.001428842544555664 length of segment : 24 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0006387233734130859 length of segment : 17 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.00047779083251953125 length of segment : 18 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 65 time to create 1 rle with old method : 0.00011420249938964844 length of segment : 13 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002574920654296875 length of segment : 12 time for calcul the mask position with numpy : 0.00028133392333984375 nb_pixel_total : 14043 time to create 1 rle with old method : 0.016914844512939453 length of segment : 245 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.00016689300537109375 length of segment : 11 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 3152 time to create 1 rle with old method : 0.004006385803222656 length of segment : 52 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 569 time to create 1 rle with old method : 0.0008475780487060547 length of segment : 19 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.0001652240753173828 length of segment : 11 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 784 time to create 1 rle with old method : 0.0010609626770019531 length of segment : 35 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 860 time to create 1 rle with old method : 0.0011799335479736328 length of segment : 18 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 607 time to create 1 rle with old method : 0.0008485317230224609 length of segment : 31 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.0008282661437988281 length of segment : 38 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.00041675567626953125 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.57109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 28 time for calcul the mask position with numpy : 0.00010371208190917969 nb_pixel_total : 2154 time to create 1 rle with old method : 0.0026900768280029297 length of segment : 67 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 680 time to create 1 rle with old method : 0.0009930133819580078 length of segment : 40 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 649 time to create 1 rle with old method : 0.0009229183197021484 length of segment : 33 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003783702850341797 length of segment : 26 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0007028579711914062 length of segment : 32 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 429 time to create 1 rle with old method : 0.000675201416015625 length of segment : 16 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0007772445678710938 length of segment : 22 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 825 time to create 1 rle with old method : 0.0011680126190185547 length of segment : 32 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.0002186298370361328 length of segment : 16 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1097 time to create 1 rle with old method : 0.001497030258178711 length of segment : 39 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0004119873046875 length of segment : 24 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004885196685791016 length of segment : 17 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0009908676147460938 length of segment : 46 time for calcul the mask position with numpy : 0.0001728534698486328 nb_pixel_total : 4131 time to create 1 rle with old method : 0.005265235900878906 length of segment : 105 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003387928009033203 length of segment : 17 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1089 time to create 1 rle with old method : 0.0014865398406982422 length of segment : 41 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 756 time to create 1 rle with old method : 0.0010237693786621094 length of segment : 33 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.00020194053649902344 length of segment : 14 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0006012916564941406 length of segment : 22 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.0005218982696533203 length of segment : 18 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1255 time to create 1 rle with old method : 0.0015916824340820312 length of segment : 48 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.000743865966796875 length of segment : 27 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1477 time to create 1 rle with old method : 0.002039670944213867 length of segment : 47 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.0009465217590332031 length of segment : 30 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0008103847503662109 length of segment : 20 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 1281 time to create 1 rle with old method : 0.0017817020416259766 length of segment : 46 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0009713172912597656 length of segment : 24 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0007555484771728516 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: -122.03594 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 : 4.38690185546875e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0005571842193603516 length of segment : 18 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0004909038543701172 length of segment : 13 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 1029 time to create 1 rle with old method : 0.0013384819030761719 length of segment : 35 time for calcul the mask position with numpy : 0.00021576881408691406 nb_pixel_total : 13871 time to create 1 rle with old method : 0.015821218490600586 length of segment : 270 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 1732 time to create 1 rle with old method : 0.0020761489868164062 length of segment : 122 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 752 time to create 1 rle with old method : 0.0010645389556884766 length of segment : 20 time for calcul the mask position with numpy : 0.0002627372741699219 nb_pixel_total : 9155 time to create 1 rle with old method : 0.011424064636230469 length of segment : 193 time for calcul the mask position with numpy : 0.00026106834411621094 nb_pixel_total : 8485 time to create 1 rle with old method : 0.009990215301513672 length of segment : 188 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 243.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 122.76797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1314 time to create 1 rle with old method : 0.0018000602722167969 length of segment : 138 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 956 time to create 1 rle with old method : 0.0012781620025634766 length of segment : 52 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 876 time to create 1 rle with old method : 0.0012888908386230469 length of segment : 56 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 60 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1595 time to create 1 rle with old method : 0.002076864242553711 length of segment : 131 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1831 time to create 1 rle with old method : 0.002312183380126953 length of segment : 43 Processing 1 images image shape: (280, 400, 3) min: 6.00000 max: 189.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 60.80312 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009377002716064453 nb_pixel_total : 105718 time to create 1 rle with old method : 0.11430668830871582 length of segment : 281 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 : 8.678436279296875e-05 nb_pixel_total : 2313 time to create 1 rle with old method : 0.0029594898223876953 length of segment : 64 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.00037598609924316406 length of segment : 32 time for calcul the mask position with numpy : 0.00010704994201660156 nb_pixel_total : 3939 time to create 1 rle with old method : 0.0056264400482177734 length of segment : 79 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00042247772216796875 length of segment : 18 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.0009410381317138672 length of segment : 32 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1334 time to create 1 rle with old method : 0.0016417503356933594 length of segment : 77 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 38 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0008032321929931641 length of segment : 49 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.00026798248291015625 length of segment : 28 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005891323089599609 length of segment : 32 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 607 time to create 1 rle with old method : 0.0008399486541748047 length of segment : 45 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0003046989440917969 length of segment : 21 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004112720489501953 length of segment : 24 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004780292510986328 length of segment : 29 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 859 time to create 1 rle with old method : 0.0012047290802001953 length of segment : 26 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0009264945983886719 length of segment : 34 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005071163177490234 length of segment : 36 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0004782676696777344 length of segment : 39 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006291866302490234 length of segment : 28 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005125999450683594 length of segment : 31 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005218982696533203 length of segment : 35 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0005946159362792969 