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 : 1251291 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 : ['2582951'] with mtr_portfolio_ids : ['20513076'] and first list_photo_ids : [] new path : /proc/1251291/ 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 : 0.37668848037719727 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 Thu Feb 13 19:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10772 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-13 19:20:31.859164: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-13 19:20:31.887276: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-13 19:20:31.889151: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f14b4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-13 19:20:31.889199: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-13 19:20:31.892734: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-13 19:20:32.153201: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3107e160 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-13 19:20:32.153264: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-13 19:20:32.155595: 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 2025-02-13 19:20:32.156485: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-13 19:20:32.160896: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-13 19:20:32.178929: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-13 19:20:32.180515: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-13 19:20:32.203220: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-13 19:20:32.207276: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-13 19:20:32.254944: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-13 19:20:32.256800: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-13 19:20:32.257301: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-13 19:20:32.258275: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-13 19:20:32.258298: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-13 19:20:32.258310: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-13 19:20:32.260492: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9983 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. 2025-02-13 19:20:32.569786: 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 2025-02-13 19:20:32.569876: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-13 19:20:32.569900: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-13 19:20:32.569921: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-13 19:20:32.569941: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-13 19:20:32.569961: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-13 19:20:32.569981: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-13 19:20:32.570001: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-13 19:20:32.571573: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-13 19:20:32.572981: 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 2025-02-13 19:20:32.573017: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-13 19:20:32.573036: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-13 19:20:32.573053: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-13 19:20:32.573070: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-13 19:20:32.573087: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-13 19:20:32.573104: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-13 19:20:32.573121: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-13 19:20:32.574838: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-13 19:20:32.574877: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-13 19:20:32.574887: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-13 19:20:32.574920: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-13 19:20:32.576750: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9983 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 : [] 2025-02-13 19:20:39.643133: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-13 19:20:39.818196: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 3 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.81328 max: 148.49453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 895 time to create 1 rle with old method : 0.0019402503967285156 length of segment : 36 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 846 time to create 1 rle with old method : 0.0018067359924316406 length of segment : 39 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.0003409385681152344 length of segment : 29 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.00017189979553222656 length of segment : 16 length of segment : 0 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.000354766845703125 length of segment : 28 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.0003135204315185547 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.07500 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 3586 time to create 1 rle with old method : 0.004575967788696289 length of segment : 38 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005562305450439453 length of segment : 24 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 2238 time to create 1 rle with old method : 0.0026717185974121094 length of segment : 44 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.0009684562683105469 length of segment : 35 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.0003294944763183594 length of segment : 23 length of segment : 0 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0009007453918457031 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.37969 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 : 4.887580871582031e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0010061264038085938 length of segment : 45 time for calcul the mask position with numpy : 0.00010466575622558594 nb_pixel_total : 6391 time to create 1 rle with old method : 0.007567167282104492 length of segment : 109 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 723 time to create 1 rle with old method : 0.0013468265533447266 length of segment : 30 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1348 time to create 1 rle with old method : 0.0023131370544433594 length of segment : 39 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1511 time to create 1 rle with old method : 0.0028142929077148438 length of segment : 26 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1611 time to create 1 rle with old method : 0.0036869049072265625 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.89141 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0010302066802978516 length of segment : 24 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0005834102630615234 length of segment : 19 time for calcul