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 : 3829079 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 : ['2616930'] with mtr_portfolio_ids : ['20848651'] and first list_photo_ids : [] new path : /proc/3829079/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 3 ; length of list_pids : 3 ; length of list_args : 3 time to download the photos : 0.38292431831359863 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Wed Feb 26 18:20:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 3000 l 3632 free memory gpu now : 2062 wait 20 seconds l 3637 free memory gpu now : 2062 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-26 18:20:54.290970: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-26 18:20:54.323145: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-26 18:20:54.325644: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f03b0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-26 18:20:54.325710: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-26 18:20:54.331391: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-26 18:20:54.597885: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1acf2c00 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-26 18:20:54.597963: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-26 18:20:54.599776: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-26 18:20:54.601136: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 18:20:54.621809: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 18:20:54.633410: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 18:20:54.635652: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 18:20:54.649644: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 18:20:54.652978: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 18:20:54.690221: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 18:20:54.691543: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 18:20:54.691662: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 18:20:54.693020: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-26 18:20:54.693041: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-26 18:20:54.693052: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-26 18:20:54.694246: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1685 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-02-26 18:20:55.046547: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-26 18:20:55.046648: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 18:20:55.046672: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 18:20:55.046694: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 18:20:55.046714: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 18:20:55.046734: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 18:20:55.046753: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 18:20:55.046773: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 18:20:55.047734: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 18:20:55.048880: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-26 18:20:55.048925: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 18:20:55.048944: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 18:20:55.048961: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 18:20:55.048978: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 18:20:55.048995: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 18:20:55.049011: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 18:20:55.049028: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 18:20:55.049981: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 18:20:55.050021: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-26 18:20:55.050031: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-26 18:20:55.050041: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-26 18:20:55.051069: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1685 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-26 18:21:03.152125: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 18:21:03.471261: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 18:21:05.396883: 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. 2025-02-26 18:21:05.396954: 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. 2025-02-26 18:21:05.403648: 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. 2025-02-26 18:21:05.403699: 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. 2025-02-26 18:21:05.456084: 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. 2025-02-26 18:21:05.456141: 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. 2025-02-26 18:21:05.499168: 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. 2025-02-26 18:21:05.499217: 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. 2025-02-26 18:21:05.551490: 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. 2025-02-26 18:21:05.551549: 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. 2025-02-26 18:21:05.553220: 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. 2025-02-26 18:21:05.595086: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.596183: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.657825: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.658811: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.661030: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.661954: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.670356: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.671375: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.673584: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.674538: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.681281: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.682177: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.684303: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.685204: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.716418: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.716998: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.717529: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.718061: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.722055: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.722626: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.739918: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.740544: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.741082: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.741618: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.754988: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.755581: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.756130: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.756665: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.761452: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.762012: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.766758: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.767326: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.779373: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.779931: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.784247: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.784828: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.785692: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.786250: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.796911: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.797516: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.798097: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.798625: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.799182: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.799753: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.870670: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.871246: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.879139: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.879680: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.900729: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.901444: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.902114: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.902766: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.907001: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.907651: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.908177: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.908701: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.909660: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.909678: 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. 2025-02-26 18:21:05.919925: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.920459: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.929438: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.929968: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.930469: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.930964: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.931502: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-26 18:21:05.932028: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.15G (1231945728 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 : 3 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.02031 max: 148.79531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 958 time to create 1 rle with old method : 0.006248950958251953 length of segment : 35 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.009103059768676758 length of segment : 44 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0008363723754882812 length of segment : 47 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 819 time to create 1 rle with old method : 0.0014300346374511719 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.32500 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 : 4.3392181396484375e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.000492095947265625 length of segment : 37 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 2781 time to create 1 rle with old method : 0.003506183624267578 length of segment : 59 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1069 time to create 1 rle with old method : 0.001398324966430664 length of segment : 49 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 3136 time to create 1 rle with old method : 0.004075050354003906 length of segment : 49 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 3699 time to create 1 rle with old method : 0.004813194274902344 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.02422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00026679039001464844 nb_pixel_total : 8482 time to create 1 rle with old method : 0.013904809951782227 length of segment : 136 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 5854 time to create 1 rle with old method : 0.009463310241699219 length of segment : 100 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.001294851303100586 length of segment : 43 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1291 time to create 1 rle with old method : 0.0025739669799804688 length of segment : 56 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 0.00011992454528808594 nb_pixel_total : 4305 time to create 1 rle with old method : 0.0053861141204833984 length of segment : 119 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 2246 time to create 1 rle with old method : 0.002701997756958008 length of segment : 88 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.0011262893676757812 length of segment : 65 time for calcul the mask position with numpy : 0.0001246929168701172 nb_pixel_total : 5734 time to create 1 rle with old method : 0.006956338882446289 length of segment : 76 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.0001785755157470703 length of segment : 16 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.00031828880310058594 length of segment : 23 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 236.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 118.18203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1181 time to create 1 rle with old method : 0.0015897750854492188 length of segment : 33 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0008013248443603516 length of segment : 19 time for calcul the mask position with numpy : 0.0006477832794189453 nb_pixel_total : 58609 time to create 1 rle with old method : 0.06634163856506348 length of segment : 301 Processing 1 images image shape: (400, 400, 3) min: 25.