length of segment : 26 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: 150.12734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 37 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 2482 time to create 1 rle with old method : 0.0030388832092285156 length of segment : 57 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.00024247169494628906 length of segment : 18 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 992 time to create 1 rle with old method : 0.0013170242309570312 length of segment : 46 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 2362 time to create 1 rle with old method : 0.0030531883239746094 length of segment : 94 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1605 time to create 1 rle with old method : 0.0020422935485839844 length of segment : 58 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1876 time to create 1 rle with old method : 0.002348184585571289 length of segment : 58 time for calcul the mask position with numpy : 0.00011539459228515625 nb_pixel_total : 5581 time to create 1 rle with old method : 0.006979227066040039 length of segment : 83 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 973 time to create 1 rle with old method : 0.0012905597686767578 length of segment : 44 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.00022363662719726562 length of segment : 35 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 987 time to create 1 rle with old method : 0.0013580322265625 length of segment : 48 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00023698806762695312 length of segment : 10 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0008363723754882812 length of segment : 34 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 986 time to create 1 rle with old method : 0.001318216323852539 length of segment : 69 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0004987716674804688 length of segment : 24 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 805 time to create 1 rle with old method : 0.001013040542602539 length of segment : 67 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.00030517578125 length of segment : 25 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0004353523254394531 length of segment : 26 time for calcul the mask position with numpy : 0.0001316070556640625 nb_pixel_total : 5786 time to create 1 rle with old method : 0.008837461471557617 length of segment : 191 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.0008537769317626953 length of segment : 33 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002956390380859375 length of segment : 17 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00023245811462402344 length of segment : 13 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.00032639503479003906 length of segment : 17 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0007040500640869141 length of segment : 28 time for calcul the mask position with numpy : 2.8133392333984375e-05 nb_pixel_total : 57 time to create 1 rle with old method : 8.869171142578125e-05 length of segment : 20 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0005488395690917969 length of segment : 18 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 723 time to create 1 rle with old method : 0.0009391307830810547 length of segment : 37 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.0010120868682861328 length of segment : 44 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.00033926963806152344 length of segment : 22 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0006291866302490234 length of segment : 14 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.00030541419982910156 length of segment : 16 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.00029921531677246094 length of segment : 23 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 2168 time to create 1 rle with old method : 0.0026602745056152344 length of segment : 91 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 561 time to create 1 rle with old method : 0.0007486343383789062 length of segment : 34 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0005199909210205078 length of segment : 26 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0006182193756103516 length of segment : 28 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0018267631530761719 length of segment : 112 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.00024271011352539062 length of segment : 13 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: 145.22109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0004773139953613281 length of segment : 23 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 682 time to create 1 rle with old method : 0.0008921623229980469 length of segment : 30 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0005996227264404297 length of segment : 30 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 3761 time to create 1 rle with old method : 0.004580020904541016 length of segment : 65 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 56 time to create 1 rle with old method : 0.00011920928955078125 length of segment : 17 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006542205810546875 length of segment : 26 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0006723403930664062 length of segment : 27 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004353523254394531 length of segment : 17 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 577 time to create 1 rle with old method : 0.0007810592651367188 length of segment : 50 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001957416534423828 length of segment : 27 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.0005578994750976562 length of segment : 19 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00043773651123046875 length of segment : 26 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0008823871612548828 length of segment : 37 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0004858970642089844 length of segment : 26 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: 135.53750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.0004918575286865234 nb_pixel_total : 43087 time to create 1 rle with old method : 0.047402143478393555 length of segment : 236 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.00032711029052734375 length of segment : 35 Detection mask done ! Trying to reset tf kernel 2004343 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 751 tf kernel not reseted sub process len(results) : 337 len(list_Values) 337 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 337 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2165 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Catched exception ! Connect or reconnect ! Number saved : None batch 1 Loaded 337 chid ids of type : 4228 Number RLEs to save : 17350 save missing photos in datou_result : time spend for datou_step_exec : 43.37565588951111 time spend to save output : 8.714058637619019 total time spend for step 1 : 52.08971452713013 step2:brightness Fri Feb 21 09:21:20 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1740126028_2003125_1338695305_d3bf701ba77784b9055260041fcbe51b.jpg treat image : temp/1740126028_2003125_1338695302_24a195f6d20c5904a9b4bff5300e14b9.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 2 time used for this insertion : 0.015849828720092773 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.015009164810180664 save missing photos in datou_result : time spend for datou_step_exec : 0.5271358489990234 time spend to save output : 0.03708291053771973 total time spend for step 2 : 0.5642187595367432 step3:blur_detection Fri Feb 21 09:21:21 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1740126028_2003125_1338695305_d3bf701ba77784b9055260041fcbe51b.jpg resize: (1080, 1920) 1338695305 -7.486367152238917 treat image : temp/1740126028_2003125_1338695302_24a195f6d20c5904a9b4bff5300e14b9.jpg resize: (1080, 1920) 1338695302 -7.480693710060397 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 2 time used for this insertion : 0.01514291763305664 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.01551508903503418 save missing photos in datou_result : time spend for datou_step_exec : 1.622251272201538 time spend to save output : 0.03522181510925293 total time spend for step 3 : 1.657473087310791 step4:rle_unique_nms_with_priority Fri Feb 21 09:21:23 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 337 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 170 nb_hashtags : 8 time to prepare the origin masks : 1.2625412940979004 time for calcul the mask position with numpy : 0.02770709991455078 nb_pixel_total : 1644504 time to create 1 rle with new method : 0.37778759002685547 time for calcul the mask position with numpy : 0.008378982543945312 nb_pixel_total : 19601 time to create 1 rle with old method : 0.020872116088867188 time for calcul the mask position with numpy : 0.008159399032592773 nb_pixel_total : 4389 time to create 1 rle with old method : 0.006238222122192383 time for calcul the mask position with numpy : 0.010222434997558594 nb_pixel_total : 18532 time to create 1 rle with old method : 0.020558595657348633 time for calcul the mask position with numpy : 0.009074211120605469 nb_pixel_total : 641 time to create 1 rle with old method : 0.0010101795196533203 time for calcul the mask position with numpy : 0.009897470474243164 nb_pixel_total : 74 time to create 1 rle with old method : 9.775161743164062e-05 time for calcul the mask position with numpy : 0.008467435836791992 nb_pixel_total : 876 time to create 1 rle with old method : 0.0014734268188476562 time for calcul the mask position with numpy : 0.00960087776184082 nb_pixel_total : 166 time to create 1 rle with old method : 0.0003032684326171875 time for calcul the mask position with numpy : 0.009671211242675781 nb_pixel_total : 32 