the mask position with numpy : 0.0001780986785888672 nb_pixel_total : 9092 time to create 1 rle with old method : 0.01491546630859375 length of segment : 108 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 892 time to create 1 rle with old method : 0.001565694808959961 length of segment : 35 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: 114.79141 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 : 1245 time to create 1 rle with old method : 0.0015969276428222656 length of segment : 38 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007469654083251953 length of segment : 20 time for calcul the mask position with numpy : 0.0006077289581298828 nb_pixel_total : 58195 time to create 1 rle with old method : 0.06573081016540527 length of segment : 359 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.00017261505126953125 length of segment : 9 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 36 time for calcul the mask position with numpy : 0.00015997886657714844 nb_pixel_total : 2990 time to create 1 rle with old method : 0.0035495758056640625 length of segment : 153 time for calcul the mask position with numpy : 0.0007715225219726562 nb_pixel_total : 70695 time to create 1 rle with old method : 0.07777595520019531 length of segment : 328 Processing 1 images image shape: (400, 400, 3) min: 25.00000 max: 228.00000 molded_images shape: (1, 640, 640, 3) min: -80.94219 max: 98.12344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.001672506332397461 nb_pixel_total : 152394 time to create 1 rle with new method : 0.002346515655517578 length of segment : 399 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -105.41094 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 : 5.030632019042969e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0005812644958496094 length of segment : 17 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 2353 time to create 1 rle with old method : 0.0040912628173828125 length of segment : 50 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1270 time to create 1 rle with old method : 0.0022885799407958984 length of segment : 30 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0006978511810302734 length of segment : 24 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1201 time to create 1 rle with old method : 0.002156972885131836 length of segment : 34 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 606 time to create 1 rle with old method : 0.0011534690856933594 length of segment : 24 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1230 time to create 1 rle with old method : 0.0021867752075195312 length of segment : 35 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 747 time to create 1 rle with old method : 0.0013797283172607422 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 15.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -99.57891 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.0008149147033691406 length of segment : 33 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.00040984153747558594 length of segment : 42 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004703998565673828 length of segment : 22 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 608 time to create 1 rle with old method : 0.0007677078247070312 length of segment : 27 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 613 time to create 1 rle with old method : 0.0008454322814941406 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.27813 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 : 8.440017700195312e-05 nb_pixel_total : 2093 time to create 1 rle with old method : 0.002473592758178711 length of segment : 143 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1387 time to create 1 rle with old method : 0.001650094985961914 length of segment : 41 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 726 time to create 1 rle with old method : 0.0008859634399414062 length of segment : 34 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005128383636474609 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: 145.19375 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 : 642 time to create 1 rle with old method : 0.0008134841918945312 length of segment : 44 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 1816 time to create 1 rle with old method : 0.002211332321166992 length of segment : 89 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 405 time to create 1 rle with old method : 0.0010128021240234375 length of segment : 23 time for calcul the mask position with numpy : 0.00014162063598632812 nb_pixel_total : 523 time to create 1 rle with old method : 0.0008301734924316406 length of segment : 59 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002892017364501953 length of segment : 49 Processing 1 images image shape: (280, 400, 3) min: 15.00000 max: 212.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 92.77578 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012674331665039062 nb_pixel_total : 105804 time to create 1 rle with old method : 0.12997031211853027 length of segment : 281 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.60781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 748 time to create 1 rle with old method : 0.0009646415710449219 length of segment : 31 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 3615 time to create 1 rle with old method : 0.005084037780761719 length of segment : 128 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 3597 time to create 1 rle with old method : 0.00421905517578125 length of segment : 63 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.00037217140197753906 length of segment : 25 time for calcul the mask position with numpy : 0.00022077560424804688 nb_pixel_total : 8231 time to create 1 rle with old method : 0.01006937026977539 length of segment : 162 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1616 time to create 1 rle with old method : 0.00201416015625 length of segment : 39 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 747 time to create 1 rle with old method : 0.0009658336639404297 length of segment : 35 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0002624988555908203 length of segment : 24 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0008819103240966797 length of segment : 36 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1475 time to create 1 rle with old method : 0.0017709732055664062 length of segment : 39 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.0002617835998535156 length of segment : 24 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.000644683837890625 length of segment : 39 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002980232238769531 