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -84.91094 max: 76.60781 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: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -102.58672 max: 146.15859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 1183 time to create 1 rle with old method : 0.0024077892303466797 length of segment : 43 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0004017353057861328 length of segment : 35 time for calcul the mask position with numpy : 0.0002243518829345703 nb_pixel_total : 9665 time to create 1 rle with old method : 0.01135563850402832 length of segment : 131 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.08672 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.001009225845336914 length of segment : 25 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0008585453033447266 length of segment : 25 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.0005340576171875 length of segment : 16 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.00045180320739746094 length of segment : 14 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.0002651214599609375 length of segment : 9 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0007872581481933594 length of segment : 14 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0005745887756347656 length of segment : 24 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 827 time to create 1 rle with old method : 0.0015442371368408203 length of segment : 26 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0005643367767333984 length of segment : 16 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0011680126190185547 length of segment : 21 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0002453327178955078 length of segment : 9 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1146 time to create 1 rle with old method : 0.0018270015716552734 length of segment : 85 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00014925003051757812 length of segment : 11 time for calcul the mask position with numpy : 0.0003018379211425781 nb_pixel_total : 21490 time to create 1 rle with old method : 0.024375200271606445 length of segment : 190 time for calcul the mask position with numpy : 0.00034689903259277344 nb_pixel_total : 21827 time to create 1 rle with old method : 0.025250911712646484 length of segment : 150 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 768 time to create 1 rle with old method : 0.0010616779327392578 length of segment : 35 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1177 time to create 1 rle with old method : 0.0015692710876464844 length of segment : 40 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.00020813941955566406 length of segment : 8 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004296302795410156 length of segment : 26 time for calcul the mask position with numpy : 0.0002620220184326172 nb_pixel_total : 17749 time to create 1 rle with old method : 0.01996016502380371 length of segment : 303 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.48516 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 : 5.3882598876953125e-05 nb_pixel_total : 947 time to create 1 rle with old method : 0.0013155937194824219 length of segment : 39 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.0001544952392578125 length of segment : 7 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 5773 time to create 1 rle with old method : 0.006785392761230469 length of segment : 145 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0015783309936523438 length of segment : 155 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 1016 time to create 1 rle with old method : 0.0014104843139648438 length of segment : 34 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 857 time to create 1 rle with old method : 0.0011565685272216797 length of segment : 21 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 6307 time to create 1 rle with old method : 0.007298946380615234 length of segment : 121 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003616809844970703 length of segment : 18 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.94375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 745 time to create 1 rle with old method : 0.0010273456573486328 length of segment : 60 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00018286705017089844 length of segment : 17 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 2274 time to create 1 rle with old method : 0.003046751022338867 length of segment : 106 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 2297 time to create 1 rle with old method : 0.0031049251556396484 length of segment : 107 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1751 time to create 1 rle with old method : 0.0021495819091796875 length of segment : 86 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0007178783416748047 length of segment : 32 time for calcul the mask position with numpy : 0.0001595020294189453 nb_pixel_total : 4583 time to create 1 rle with old method : 0.005258083343505859 length of segment : 210 Processing 1 images image shape: (280, 400, 3) min: 17.00000 max: 193.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 76.77578 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0018661022186279297 nb_pixel_total : 104444 time to create 1 rle with old method : 0.11959290504455566 length of segment : 286 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: 150.57266 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 2818 time to create 1 rle with old method : 0.0036928653717041016 length of segment : 49 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 667 time to create 1 rle with old method : 0.0008633136749267578 length of segment : 56 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 3435 time to create 1 rle with old method : 0.0042476654052734375 length of segment : 69 time for calcul the mask position with numpy : 0.00019311904907226562 nb_pixel_total : 9801 time to create 1 rle with old method : 0.011600017547607422 length of segment : 193 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1553 time to create 1 rle with old method : 0.0019888877868652344 length of segment : 84 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1074 time to create 1 rle with old method : 0.0014290809631347656 length of segment : 33 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 2436 time to create 1 rle with old method : 0.002872467041015625 length of segment : 83 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 875 time to create 1 rle with old method : 0.0012319087982177734 length of segment : 37 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0007333755493164062 length of segment : 46 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.001378774642944336 length of segment : 48 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: 151.02969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 0.00012302398681640625 nb_pixel_total : 2129 time to create 1 rle with old method : 0.002700328826904297 length of segment : 64 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0004138946533203125 length of segment : 12 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1942 time to create 1 rle with old method : 0.002588510513305664 length of segment : 49 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 1424 time to create 1 rle with old method : 0.001962423324584961 length of segment : 39 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 618 time to create 1 rle with old method : 0.0008172988891601562 length of segment : 44 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0004138946533203125 length of segment : 20 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 593 time to create 1 rle with old method : 0.0007798671722412109 length of segment : 55 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 1388 time to create 1 rle with old method : 0.0018634796142578125 length of segment : 92 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.0005657672882080078 length of segment : 12 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0005097389221191406 length of segment : 29 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003001689910888672 length of segment : 23 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.0001785755157470703 length of segment : 11 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1519 time to create 1 rle with old method : 0.0019931793212890625 length of segment : 59 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1366 time to create 1 rle with old method : 0.0021898746490478516 length of segment : 62 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001590251922607422 length of segment : 14 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 576 time to create 1 rle with old method : 0.0007359981536865234 length of segment : 40 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003781318664550781 length of segment : 20 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0012295246124267578 length of segment : 43 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0004971027374267578 length of segment : 17 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005469322204589844 length of segment : 30 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.0001919269561767578 length of segment : 10 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1352 time to create 1 rle with old method : 0.0017919540405273438 length of segment : 57 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 951 time to create 1 rle with old method : 0.002613067626953125 length of segment : 52 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1416 time to create 1 rle with old method : 0.001889944076538086 length of segment : 56 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0003523826599121094 length of segment : 13 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1032 time to create 1 rle with old method : 0.001352548599243164 length of segment : 38 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: 145.83828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00022673606872558594 length of segment : 17 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.00038552284240722656 length of segment : 30 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.00023031234741210938 length of segment : 22 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003097057342529297 length of segment : 29 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004968643188476562 length of segment : 55 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: 131.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.23906 max: 149.27187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.0014491081237792969 length of segment : 39 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 833 time to create 1 rle with old method : 0.0011224746704101562 length of segment : 43 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002067089080810547 length of segment : 26 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 768 time to create 1 rle with old method : 0.001071929931640625 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.44219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 2254 time to create 1 rle with old method : 0.002671957015991211 length of segment : 47 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0007841587066650391 length of segment : 51 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.00027251243591308594 length of segment : 28 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 2663 time to create 1 rle with old method : 0.0032286643981933594 length of segment : 52 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 709 time to create 1 rle with old method : 0.0008873939514160156 length of segment : 46 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 3166 time to create 1 rle with old method : 0.0042688846588134766 length of segment : 65 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005972385406494141 length of segment : 28 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005621910095214844 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: -105.87578 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1305 time to create 1 rle with old method : 0.001626729965209961 length of segment : 132 time for calcul the mask position with numpy : 0.00011086463928222656 nb_pixel_total : 3689 time to create 1 rle with old method : 0.0047228336334228516 length of segment : 109 time for calcul the mask position with numpy : 0.00014066696166992188 nb_pixel_total : 6652 time to create 1 rle with old method : 0.009970903396606445 length of segment : 103 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0008985996246337891 length of segment : 22 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.001230478286743164 length of segment : 64 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002465248107910156 length of segment : 27 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 3925 time to create 1 rle with old method : 0.004566192626953125 length of segment : 99 time for calcul the mask position with numpy : 0.00013136863708496094 nb_pixel_total : 4004 time to create 1 rle with old method : 0.005479335784912109 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: -121.26250 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 : 0.00012612342834472656 nb_pixel_total : 6301 time to create 1 rle with old method : 0.007389068603515625 length of segment : 137 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006957054138183594 length of segment : 57 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006990432739257812 length of segment : 25 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0007276535034179688 length of segment : 60 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 2003 time to create 1 rle with old method : 0.0024347305297851562 length of segment : 100 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 5183 time to create 1 rle with old method : 0.00630640983581543 length of segment : 80 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: 119.74062 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007164478302001953 length of segment : 19 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.000728607177734375 length of segment : 19 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 850 time to create 1 rle with old method : 0.0011143684387207031 length of segment : 50 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00024318695068359375 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 15.00000 max: 174.00000 molded_images shape: (1, 640, 640, 3) min: -99.02031 max: 60.62344 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: -115.13750 max: 142.67422 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 0.0003619194030761719 nb_pixel_total : 17544 time to create 1 rle with old method : 0.027797698974609375 length of segment : 218 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0006117820739746094 