time to create 1 rle with old method : 0.00010800361633300781 time for calcul the mask position with numpy : 0.009704113006591797 nb_pixel_total : 2667 time to create 1 rle with old method : 0.003219127655029297 time for calcul the mask position with numpy : 0.00884246826171875 nb_pixel_total : 55778 time to create 1 rle with old method : 0.06168055534362793 time for calcul the mask position with numpy : 0.008417606353759766 nb_pixel_total : 937 time to create 1 rle with old method : 0.001111745834350586 time for calcul the mask position with numpy : 0.008338451385498047 nb_pixel_total : 3958 time to create 1 rle with old method : 0.004487276077270508 time for calcul the mask position with numpy : 0.008398294448852539 nb_pixel_total : 298 time to create 1 rle with old method : 0.00034928321838378906 time for calcul the mask position with numpy : 0.00840616226196289 nb_pixel_total : 742 time to create 1 rle with old method : 0.0008318424224853516 time for calcul the mask position with numpy : 0.008387088775634766 nb_pixel_total : 258 time to create 1 rle with old method : 0.00030422210693359375 time for calcul the mask position with numpy : 0.008374691009521484 nb_pixel_total : 2604 time to create 1 rle with old method : 0.0029249191284179688 time for calcul the mask position with numpy : 0.00839853286743164 nb_pixel_total : 483 time to create 1 rle with old method : 0.0005786418914794922 time for calcul the mask position with numpy : 0.008399724960327148 nb_pixel_total : 2732 time to create 1 rle with old method : 0.00310516357421875 time for calcul the mask position with numpy : 0.008306026458740234 nb_pixel_total : 874 time to create 1 rle with old method : 0.0009944438934326172 time for calcul the mask position with numpy : 0.00841212272644043 nb_pixel_total : 8239 time to create 1 rle with old method : 0.009796857833862305 time for calcul the mask position with numpy : 0.008980751037597656 nb_pixel_total : 113 time to create 1 rle with old method : 0.00014591217041015625 time for calcul the mask position with numpy : 0.0086822509765625 nb_pixel_total : 67 time to create 1 rle with old method : 8.893013000488281e-05 time for calcul the mask position with numpy : 0.008473396301269531 nb_pixel_total : 435 time to create 1 rle with old method : 0.0006260871887207031 time for calcul the mask position with numpy : 0.00839543342590332 nb_pixel_total : 3531 time to create 1 rle with old method : 0.0038118362426757812 time for calcul the mask position with numpy : 0.008667230606079102 nb_pixel_total : 1037 time to create 1 rle with old method : 0.0012156963348388672 time for calcul the mask position with numpy : 0.008335351943969727 nb_pixel_total : 570 time to create 1 rle with old method : 0.0006961822509765625 time for calcul the mask position with numpy : 0.008739233016967773 nb_pixel_total : 107 time to create 1 rle with old method : 0.00013566017150878906 time for calcul the mask position with numpy : 0.008414030075073242 nb_pixel_total : 248 time to create 1 rle with old method : 0.00028443336486816406 time for calcul the mask position with numpy : 0.008161783218383789 nb_pixel_total : 796 time to create 1 rle with old method : 0.0009090900421142578 time for calcul the mask position with numpy : 0.008350133895874023 nb_pixel_total : 13764 time to create 1 rle with old method : 0.016084671020507812 time for calcul the mask position with numpy : 0.008343696594238281 nb_pixel_total : 35 time to create 1 rle with old method : 6.937980651855469e-05 time for calcul the mask position with numpy : 0.008345365524291992 nb_pixel_total : 768 time to create 1 rle with old method : 0.0008826255798339844 time for calcul the mask position with numpy : 0.008488655090332031 nb_pixel_total : 3990 time to create 1 rle with old method : 0.004529237747192383 time for calcul the mask position with numpy : 0.008406639099121094 nb_pixel_total : 586 time to create 1 rle with old method : 0.0006678104400634766 time for calcul the mask position with numpy : 0.008414268493652344 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0012454986572265625 time for calcul the mask position with numpy : 0.008394241333007812 nb_pixel_total : 1951 time to create 1 rle with old method : 0.0022125244140625 time for calcul the mask position with numpy : 0.008397340774536133 nb_pixel_total : 13 time to create 1 rle with old method : 6.389617919921875e-05 time for calcul the mask position with numpy : 0.00840902328491211 nb_pixel_total : 322 time to create 1 rle with old method : 0.0003809928894042969 time for calcul the mask position with numpy : 0.008383750915527344 nb_pixel_total : 9698 time to create 1 rle with old method : 0.01076197624206543 time for calcul the mask position with numpy : 0.008410215377807617 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002772808074951172 time for calcul the mask position with numpy : 0.008424997329711914 nb_pixel_total : 255 time to create 1 rle with old method : 0.0003314018249511719 time for calcul the mask position with numpy : 0.00837850570678711 nb_pixel_total : 1815 time to create 1 rle with old method : 0.002088785171508789 time for calcul the mask position with numpy : 0.008531808853149414 nb_pixel_total : 630 time to create 1 rle with old method : 0.000980377197265625 time for calcul the mask position with numpy : 0.008464336395263672 nb_pixel_total : 4855 time to create 1 rle with old method : 0.0054473876953125 time for calcul the mask position with numpy : 0.008533239364624023 nb_pixel_total : 1360 time to create 1 rle with old method : 0.0015964508056640625 time for calcul the mask position with numpy : 0.00855708122253418 nb_pixel_total : 1715 time to create 1 rle with old method : 0.001968860626220703 time for calcul the mask position with numpy : 0.008600950241088867 nb_pixel_total : 385 time to create 1 rle with old method : 0.000492095947265625 time for calcul the mask position with numpy : 0.008592605590820312 nb_pixel_total : 573 time to create 1 rle with old method : 0.0006902217864990234 time for calcul the mask position with numpy : 0.008739471435546875 nb_pixel_total : 1262 time to create 1 rle with old method : 0.0021085739135742188 time for calcul the mask position with numpy : 0.009746313095092773 nb_pixel_total : 609 time to create 1 rle with old method : 0.0010361671447753906 time for calcul the mask position with numpy : 0.009763002395629883 nb_pixel_total : 474 time to create 1 rle with old method : 0.0008642673492431641 time for calcul the mask position with numpy : 0.009748697280883789 nb_pixel_total : 8 time to create 1 rle with old method : 6.389617919921875e-05 time for calcul the mask position with numpy : 0.009924650192260742 nb_pixel_total : 168 time to create 1 rle with old method : 0.0003337860107421875 time for calcul the mask position with numpy : 0.01095271110534668 nb_pixel_total : 1155 time to create 1 rle with old method : 0.0021812915802001953 time for calcul the mask position with numpy : 0.011034011840820312 nb_pixel_total : 398 time to create 1 rle with old method : 0.0007624626159667969 time for calcul the mask position with numpy : 0.0166780948638916 nb_pixel_total : 2833 time to create 1 rle with old method : 0.00468134880065918 time for calcul the mask position with numpy : 0.009620189666748047 nb_pixel_total : 489 time to create 1 rle with old method : 0.0008208751678466797 time for calcul the mask position with numpy : 0.009716033935546875 nb_pixel_total : 166 time to create 1 rle with old method : 0.0003025531768798828 time for calcul the mask position with numpy : 0.009695053100585938 nb_pixel_total : 455 time to create 1 rle with old method : 0.0007815361022949219 time for calcul the mask position with numpy : 0.011071443557739258 nb_pixel_total : 807 time to create 1 rle with old method : 0.0014452934265136719 time for calcul the mask position with numpy : 0.010914087295532227 nb_pixel_total : 20 time to create 1 rle with old method : 9.894371032714844e-05 time for calcul the mask position with numpy : 0.011304140090942383 nb_pixel_total : 1985 time to create 1 rle with old method : 0.003728628158569336 time for calcul the mask position with numpy : 0.011114835739135742 nb_pixel_total : 235 time to create 1 rle with old method : 0.00045299530029296875 time for calcul the mask position with numpy : 0.009227991104125977 nb_pixel_total : 148 time to create 1 rle with old method : 0.00018978118896484375 time for calcul the mask position with numpy : 0.008634567260742188 nb_pixel_total : 7 time to create 1 rle with old method : 6.890296936035156e-05 time for calcul the mask position with numpy : 0.00855708122253418 nb_pixel_total : 152 time to create 1 rle with old method : 0.0001957416534423828 time for calcul the mask position with numpy : 0.008541345596313477 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002541542053222656 time for calcul the mask position with numpy : 0.00850534439086914 nb_pixel_total : 565 time to create 1 rle with old method : 0.0006608963012695312 time for calcul the mask position with numpy : 0.008484601974487305 nb_pixel_total : 38 time to create 1 rle with old method : 7.009506225585938e-05 time for calcul the mask position with numpy : 0.00848841667175293 nb_pixel_total : 528 time to create 1 rle with old method : 0.0006604194641113281 time for calcul the mask position with numpy : 0.008617162704467773 nb_pixel_total : 1508 time to create 1 rle with old method : 0.0017077922821044922 time for calcul the mask position with numpy : 0.008521080017089844 nb_pixel_total : 6 time to create 1 rle with old method : 2.7179718017578125e-05 time for calcul the mask position with numpy : 0.00850820541381836 nb_pixel_total : 378 time to create 1 rle with old method : 0.00044083595275878906 time for calcul the mask position with numpy : 0.008579730987548828 nb_pixel_total : 157 time to create 1 rle with old method : 0.00020241737365722656 time for calcul the mask position with numpy : 