length of segment : 16 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.0002894401550292969 length of segment : 19 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0003008842468261719 length of segment : 16 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0005772113800048828 length of segment : 17 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.00022649765014648438 length of segment : 13 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.00018906593322753906 length of segment : 12 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00018739700317382812 length of segment : 26 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 815 time to create 1 rle with old method : 0.0010433197021484375 length of segment : 38 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004374980926513672 length of segment : 21 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0003070831298828125 length of segment : 17 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.85391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005440711975097656 length of segment : 56 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0003745555877685547 length of segment : 14 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003287792205810547 length of segment : 26 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 37 time to create 1 rle with old method : 7.128715515136719e-05 length of segment : 14 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00019669532775878906 length of segment : 25 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.00016307830810546875 length of segment : 23 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0008530616760253906 length of segment : 32 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: -118.31328 max: 149.22891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 807 time to create 1 rle with old method : 0.0010514259338378906 length of segment : 31 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 887 time to create 1 rle with old method : 0.001112222671508789 length of segment : 33 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00024199485778808594 length of segment : 31 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00021266937255859375 length of segment : 28 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.00020551681518554688 length of segment : 24 length of segment : 0 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.0002598762512207031 length of segment : 24 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.0002269744873046875 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.12578 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 : 9.799003601074219e-05 nb_pixel_total : 3995 time to create 1 rle with old method : 0.004964590072631836 length of segment : 40 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 824 time to create 1 rle with old method : 0.0010671615600585938 length of segment : 43 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00020265579223632812 length of segment : 23 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 861 time to create 1 rle with old method : 0.0010313987731933594 length of segment : 43 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 914 time to create 1 rle with old method : 0.0011522769927978516 length of segment : 56 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 814 time to create 1 rle with old method : 0.0010027885437011719 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -105.33672 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 : 5.650520324707031e-05 nb_pixel_total : 1488 time to create 1 rle with old method : 0.0018417835235595703 length of segment : 36 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 572 time to create 1 rle with old method : 0.0007374286651611328 length of segment : 38 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 1174 time to create 1 rle with old method : 0.0014576911926269531 length of segment : 45 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 6196 time to create 1 rle with old method : 0.006912946701049805 length of segment : 121 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 2354 time to create 1 rle with old method : 0.0029938220977783203 length of segment : 64 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0009739398956298828 length of segment : 24 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 3558 time to create 1 rle with old method : 0.004557609558105469 length of segment : 42 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1313 time to create 1 rle with old method : 0.0016324520111083984 length of segment : 37 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1985 time to create 1 rle with old method : 0.002532482147216797 length of segment : 56 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 2346 time to create 1 rle with old method : 0.002807140350341797 length of segment : 57 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.85625 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 : 4.57763671875e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0007450580596923828 length of segment : 25 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0004982948303222656 length of segment : 21 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 966 time to create 1 rle with old method : 0.0012633800506591797 length of segment : 40 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 1536 time to create 1 rle with old method : 0.001888275146484375 length of segment : 78 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 249.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 122.59609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.0007348060607910156 length of segment : 20 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003123283386230469 length of segment : 38 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 1292 time to create 1 rle with old method : 0.0015535354614257812 length of segment : 68 time for calcul the mask position with numpy : 0.0006709098815917969 nb_pixel_total : 63346 time to create 1 rle with old method : 0.0705728530883789 length of segment : 413 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 2182 time to create 1 rle with old method : 0.00266265869140625 length of segment : 64 Processing 1 images image shape: (400, 400, 3) min: 26.00000 max: 231.00000 molded_images shape: (1, 640, 640, 3) min: -84.09063 max: 99.49844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.001962900161743164 nb_pixel_total : 149624 time to create 1 rle with old method : 0.20749187469482422 length of segment : 394 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.27031 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 : 