length of segment : 55 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 138 time to create 1 rle with old method : 0.00023365020751953125 length of segment : 15 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003383159637451172 length of segment : 14 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.00022077560424804688 length of segment : 14 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.0003314018249511719 length of segment : 11 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.50078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 0.000316619873046875 nb_pixel_total : 18613 time to create 1 rle with old method : 0.021201610565185547 length of segment : 160 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004856586456298828 length of segment : 27 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.0001850128173828125 length of segment : 8 time for calcul the mask position with numpy : 0.0002734661102294922 nb_pixel_total : 10383 time to create 1 rle with old method : 0.012877702713012695 length of segment : 168 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1133 time to create 1 rle with old method : 0.0015096664428710938 length of segment : 50 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 405 time to create 1 rle with old method : 0.0005514621734619141 length of segment : 25 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0006651878356933594 length of segment : 16 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004916191101074219 length of segment : 18 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 2160 time to create 1 rle with old method : 0.0026366710662841797 length of segment : 55 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00017571449279785156 length of segment : 23 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.0004520416259765625 length of segment : 19 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007348060607910156 length of segment : 40 time for calcul the mask position with numpy : 0.00023674964904785156 nb_pixel_total : 11621 time to create 1 rle with old method : 0.013864994049072266 length of segment : 158 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0011491775512695312 length of segment : 27 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 569 time to create 1 rle with old method : 0.0007886886596679688 length of segment : 28 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.0001163482666015625 length of segment : 14 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0006325244903564453 length of segment : 23 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003058910369873047 length of segment : 15 time for calcul the mask position with numpy : 0.00034499168395996094 nb_pixel_total : 12689 time to create 1 rle with old method : 0.016575336456298828 length of segment : 199 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007150173187255859 length of segment : 26 time for calcul the mask position with numpy : 0.00024580955505371094 nb_pixel_total : 12889 time to create 1 rle with old method : 0.014867067337036133 length of segment : 200 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.09844 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 2230 time to create 1 rle with old method : 0.0026497840881347656 length of segment : 145 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 808 time to create 1 rle with old method : 0.0011432170867919922 length of segment : 21 time for calcul the mask position with numpy : 0.0001621246337890625 nb_pixel_total : 5476 time to create 1 rle with old method : 0.006567478179931641 length of segment : 191 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 1163 time to create 1 rle with old method : 0.0014925003051757812 length of segment : 38 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 823 time to create 1 rle with old method : 0.001161813735961914 length of segment : 34 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001633167266845703 length of segment : 7 time for calcul the mask position with numpy : 0.0004317760467529297 nb_pixel_total : 9837 time to create 1 rle with old method : 0.012064218521118164 length of segment : 312 time for calcul the mask position with numpy : 0.00018024444580078125 nb_pixel_total : 5944 time to create 1 rle with old method : 0.0071773529052734375 length of segment : 187 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1244 time to create 1 rle with old method : 0.0016188621520996094 length of segment : 39 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.99844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 785 time to create 1 rle with old method : 0.0010399818420410156 length of segment : 76 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 1648 time to create 1 rle with old method : 0.0023047924041748047 length of segment : 83 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 2370 time to create 1 rle with old method : 0.003133058547973633 length of segment : 102 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.0001609325408935547 length of segment : 13 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 2089 time to create 1 rle with old method : 0.0027627944946289062 length of segment : 89 time for calcul the mask position with numpy : 0.0002467632293701172 nb_pixel_total : 3966 time to create 1 rle with old method : 0.004929542541503906 length of segment : 221 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 669 time to create 1 rle with old method : 0.000926971435546875 length of segment : 40 time for calcul the mask position with numpy : 0.00022840499877929688 nb_pixel_total : 4404 time to create 1 rle with old method : 0.005269765853881836 length of segment : 225 Processing 1 images image shape: (280, 400, 3) min: 11.00000 max: 190.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 53.43984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012874603271484375 nb_pixel_total : 105166 time to create 1 rle with old method : 0.1180579662322998 length of segment : 285 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: 150.81875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 2979 time to create 1 rle with old method : 0.003628969192504883 length of segment : 47 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 3293 time to create 1 rle with old method : 0.0039920806884765625 length of segment : 70 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 2597 time to create 1 rle with old method : 0.003086566925048828 length of segment : 79 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0008630752563476562 length of segment : 60 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 995 time to create 1 rle with old method : 0.0012521743774414062 length of segment : 51 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1075 time to create 1 rle with old method : 0.0014541149139404297 length of segment : 40 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1226 time to create 1 rle with old method : 0.0016040802001953125 length of segment : 44 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1141 time to create 1 rle with old method : 0.0014431476593017578 length of segment : 51 time for calcul the mask position with numpy : 0.00016307830810546875 nb_pixel_total : 8544 time to create 1 rle with old method : 0.010034561157226562 length of segment : 168 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: 149.33437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 2128 time to create 1 rle with old method : 0.002737283706665039 length of segment : 65 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1613 time to create 1 rle with old method : 0.0019176006317138672 length of segment : 101 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1947 time to create 1 rle with old method : 0.002455472946166992 length of segment : 49 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.000522613525390625 length of segment : 17 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00015306472778320312 length of segment : 12 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1532 time to create 1 rle with old method : 0.0019192695617675781 length of segment : 38 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.00015020370483398438 length of segment : 14 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 753 time to create 1 rle with old method : 0.0009756088256835938 length of segment : 34 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005700588226318359 length of segment : 19 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1693 time to create 1 rle with old method : 0.002039194107055664 length of segment : 66 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003414154052734375 length of segment : 21 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1299 time to create 1 rle with old method : 0.0016548633575439453 length of segment : 57 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00025963783264160156 length of segment : 13 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.00031757354736328125 length of segment : 49 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 837 time to create 1 rle with old method : 0.001056671142578125 length of segment : 39 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1453 time to create 1 rle with old method : 0.0017848014831542969 length of segment : 56 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00035500526428222656 length of segment : 18 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003845691680908203 length of segment : 18 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00042247772216796875 length of segment : 14 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.85391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.00023794174194335938 length of segment : 18 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.00040984153747558594 length of segment : 29 length of segment : 0 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003669261932373047 length of segment : 29 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0006170272827148438 length of segment : 23 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.00029587745666503906 length of segment : 19 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: 139.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0005211830139160156 length of segment : 64 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: -118.37578 max: 147.54141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 845 time to create 1 rle with old method : 0.0011715888977050781 length of segment : 40 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 899 time to create 1 rle with old method : 0.0011680126190185547 length of segment : 40 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.00021719932556152344 length of segment : 33 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 749 time to create 1 rle with old method : 0.0010428428649902344 length of segment : 34 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 1267 time to create 1 rle with old method : 0.0018968582153320312 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.64922 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 : 4.673004150390625e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002925395965576172 length of segment : 27 time for calcul the mask position with numpy : 0.00011682510375976562 nb_pixel_total : 6172 time to create 1 rle with old method : 0.007739067077636719 length of segment : 89 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005519390106201172 length of segment : 42 time for calcul the mask position with numpy : 0.00013875961303710938 nb_pixel_total : 3600 time to create 1 rle with old method : 0.004872798919677734 length of segment : 65 time for calcul the mask position with numpy : 0.00011801719665527344 nb_pixel_total : 324 time to create 1 rle with old method : 0.0007762908935546875 length of segment : 27 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0007128715515136719 length of segment : 62 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 5065 time to create 1 rle with old method : 0.006005287170410156 length of segment : 80 time for calcul the mask position with numpy : 0.00011324882507324219 nb_pixel_total : 3505 time to create 1 rle with old method : 0.004614114761352539 length of segment : 66 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -107.28984 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 2908 time to create 1 rle with old method : 0.0038712024688720703 length of segment : 103 time for calcul the mask position with numpy : 0.00020194053649902344 nb_pixel_total : 4888 time to create 1 rle with old method : 0.006338596343994141 length of segment : 128 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.000919342041015625 length of segment : 20 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003600120544433594 length of segment : 15 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0006251335144042969 length of segment : 17 time for calcul the mask position with numpy : 9.989738464355469e-05 nb_pixel_total : 3723 time to create 1 rle with old method : 0.004752159118652344 length of segment : 55 time for calcul the mask position with numpy : 0.00014209747314453125 nb_pixel_total : 7348 time to create 1 rle with old method : 0.009509801864624023 length of segment : 70 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 1104 time to create 1 rle with old method : 0.0016698837280273438 length of segment : 27 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 2067 time to create 1 rle with old method : 0.0028238296508789062 length of segment : 91 time for calcul the mask position with numpy : 0.00013899803161621094 nb_pixel_total : 3374 time to create 1 rle with old method : 0.004445314407348633 length of segment : 155 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.26250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00012040138244628906 nb_pixel_total : 4597 time to create 1 rle with old method : 0.005957126617431641 length of segment : 124 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0006849765777587891 length of segment : 48 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 2567 time to create 1 rle with old method : 0.0033974647521972656 length of segment : 90 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 250.