0.008651018142700195 nb_pixel_total : 103 time to create 1 rle with old method : 0.00013566017150878906 time for calcul the mask position with numpy : 0.008569955825805664 nb_pixel_total : 446 time to create 1 rle with old method : 0.0006732940673828125 time for calcul the mask position with numpy : 0.008563518524169922 nb_pixel_total : 54 time to create 1 rle with old method : 0.00011610984802246094 time for calcul the mask position with numpy : 0.008615493774414062 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005347728729248047 time for calcul the mask position with numpy : 0.008561372756958008 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004100799560546875 time for calcul the mask position with numpy : 0.008528947830200195 nb_pixel_total : 702 time to create 1 rle with old method : 0.0008234977722167969 time for calcul the mask position with numpy : 0.008600234985351562 nb_pixel_total : 222 time to create 1 rle with old method : 0.0002682209014892578 time for calcul the mask position with numpy : 0.008564949035644531 nb_pixel_total : 9 time to create 1 rle with old method : 4.267692565917969e-05 time for calcul the mask position with numpy : 0.008736848831176758 nb_pixel_total : 1392 time to create 1 rle with old method : 0.001674652099609375 time for calcul the mask position with numpy : 0.00972747802734375 nb_pixel_total : 594 time to create 1 rle with old method : 0.0008723735809326172 time for calcul the mask position with numpy : 0.010720491409301758 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006039142608642578 time for calcul the mask position with numpy : 0.008520364761352539 nb_pixel_total : 605 time to create 1 rle with old method : 0.0007259845733642578 time for calcul the mask position with numpy : 0.008483171463012695 nb_pixel_total : 383 time to create 1 rle with old method : 0.00046563148498535156 time for calcul the mask position with numpy : 0.008598804473876953 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002560615539550781 time for calcul the mask position with numpy : 0.009195089340209961 nb_pixel_total : 712 time to create 1 rle with old method : 0.0012099742889404297 time for calcul the mask position with numpy : 0.009695768356323242 nb_pixel_total : 22 time to create 1 rle with old method : 7.295608520507812e-05 time for calcul the mask position with numpy : 0.009648561477661133 nb_pixel_total : 236 time to create 1 rle with old method : 0.00041794776916503906 time for calcul the mask position with numpy : 0.00965571403503418 nb_pixel_total : 50 time to create 1 rle with old method : 0.00016164779663085938 time for calcul the mask position with numpy : 0.009616613388061523 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004658699035644531 time for calcul the mask position with numpy : 0.009678363800048828 nb_pixel_total : 872 time to create 1 rle with old method : 0.0015180110931396484 time for calcul the mask position with numpy : 0.008652925491333008 nb_pixel_total : 562 time to create 1 rle with old method : 0.0006604194641113281 time for calcul the mask position with numpy : 0.009530782699584961 nb_pixel_total : 106071 time to create 1 rle with old method : 0.11889147758483887 time for calcul the mask position with numpy : 0.008548259735107422 nb_pixel_total : 134 time to create 1 rle with old method : 0.000171661376953125 time for calcul the mask position with numpy : 0.008431434631347656 nb_pixel_total : 2512 time to create 1 rle with old method : 0.0028769969940185547 time for calcul the mask position with numpy : 0.008592844009399414 nb_pixel_total : 164 time to create 1 rle with old method : 0.00020956993103027344 time for calcul the mask position with numpy : 0.008417129516601562 nb_pixel_total : 515 time to create 1 rle with old method : 0.0005929470062255859 time for calcul the mask position with numpy : 0.008706331253051758 nb_pixel_total : 269 time to create 1 rle with old method : 0.0004200935363769531 time for calcul the mask position with numpy : 0.009705305099487305 nb_pixel_total : 306 time to create 1 rle with old method : 0.00035953521728515625 time for calcul the mask position with numpy : 0.00854349136352539 nb_pixel_total : 322 time to create 1 rle with old method : 0.0003886222839355469 time for calcul the mask position with numpy : 0.008431673049926758 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001285076141357422 time for calcul the mask position with numpy : 0.008408784866333008 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004138946533203125 time for calcul the mask position with numpy : 0.0084991455078125 nb_pixel_total : 367 time to create 1 rle with old method : 0.00044417381286621094 time for calcul the mask position with numpy : 0.008525848388671875 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002009868621826172 time for calcul the mask position with numpy : 0.008555173873901367 nb_pixel_total : 330 time to create 1 rle with old method : 0.0003960132598876953 time for calcul the mask position with numpy : 0.008555173873901367 nb_pixel_total : 1176 time to create 1 rle with old method : 0.0013828277587890625 time for calcul the mask position with numpy : 0.008560895919799805 nb_pixel_total : 337 time to create 1 rle with old method : 0.00041937828063964844 time for calcul the mask position with numpy : 0.00850534439086914 nb_pixel_total : 19 time to create 1 rle with old method : 5.459785461425781e-05 time for calcul the mask position with numpy : 0.008443832397460938 nb_pixel_total : 525 time to create 1 rle with old method : 0.0006432533264160156 time for calcul the mask position with numpy : 0.008485555648803711 nb_pixel_total : 5196 time to create 1 rle with old method : 0.0058934688568115234 time for calcul the mask position with numpy : 0.008566856384277344 nb_pixel_total : 1227 time to create 1 rle with old method : 0.0014317035675048828 time for calcul the mask position with numpy : 0.00858163833618164 nb_pixel_total : 640 time to create 1 rle with old method : 0.0007562637329101562 time for calcul the mask position with numpy : 0.009069204330444336 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007238388061523438 time for calcul the mask position with numpy : 0.008698225021362305 nb_pixel_total : 26716 time to create 1 rle with old method : 0.02967357635498047 time for calcul the mask position with numpy : 0.008486032485961914 nb_pixel_total : 13 time to create 1 rle with old method : 3.0994415283203125e-05 time for calcul the mask position with numpy : 0.008425235748291016 nb_pixel_total : 662 time to create 1 rle with old method : 0.0007677078247070312 time for calcul the mask position with numpy : 0.008429765701293945 nb_pixel_total : 1013 time to create 1 rle with old method : 0.0011665821075439453 time for calcul the mask position with numpy : 0.008446455001831055 nb_pixel_total : 668 time to create 1 rle with old method : 0.0007708072662353516 time for calcul the mask position with numpy : 0.008567333221435547 nb_pixel_total : 44886 time to create 1 rle with old method : 0.04949831962585449 time for calcul the mask position with numpy : 0.008466243743896484 nb_pixel_total : 397 time to create 1 rle with old method : 0.0004787445068359375 time for calcul the mask position with numpy : 0.008382081985473633 nb_pixel_total : 464 time to create 1 rle with old method : 0.000530242919921875 time for calcul the mask position with numpy : 0.008388042449951172 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003178119659423828 time for calcul the mask position with numpy : 0.008393526077270508 nb_pixel_total : 177 time to create 1 rle with old method : 0.00020003318786621094 time for calcul the mask position with numpy : 0.00838017463684082 nb_pixel_total : 201 time to create 1 rle with old method : 0.00023651123046875 time for calcul the mask position with numpy : 0.008426189422607422 nb_pixel_total : 327 time to create 1 rle with old method : 0.0004057884216308594 time for calcul the mask position with numpy : 0.008403539657592773 nb_pixel_total : 2053 time to create 1 rle with old method : 0.0023565292358398438 time for calcul the mask position with numpy : 0.008409976959228516 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003452301025390625 time for calcul the mask position with numpy : 0.008440017700195312 nb_pixel_total : 239 time to create 1 rle with old method : 0.0002810955047607422 time for calcul the mask position with numpy : 0.008424997329711914 nb_pixel_total : 461 time to create 1 rle with old method : 0.0005209445953369141 time for calcul the mask position with numpy : 0.0084075927734375 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003349781036376953 time for calcul the mask position with numpy : 0.008391141891479492 nb_pixel_total : 857 time to create 1 rle with old method : 0.0009980201721191406 time for calcul the mask position with numpy : 0.008407354354858398 nb_pixel_total : 2555 time to create 1 rle with old method : 0.0029098987579345703 time for calcul the mask position with numpy : 0.008394002914428711 nb_pixel_total : 421 time to create 1 rle with old method : 0.0005054473876953125 time for calcul the mask position with numpy : 0.008400201797485352 nb_pixel_total : 436 time to create 1 rle with old method : 0.0004935264587402344 time for calcul the mask position with numpy : 0.008392572402954102 nb_pixel_total : 27 time to create 1 rle with old method : 5.245208740234375e-05 time for calcul the mask position with numpy : 0.008375167846679688 nb_pixel_total : 294 time to create 1 rle with old method : 0.0003440380096435547 time for calcul the mask position with numpy : 0.008382320404052734 nb_pixel_total : 3480 time to create 1 rle with old method : 0.003958463668823242 time for calcul the mask position with numpy : 0.00837850570678711 nb_pixel_total : 195 time to create 1 rle with old method : 0.00025177001953125 time for calcul the mask position with numpy : 0.008403301239013672 nb_pixel_total : 