4.601478576660156e-05 nb_pixel_total : 698 time to create 1 rle with old method : 0.0009202957153320312 length of segment : 34 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 2445 time to create 1 rle with old method : 0.002997159957885742 length of segment : 49 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1288 time to create 1 rle with old method : 0.0016167163848876953 length of segment : 28 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00028634071350097656 length of segment : 14 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 987 time to create 1 rle with old method : 0.0012972354888916016 length of segment : 32 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 1200 time to create 1 rle with old method : 0.002730846405029297 length of segment : 36 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1017 time to create 1 rle with old method : 0.001222848892211914 length of segment : 50 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0012774467468261719 length of segment : 30 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003838539123535156 length of segment : 15 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.00041794776916503906 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -101.06328 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 : 4.673004150390625e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0004684925079345703 length of segment : 15 time for calcul the mask position with numpy : 0.0006411075592041016 nb_pixel_total : 287 time to create 1 rle with old method : 0.0005421638488769531 length of segment : 46 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.000759124755859375 length of segment : 31 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0007557868957519531 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.41484 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 : 8.249282836914062e-05 nb_pixel_total : 1888 time to create 1 rle with old method : 0.002236604690551758 length of segment : 127 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0003085136413574219 length of segment : 16 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 946 time to create 1 rle with old method : 0.0012857913970947266 length of segment : 34 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1344 time to create 1 rle with old method : 0.0016651153564453125 length of segment : 42 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.0005035400390625 length of segment : 41 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003750324249267578 length of segment : 15 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 1316 time to create 1 rle with old method : 0.0016207695007324219 length of segment : 41 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0009751319885253906 length of segment : 38 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: 144.13125 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0006990432739257812 length of segment : 41 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005512237548828125 length of segment : 24 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1703 time to create 1 rle with old method : 0.002106189727783203 length of segment : 81 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1720 time to create 1 rle with old method : 0.0020194053649902344 length of segment : 54 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00027942657470703125 length of segment : 32 time for calcul the mask position with numpy : 0.0001571178436279297 nb_pixel_total : 1956 time to create 1 rle with old method : 0.0023632049560546875 length of segment : 177 Processing 1 images image shape: (280, 400, 3) min: 12.00000 max: 219.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 99.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008971691131591797 nb_pixel_total : 106476 time to create 1 rle with old method : 0.11705684661865234 length of segment : 284 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: 150.67031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 952 time to create 1 rle with old method : 0.001209259033203125 length of segment : 33 time for calcul the mask position with numpy : 0.00012350082397460938 nb_pixel_total : 3704 time to create 1 rle with old method : 0.004352092742919922 length of segment : 116 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 3621 time to create 1 rle with old method : 0.004220008850097656 length of segment : 63 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0004799365997314453 length of segment : 23 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1071 time to create 1 rle with old method : 0.001310586929321289 length of segment : 68 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1185 time to create 1 rle with old method : 0.001504659652709961 length of segment : 56 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0004303455352783203 length of segment : 29 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 2883 time to create 1 rle with old method : 0.003501415252685547 length of segment : 64 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 672 time to create 1 rle with old method : 0.0008821487426757812 length of segment : 31 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.00027942657470703125 length of segment : 29 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 3254 time to create 1 rle with old method : 0.003780364990234375 length of segment : 94 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005791187286376953 length of segment : 32 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 613 time to create 1 rle with old method : 0.0007936954498291016 length of segment : 29 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004425048828125 length of segment : 19 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002455711364746094 length of segment : 24 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004558563232421875 length of segment : 24 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0003788471221923828 length of segment : 20 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 53 time to create 1 rle with old method : 0.0001087188720703125 length of segment : 6 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1470 time to create 1 rle with old method : 0.0017628669738769531 length of segment : 40 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005731582641601562 length of segment : 24 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.0003921985626220703 length of segment : 22 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.00029730796813964844 length of segment : 18 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004279613494873047 length of segment : 20 