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 125.06484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0006635189056396484 length of segment : 18 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 2626 time to create 1 rle with old method : 0.0032143592834472656 length of segment : 64 time for calcul the mask position with numpy : 0.000705718994140625 nb_pixel_total : 64114 time to create 1 rle with old method : 0.08195972442626953 length of segment : 290 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 193.00000 molded_images shape: (1, 640, 640, 3) min: -90.86797 max: 66.22500 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: -115.45781 max: 142.60391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.0001881122589111328 nb_pixel_total : 9526 time to create 1 rle with old method : 0.01097559928894043 length of segment : 146 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001995563507080078 length of segment : 15 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 2935 time to create 1 rle with old method : 0.0037331581115722656 length of segment : 52 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0010807514190673828 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.10625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0008003711700439453 length of segment : 27 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005261898040771484 length of segment : 27 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 810 time to create 1 rle with old method : 0.001140594482421875 length of segment : 70 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 711 time to create 1 rle with old method : 0.0009603500366210938 length of segment : 60 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.0003750324249267578 length of segment : 11 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 529 time to create 1 rle with old method : 0.0007479190826416016 length of segment : 26 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0005655288696289062 length of segment : 23 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0012428760528564453 length of segment : 51 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003037452697753906 length of segment : 16 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.0001857280731201172 length of segment : 7 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0007364749908447266 length of segment : 16 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 728 time to create 1 rle with old method : 0.0010018348693847656 length of segment : 26 time for calcul the mask position with numpy : 0.00027060508728027344 nb_pixel_total : 6603 time to create 1 rle with old method : 0.008346080780029297 length of segment : 175 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0004737377166748047 length of segment : 21 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0007877349853515625 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: -118.31328 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.00014853477478027344 length of segment : 7 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1630 time to create 1 rle with old method : 0.002026796340942383 length of segment : 122 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 981 time to create 1 rle with old method : 0.0013842582702636719 length of segment : 40 time for calcul the mask position with numpy : 0.00014853477478027344 nb_pixel_total : 6133 time to create 1 rle with old method : 0.008334636688232422 length of segment : 171 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 889 time to create 1 rle with old method : 0.0012700557708740234 length of segment : 23 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1263 time to create 1 rle with old method : 0.0015561580657958984 length of segment : 41 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.37734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00039839744567871094 length of segment : 23 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 680 time to create 1 rle with old method : 0.0013778209686279297 length of segment : 66 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 2187 time to create 1 rle with old method : 0.0026810169219970703 length of segment : 100 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1681 time to create 1 rle with old method : 0.002166748046875 length of segment : 87 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0008549690246582031 length of segment : 32 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 1710 time to create 1 rle with old method : 0.002278566360473633 length of segment : 105 time for calcul the mask position with numpy : 0.00023674964904785156 nb_pixel_total : 4856 time to create 1 rle with old method : 0.006315469741821289 length of segment : 230 Processing 1 images image shape: (280, 400, 3) min: 9.00000 max: 203.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 64.03359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0015726089477539062 nb_pixel_total : 105790 time to create 1 rle with old method : 0.12469601631164551 length of segment : 283 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: 150.60781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 3303 time to create 1 rle with old method : 0.004132986068725586 length of segment : 51 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0007688999176025391 length of segment : 50 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2777 time to create 1 rle with old method : 0.003470897674560547 length of segment : 87 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1430 time to create 1 rle with old method : 0.0018303394317626953 length of segment : 50 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.0010497570037841797 length of segment : 55 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1173 time to create 1 rle with old method : 0.001550436019897461 length of segment : 38 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 783 time to create 1 rle with old method : 0.001194000244140625 length of segment : 49 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.0004875659942626953 length of segment : 26 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.00041937828063964844 length of segment : 18 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.20937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.00038433074951171875 length of segment : 16 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 2158 time to create 1 rle with old method : 0.00274658203125 length of segment : 66 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1991 time to create 1 rle with old method : 0.00260162353515625 length of segment : 54 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1682 time to create 1 rle with old method : 0.0021178722381591797 length of segment : 101 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1417 time to create 1 rle with old method : 0.001817464828491211 length of segment : 38 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1582 time to create 1 rle with old method : 0.0019752979278564453 length of segment : 56 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 2955 time to create 1 rle with old method : 0.0035834312438964844 length of segment : 95 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 906 time to create 1 rle with old method : 0.0014111995697021484 length of segment : 39 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 843 time to create 1 rle with old method : 0.0013289451599121094 length of segment : 36 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.00036144256591796875 length of segment : 18 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 946 time to create 1 rle with old method : 0.0012371540069580078 length of segment : 31 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1657 time to create 1 rle with old method : 0.002025604248046875 length of segment : 58 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 570 time to create 1 rle with old method : 0.0007758140563964844 length of segment : 42 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00022649765014648438 length of segment : 17 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00022459030151367188 length of segment : 13 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.000396728515625 length of segment : 17 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.00030040740966796875 length of segment : 18 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.71328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002720355987548828 length of segment : 18 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.00037789344787597656 length of segment : 27 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0003082752227783203 length of segment : 18 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.00029754638671875 length of segment : 27 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 5 time to create 1 rle with old method : 2.2649765014648438e-05 length of segment : 5 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003478527069091797 length of segment : 28 time for calcul the mask position with numpy : 0.0002052783966064453 nb_pixel_total : 1153 time to create 1 rle with old method : 0.001440286636352539 length of segment : 92 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: 136.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00027298927307128906 length of segment : 38 Detection mask done ! Trying to reset tf kernel 3830697 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 88 tf kernel not reseted sub process len(results) : 308 len(list_Values) 308 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 308 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 : 1111 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 308 chid ids of type : 4228 Number RLEs to save : 18439 save missing photos in datou_result : time spend for datou_step_exec : 48.3438777923584 time spend to save output : 1.3020224571228027 total time spend for step 1 : 49.6459002494812 step2:brightness Wed Feb 26 18:21:20 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/1740590430_3829079_1339759616_6c1009a0a2eb83b7d55efabc2b01532c.jpg treat image : temp/1740590430_3829079_1339759581_06f75281224ad0231184c6d72188d478.jpg treat image : temp/1740590430_3829079_1339759579_cfa70172aa36bf9f9238995e7bb9e5fc.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 : 3 time used for this insertion : 0.012557506561279297 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 3 time used for this insertion : 0.011384010314941406 save missing photos in datou_result : time spend for datou_step_exec : 0.854550838470459 time spend to save output : 0.02863931655883789 total time spend for step 2 : 0.8831901550292969 step3:blur_detection Wed Feb 26 18:21:21 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/1740590430_3829079_1339759616_6c1009a0a2eb83b7d55efabc2b01532c.jpg resize: (1080, 1920) 1339759616 -7.480999422543179 treat image : temp/1740590430_3829079_1339759581_06f75281224ad0231184c6d72188d478.jpg resize: (1080, 1920) 1339759581 -7.212368463712293 treat image : temp/1740590430_3829079_1339759579_cfa70172aa36bf9f9238995e7bb9e5fc.jpg resize: (1080, 1920) 1339759579 -7.419221297940588 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 : 3 time used for this insertion : 0.04495501518249512 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 3 time used for this insertion : 0.010927200317382812 save missing photos in datou_result : time spend for datou_step_exec : 3.0336191654205322 time spend to save output : 0.060303449630737305 total time spend for step 3 : 3.0939226150512695 step4:rle_unique_nms_with_priority Wed Feb 26 18:21:24 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 308 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 102 nb_hashtags : 7 time to prepare the origin masks : 1.362717628479004 time for calcul the mask position with numpy : 0.08582162857055664 nb_pixel_total : 1766000 time to create 1 rle with new method : 0.12688708305358887 time for calcul the mask position with numpy : 0.008605241775512695 nb_pixel_total : 8482 time to create 1 rle with old method : 0.009408712387084961 time for calcul the mask position with numpy : 0.00869894027709961 nb_pixel_total : 58609 time to create 1 rle with old method : 0.06372189521789551 time for calcul the mask position with numpy : 0.008493661880493164 nb_pixel_total : 348 time to create 1 rle with old method : 0.00040602684020996094 time for calcul the mask position with numpy : 0.008430242538452148 nb_pixel_total : 958 time to create 1 rle with old method : 0.0010998249053955078 time for calcul the mask position with numpy : 0.008415937423706055 nb_pixel_total : 111 time to create 1 rle with old method : 0.00017213821411132812 time for calcul the mask position with numpy : 0.008418083190917969 nb_pixel_total : 498 time to create 1 rle with old method : 0.000576019287109375 time for calcul the mask position with numpy : 0.008468151092529297 nb_pixel_total : 32 time to create 1 rle