657 time to create 1 rle with old method : 0.0007805824279785156 time for calcul the mask position with numpy : 0.008482933044433594 nb_pixel_total : 1972 time to create 1 rle with old method : 0.0034279823303222656 time for calcul the mask position with numpy : 0.008699178695678711 nb_pixel_total : 12 time to create 1 rle with old method : 3.170967102050781e-05 time for calcul the mask position with numpy : 0.008403301239013672 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004105567932128906 time for calcul the mask position with numpy : 0.008372068405151367 nb_pixel_total : 400 time to create 1 rle with old method : 0.00047087669372558594 time for calcul the mask position with numpy : 0.008391141891479492 nb_pixel_total : 45 time to create 1 rle with old method : 9.179115295410156e-05 time for calcul the mask position with numpy : 0.011111259460449219 nb_pixel_total : 816 time to create 1 rle with old method : 0.0009284019470214844 time for calcul the mask position with numpy : 0.008389711380004883 nb_pixel_total : 36 time to create 1 rle with old method : 7.43865966796875e-05 time for calcul the mask position with numpy : 0.008303642272949219 nb_pixel_total : 302 time to create 1 rle with old method : 0.00033974647521972656 time for calcul the mask position with numpy : 0.008233308792114258 nb_pixel_total : 591 time to create 1 rle with old method : 0.0006844997406005859 time for calcul the mask position with numpy : 0.008405685424804688 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005199909210205078 time for calcul the mask position with numpy : 0.00838160514831543 nb_pixel_total : 650 time to create 1 rle with old method : 0.0006794929504394531 time for calcul the mask position with numpy : 0.008179187774658203 nb_pixel_total : 1224 time to create 1 rle with old method : 0.0014157295227050781 time for calcul the mask position with numpy : 0.008203744888305664 nb_pixel_total : 236 time to create 1 rle with old method : 0.0002734661102294922 time for calcul the mask position with numpy : 0.00823831558227539 nb_pixel_total : 170 time to create 1 rle with old method : 0.0001926422119140625 time for calcul the mask position with numpy : 0.008318185806274414 nb_pixel_total : 139 time to create 1 rle with old method : 0.00020265579223632812 time for calcul the mask position with numpy : 0.008377790451049805 nb_pixel_total : 2602 time to create 1 rle with old method : 0.0029256343841552734 time for calcul the mask position with numpy : 0.008302450180053711 nb_pixel_total : 1692 time to create 1 rle with old method : 0.001789093017578125 time for calcul the mask position with numpy : 0.008318185806274414 nb_pixel_total : 760 time to create 1 rle with old method : 0.0008749961853027344 time for calcul the mask position with numpy : 0.008376836776733398 nb_pixel_total : 45 time to create 1 rle with old method : 5.9604644775390625e-05 time for calcul the mask position with numpy : 0.00823211669921875 nb_pixel_total : 4168 time to create 1 rle with old method : 0.004766702651977539 time for calcul the mask position with numpy : 0.008139610290527344 nb_pixel_total : 89 time to create 1 rle with old method : 0.00016546249389648438 time for calcul the mask position with numpy : 0.008284568786621094 nb_pixel_total : 1084 time to create 1 rle with old method : 0.0012450218200683594 time for calcul the mask position with numpy : 0.008373737335205078 nb_pixel_total : 681 time to create 1 rle with old method : 0.0007772445678710938 time for calcul the mask position with numpy : 0.008308649063110352 nb_pixel_total : 1645 time to create 1 rle with old method : 0.0018579959869384766 time for calcul the mask position with numpy : 0.008221864700317383 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002300739288330078 time for calcul the mask position with numpy : 0.00830388069152832 nb_pixel_total : 480 time to create 1 rle with old method : 0.0005469322204589844 time for calcul the mask position with numpy : 0.00805521011352539 nb_pixel_total : 461 time to create 1 rle with old method : 0.0005390644073486328 time for calcul the mask position with numpy : 0.008085489273071289 nb_pixel_total : 246 time to create 1 rle with old method : 0.0002918243408203125 create new chi : 2.406764030456543 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.006423234939575195 batch 1 Loaded 171 chid ids of type : 4230 Number RLEs to save : 16947 TO DO : save crop sub photo not yet done ! save time : 9.56744384765625 nb_obj : 166 nb_hashtags : 8 time to prepare the origin masks : 2.6534242630004883 time for calcul the mask position with numpy : 0.029268264770507812 nb_pixel_total : 1689615 time to create 1 rle with new method : 0.06794857978820801 time for calcul the mask position with numpy : 0.0061397552490234375 nb_pixel_total : 5423 time to create 1 rle with old method : 0.005910396575927734 time for calcul the mask position with numpy : 0.005956411361694336 nb_pixel_total : 992 time to create 1 rle with old method : 0.0012793540954589844 time for calcul the mask position with numpy : 0.006191730499267578 nb_pixel_total : 61798 time to create 1 rle with old method : 0.06648707389831543 time for calcul the mask position with numpy : 0.0060062408447265625 nb_pixel_total : 953 time to create 1 rle with old method : 0.0010943412780761719 time for calcul the mask position with numpy : 0.005980968475341797 nb_pixel_total : 81 time to create 1 rle with old method : 9.679794311523438e-05 time for calcul the mask position with numpy : 0.006010293960571289 nb_pixel_total : 790 time to create 1 rle with old method : 0.0009157657623291016 time for calcul the mask position with numpy : 0.006120920181274414 nb_pixel_total : 169 time to create 1 rle with old method : 0.00020837783813476562 time for calcul the mask position with numpy : 0.006011247634887695 nb_pixel_total : 88 time to create 1 rle with old method : 0.00011801719665527344 time for calcul the mask position with numpy : 0.005983829498291016 nb_pixel_total : 113 time to create 1 rle with old method : 0.00015163421630859375 time for calcul the mask position with numpy : 0.006083488464355469 nb_pixel_total : 59 time to create 1 rle with old method : 0.00011348724365234375 time for calcul the mask position with numpy : 0.006035566329956055 nb_pixel_total : 336 time to create 1 rle with old method : 0.00043892860412597656 time for calcul the mask position with numpy : 0.005827665328979492 nb_pixel_total : 2665 time to create 1 rle with old method : 0.002955198287963867 time for calcul the mask position with numpy : 0.005953788757324219 nb_pixel_total : 9045 time to create 1 rle with old method : 0.010347127914428711 time for calcul the mask position with numpy : 0.006007671356201172 nb_pixel_total : 610 time to create 1 rle with old method : 0.0007038116455078125 time for calcul the mask position with numpy : 0.0058803558349609375 nb_pixel_total : 988 time to create 1 rle with old method : 0.0011608600616455078 time for calcul the mask position with numpy : 0.005801200866699219 nb_pixel_total : 1153 time to create 1 rle with old method : 0.0012023448944091797 time for calcul the mask position with numpy : 0.0059282779693603516 nb_pixel_total : 1170 time to create 1 rle with old method : 0.001306295394897461 time for calcul the mask position with numpy : 0.005938291549682617 nb_pixel_total : 876 time to create 1 rle with old method : 0.0009427070617675781 time for calcul the mask position with numpy : 0.005806446075439453 nb_pixel_total : 481 time to create 1 rle with old method : 0.0005352497100830078 time for calcul the mask position with numpy : 0.005800724029541016 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002429485321044922 time for calcul the mask position with numpy : 0.005842685699462891 nb_pixel_total : 455 time to create 1 rle with old method : 0.0005435943603515625 time for calcul the mask position with numpy : 0.005817413330078125 nb_pixel_total : 3032 time to create 1 rle with old method : 0.003267526626586914 time for calcul the mask position with numpy : 0.005811452865600586 nb_pixel_total : 652 time to create 1 rle with old method : 0.0008101463317871094 time for calcul the mask position with numpy : 0.005869626998901367 nb_pixel_total : 9078 time to create 1 rle with old method : 0.009691953659057617 time for calcul the mask position with numpy : 0.006055355072021484 nb_pixel_total : 95 time to create 1 rle with old method : 0.00011754035949707031 time for calcul the mask position with numpy : 0.00596165657043457 nb_pixel_total : 3317 time to create 1 rle with old method : 0.0036895275115966797 time for calcul the mask position with numpy : 0.0064814090728759766 nb_pixel_total : 1056 time to create 1 rle with old method : 0.0011868476867675781 time for calcul the mask position with numpy : 0.00589752197265625 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005016326904296875 time for calcul the mask position with numpy : 0.0058515071868896484 nb_pixel_total : 104 time to create 1 rle with old method : 0.00013899803161621094 time for calcul the mask position with numpy : 0.005831480026245117 nb_pixel_total : 1477 time to create 1 rle with old method : 0.0016160011291503906 time for calcul the mask position with numpy : 0.005793333053588867 nb_pixel_total : 13871 time to create 1 rle with old method : 0.015106916427612305 time for calcul the mask position with numpy : 0.005796670913696289 nb_pixel_total : 756 time to create 1 rle with old method : 0.0009093284606933594 time for calcul the mask position with numpy : 0.005690813064575195 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006821155548095703 time for calcul the mask position with numpy : 0.005913734436035156 nb_pixel_total : 4131 time to create 1 rle with old method : 0.004545450210571289 time for calcul the mask position with numpy : 0.005846738815307617 nb_pixel_total : 562 time to create 1 rle with old method : 0.0006582736968994141 time for