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1073 time to create 1 rle with old method : 0.0013964176177978516 length of segment : 43 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 819 time to create 1 rle with old method : 0.0010173320770263672 length of segment : 40 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: 148.49453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0003108978271484375 length of segment : 41 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 11 time to create 1 rle with old method : 0.00019025802612304688 length of segment : 5 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 59 time to create 1 rle with old method : 9.822845458984375e-05 length of segment : 21 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001456737518310547 length of segment : 13 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002734661102294922 length of segment : 26 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002071857452392578 length of segment : 22 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 636 time to create 1 rle with old method : 0.0009508132934570312 length of segment : 38 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: 137.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0003979206085205078 nb_pixel_total : 39507 time to create 1 rle with old method : 0.045693159103393555 length of segment : 231 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: -118.46563 max: 148.86172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 801 time to create 1 rle with old method : 0.0010547637939453125 length of segment : 39 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 899 time to create 1 rle with old method : 0.0011944770812988281 length of segment : 41 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00015664100646972656 length of segment : 30 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 61 time to create 1 rle with old method : 9.942054748535156e-05 length of segment : 16 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.00017333030700683594 length of segment : 17 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001747608184814453 length of segment : 32 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 53 time to create 1 rle with old method : 0.00010943412780761719 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: -118.59844 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 850 time to create 1 rle with old method : 0.0010952949523925781 length of segment : 40 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005087852478027344 length of segment : 40 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 784 time to create 1 rle with old method : 0.0009446144104003906 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -92.54766 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 : 0.00011110305786132812 nb_pixel_total : 3364 time to create 1 rle with old method : 0.006352901458740234 length of segment : 56 time for calcul the mask position with numpy : 0.00014972686767578125 nb_pixel_total : 6266 time to create 1 rle with old method : 0.011815071105957031 length of segment : 103 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1296 time to create 1 rle with old method : 0.0016045570373535156 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.89141 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.0003819465637207031 length of segment : 22 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0007767677307128906 length of segment : 26 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 249.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 111.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.000762939453125 length of segment : 20 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.00031495094299316406 length of segment : 37 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.00015044212341308594 length of segment : 19 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002651214599609375 length of segment : 17 time for calcul the mask position with numpy : 0.000606536865234375 nb_pixel_total : 63378 time to create 1 rle with old method : 0.06832671165466309 length of segment : 275 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1983 time to create 1 rle with old method : 0.002355337142944336 length of segment : 50 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1960 time to create 1 rle with old method : 0.002485513687133789 length of segment : 50 Processing 1 images image shape: (400, 400, 3) min: 28.00000 max: 227.00000 molded_images shape: (1, 640, 640, 3) min: -80.69219 max: 97.55703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012674331665039062 nb_pixel_total : 149251 time to create 1 rle with old method : 0.16030144691467285 length of segment : 391 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -102.13750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 2387 time to create 1 rle with old method : 0.002856016159057617 length of segment : 48 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 1211 time to create 1 rle with old method : 0.00153350830078125 length of segment : 26 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.0003933906555175781 length of segment : 17 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003514289855957031 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -93.13750 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 : 0.00019073486328125 nb_pixel_total : 4855 time to create 1 rle with old method : 0.005537986755371094 length of segment : 274 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00031828880310058594 length of segment : 40 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.000148773193359375 length of segment : 14 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005974769592285156 length of segment : 21 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0007088184356689453 length of segment : 31 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0007982254028320312 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.27813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 2032 time to create 1 rle with old method : 0.0024139881134033203 length of segment : 143 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1359 time to create 1 rle with old method : 0.0015802383422851562 length of segment : 41 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 429 time to create 1 rle with old method : 0.0005192756652832031 length of segment : 41 time for calcul the mask position with numpy : 0.00015854835510253906 nb_pixel_total : 2781 time to create 1 rle with old method : 0.0033066272735595703 length of segment : 207 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 769 time to create 1 rle with old method : 0.0009367465972900391 length of segment : 36 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: 144.