with old method : 7.843971252441406e-05 time for calcul the mask position with numpy : 0.011221647262573242 nb_pixel_total : 241 time to create 1 rle with old method : 0.0005807876586914062 time for calcul the mask position with numpy : 0.012984991073608398 nb_pixel_total : 2781 time to create 1 rle with old method : 0.003983259201049805 time for calcul the mask position with numpy : 0.00860285758972168 nb_pixel_total : 870 time to create 1 rle with old method : 0.0010914802551269531 time for calcul the mask position with numpy : 0.00845193862915039 nb_pixel_total : 775 time to create 1 rle with old method : 0.0009076595306396484 time for calcul the mask position with numpy : 0.008435487747192383 nb_pixel_total : 903 time to create 1 rle with old method : 0.0010685920715332031 time for calcul the mask position with numpy : 0.008405685424804688 nb_pixel_total : 12 time to create 1 rle with old method : 3.0040740966796875e-05 time for calcul the mask position with numpy : 0.008432865142822266 nb_pixel_total : 231 time to create 1 rle with old method : 0.0002777576446533203 time for calcul the mask position with numpy : 0.008401632308959961 nb_pixel_total : 1069 time to create 1 rle with old method : 0.0012581348419189453 time for calcul the mask position with numpy : 0.008397579193115234 nb_pixel_total : 1291 time to create 1 rle with old method : 0.001500844955444336 time for calcul the mask position with numpy : 0.008516550064086914 nb_pixel_total : 2246 time to create 1 rle with old method : 0.002602100372314453 time for calcul the mask position with numpy : 0.008656024932861328 nb_pixel_total : 5854 time to create 1 rle with old method : 0.0064318180084228516 time for calcul the mask position with numpy : 0.008630752563476562 nb_pixel_total : 4305 time to create 1 rle with old method : 0.004820108413696289 time for calcul the mask position with numpy : 0.008501052856445312 nb_pixel_total : 1181 time to create 1 rle with old method : 0.001332998275756836 time for calcul the mask position with numpy : 0.008489608764648438 nb_pixel_total : 5734 time to create 1 rle with old method : 0.006235837936401367 time for calcul the mask position with numpy : 0.00883030891418457 nb_pixel_total : 556 time to create 1 rle with old method : 0.000850677490234375 time for calcul the mask position with numpy : 0.008668184280395508 nb_pixel_total : 827 time to create 1 rle with old method : 0.0009407997131347656 time for calcul the mask position with numpy : 0.008800745010375977 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001671314239501953 time for calcul the mask position with numpy : 0.010842323303222656 nb_pixel_total : 1177 time to create 1 rle with old method : 0.0014934539794921875 time for calcul the mask position with numpy : 0.008681774139404297 nb_pixel_total : 21288 time to create 1 rle with old method : 0.023319721221923828 time for calcul the mask position with numpy : 0.008765220642089844 nb_pixel_total : 15 time to create 1 rle with old method : 0.00018930435180664062 time for calcul the mask position with numpy : 0.008603096008300781 nb_pixel_total : 1146 time to create 1 rle with old method : 0.0013277530670166016 time for calcul the mask position with numpy : 0.008713245391845703 nb_pixel_total : 836 time to create 1 rle with old method : 0.001031637191772461 time for calcul the mask position with numpy : 0.008606910705566406 nb_pixel_total : 5773 time to create 1 rle with old method : 0.006365299224853516 time for calcul the mask position with numpy : 0.008658647537231445 nb_pixel_total : 4580 time to create 1 rle with old method : 0.005345582962036133 time for calcul the mask position with numpy : 0.008615493774414062 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003192424774169922 time for calcul the mask position with numpy : 0.011140108108520508 nb_pixel_total : 9665 time to create 1 rle with old method : 0.01068878173828125 time for calcul the mask position with numpy : 0.008840799331665039 nb_pixel_total : 1016 time to create 1 rle with old method : 0.0011928081512451172 time for calcul the mask position with numpy : 0.008656740188598633 nb_pixel_total : 664 time to create 1 rle with old method : 0.000812530517578125 time for calcul the mask position with numpy : 0.008831024169921875 nb_pixel_total : 104 time to create 1 rle with old method : 0.00018787384033203125 time for calcul the mask position with numpy : 0.008721113204956055 nb_pixel_total : 2274 time to create 1 rle with old method : 0.0034635066986083984 time for calcul the mask position with numpy : 0.01079702377319336 nb_pixel_total : 136 time to create 1 rle with old method : 0.000354766845703125 time for calcul the mask position with numpy : 0.009715557098388672 nb_pixel_total : 4566 time to create 1 rle with old method : 0.005859375 time for calcul the mask position with numpy : 0.01029348373413086 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0016741752624511719 time for calcul the mask position with numpy : 0.00868535041809082 nb_pixel_total : 453 time to create 1 rle with old method : 0.0005576610565185547 time for calcul the mask position with numpy : 0.008622884750366211 nb_pixel_total : 4 time to create 1 rle with old method : 2.6702880859375e-05 time for calcul the mask position with numpy : 0.008554458618164062 nb_pixel_total : 106 time to create 1 rle with old method : 0.00022673606872558594 time for calcul the mask position with numpy : 0.00856637954711914 nb_pixel_total : 216 time to create 1 rle with old method : 0.00028014183044433594 time for calcul the mask position with numpy : 0.008587360382080078 nb_pixel_total : 502 time to create 1 rle with old method : 0.0005927085876464844 time for calcul the mask position with numpy : 0.008471965789794922 nb_pixel_total : 745 time to create 1 rle with old method : 0.0008835792541503906 time for calcul the mask position with numpy : 0.008533477783203125 nb_pixel_total : 947 time to create 1 rle with old method : 0.0011610984802246094 time for calcul the mask position with numpy : 0.008555889129638672 nb_pixel_total : 1751 time to create 1 rle with old method : 0.001956462860107422 time for calcul the mask position with numpy : 0.008594512939453125 nb_pixel_total : 448 time to create 1 rle with old method : 0.0005316734313964844 time for calcul the mask position with numpy : 0.00853276252746582 nb_pixel_total : 81 time to create 1 rle with old method : 0.00012111663818359375 time for calcul the mask position with numpy : 0.008571863174438477 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001232624053955078 time for calcul the mask position with numpy : 0.008591651916503906 nb_pixel_total : 1183 time to create 1 rle with old method : 0.0013244152069091797 time for calcul the mask position with numpy : 0.008660078048706055 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003337860107421875 time for calcul the mask position with numpy : 0.008553028106689453 nb_pixel_total : 218 time to create 1 rle with old method : 0.0002734661102294922 time for calcul the mask position with numpy : 0.008514881134033203 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006122589111328125 time for calcul the mask position with numpy : 0.008564949035644531 nb_pixel_total : 326 time to create 1 rle with old method : 0.0003933906555175781 time for calcul the mask position with numpy : 0.008540630340576172 nb_pixel_total : 278 time to create 1 rle with old method : 0.0003726482391357422 time for calcul the mask position with numpy : 0.008496999740600586 nb_pixel_total : 857 time to create 1 rle with old method : 0.0010211467742919922 time for calcul the mask position with numpy : 0.008561372756958008 nb_pixel_total : 25 time to create 1 rle with old method : 5.8650970458984375e-05 time for calcul the mask position with numpy : 0.008538484573364258 nb_pixel_total : 341 time to create 1 rle with old method : 0.0003924369812011719 time for calcul the mask position with numpy : 0.00897836685180664 nb_pixel_total : 104444 time to create 1 rle with old method : 0.11439275741577148 time for calcul the mask position with numpy : 0.00845789909362793 nb_pixel_total : 9711 time to create 1 rle with old method : 0.010728836059570312 time for calcul the mask position with numpy : 0.008490324020385742 nb_pixel_total : 49 time to create 1 rle with old method : 8.916854858398438e-05 time for calcul the mask position with numpy : 0.008429765701293945 nb_pixel_total : 1519 time to create 1 rle with old method : 0.0017113685607910156 time for calcul the mask position with numpy : 0.008414268493652344 nb_pixel_total : 576 time to create 1 rle with old method : 0.0006511211395263672 time for calcul the mask position with numpy : 0.008425474166870117 nb_pixel_total : 333 time to create 1 rle with old method : 0.0003864765167236328 time for calcul the mask position with numpy : 0.008475065231323242 nb_pixel_total : 368 time to create 1 rle with old method : 0.0006887912750244141 time for calcul the mask position with numpy : 0.00885629653930664 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003254413604736328 time for calcul the mask position with numpy : 0.008476495742797852 nb_pixel_total : 1074 time to create 1 rle with old method : 0.0012218952178955078 time for calcul the mask position with numpy : 0.010191917419433594 nb_pixel_total : 88 time to create 1 rle with old method : 0.00012874603271484375 time for calcul the mask position with numpy : 0.00835108757019043 nb_pixel_total : 137 time to create 1 rle with old method : 0.00018930435180664062 time for calcul the mask position with numpy : 0.008339643478393555 nb_pixel_total : 593 time to create 1 rle with old method : 0.0006840229034423828 time for calcul the mask position with numpy : 0.008358478546142578 nb_pixel_total : 14 time to create 1 rle with old method : 3.9577484130859375e-05 time for calcul the mask position with numpy : 0.008440732955932617 nb_pixel_total : 170 time to create 1 rle with old method : 0.00020503997802734375 time for calcul the mask position with numpy : 0.008787870407104492 nb_pixel_total : 12 time to create 1 rle with old method : 6.67572021484375e-05 time for calcul the mask position with numpy : 0.008541107177734375 nb_pixel_total : 94 time to create 1 rle with old method : 0.00012731552124023438 time for calcul the mask position with numpy : 0.008442163467407227 nb_pixel_total : 105 time to create 1 rle with old method : 0.00016188621520996094 time for calcul the mask position with numpy : 0.008415937423706055 nb_pixel_total : 2818 time to create 1 rle with old method : 0.0031478404998779297 time for calcul the mask position with numpy : 0.008281946182250977 nb_pixel_total : 1352 time to create 1 rle with old method : 0.0015115737915039062 time for calcul the mask position with numpy : 0.008336305618286133 nb_pixel_total : 1388 time to create 1 rle with old method : 0.001558065414428711 time for calcul the mask position with numpy : 0.008369207382202148 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003159046173095703 time for calcul the mask position with numpy : 0.008415937423706055 nb_pixel_total : 227 time to create 1 rle with old method : 0.0002703666687011719 time for calcul the mask position with numpy : 0.008387327194213867 nb_pixel_total : 875 time to create 1 rle with old method : 0.0010094642639160156 time for calcul the mask position with numpy : 0.008471250534057617 nb_pixel_total : 3435 time to create 1 rle with old method : 0.003755807876586914 time for calcul the mask position with numpy : 0.008340835571289062 nb_pixel_total : 667 time to create 1 rle with old method : 0.0007419586181640625 time for calcul the mask position with numpy : 0.008364200592041016 nb_pixel_total : 2129 time to create 1 rle with old method : 0.002371549606323242 time for calcul the mask position with numpy : 0.008366107940673828 nb_pixel_total : 1424 time to create 1 rle with old method : 0.0016329288482666016 time for calcul the mask position with numpy : 0.008399724960327148 nb_pixel_total : 162 time to create 1 rle with old method : 0.00018596649169921875 time for calcul the mask position with numpy : 0.008352279663085938 nb_pixel_total : 2436 time to create 1 rle with old method : 0.0027141571044921875 time for calcul the mask position with numpy : 0.008383512496948242 nb_pixel_total : 306 time to create 1 rle with old method : 0.0003726482391357422 time for calcul the mask position with numpy : 0.008357524871826172 nb_pixel_total : 203 time to create 1 rle with old method : 0.00023603439331054688 time for calcul the mask position with numpy : 0.00838613510131836 nb_pixel_total : 1553 time to create 1 rle with old method : 0.0017900466918945312 time for calcul the mask position with numpy : 0.00923776626586914 nb_pixel_total : 195 time to create 1 rle with old method : 0.00022912025451660156 time for calcul the mask position with numpy : 0.008391857147216797 nb_pixel_total : 236 time to create 1 rle with old method : 0.00027370452880859375 time for calcul the mask position with numpy : 0.008331775665283203 nb_pixel_total : 903 time to create 1 rle with old method : 0.0010640621185302734 time for calcul the mask position with numpy : 0.008364439010620117 nb_pixel_total : 1942 time to create 1 rle with old method : 0.002151966094970703 time for calcul the mask position with numpy : 0.008266687393188477 nb_pixel_total : 275 time to create 1 rle with old method : 0.00037789344787597656 time for calcul the mask position with numpy : 0.00820469856262207 nb_pixel_total : 555 time to create 1 rle with old method : 0.0006284713745117188 time for calcul the mask position with numpy : 0.008300065994262695 nb_pixel_total : 498 time to create 1 rle with old method : 0.0006229877471923828 time for calcul