calcul the mask position with numpy : 0.005813121795654297 nb_pixel_total : 124 time to create 1 rle with old method : 0.0001590251922607422 time for calcul the mask position with numpy : 0.0059814453125 nb_pixel_total : 1029 time to create 1 rle with old method : 0.0011570453643798828 time for calcul the mask position with numpy : 0.005980253219604492 nb_pixel_total : 1831 time to create 1 rle with old method : 0.0021011829376220703 time for calcul the mask position with numpy : 0.005936384201049805 nb_pixel_total : 14043 time to create 1 rle with old method : 0.015275716781616211 time for calcul the mask position with numpy : 0.005838871002197266 nb_pixel_total : 332 time to create 1 rle with old method : 0.00037026405334472656 time for calcul the mask position with numpy : 0.005704402923583984 nb_pixel_total : 94 time to create 1 rle with old method : 0.00011849403381347656 time for calcul the mask position with numpy : 0.005621910095214844 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003008842468261719 time for calcul the mask position with numpy : 0.005822658538818359 nb_pixel_total : 199 time to create 1 rle with old method : 0.00026607513427734375 time for calcul the mask position with numpy : 0.0057942867279052734 nb_pixel_total : 916 time to create 1 rle with old method : 0.0010848045349121094 time for calcul the mask position with numpy : 0.005648612976074219 nb_pixel_total : 1314 time to create 1 rle with old method : 0.0014765262603759766 time for calcul the mask position with numpy : 0.005725860595703125 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005457401275634766 time for calcul the mask position with numpy : 0.005635499954223633 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005233287811279297 time for calcul the mask position with numpy : 0.005768299102783203 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006103515625 time for calcul the mask position with numpy : 0.005727529525756836 nb_pixel_total : 9155 time to create 1 rle with old method : 0.010301589965820312 time for calcul the mask position with numpy : 0.005591869354248047 nb_pixel_total : 1732 time to create 1 rle with old method : 0.002048015594482422 time for calcul the mask position with numpy : 0.005655527114868164 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006136894226074219 time for calcul the mask position with numpy : 0.005984306335449219 nb_pixel_total : 116 time to create 1 rle with old method : 0.0001938343048095703 time for calcul the mask position with numpy : 0.0059833526611328125 nb_pixel_total : 1255 time to create 1 rle with old method : 0.0014712810516357422 time for calcul the mask position with numpy : 0.005883455276489258 nb_pixel_total : 663 time to create 1 rle with old method : 0.0008592605590820312 time for calcul the mask position with numpy : 0.005965709686279297 nb_pixel_total : 1097 time to create 1 rle with old method : 0.0012536048889160156 time for calcul the mask position with numpy : 0.006253719329833984 nb_pixel_total : 24 time to create 1 rle with old method : 7.367134094238281e-05 time for calcul the mask position with numpy : 0.006181240081787109 nb_pixel_total : 313 time to create 1 rle with old method : 0.0003840923309326172 time for calcul the mask position with numpy : 0.006216287612915039 nb_pixel_total : 2678 time to create 1 rle with old method : 0.0035758018493652344 time for calcul the mask position with numpy : 0.005679607391357422 nb_pixel_total : 159 time to create 1 rle with old method : 0.00020956993103027344 time for calcul the mask position with numpy : 0.005933284759521484 nb_pixel_total : 313 time to create 1 rle with old method : 0.0003674030303955078 time for calcul the mask position with numpy : 0.006868124008178711 nb_pixel_total : 149 time to create 1 rle with old method : 0.00018286705017089844 time for calcul the mask position with numpy : 0.009489774703979492 nb_pixel_total : 825 time to create 1 rle with old method : 0.0008840560913085938 time for calcul the mask position with numpy : 0.009671449661254883 nb_pixel_total : 2154 time to create 1 rle with old method : 0.0024671554565429688 time for calcul the mask position with numpy : 0.009720087051391602 nb_pixel_total : 345 time to create 1 rle with old method : 0.00037932395935058594 time for calcul the mask position with numpy : 0.009604930877685547 nb_pixel_total : 11 time to create 1 rle with old method : 3.457069396972656e-05 time for calcul the mask position with numpy : 0.010020017623901367 nb_pixel_total : 76 time to create 1 rle with old method : 0.00010156631469726562 time for calcul the mask position with numpy : 0.009851932525634766 nb_pixel_total : 607 time to create 1 rle with old method : 0.0010509490966796875 time for calcul the mask position with numpy : 0.011113643646240234 nb_pixel_total : 215 time to create 1 rle with old method : 0.00037407875061035156 time for calcul the mask position with numpy : 0.011279106140136719 nb_pixel_total : 121 time to create 1 rle with old method : 0.0002429485321044922 time for calcul the mask position with numpy : 0.011244535446166992 nb_pixel_total : 534 time to create 1 rle with old method : 0.0008900165557861328 time for calcul the mask position with numpy : 0.011511564254760742 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002918243408203125 time for calcul the mask position with numpy : 0.011408805847167969 nb_pixel_total : 109 time to create 1 rle with old method : 0.00020623207092285156 time for calcul the mask position with numpy : 0.011313438415527344 nb_pixel_total : 447 time to create 1 rle with old method : 0.0007522106170654297 time for calcul the mask position with numpy : 0.01124119758605957 nb_pixel_total : 35 time to create 1 rle with old method : 6.461143493652344e-05 time for calcul the mask position with numpy : 0.009597301483154297 nb_pixel_total : 429 time to create 1 rle with old method : 0.0005095005035400391 time for calcul the mask position with numpy : 0.00989985466003418 nb_pixel_total : 288 time to create 1 rle with old method : 0.0003426074981689453 time for calcul the mask position with numpy : 0.010325193405151367 nb_pixel_total : 295 time to create 1 rle with old method : 0.0003437995910644531 time for calcul the mask position with numpy : 0.009844541549682617 nb_pixel_total : 21 time to create 1 rle with old method : 5.507469177246094e-05 time for calcul the mask position with numpy : 0.010183334350585938 nb_pixel_total : 783 time to create 1 rle with old method : 0.000843048095703125 time for calcul the mask position with numpy : 0.010144948959350586 nb_pixel_total : 244 time to create 1 rle with old method : 0.00028443336486816406 time for calcul the mask position with numpy : 0.009987592697143555 nb_pixel_total : 1281 time to create 1 rle with old method : 0.0015342235565185547 time for calcul the mask position with numpy : 0.00951075553894043 nb_pixel_total : 649 time to create 1 rle with old method : 0.0007681846618652344 time for calcul the mask position with numpy : 0.010079145431518555 nb_pixel_total : 680 time to create 1 rle with old method : 0.000774383544921875 time for calcul the mask position with numpy : 0.010271072387695312 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006248950958251953 time for calcul the mask position with numpy : 0.009894609451293945 nb_pixel_total : 242 time to create 1 rle with old method : 0.00027871131896972656 time for calcul the mask position with numpy : 0.009787797927856445 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004124641418457031 time for calcul the mask position with numpy : 0.009666681289672852 nb_pixel_total : 569 time to create 1 rle with old method : 0.0006542205810546875 time for calcul the mask position with numpy : 0.009619712829589844 nb_pixel_total : 27 time to create 1 rle with old method : 8.034706115722656e-05 time for calcul the mask position with numpy : 0.013365030288696289 nb_pixel_total : 962 time to create 1 rle with old method : 0.001096487045288086 time for calcul the mask position with numpy : 0.009484052658081055 nb_pixel_total : 752 time to create 1 rle with old method : 0.0008835792541503906 time for calcul the mask position with numpy : 0.009978055953979492 nb_pixel_total : 105718 time to create 1 rle with old method : 0.11918377876281738 time for calcul the mask position with numpy : 0.009589433670043945 nb_pixel_total : 137 time to create 1 rle with old method : 0.00018358230590820312 time for calcul the mask position with numpy : 0.009508848190307617 nb_pixel_total : 3142 time to create 1 rle with old method : 0.0036258697509765625 time for calcul the mask position with numpy : 0.009542465209960938 nb_pixel_total : 187 time to create 1 rle with old method : 0.00024509429931640625 time for calcul the mask position with numpy : 0.00956416130065918 nb_pixel_total : 158 time to create 1 rle with old method : 0.00021576881408691406 time for calcul the mask position with numpy : 0.009458303451538086 nb_pixel_total : 5786 time to create 1 rle with old method : 0.006538867950439453 time for calcul the mask position with numpy : 0.009537935256958008 nb_pixel_total : 224 time to create 1 rle with old method : 0.0002770423889160156 time for calcul the mask position with numpy : 0.005914449691772461 nb_pixel_total : 805 time to create 1 rle with old method : 0.0009818077087402344 time for calcul the mask position with numpy : 0.006024837493896484 nb_pixel_total : 390 time to create 1 rle with old method : 0.0004980564117431641 time for calcul the mask position with numpy : 0.0059680938720703125 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005238056182861328 time for calcul the mask position with numpy : 0.00600743293762207 nb_pixel_total : 130 time to create 1 rle with old method : 0.00018405914306640625 time for calcul the mask position with numpy : 0.006007671356201172 nb_pixel_total : 267 time to create 1 rle with old method : 0.000324249267578125 time for