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005528926849365234 length of segment : 23 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1848 time to create 1 rle with old method : 0.0021288394927978516 length of segment : 55 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006041526794433594 length of segment : 35 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1767 time to create 1 rle with old method : 0.002062559127807617 length of segment : 87 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0005879402160644531 length of segment : 38 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 629 time to create 1 rle with old method : 0.0008139610290527344 length of segment : 77 time for calcul the mask position with numpy : 0.0002238750457763672 nb_pixel_total : 4215 time to create 1 rle with old method : 0.004956960678100586 length of segment : 237 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 1154 time to create 1 rle with old method : 0.001463174819946289 length of segment : 60 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1194 time to create 1 rle with old method : 0.0014781951904296875 length of segment : 64 time for calcul the mask position with numpy : 0.0001690387725830078 nb_pixel_total : 3042 time to create 1 rle with old method : 0.003567934036254883 length of segment : 214 Processing 1 images image shape: (280, 400, 3) min: 27.00000 max: 214.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 94.53359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0011227130889892578 nb_pixel_total : 106328 time to create 1 rle with old method : 0.11668944358825684 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1510 time to create 1 rle with old method : 0.0018310546875 length of segment : 44 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.0010068416595458984 length of segment : 30 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 3640 time to create 1 rle with old method : 0.00418853759765625 length of segment : 64 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 3040 time to create 1 rle with old method : 0.0036046504974365234 length of segment : 65 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 673 time to create 1 rle with old method : 0.0008177757263183594 length of segment : 47 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 3049 time to create 1 rle with old method : 0.0035343170166015625 length of segment : 148 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.0001125335693359375 length of segment : 12 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.00042724609375 length of segment : 28 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.0006558895111083984 length of segment : 33 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003292560577392578 length of segment : 28 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 680 time to create 1 rle with old method : 0.0008766651153564453 length of segment : 32 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.0006923675537109375 length of segment : 31 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 678 time to create 1 rle with old method : 0.0008783340454101562 length of segment : 31 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004055500030517578 length of segment : 21 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.00025773048400878906 length of segment : 24 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.00040078163146972656 length of segment : 24 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.00033473968505859375 length of segment : 19 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.00035572052001953125 length of segment : 19 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003457069396972656 length of segment : 48 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.0010113716125488281 length of segment : 31 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00014019012451171875 length of segment : 10 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.0002741813659667969 length of segment : 16 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004649162292480469 length of segment : 23 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: 147.06484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0004711151123046875 length of segment : 52 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.00012183189392089844 length of segment : 11 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0004050731658935547 length of segment : 24 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00022149085998535156 length of segment : 22 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0002887248992919922 length of segment : 40 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005779266357421875 length of segment : 30 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.0002503395080566406 length of segment : 19 time for calcul the mask position with numpy : 0.0006227493286132812 nb_pixel_total : 36621 time to create 1 rle with old method : 0.040898799896240234 length of segment : 238 Detection mask done ! Trying to reset tf kernel 1251711 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1706 tf kernel not reseted sub process len(results) : 260 len(list_Values) 260 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 260 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 : 6995 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 260 chid ids of type : 4228 Number RLEs to save : 14223 save missing photos in datou_result : time spend for datou_step_exec : 25.65111231803894 time spend to save output : 1.1253132820129395 total time spend for step 1 : 26.77642560005188 step2:brightness Thu Feb 13 19:20:55 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/1739470828_1251291_1337396817_e9b2d238f17d8b24f6da02da2b232267.jpg treat image : temp/1739470828_1251291_1337396814_b49f87b3fda77a2a093d9f5d401f2936.jpg treat image : temp/1739470828_1251291_1337396812_6948974129e4d1a73a60fa8a6139c4bc.