the mask position with numpy : 0.008735179901123047 nb_pixel_total : 618 time to create 1 rle with old method : 0.0007128715515136719 time for calcul the mask position with numpy : 0.008356332778930664 nb_pixel_total : 1032 time to create 1 rle with old method : 0.0012462139129638672 time for calcul the mask position with numpy : 0.00832676887512207 nb_pixel_total : 466 time to create 1 rle with old method : 0.0005145072937011719 create new chi : 1.4604754447937012 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 : 0.006432533264160156 batch 1 Loaded 103 chid ids of type : 4230 Number RLEs to save : 11516 TO DO : save crop sub photo not yet done ! save time : 2.26051664352417 nb_obj : 109 nb_hashtags : 7 time to prepare the origin masks : 2.3281710147857666 time for calcul the mask position with numpy : 0.16198372840881348 nb_pixel_total : 1796111 time to create 1 rle with new method : 0.34955477714538574 time for calcul the mask position with numpy : 0.012354612350463867 nb_pixel_total : 2254 time to create 1 rle with old method : 0.0028772354125976562 time for calcul the mask position with numpy : 0.011368751525878906 nb_pixel_total : 751 time to create 1 rle with old method : 0.0010275840759277344 time for calcul the mask position with numpy : 0.01098012924194336 nb_pixel_total : 32 time to create 1 rle with old method : 6.628036499023438e-05 time for calcul the mask position with numpy : 0.010820865631103516 nb_pixel_total : 3925 time to create 1 rle with old method : 0.004698276519775391 time for calcul the mask position with numpy : 0.010870218276977539 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003275871276855469 time for calcul the mask position with numpy : 0.011601686477661133 nb_pixel_total : 199 time to create 1 rle with old method : 0.00026535987854003906 time for calcul the mask position with numpy : 0.009559392929077148 nb_pixel_total : 1305 time to create 1 rle with old method : 0.0015575885772705078 time for calcul the mask position with numpy : 0.01264333724975586 nb_pixel_total : 102 time to create 1 rle with old method : 0.00017118453979492188 time for calcul the mask position with numpy : 0.012624979019165039 nb_pixel_total : 52 time to create 1 rle with old method : 0.00012445449829101562 time for calcul the mask position with numpy : 0.007922172546386719 nb_pixel_total : 983 time to create 1 rle with old method : 0.0014185905456542969 time for calcul the mask position with numpy : 0.007636308670043945 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002009868621826172 time for calcul the mask position with numpy : 0.007818222045898438 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005106925964355469 time for calcul the mask position with numpy : 0.0070590972900390625 nb_pixel_total : 833 time to create 1 rle with old method : 0.0011506080627441406 time for calcul the mask position with numpy : 0.008154630661010742 nb_pixel_total : 824 time to create 1 rle with old method : 0.0011916160583496094 time for calcul the mask position with numpy : 0.006981849670410156 nb_pixel_total : 2663 time to create 1 rle with old method : 0.003007173538208008 time for calcul the mask position with numpy : 0.006827354431152344 nb_pixel_total : 589 time to create 1 rle with old method : 0.0006763935089111328 time for calcul the mask position with numpy : 0.006625175476074219 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006372928619384766 time for calcul the mask position with numpy : 0.008737564086914062 nb_pixel_total : 709 time to create 1 rle with old method : 0.0008015632629394531 time for calcul the mask position with numpy : 0.006520986557006836 nb_pixel_total : 565 time to create 1 rle with old method : 0.00064849853515625 time for calcul the mask position with numpy : 0.006483793258666992 nb_pixel_total : 2003 time to create 1 rle with old method : 0.002244234085083008 time for calcul the mask position with numpy : 0.006226778030395508 nb_pixel_total : 537 time to create 1 rle with old method : 0.0006442070007324219 time for calcul the mask position with numpy : 0.006323575973510742 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005271434783935547 time for calcul the mask position with numpy : 0.006549358367919922 nb_pixel_total : 6652 time to create 1 rle with old method : 0.007212162017822266 time for calcul the mask position with numpy : 0.009086132049560547 nb_pixel_total : 6301 time to create 1 rle with old method : 0.010266780853271484 time for calcul the mask position with numpy : 0.0066835880279541016 nb_pixel_total : 139 time to create 1 rle with old method : 0.00018787384033203125 time for calcul the mask position with numpy : 0.007390737533569336 nb_pixel_total : 5183 time to create 1 rle with old method : 0.006944417953491211 time for calcul the mask position with numpy : 0.006281375885009766 nb_pixel_total : 3689 time to create 1 rle with old method : 0.0042514801025390625 time for calcul the mask position with numpy : 0.006346225738525391 nb_pixel_total : 850 time to create 1 rle with old method : 0.001001119613647461 time for calcul the mask position with numpy : 0.006369829177856445 nb_pixel_total : 38 time to create 1 rle with old method : 9.489059448242188e-05 time for calcul the mask position with numpy : 0.00636744499206543 nb_pixel_total : 507 time to create 1 rle with old method : 0.0009224414825439453 time for calcul the mask position with numpy : 0.007218599319458008 nb_pixel_total : 18613 time to create 1 rle with old method : 0.02183818817138672 time for calcul the mask position with numpy : 0.006937742233276367 nb_pixel_total : 1133 time to create 1 rle with old method : 0.0013611316680908203 time for calcul the mask position with numpy : 0.007188558578491211 nb_pixel_total : 5476 time to create 1 rle with old method : 0.0062482357025146484 time for calcul the mask position with numpy : 0.006670713424682617 nb_pixel_total : 1959 time to create 1 rle with old method : 0.0023636817932128906 time for calcul the mask position with numpy : 0.006691455841064453 nb_pixel_total : 173 time to create 1 rle with old method : 0.0003204345703125 time for calcul the mask position with numpy : 0.006587982177734375 nb_pixel_total : 2160 time to create 1 rle with old method : 0.0025262832641601562 time for calcul the mask position with numpy : 0.00664973258972168 nb_pixel_total : 617 time to create 1 rle with old method : 0.0008766651153564453 time for calcul the mask position with numpy : 0.006865978240966797 nb_pixel_total : 2829 time to create 1 rle with old method : 0.0035097599029541016 time for calcul the mask position with numpy : 0.006917238235473633 nb_pixel_total : 10383 time to create 1 rle with old method : 0.011815309524536133 time for calcul the mask position with numpy : 0.007114410400390625 nb_pixel_total : 1163 time to create 1 rle with old method : 0.0016007423400878906 time for calcul the mask position with numpy : 0.008111238479614258 nb_pixel_total : 107 time to create 1 rle with old method : 0.00021648406982421875 time for calcul the mask position with numpy : 0.008903026580810547 nb_pixel_total : 448 time to create 1 rle with old method : 0.0006456375122070312 time for calcul the mask position with numpy : 0.007620811462402344 nb_pixel_total : 642 time to create 1 rle with old method : 0.0008955001831054688 time for calcul the mask position with numpy : 0.007540702819824219 nb_pixel_total : 17544 time to create 1 rle with old method : 0.02065587043762207 time for calcul the mask position with numpy : 0.007019996643066406 nb_pixel_total : 3966 time to create 1 rle with old method : 0.0048828125 time for calcul the mask position with numpy : 0.007493734359741211 nb_pixel_total : 71 time to create 1 rle with old method : 0.0001068115234375 time for calcul the mask position with numpy : 0.0070018768310546875 nb_pixel_total : 96 time to create 1 rle with old method : 0.0001678466796875 time for calcul the mask position with numpy : 0.007539033889770508 nb_pixel_total : 2330 time to create 1 rle with old method : 0.003142118453979492 time for calcul the mask position with numpy : 0.0074694156646728516 nb_pixel_total : 719 time to create 1 rle with old method : 0.0011320114135742188 time for calcul the mask position with numpy : 0.007561922073364258 nb_pixel_total : 113 time to create 1 rle with old method : 0.0005145072937011719 time for calcul the mask position with numpy : 0.006845235824584961 nb_pixel_total : 9795 time to create 1 rle with old method : 0.01180577278137207 time for calcul the mask position with numpy : 0.010833501815795898 nb_pixel_total : 2230 time to create 1 rle with old method : 0.0033082962036132812 time for calcul the mask position with numpy : 0.0066509246826171875 nb_pixel_total : 405 time to create 1 rle with old method : 0.00048232078552246094 time for calcul the mask position with numpy : 0.007147550582885742 nb_pixel_total : 103 time to create 1 rle with old method : 0.00015592575073242188 time for calcul the mask position with numpy : 0.007102012634277344 nb_pixel_total : 558 time to create 1 rle with old method : 0.0006632804870605469 time for calcul the mask position with numpy : 0.007314920425415039 nb_pixel_total : 109 time to create 1 rle with old method : 0.000152587890625 time for calcul the mask position with numpy : 0.008111715316772461 nb_pixel_total : 785 time to create 1 rle with old method : 0.0009489059448242188 time for calcul the mask position with numpy : 0.008085966110229492 nb_pixel_total : 823 time to create 1 rle with old method : 0.0011038780212402344 time for calcul the mask position with numpy : 0.007241725921630859 nb_pixel_total : 794 time to create 1 rle with old method : 0.0009381771087646484 time for calcul the mask position with numpy : 0.006899118423461914 nb_pixel_total : 1648 time to create 1 rle with old method : 0.0018610954284667969 time for calcul the mask position with numpy : 0.006288766860961914 nb_pixel_total : 88 time to create 1 rle with old method : 0.00011992454528808594 time for calcul the mask position with numpy : 0.006172657012939453 nb_pixel_total : 138 time to create 1 rle with old method : 0.0001742839813232422 time for calcul the mask position with numpy : 0.00617671012878418 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002646446228027344 time for calcul the mask position with numpy : 0.006088733673095703 nb_pixel_total : 231 time to create 1 rle with old method : 0.00027751922607421875 time for calcul the mask position with numpy : 0.0064623355865478516 nb_pixel_total : 395 time to create 1 rle with old method : 0.00048279762268066406 time for calcul the mask position with numpy : 0.0060939788818359375 nb_pixel_total : 316 time to create 1 rle with old method : 0.00039386749267578125 time for calcul the mask position with numpy : 0.0061283111572265625 nb_pixel_total : 202 time to create 1 rle with old method : 0.00025177001953125 time for calcul the mask position with numpy : 0.0063207149505615234 nb_pixel_total : 569 time to create 1 rle with old method : 0.0009057521820068359 time for calcul the mask position with numpy : 0.006781101226806641 nb_pixel_total : 342 time to create 1 rle with old method : 0.000446319580078125 time for calcul the mask position with numpy : 0.0063936710357666016 nb_pixel_total : 314 time to create 1 rle with old method : 0.0003764629364013672 time for calcul the mask position with numpy : 0.006180763244628906 nb_pixel_total : 808 time to create 1 rle with old method : 0.0008978843688964844 time for calcul the mask position with numpy : 0.006470680236816406 nb_pixel_total : 41 time to create 1 rle with old method : 7.987022399902344e-05 time for calcul the mask position with numpy : 0.006016731262207031 nb_pixel_total : 118 time to create 1 rle with old method : 0.00016808509826660156 time for calcul the mask position with numpy : 0.0064470767974853516 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005266666412353516 time for calcul the mask position with numpy : 0.011356592178344727 nb_pixel_total : 105166 time to create 1 rle with old method : 0.15454983711242676 time for calcul the mask position with numpy : 0.0068204402923583984 nb_pixel_total : 1693 time to create 1 rle with old method : 0.001941680908203125 time for calcul the mask position with numpy : 0.006689310073852539 nb_pixel_total : 8438 time to create 1 rle with old method : 0.009959936141967773 time for calcul the mask position with numpy : 0.006789445877075195 nb_pixel_total : 412 time to create 1 rle with old method : 0.00047850608825683594 time for calcul the mask position with numpy : 0.006379604339599609 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002791881561279297 time for calcul the mask position with numpy : 0.006249427795410156 nb_pixel_total : 35 time to create 1 rle with old method : 7.581710815429688e-05 time for calcul the mask position with numpy : 0.006122112274169922 nb_pixel_total : 164 time to create 1 rle with old method : 0.00021839141845703125 time for calcul the mask position with numpy : 0.006428241729736328 nb_pixel_total : 290 time to create 1 rle with old method : 0.00034236907958984375 time for calcul the mask position with numpy : 0.0062367916107177734 nb_pixel_total : 243 time to create 1 rle with old method : 0.00029349327087402344 time for calcul the mask position with numpy : 0.006299495697021484 nb_pixel_total : 370 time to create 1 rle with old method : 0.00045180320739746094 time for calcul the mask position with numpy : 0.006249427795410156 nb_pixel_total : 92 time to create 1 rle with old method : 0.00012421607971191406 time for calcul the mask position with numpy : 0.0063364505767822266 nb_pixel_total : 149 time to create 1 rle with old method : 0.00019121170043945312 time for calcul the