calcul the mask position with numpy : 0.005959987640380859 nb_pixel_total : 346 time to create 1 rle with old method : 0.00041103363037109375 time for calcul the mask position with numpy : 0.005838155746459961 nb_pixel_total : 8 time to create 1 rle with old method : 3.4809112548828125e-05 time for calcul the mask position with numpy : 0.005970478057861328 nb_pixel_total : 154 time to create 1 rle with old method : 0.0001742839813232422 time for calcul the mask position with numpy : 0.006010770797729492 nb_pixel_total : 37 time to create 1 rle with old method : 6.961822509765625e-05 time for calcul the mask position with numpy : 0.005754947662353516 nb_pixel_total : 358 time to create 1 rle with old method : 0.0003781318664550781 time for calcul the mask position with numpy : 0.005987882614135742 nb_pixel_total : 992 time to create 1 rle with old method : 0.0010673999786376953 time for calcul the mask position with numpy : 0.005982875823974609 nb_pixel_total : 682 time to create 1 rle with old method : 0.0007882118225097656 time for calcul the mask position with numpy : 0.00593256950378418 nb_pixel_total : 987 time to create 1 rle with old method : 0.001148223876953125 time for calcul the mask position with numpy : 0.00589299201965332 nb_pixel_total : 567 time to create 1 rle with old method : 0.0006670951843261719 time for calcul the mask position with numpy : 0.0059778690338134766 nb_pixel_total : 19 time to create 1 rle with old method : 6.914138793945312e-05 time for calcul the mask position with numpy : 0.005866050720214844 nb_pixel_total : 973 time to create 1 rle with old method : 0.0010600090026855469 time for calcul the mask position with numpy : 0.005933523178100586 nb_pixel_total : 646 time to create 1 rle with old method : 0.0007040500640869141 time for calcul the mask position with numpy : 0.006254434585571289 nb_pixel_total : 43087 time to create 1 rle with old method : 0.046666622161865234 time for calcul the mask position with numpy : 0.005970954895019531 nb_pixel_total : 835 time to create 1 rle with old method : 0.0008912086486816406 time for calcul the mask position with numpy : 0.005801200866699219 nb_pixel_total : 17 time to create 1 rle with old method : 4.6253204345703125e-05 time for calcul the mask position with numpy : 0.0057184696197509766 nb_pixel_total : 471 time to create 1 rle with old method : 0.0005037784576416016 time for calcul the mask position with numpy : 0.005654096603393555 nb_pixel_total : 281 time to create 1 rle with old method : 0.00031447410583496094 time for calcul the mask position with numpy : 0.005552768707275391 nb_pixel_total : 388 time to create 1 rle with old method : 0.00041675567626953125 time for calcul the mask position with numpy : 0.0056307315826416016 nb_pixel_total : 159 time to create 1 rle with old method : 0.00019741058349609375 time for calcul the mask position with numpy : 0.005671262741088867 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002300739288330078 time for calcul the mask position with numpy : 0.005584001541137695 nb_pixel_total : 305 time to create 1 rle with old method : 0.0003361701965332031 time for calcul the mask position with numpy : 0.005618572235107422 nb_pixel_total : 2313 time to create 1 rle with old method : 0.0024552345275878906 time for calcul the mask position with numpy : 0.0056400299072265625 nb_pixel_total : 217 time to create 1 rle with old method : 0.00024056434631347656 time for calcul the mask position with numpy : 0.005772590637207031 nb_pixel_total : 312 time to create 1 rle with old method : 0.0003528594970703125 time for calcul the mask position with numpy : 0.005639314651489258 nb_pixel_total : 100 time to create 1 rle with old method : 0.0001285076141357422 time for calcul the mask position with numpy : 0.006039857864379883 nb_pixel_total : 496 time to create 1 rle with old method : 0.0005762577056884766 time for calcul the mask position with numpy : 0.005855083465576172 nb_pixel_total : 577 time to create 1 rle with old method : 0.0006620883941650391 time for calcul the mask position with numpy : 0.005909919738769531 nb_pixel_total : 74 time to create 1 rle with old method : 0.00011992454528808594 time for calcul the mask position with numpy : 0.006056785583496094 nb_pixel_total : 329 time to create 1 rle with old method : 0.00037288665771484375 time for calcul the mask position with numpy : 0.005973100662231445 nb_pixel_total : 606 time to create 1 rle with old method : 0.0006654262542724609 time for calcul the mask position with numpy : 0.005934715270996094 nb_pixel_total : 2482 time to create 1 rle with old method : 0.002767801284790039 time for calcul the mask position with numpy : 0.006098270416259766 nb_pixel_total : 439 time to create 1 rle with old method : 0.0004913806915283203 time for calcul the mask position with numpy : 0.005931377410888672 nb_pixel_total : 284 time to create 1 rle with old method : 0.00035309791564941406 time for calcul the mask position with numpy : 0.005850076675415039 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005044937133789062 time for calcul the mask position with numpy : 0.005978107452392578 nb_pixel_total : 3939 time to create 1 rle with old method : 0.004378795623779297 time for calcul the mask position with numpy : 0.006036520004272461 nb_pixel_total : 7 time to create 1 rle with old method : 4.172325134277344e-05 time for calcul the mask position with numpy : 0.006023406982421875 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003211498260498047 time for calcul the mask position with numpy : 0.005957603454589844 nb_pixel_total : 1334 time to create 1 rle with old method : 0.0015032291412353516 time for calcul the mask position with numpy : 0.005973339080810547 nb_pixel_total : 1876 time to create 1 rle with old method : 0.0022165775299072266 time for calcul the mask position with numpy : 0.006103992462158203 nb_pixel_total : 374 time to create 1 rle with old method : 0.00044083595275878906 time for calcul the mask position with numpy : 0.006131172180175781 nb_pixel_total : 341 time to create 1 rle with old method : 0.0003986358642578125 time for calcul the mask position with numpy : 0.006145477294921875 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002276897430419922 time for calcul the mask position with numpy : 0.0058765411376953125 nb_pixel_total : 88 time to create 1 rle with old method : 0.00011181831359863281 time for calcul the mask position with numpy : 0.006230592727661133 nb_pixel_total : 200 time to create 1 rle with old method : 0.00024700164794921875 time for calcul the mask position with numpy : 0.006206989288330078 nb_pixel_total : 40 time to create 1 rle with old method : 6.651878356933594e-05 time for calcul the mask position with numpy : 0.006153583526611328 nb_pixel_total : 986 time to create 1 rle with old method : 0.0011289119720458984 time for calcul the mask position with numpy : 0.006234407424926758 nb_pixel_total : 318 time to create 1 rle with old method : 0.0003876686096191406 time for calcul the mask position with numpy : 0.006117343902587891 nb_pixel_total : 646 time to create 1 rle with old method : 0.0008411407470703125 time for calcul the mask position with numpy : 0.006275177001953125 nb_pixel_total : 2362 time to create 1 rle with old method : 0.0027375221252441406 time for calcul the mask position with numpy : 0.006227016448974609 nb_pixel_total : 151 time to create 1 rle with old method : 0.00020813941955566406 time for calcul the mask position with numpy : 0.0063266754150390625 nb_pixel_total : 2168 time to create 1 rle with old method : 0.0025293827056884766 time for calcul the mask position with numpy : 0.005922794342041016 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001399517059326172 time for calcul the mask position with numpy : 0.005884408950805664 nb_pixel_total : 5581 time to create 1 rle with old method : 0.006179094314575195 time for calcul the mask position with numpy : 0.006085872650146484 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007021427154541016 time for calcul the mask position with numpy : 0.006143331527709961 nb_pixel_total : 57 time to create 1 rle with old method : 8.225440979003906e-05 time for calcul the mask position with numpy : 0.0060503482818603516 nb_pixel_total : 62 time to create 1 rle with old method : 0.00011110305786132812 time for calcul the mask position with numpy : 0.00628209114074707 nb_pixel_total : 56 time to create 1 rle with old method : 0.00010943412780761719 time for calcul the mask position with numpy : 0.006153583526611328 nb_pixel_total : 614 time to create 1 rle with old method : 0.0007448196411132812 time for calcul the mask position with numpy : 0.007279396057128906 nb_pixel_total : 1605 time to create 1 rle with old method : 0.002758502960205078 time for calcul the mask position with numpy : 0.007069826126098633 nb_pixel_total : 650 time to create 1 rle with old method : 0.000743865966796875 time for calcul the mask position with numpy : 0.006439924240112305 nb_pixel_total : 474 time to create 1 rle with old method : 0.0005552768707275391 time for calcul the mask position with numpy : 0.006621360778808594 nb_pixel_total : 279 time to create 1 rle with old method : 0.0005559921264648438 time for calcul the mask position with numpy : 0.0065419673919677734 nb_pixel_total : 223 time to create 1 rle with old method : 0.0002720355987548828 time for calcul the mask position with numpy : 0.0062634944915771484 nb_pixel_total : 1 time to create 1 rle with old method : 1.9550323486328125e-05 create new chi : 1.6774377822875977 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.002003908157348633 batch 1 Loaded 167 chid ids of type : 4230 Number RLEs to save : 16242 TO DO : save crop sub photo not yet done ! save time : 5.5967395305633545 map_output_result : {1338695305: (0.0, 'Should be the crop_list due to order', 0.0), 1338695302: (0.0, 'Should be the crop_list due to order', 