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 : 0.011916399002075195 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 : 0.010710716247558594 save missing photos in datou_result : time spend for datou_step_exec : 0.7278668880462646 time spend to save output : 0.026858091354370117 total time spend for step 2 : 0.7547249794006348 step3:blur_detection Thu Feb 13 19:20:56 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/1739470828_1251291_1337396817_e9b2d238f17d8b24f6da02da2b232267.jpg resize: (1080, 1920) 1337396817 -7.78161546998226 treat image : temp/1739470828_1251291_1337396814_b49f87b3fda77a2a093d9f5d401f2936.jpg resize: (1080, 1920) 1337396814 -7.745493203729844 treat image : temp/1739470828_1251291_1337396812_6948974129e4d1a73a60fa8a6139c4bc.jpg resize: (1080, 1920) 1337396812 -7.8181073494850954 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 : 0.011206626892089844 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 : 0.01236867904663086 save missing photos in datou_result : time spend for datou_step_exec : 2.327432155609131 time spend to save output : 0.027879953384399414 total time spend for step 3 : 2.3553121089935303 step4:rle_unique_nms_with_priority Thu Feb 13 19:20:58 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 260 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 82 nb_hashtags : 7 time to prepare the origin masks : 1.2239785194396973 time for calcul the mask position with numpy : 0.02144622802734375 nb_pixel_total : 1668749 time to create 1 rle with new method : 0.05135965347290039 time for calcul the mask position with numpy : 0.008402109146118164 nb_pixel_total : 285 time to create 1 rle with old method : 0.0003807544708251953 time for calcul the mask position with numpy : 0.008203268051147461 nb_pixel_total : 1348 time to create 1 rle with old method : 0.0015187263488769531 time for calcul the mask position with numpy : 0.00812673568725586 nb_pixel_total : 3586 time to create 1 rle with old method : 0.004858970642089844 time for calcul the mask position with numpy : 0.008921384811401367 nb_pixel_total : 2964 time to create 1 rle with old method : 0.0034575462341308594 time for calcul the mask position with numpy : 0.008390665054321289 nb_pixel_total : 15665 time to create 1 rle with old method : 0.017304182052612305 time for calcul the mask position with numpy : 0.008455514907836914 nb_pixel_total : 797 time to create 1 rle with old method : 0.0009245872497558594 time for calcul the mask position with numpy : 0.008658170700073242 nb_pixel_total : 58195 time to create 1 rle with old method : 0.062416791915893555 time for calcul the mask position with numpy : 0.008479833602905273 nb_pixel_total : 154 time to create 1 rle with old method : 0.00018477439880371094 time for calcul the mask position with numpy : 0.00842738151550293 nb_pixel_total : 66 time to create 1 rle with old method : 0.00010251998901367188 time for calcul the mask position with numpy : 0.008502006530761719 nb_pixel_total : 701 time to create 1 rle with old method : 0.000812530517578125 time for calcul the mask position with numpy : 0.008437156677246094 nb_pixel_total : 416 time to create 1 rle with old method : 0.00047469139099121094 time for calcul the mask position with numpy : 0.008424520492553711 nb_pixel_total : 895 time to create 1 rle with old method : 0.0009784698486328125 time for calcul the mask position with numpy : 0.00845646858215332 nb_pixel_total : 235 time to create 1 rle with old method : 0.00026607513427734375 time for calcul the mask position with numpy : 0.008436203002929688 nb_pixel_total : 42 time to create 1 rle with old method : 6.461143493652344e-05 time for calcul the mask position with numpy : 0.008494138717651367 nb_pixel_total : 64 time to create 1 rle with old method : 9.846687316894531e-05 time for calcul the mask position with numpy : 0.008570432662963867 nb_pixel_total : 32 time to create 1 rle with old method : 8.845329284667969e-05 time for calcul the mask position with numpy : 0.008556604385375977 nb_pixel_total : 2238 time to create 1 rle with old method : 0.0025873184204101562 time for calcul the mask position with numpy : 0.008525848388671875 nb_pixel_total : 229 time to create 1 rle with old method : 0.0002803802490234375 time for calcul the mask position with numpy : 0.008508920669555664 nb_pixel_total : 781 time to create 1 rle with old method : 0.0009491443634033203 time for calcul the mask position with numpy : 0.00852823257446289 nb_pixel_total : 723 time to create 1 rle with old method : 0.000858306884765625 time for calcul the mask position with numpy : 0.008608341217041016 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005528926849365234 time for calcul the mask position with numpy : 0.008557796478271484 nb_pixel_total : 1511 time to create 1 rle with old method : 0.001752614974975586 time for calcul the mask position with numpy : 0.010156393051147461 nb_pixel_total : 295 time to create 1 rle with old method : 0.00035762786865234375 time for calcul the mask position with numpy : 0.00838780403137207 nb_pixel_total : 6391 time to create 1 rle with old method : 0.007226228713989258 time for calcul the mask position with numpy : 0.008435964584350586 nb_pixel_total : 9092 time to create 1 rle with old method : 0.010214805603027344 time for calcul the mask position with numpy : 0.008422374725341797 nb_pixel_total : 99 time to create 1 rle with old method : 0.0001239776611328125 time for calcul the mask position with numpy : 0.008179664611816406 nb_pixel_total : 1245 time to create 1 rle with old method : 0.0013670921325683594 time for calcul the mask position with numpy : 0.008196353912353516 nb_pixel_total : 892 time to create 1 rle with old method : 0.0010259151458740234 time for calcul the mask position with numpy : 0.008237123489379883 nb_pixel_total : 530 time to create 1 rle with old method : 0.0006258487701416016 time for calcul the mask position with numpy : 0.008959531784057617 nb_pixel_total : 152394 time to create 1 rle with new method : 0.03887772560119629 time for calcul the mask position with numpy : 0.008268594741821289 nb_pixel_total : 608 time to create 1 rle with old method : 0.0006976127624511719 time for calcul the mask position with numpy : 0.008231878280639648 nb_pixel_total : 726 time to create 1 rle with old method : 0.0008244514465332031 time for calcul the mask position with numpy : 0.008271932601928711 nb_pixel_total : 1387 time to create 1 rle with old method : 0.001569986343383789 time for calcul the mask position with numpy : 0.008068561553955078 nb_pixel_total : 197 time to create 1 rle with old method : 0.00024056434631347656 time for calcul the mask position with numpy : 0.008466720581054688 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006184577941894531 time for calcul the mask position with numpy : 0.008317708969116211 nb_pixel_total : 562 time to create 1 rle with old method : 0.0006349086761474609 time for calcul the mask position with numpy : 0.008309125900268555 nb_pixel_total : 2093 time to create 1 rle with old method : 0.0023925304412841797 time for calcul the mask position with numpy : 0.008156776428222656 nb_pixel_total : 613 time to create 1 rle with old method : 0.0007152557373046875 time for calcul the mask position with numpy : 0.008247137069702148 nb_pixel_total : 294 time to create 1 rle