mask position with numpy : 0.006295442581176758 nb_pixel_total : 247 time to create 1 rle with old method : 0.0002765655517578125 time for calcul the mask position with numpy : 0.006547212600708008 nb_pixel_total : 837 time to create 1 rle with old method : 0.0009374618530273438 time for calcul the mask position with numpy : 0.006643772125244141 nb_pixel_total : 1613 time to create 1 rle with old method : 0.0018334388732910156 time for calcul the mask position with numpy : 0.006728410720825195 nb_pixel_total : 2979 time to create 1 rle with old method : 0.003376007080078125 time for calcul the mask position with numpy : 0.006629467010498047 nb_pixel_total : 1299 time to create 1 rle with old method : 0.0014846324920654297 time for calcul the mask position with numpy : 0.006369829177856445 nb_pixel_total : 249 time to create 1 rle with old method : 0.00030517578125 time for calcul the mask position with numpy : 0.0064051151275634766 nb_pixel_total : 24 time to create 1 rle with old method : 7.05718994140625e-05 time for calcul the mask position with numpy : 0.006697893142700195 nb_pixel_total : 343 time to create 1 rle with old method : 0.00041413307189941406 time for calcul the mask position with numpy : 0.006609201431274414 nb_pixel_total : 1226 time to create 1 rle with old method : 0.0014145374298095703 time for calcul the mask position with numpy : 0.006734132766723633 nb_pixel_total : 1075 time to create 1 rle with old method : 0.0012805461883544922 time for calcul the mask position with numpy : 0.006682872772216797 nb_pixel_total : 3293 time to create 1 rle with old method : 0.0036039352416992188 time for calcul the mask position with numpy : 0.0060558319091796875 nb_pixel_total : 701 time to create 1 rle with old method : 0.0007498264312744141 time for calcul the mask position with numpy : 0.006039142608642578 nb_pixel_total : 223 time to create 1 rle with old method : 0.0002713203430175781 time for calcul the mask position with numpy : 0.006039857864379883 nb_pixel_total : 2128 time to create 1 rle with old method : 0.002595663070678711 time for calcul the mask position with numpy : 0.0061647891998291016 nb_pixel_total : 1532 time to create 1 rle with old method : 0.001764535903930664 time for calcul the mask position with numpy : 0.006131410598754883 nb_pixel_total : 2597 time to create 1 rle with old method : 0.003124237060546875 time for calcul the mask position with numpy : 0.008472681045532227 nb_pixel_total : 90 time to create 1 rle with old method : 0.00011992454528808594 time for calcul the mask position with numpy : 0.010566234588623047 nb_pixel_total : 170 time to create 1 rle with old method : 0.0002911090850830078 time for calcul the mask position with numpy : 0.008193492889404297 nb_pixel_total : 995 time to create 1 rle with old method : 0.0011026859283447266 time for calcul the mask position with numpy : 0.008154153823852539 nb_pixel_total : 1947 time to create 1 rle with old method : 0.002106189727783203 time for calcul the mask position with numpy : 0.008147954940795898 nb_pixel_total : 308 time to create 1 rle with old method : 0.0003495216369628906 time for calcul the mask position with numpy : 0.008135080337524414 nb_pixel_total : 753 time to create 1 rle with old method : 0.0008788108825683594 time for calcul the mask position with numpy : 0.008191585540771484 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002493858337402344 create new chi : 1.6976959705352783 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 : 0.001650094985961914 batch 1 Loaded 110 chid ids of type : 4230 Number RLEs to save : 13168 TO DO : save crop sub photo not yet done ! save time : 1.8129618167877197 nb_obj : 96 nb_hashtags : 7 time to prepare the origin masks : 1.520308017730713 time for calcul the mask position with numpy : 0.01985025405883789 nb_pixel_total : 1779369 time to create 1 rle with new method : 0.03951907157897949 time for calcul the mask position with numpy : 0.006597757339477539 nb_pixel_total : 427 time to create 1 rle with old method : 0.0006031990051269531 time for calcul the mask position with numpy : 0.0067212581634521484 nb_pixel_total : 6172 time to create 1 rle with old method : 0.007670164108276367 time for calcul the mask position with numpy : 0.006681919097900391 nb_pixel_total : 5 time to create 1 rle with old method : 7.772445678710938e-05 time for calcul the mask position with numpy : 0.006593465805053711 nb_pixel_total : 2067 time to create 1 rle with old method : 0.002547740936279297 time for calcul the mask position with numpy : 0.006867885589599609 nb_pixel_total : 68 time to create 1 rle with old method : 0.0001544952392578125 time for calcul the mask position with numpy : 0.007167339324951172 nb_pixel_total : 378 time to create 1 rle with old method : 0.000545501708984375 time for calcul the mask position with numpy : 0.007831335067749023 nb_pixel_total : 64114 time to create 1 rle with old method : 0.08011817932128906 time for calcul the mask position with numpy : 0.007315397262573242 nb_pixel_total : 845 time to create 1 rle with old method : 0.0009837150573730469 time for calcul the mask position with numpy : 0.007157087326049805 nb_pixel_total : 151 time to create 1 rle with old method : 0.0002014636993408203 time for calcul the mask position with numpy : 0.007945060729980469 nb_pixel_total : 899 time to create 1 rle with old method : 0.001127004623413086 time for calcul the mask position with numpy : 0.00824284553527832 nb_pixel_total : 1267 time to create 1 rle with old method : 0.0016896724700927734 time for calcul the mask position with numpy : 0.0073244571685791016 nb_pixel_total : 235 time to create 1 rle with old method : 0.00034165382385253906 time for calcul the mask position with numpy : 0.007005453109741211 nb_pixel_total : 515 time to create 1 rle with old method : 0.000637054443359375 time for calcul the mask position with numpy : 0.006890296936035156 nb_pixel_total : 3600 time to create 1 rle with old method : 0.004816770553588867 time for calcul the mask position with numpy : 0.0076143741607666016 nb_pixel_total : 170 time to create 1 rle with old method : 0.00029349327087402344 time for calcul the mask position with numpy : 0.007262229919433594 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002453327178955078 time for calcul the mask position with numpy : 0.006318569183349609 nb_pixel_total : 464 time to create 1 rle with old method : 0.0006451606750488281 time for calcul the mask position with numpy : 0.0066564083099365234 nb_pixel_total : 3723 time to create 1 rle with old method : 0.004776954650878906 time for calcul the mask position with numpy : 0.0071146488189697266 nb_pixel_total : 2567 time to create 1 rle with old method : 0.003185272216796875 time for calcul the mask position with numpy : 0.006946086883544922 nb_pixel_total : 1104 time to create 1 rle with old method : 0.00136566162109375 time for calcul the mask position with numpy : 0.006903648376464844 nb_pixel_total : 4888 time to create 1 rle with old method : 0.0057849884033203125 time for calcul the mask position with numpy : 0.007119178771972656 nb_pixel_total : 4597 time to create 1 rle with old method : 0.005516529083251953 time for calcul the mask position with numpy : 0.007421731948852539 nb_pixel_total : 2908 time to create 1 rle with old method : 0.004086017608642578 time for calcul the mask position with numpy : 0.007630348205566406 nb_pixel_total : 2625 time to create 1 rle with old method : 0.0036079883575439453 time for calcul the mask position with numpy : 0.007333517074584961 nb_pixel_total : 7348 time to create 1 rle with old method : 0.01001429557800293 time for calcul the mask position with numpy : 0.007525920867919922 nb_pixel_total : 98 time to create 1 rle with old method : 0.0003151893615722656 time for calcul the mask position with numpy : 0.007669687271118164 nb_pixel_total : 225 time to create 1 rle with old method : 0.0002925395965576172 time for calcul the mask position with numpy : 0.008012771606445312 nb_pixel_total : 431 time to create 1 rle with old method : 0.0006353855133056641 time for calcul the mask position with numpy : 0.007745504379272461 nb_pixel_total : 5 time to create 1 rle with old method : 3.528594970703125e-05 time for calcul the mask position with numpy : 0.007886171340942383 nb_pixel_total : 219 time to create 1 rle with old method : 0.0003745555877685547 time for calcul the mask position with numpy : 0.0062334537506103516 nb_pixel_total : 888 time to create 1 rle with old method : 0.0011577606201171875 time for calcul the mask position with numpy : 0.007598400115966797 nb_pixel_total : 6133 time to create 1 rle with old method : 0.008435487747192383 time for calcul the mask position with numpy : 0.006896495819091797 nb_pixel_total : 6603 time to create 1 rle with old method : 0.008910894393920898 time for calcul the mask position with numpy : 0.007358074188232422 nb_pixel_total : 1263 time to create 1 rle with old method : 0.0017247200012207031 time for calcul the mask position with numpy : 0.007601499557495117 nb_pixel_total : 711 time to create 1 rle with old method : 0.0010714530944824219 time for calcul the mask position with numpy : 0.007827043533325195 nb_pixel_total : 9526 time to create 1 rle with old method : 0.012992143630981445 time for calcul the mask position with numpy : 0.007991313934326172 nb_pixel_total : 176 time to create 1 rle with old method : 0.00029158592224121094 time for calcul the mask position with numpy : 0.007905244827270508 nb_pixel_total : 4856 time to create 1 rle with old method : 0.006615400314331055 time for calcul the mask position with numpy : 0.007885217666625977 nb_pixel_total : 2142 time to create 1 rle with old method : 0.0031430721282958984 time for calcul the mask position with numpy : 0.008643388748168945 nb_pixel_total : 55 time to create 1 rle with old method : 0.00014591217041015625 time for calcul the mask position with numpy : 0.013274669647216797 nb_pixel_total : 523 time to create 1 rle with old method : 0.0008800029754638672 time for calcul the mask position with numpy : 0.01444244384765625 nb_pixel_total : 1630 time to create 1 rle with old method : 0.002368927001953125 time for calcul the mask position with numpy : 0.013448715209960938 nb_pixel_total : 398 time to create 1 rle with old method : 0.0005369186401367188 time for calcul the mask position with numpy : 0.012919187545776367 nb_pixel_total : 10 time to create 1 rle with old method : 6.508827209472656e-05 time for calcul the mask position with numpy : 0.00783848762512207 nb_pixel_total : 810 time to create 1 rle with old method : 0.0010955333709716797 time for calcul the mask position with numpy : 0.008182048797607422 nb_pixel_total : 53 time to create 1 rle with old method : 0.00012302398681640625 time for calcul the mask position with numpy : 0.008093118667602539 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007865428924560547 time for calcul the mask position with numpy : 0.008249998092651367 nb_pixel_total : 680 time to create 1 rle with old method : 0.0010333061218261719 time for calcul the mask position with numpy : 0.009142160415649414 nb_pixel_total : 2935 time to create 1 rle with old method : 0.004940032958984375 time for calcul the mask position with numpy : 0.009639978408813477 nb_pixel_total : 981 time to create 1 rle with old method : 0.001538991928100586 time for calcul the mask position with numpy : 0.008373022079467773 nb_pixel_total : 1681 time to create 1 rle with old method : 0.002723217010498047 time for calcul the mask position with numpy : 0.009470939636230469 nb_pixel_total : 728 time to create 1 rle with old method : 0.001355886459350586 time for calcul the mask position with numpy : 0.009569168090820312 nb_pixel_total : 82 time to create 1 rle with old method : 0.00018310546875 time for calcul the mask position with numpy : 0.009436607360839844 nb_pixel_total : 115 time to create 1 rle with old method : 0.0002090930938720703 time for calcul the mask position with numpy : 0.00937795639038086 nb_pixel_total : 307 time to create 1 rle with old method : 0.000591278076171875 time for calcul the mask position with numpy : 0.01306605339050293 nb_pixel_total : 199 time to create 1 rle with old method : 0.0004456043243408203 time for calcul the mask position with numpy : 0.013521432876586914 nb_pixel_total : 529 time to create 1 rle with old method : 0.0008981227874755859 time for calcul the mask position with numpy : 0.013224363327026367 nb_pixel_total : 375 time to create 1 rle with old method : 0.0006117820739746094 time for calcul the mask position with numpy : 0.013132572174072266 nb_pixel_total : 889 time to create 1 rle with old method : 0.0015804767608642578 time for calcul the mask position with numpy : 0.013505220413208008 nb_pixel_total : 46 time to create 1 rle with old method : 0.00015592575073242188 time for calcul the mask position with numpy : 0.012647390365600586 nb_pixel_total : 484 time to create 1 rle with old method : 0.0008823871612548828 time for calcul the mask position with numpy : 0.014773368835449219 nb_pixel_total : 105790 time to create 1 rle with old method : 0.11976790428161621 time for calcul the mask position with numpy : 0.010073661804199219 nb_pixel_total : 197 time to create 1 rle with old method : 0.00025534629821777344 time for calcul the mask position with numpy : 0.009856700897216797 nb_pixel_total : 105 time to create 1 rle with old method : 0.00016450881958007812 time for calcul the mask position with numpy : 0.009790658950805664 nb_pixel_total : 570 time to create 1 rle with old method : 0.000682830810546875 time for calcul the mask position with numpy : 0.006414651870727539 nb_pixel_total : 1582 time to create 1 rle with old method : 