0.0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1338695305, 1338695302] Looping around the photos to save general results len do output : 2 /1338695305.Didn't retrieve data . /1338695302.Didn't retrieve data . before output type Used above Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2603702') ('4234', '20718229', '1338695305', None, None, None, None, None, '2603702') ('4234', None, None, None, None, None, None, None, '2603702') ('4234', '20718229', '1338695302', None, None, None, None, None, '2603702') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.5487205982208252 save_final save missing photos in datou_result : time spend for datou_step_exec : 23.886000633239746 time spend to save output : 0.5491435527801514 total time spend for step 4 : 24.435144186019897 step5:crop_condition Fri Feb 21 09:21:47 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 2 ! batch 1 Loaded 338 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 141 About to insert : list_path_to_insert length 141 new photo from crops ! About to upload 141 photos upload in portfolio : 4869462 init cache_photo without model_param we have 141 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740126110_2003125 we have uploaded 141 photos in the portfolio 4869462 time of upload the photos Elapsed time : 49.57687830924988 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 48 About to insert : list_path_to_insert length 48 new photo from crops ! About to upload 48 photos upload in portfolio : 4869462 init cache_photo without model_param we have 48 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740126160_2003125 we have uploaded 48 photos in the portfolio 4869462 time of upload the photos Elapsed time : 15.432898044586182 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 7 About to insert : list_path_to_insert length 7 new photo from crops ! About to upload 7 photos upload in portfolio : 4869462 init cache_photo without model_param we have 7 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740126176_2003125 we have uploaded 7 photos in the portfolio 4869462 time of upload the photos Elapsed time : 2.668905258178711 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 23 About to insert : list_path_to_insert length 23 new photo from crops ! About to upload 23 photos upload in portfolio : 4869462 init cache_photo without model_param we have 23 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740126179_2003125 we have uploaded 23 photos in the portfolio 4869462 time of upload the photos Elapsed time : 7.438436031341553 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740126187_2003125 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.5936112403869629 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1338695305, 1338695302] Looping around the photos to save general results len do output : 220 /1338780477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780656Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338780999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338781037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2603702') ('4234', '20718229', '1338695305', None, None, None, None, None, '2603702') ('4234', None, None, None, None, None, None, None, '2603702') ('4234', '20718229', '1338695302', None, None, None, None, None, '2603702') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 662 time used for this insertion : 0.11300253868103027 save_final save missing photos in datou_result : time spend for datou_step_exec : 80.10752868652344 time spend to save output : 0.12028884887695312 total time spend for step 5 : 80.22781753540039 step6:thcl Fri Feb 21 09:23:07 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step Thcl ! we are using the classfication for only one thcl 3237 time to import caffe and check if the image exist : 0.015291213989257812 time to convert the images to numpy array : 0.05688810348510742 time to import caffe and check if the image exist : 0.01633453369140625 time to convert the images to numpy array : 0.06764435768127441 time to import caffe and check if the image exist : 0.012941598892211914 time to convert the images to numpy array : 0.07399249076843262 time to import caffe and check if the image exist : 0.014502763748168945 time to convert the images to numpy array : 0.07414555549621582 time to import caffe and check if the image exist : 0.021277427673339844 time to convert the images to numpy array : 0.06848573684692383 time to import caffe and check if the image exist : 0.01704716682434082 time to convert the images to numpy array : 0.07373547554016113 time to import caffe and check if the image exist : 0.01690220832824707 time to convert the images to numpy array : 0.07814502716064453 time to import caffe and check if the image exist : 0.012536287307739258 time to convert the images to numpy array : 0.08220386505126953 time to import caffe and check if the image exist : 0.03131604194641113 time to convert the images to numpy array : 0.06571030616760254 time to import caffe and check if the image exist : 0.02793598175048828 time to convert the images to numpy array : 0.07080578804016113 total time to convert the images to numpy array : 0.3193492889404297 list photo_ids error: [] list photo_ids correct : [1338780568, 1338780570, 1338780572, 1338780575, 1338780577, 1338780579, 1338780581, 1338780583, 1338780585, 1338780587, 1338780590, 1338780595, 1338780597, 1338780599, 1338780601, 1338780603, 1338780605, 1338780608, 1338780610, 1338780612, 1338780614, 1338780617, 1338780717, 1338780719, 1338780721, 1338780736, 1338780739, 1338780741, 1338780743, 1338780745, 1338780747, 1338780749, 1338780751, 1338780753, 1338780755, 1338780757, 1338780759, 1338780761, 1338780763, 1338780765, 1338780767, 1338780769, 1338780771, 1338780773, 1338780665, 1338780667, 1338780669, 1338780671, 1338780673, 1338780675, 1338780677, 1338780679, 1338780682, 1338780684, 1338780686, 1338780688, 1338780690, 1338780692, 1338780701, 1338780703, 1338780705, 1338780707, 1338780709, 1338780711, 1338780713, 1338780715, 1338780618, 1338780621, 1338780623, 1338780624, 1338780627, 1338780628, 1338780630, 1338780632, 1338780634, 1338780636, 1338780638, 1338780640, 1338780644, 1338780646, 1338780648, 1338780650, 1338780653, 1338780656, 1338780658, 1338780659, 1338780661, 1338780664, 1338780775, 1338780777, 1338780780, 1338780782, 1338780784, 1338780786, 1338780789, 1338780790, 1338780793, 1338780951, 1338780952, 1338780953, 1338780954, 1338780955, 1338780956, 1338780957, 1338780958, 1338780959, 1338780961, 1338780962, 1338780963, 1338780964, 1338780522, 1338780524, 1338780526, 1338780528, 1338780530, 1338780533, 1338780536, 1338780538, 1338780540, 1338780542, 1338780544, 1338780546, 1338780548, 1338780550, 1338780552, 1338780554, 1338780556, 1338780558, 1338780560, 1338780562, 1338780564, 1338780566, 1338780989, 1338780990, 1338780991, 1338780992, 1338780993, 1338780994, 1338780995, 1338780996, 1338780997, 1338780998, 1338780999, 1338781000, 1338781001, 1338781004, 1338781005, 1338781006, 1338781007, 1338781008, 1338781010, 1338781011, 1338781013, 1338781014, 1338781015, 1338781016, 1338781017, 1338781018, 1338781019, 1338781020, 1338781021, 1338781022, 1338781023, 1338781024, 1338781025, 1338781026, 1338781027, 1338781028, 1338781030, 1338781031, 1338781032, 1338781033, 1338781034, 1338781035, 1338781036, 1338781037, 1338780965, 1338780966, 1338780967, 1338780968, 1338780969, 1338780970, 1338780971, 1338780972, 1338780974, 1338780975, 1338780976, 1338780977, 1338780978, 1338780979, 1338780980, 1338780981, 1338780983, 1338780984, 1338780985, 1338780986, 1338780987, 1338780988, 1338780477, 1338780479, 1338780481, 1338780483, 1338780485, 1338780487, 1338780489, 1338780491, 1338780493, 1338780495, 1338780497, 1338780499, 1338780501, 1338780503, 1338780505, 1338780507, 1338780509, 1338780511, 1338780512, 1338780516, 1338780518, 1338780520] number of photos to traite : 220 try to delete the photos incorrect in DB tagging for thcl : 3237 To do loadFromThcl(), then load ParamDescType : thcl3237 thcls : [{'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'}] thcl {'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'} Update svm_hashtag_type_desc : 5561 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)) To loadFromThcl() : net_5561 begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 2165 wait 20 seconds l 3637 free memory gpu now : 2165 max_wait_temp : 1 max_wait : 0 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)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_rubbia_refus_2500 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_rubbia_refus_2500 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_rubbia_refus_2500 /data/models_weight/learn_rubbia_refus_2500/caffemodel size_local : 94358479 size in s3 : 94358479 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:16 caffemodel already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt size_local : 32544 size in s3 : 32544 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:15 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:09:52 mean.npy already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/synset_words.txt size_local : 334 size in s3 : 334 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:10:06 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /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/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt caffemodel_filename : /data/models_weight/learn_rubbia_refus_2500/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 1946 wait 20 seconds WARNING: Logging before InitGoogleLogging() is written to STDERR F0221 09:23:53.257336 2003125 syncedmem.cpp:78] Check failed: error == cudaSuccess (2 vs. 0) out of memory *** Check failure stack trace: *** Command terminated by signal 6 33.43user 23.39system 3:28.23elapsed 27%CPU (0avgtext+0avgdata 3223368maxresident)k 706856inputs+9328outputs (354major+2658183minor)pagefaults 0swaps