0.001965761184692383 time for calcul the mask position with numpy : 0.006139039993286133 nb_pixel_total : 274 time to create 1 rle with old method : 0.0003330707550048828 time for calcul the mask position with numpy : 0.0061337947845458984 nb_pixel_total : 120 time to create 1 rle with old method : 0.000186920166015625 time for calcul the mask position with numpy : 0.0062596797943115234 nb_pixel_total : 10 time to create 1 rle with old method : 4.458427429199219e-05 time for calcul the mask position with numpy : 0.006364583969116211 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002033710479736328 time for calcul the mask position with numpy : 0.006428241729736328 nb_pixel_total : 1173 time to create 1 rle with old method : 0.0013928413391113281 time for calcul the mask position with numpy : 0.006239414215087891 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002772808074951172 time for calcul the mask position with numpy : 0.006731510162353516 nb_pixel_total : 906 time to create 1 rle with old method : 0.0015070438385009766 time for calcul the mask position with numpy : 0.006608486175537109 nb_pixel_total : 139 time to create 1 rle with old method : 0.00027441978454589844 time for calcul the mask position with numpy : 0.0068814754486083984 nb_pixel_total : 1682 time to create 1 rle with old method : 0.002713441848754883 time for calcul the mask position with numpy : 0.00668644905090332 nb_pixel_total : 3303 time to create 1 rle with old method : 0.005304574966430664 time for calcul the mask position with numpy : 0.006874799728393555 nb_pixel_total : 2955 time to create 1 rle with old method : 0.004791736602783203 time for calcul the mask position with numpy : 0.0066754817962646484 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004229545593261719 time for calcul the mask position with numpy : 0.006700992584228516 nb_pixel_total : 240 time to create 1 rle with old method : 0.0004169940948486328 time for calcul the mask position with numpy : 0.006771087646484375 nb_pixel_total : 946 time to create 1 rle with old method : 0.0015573501586914062 time for calcul the mask position with numpy : 0.006675004959106445 nb_pixel_total : 621 time to create 1 rle with old method : 0.0010104179382324219 time for calcul the mask position with numpy : 0.006963491439819336 nb_pixel_total : 343 time to create 1 rle with old method : 0.0005955696105957031 time for calcul the mask position with numpy : 0.0063931941986083984 nb_pixel_total : 1139 time to create 1 rle with old method : 0.001295328140258789 time for calcul the mask position with numpy : 0.006273031234741211 nb_pixel_total : 2158 time to create 1 rle with old method : 0.0024213790893554688 time for calcul the mask position with numpy : 0.0063135623931884766 nb_pixel_total : 49 time to create 1 rle with old method : 9.059906005859375e-05 time for calcul the mask position with numpy : 0.006575107574462891 nb_pixel_total : 1417 time to create 1 rle with old method : 0.0016164779663085938 time for calcul the mask position with numpy : 0.006385087966918945 nb_pixel_total : 210 time to create 1 rle with old method : 0.000255584716796875 time for calcul the mask position with numpy : 0.006121635437011719 nb_pixel_total : 2777 time to create 1 rle with old method : 0.003095388412475586 time for calcul the mask position with numpy : 0.008018970489501953 nb_pixel_total : 1430 time to create 1 rle with old method : 0.001890420913696289 time for calcul the mask position with numpy : 0.008066654205322266 nb_pixel_total : 783 time to create 1 rle with old method : 0.0011210441589355469 time for calcul the mask position with numpy : 0.008312702178955078 nb_pixel_total : 1991 time to create 1 rle with old method : 0.002788066864013672 time for calcul the mask position with numpy : 0.007040739059448242 nb_pixel_total : 828 time to create 1 rle with old method : 0.0009636878967285156 time for calcul the mask position with numpy : 0.006277561187744141 nb_pixel_total : 270 time to create 1 rle with old method : 0.00040149688720703125 time for calcul the mask position with numpy : 0.006064414978027344 nb_pixel_total : 5 time to create 1 rle with old method : 2.574920654296875e-05 time for calcul the mask position with numpy : 0.00608062744140625 nb_pixel_total : 843 time to create 1 rle with old method : 0.0011780261993408203 time for calcul the mask position with numpy : 0.008621454238891602 nb_pixel_total : 207 time to create 1 rle with old method : 0.00043654441833496094 create new chi : 1.2118122577667236 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 : 0.002357959747314453 batch 1 Loaded 97 chid ids of type : 4230 Number RLEs to save : 11055 TO DO : save crop sub photo not yet done ! save time : 0.9480748176574707 map_output_result : {1339759616: (0.0, 'Should be the crop_list due to order', 0.0), 1339759581: (0.0, 'Should be the crop_list due to order', 0.0), 1339759579: (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 [1339759616, 1339759581, 1339759579] Looping around the photos to save general results len do output : 3 /1339759616.Didn't retrieve data . /1339759581.Didn't retrieve data . /1339759579.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, '2616930') ('4234', '20848651', '1339759616', None, None, None, None, None, '2616930') ('4234', None, None, None, None, None, None, None, '2616930') ('4234', '20848651', '1339759581', None, None, None, None, None, '2616930') ('4234', None, None, None, None, None, None, None, '2616930') ('4234', '20848651', '1339759579', None, None, None, None, None, '2616930') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.04909801483154297 save_final save missing photos in datou_result : time spend for datou_step_exec : 15.265827655792236 time spend to save output : 0.04935288429260254 total time spend for step 4 : 15.315180540084839 step5:crop_condition Wed Feb 26 18:21:39 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 : 3 ! batch 1 Loaded 310 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 ! map_result returned by crop_photo_return_map_crop : length : 103 About to insert : list_path_to_insert length 103 new photo from crops ! About to upload 103 photos upload in portfolio : 4869462 init cache_photo without model_param we have 103 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740590502_3829079 we have uploaded 103 photos in the portfolio 4869462 time of upload the photos Elapsed time : 27.06701135635376 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 ! map_result returned by crop_photo_return_map_crop : length : 45 About to insert : list_path_to_insert length 45 new photo from crops ! About to upload 45 photos upload in portfolio : 4869462 init cache_photo without model_param we have 45 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740590529_3829079 we have uploaded 45 photos in the portfolio 4869462 time of upload the photos Elapsed time : 9.394670486450195 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 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740590539_3829079 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9824392795562744 we have finished the crop for the class : metal 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 ! 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 : 15 About to insert : list_path_to_insert length 15 new photo from crops ! About to upload 15 photos upload in portfolio : 4869462 init cache_photo without model_param we have 15 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740590541_3829079 we have uploaded 15 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.3942177295684814 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 ! 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 : 37 About to insert : list_path_to_insert length 37 new photo from crops ! About to upload 37 photos upload in portfolio : 4869462 init cache_photo without model_param we have 37 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740590544_3829079 we have uploaded 37 photos in the portfolio 4869462 time of upload the photos Elapsed time : 9.672244787216187 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 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 [1339759616, 1339759581, 1339759579] Looping around the photos to save general results len do output : 202 /1339766496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766578Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766656Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339766729Didn'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, '2616930') ('4234', '20848651', '1339759616', None, None, None, None, None, '2616930') ('4234', None, None, None, None, None, None, None, '2616930') ('4234', '20848651', '1339759581', None, None, None, None, None, '2616930') ('4234', None, None, None, None, None, None, None, '2616930') ('4234', '20848651', '1339759579', None, None, None, None, None, '2616930') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 609 time used for this insertion : 0.03771257400512695 save_final save missing photos in datou_result : time spend for datou_step_exec : 54.89765024185181 time spend to save output : 0.044257402420043945 total time spend for step 5 : 54.94190764427185 step6:thcl Wed Feb 26 18:22:34 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 : 0.0076961517333984375 time to convert the images to numpy array : 0.031195878982543945 time to import caffe and check if the image exist : 0.012215375900268555 time to convert the images to numpy array : 0.0460813045501709 time to import caffe and check if the image exist : 0.016568899154663086 time to convert the images to numpy array : 0.05603170394897461 time to import caffe and check if the image exist : 0.02715921401977539 time to convert the images to numpy array : 0.049452781677246094 time to import caffe and check if the image exist : 0.01598978042602539 time to convert the images to numpy array : 0.062323570251464844 time to import caffe and check if the image exist : 0.018886089324951172 time to convert the images to numpy array : 0.06085324287414551 time to import caffe and check if the image exist : 0.028798818588256836 time to convert the images to numpy array : 0.052327871322631836 time to import caffe and check if the image exist : 0.0254976749420166 time to convert the images to numpy array : 0.056322336196899414 time to import caffe and check if the image exist : 0.03403806686401367 time to convert the images to numpy array : 0.048064470291137695 time to import caffe and check if the image exist : 0.024146556854248047 time to convert the images to numpy array : 0.05863165855407715 total time to convert the images to numpy array : 0.4165208339691162 list photo_ids error: [] list photo_ids correct : [1339766717, 1339766718, 1339766719, 1339766720, 1339766721, 1339766722, 1339766723, 1339766724, 1339766725, 1339766726, 1339766727, 1339766728, 1339766729, 1339766496, 1339766497, 1339766498, 1339766499, 1339766500, 1339766501, 1339766502, 1339766503, 1339766504, 1339766505, 1339766506, 1339766507, 1339766508, 1339766509, 1339766510, 1339766511, 1339766512, 1339766513, 1339766514, 1339766515, 1339766516, 1339766538, 1339766539, 1339766540, 1339766541, 1339766542, 1339766543, 1339766544, 1339766545, 1339766546, 1339766547, 1339766548, 1339766549, 1339766550, 1339766551, 1339766552, 1339766553, 1339766554, 1339766555, 1339766556, 1339766557, 1339766558, 1339766580, 1339766581, 1339766582, 1339766583, 1339766584, 1339766585, 1339766586, 1339766587, 1339766588, 1339766589, 1339766590, 1339766591, 1339766592, 1339766593, 1339766594, 1339766596, 1339766597, 1339766598, 1339766599, 1339766615, 1339766616, 1339766640, 1339766641, 1339766642, 1339766643, 1339766644, 1339766645, 1339766646, 1339766647, 1339766648, 1339766649, 1339766650, 1339766651, 1339766652, 1339766653, 1339766654, 1339766655, 1339766656, 1339766657, 1339766658, 1339766659, 1339766660, 1339766559, 1339766560, 1339766561, 1339766562, 1339766563, 1339766564, 1339766565, 1339766566, 1339766567, 1339766568, 1339766569, 1339766570, 1339766571, 1339766572, 1339766573, 1339766574, 1339766575, 1339766576, 1339766577, 1339766578, 1339766579, 1339766617, 1339766618, 1339766619, 1339766620, 1339766621, 1339766622, 1339766623, 1339766624, 1339766625, 1339766626, 1339766628, 1339766629, 1339766630, 1339766631, 1339766632, 1339766633, 1339766634, 1339766635, 1339766636, 1339766638, 1339766639, 1339766661, 1339766668, 1339766669, 1339766671, 1339766672, 1339766673, 1339766674, 1339766675, 1339766676, 1339766677, 1339766678, 1339766679, 1339766680, 1339766681, 1339766682, 1339766683, 1339766684, 1339766685, 1339766691, 1339766692, 1339766693, 1339766694, 1339766695, 1339766696, 1339766697, 1339766698, 1339766699, 1339766700, 1339766702, 1339766703, 1339766704, 1339766705, 1339766706, 1339766707, 1339766708, 1339766709, 1339766710, 1339766711, 1339766712, 1339766714, 1339766715, 1339766716, 1339766517, 1339766518, 1339766519, 1339766520, 1339766521, 1339766522, 1339766523, 1339766524, 1339766525, 1339766526, 1339766527, 1339766528, 1339766529, 1339766530, 1339766531, 1339766532, 1339766533, 1339766534, 1339766535, 1339766536, 1339766537] number of photos to traite : 202 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 : 887 wait 20 seconds l 3637 free memory gpu now : 887 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 : 668 wait 20 seconds WARNING: Logging before InitGoogleLogging() is written to STDERR F0226 18:23:20.223258 3829079 syncedmem.cpp:71] Check failed: error == cudaSuccess (2 vs. 0) out of memory *** Check failure stack trace: *** Command terminated by signal 6 39.63user 26.95system 2:55.52elapsed 37%CPU (0avgtext+0avgdata 2390064maxresident)k 1477168inputs+9056outputs (6029major+2243880minor)pagefaults 0swaps