with old method : 0.0003235340118408203 time for calcul the mask position with numpy : 0.008399724960327148 nb_pixel_total : 277 time to create 1 rle with old method : 0.00032329559326171875 time for calcul the mask position with numpy : 0.008417129516601562 nb_pixel_total : 371 time to create 1 rle with old method : 0.0004525184631347656 time for calcul the mask position with numpy : 0.008341073989868164 nb_pixel_total : 746 time to create 1 rle with old method : 0.0008513927459716797 time for calcul the mask position with numpy : 0.008330345153808594 nb_pixel_total : 403 time to create 1 rle with old method : 0.00043511390686035156 time for calcul the mask position with numpy : 0.008386850357055664 nb_pixel_total : 1201 time to create 1 rle with old method : 0.001374959945678711 time for calcul the mask position with numpy : 0.008387565612792969 nb_pixel_total : 50 time to create 1 rle with old method : 0.00010228157043457031 time for calcul the mask position with numpy : 0.008362293243408203 nb_pixel_total : 2353 time to create 1 rle with old method : 0.0026726722717285156 time for calcul the mask position with numpy : 0.008376836776733398 nb_pixel_total : 352 time to create 1 rle with old method : 0.00040268898010253906 time for calcul the mask position with numpy : 0.008372306823730469 nb_pixel_total : 642 time to create 1 rle with old method : 0.0007343292236328125 time for calcul the mask position with numpy : 0.008349418640136719 nb_pixel_total : 1816 time to create 1 rle with old method : 0.002071380615234375 time for calcul the mask position with numpy : 0.008362531661987305 nb_pixel_total : 396 time to create 1 rle with old method : 0.0004603862762451172 time for calcul the mask position with numpy : 0.008376598358154297 nb_pixel_total : 1270 time to create 1 rle with old method : 0.0014600753784179688 time for calcul the mask position with numpy : 0.008463382720947266 nb_pixel_total : 606 time to create 1 rle with old method : 0.0007195472717285156 time for calcul the mask position with numpy : 0.008858680725097656 nb_pixel_total : 105804 time to create 1 rle with old method : 0.11958098411560059 time for calcul the mask position with numpy : 0.008609771728515625 nb_pixel_total : 3597 time to create 1 rle with old method : 0.0040531158447265625 time for calcul the mask position with numpy : 0.008563995361328125 nb_pixel_total : 4699 time to create 1 rle with old method : 0.005335330963134766 time for calcul the mask position with numpy : 0.008686065673828125 nb_pixel_total : 74 time to create 1 rle with old method : 0.00010132789611816406 time for calcul the mask position with numpy : 0.008893251419067383 nb_pixel_total : 15 time to create 1 rle with old method : 4.553794860839844e-05 time for calcul the mask position with numpy : 0.00834965705871582 nb_pixel_total : 207 time to create 1 rle with old method : 0.0002353191375732422 time for calcul the mask position with numpy : 0.008359670639038086 nb_pixel_total : 146 time to create 1 rle with old method : 0.0001742839813232422 time for calcul the mask position with numpy : 0.008371114730834961 nb_pixel_total : 216 time to create 1 rle with old method : 0.0002510547637939453 time for calcul the mask position with numpy : 0.008822917938232422 nb_pixel_total : 121 time to create 1 rle with old method : 0.00015020370483398438 time for calcul the mask position with numpy : 0.00839376449584961 nb_pixel_total : 2992 time to create 1 rle with old method : 0.003420114517211914 time for calcul the mask position with numpy : 0.00842595100402832 nb_pixel_total : 748 time to create 1 rle with old method : 0.0008785724639892578 time for calcul the mask position with numpy : 0.008394479751586914 nb_pixel_total : 507 time to create 1 rle with old method : 0.0005621910095214844 time for calcul the mask position with numpy : 0.008662939071655273 nb_pixel_total : 46 time to create 1 rle with old method : 7.62939453125e-05 time for calcul the mask position with numpy : 0.00843501091003418 nb_pixel_total : 1616 time to create 1 rle with old method : 0.001874685287475586 time for calcul the mask position with numpy : 0.008418560028076172 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003185272216796875 time for calcul the mask position with numpy : 0.008413553237915039 nb_pixel_total : 23 time to create 1 rle with old method : 7.081031799316406e-05 time for calcul the mask position with numpy : 0.008425712585449219 nb_pixel_total : 747 time to create 1 rle with old method : 0.0008788108825683594 time for calcul the mask position with numpy : 0.008434772491455078 nb_pixel_total : 24 time to create 1 rle with old method : 6.127357482910156e-05 time for calcul the mask position with numpy : 0.008467435836791992 nb_pixel_total : 37 time to create 1 rle with old method : 5.793571472167969e-05 time for calcul the mask position with numpy : 0.008561849594116211 nb_pixel_total : 10 time to create 1 rle with old method : 4.76837158203125e-05 time for calcul the mask position with numpy : 0.008676767349243164 nb_pixel_total : 237 time to create 1 rle with old method : 0.0002760887145996094 time for calcul the mask position with numpy : 0.008424997329711914 nb_pixel_total : 189 time to create 1 rle with old method : 0.00023055076599121094 time for calcul the mask position with numpy : 0.008839130401611328 nb_pixel_total : 378 time to create 1 rle with old method : 0.00047516822814941406 time for calcul the mask position with numpy : 0.008404970169067383 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002503395080566406 time for calcul the mask position with numpy : 0.008660078048706055 nb_pixel_total : 514 time to create 1 rle with old method : 0.0005729198455810547 time for calcul the mask position with numpy : 0.008650541305541992 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001437664031982422 time for calcul the mask position with numpy : 0.008502006530761719 nb_pixel_total : 179 time to create 1 rle with old method : 0.00035119056701660156 time for calcul the mask position with numpy : 0.008629083633422852 nb_pixel_total : 815 time to create 1 rle with old method : 0.0009429454803466797 time for calcul the mask position with numpy : 0.008389472961425781 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002536773681640625 time for calcul the mask position with numpy : 0.008435964584350586 nb_pixel_total : 323 time to create 1 rle with old method : 0.00037932395935058594 create new chi : 1.1018831729888916 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 : 0.009586095809936523 batch 1 Loaded 83 chid ids of type : 4230 Number RLEs to save : 9176 TO DO : save crop sub photo not yet done ! save time : 0.5243203639984131 nb_obj : 95 nb_hashtags : 7 time to prepare the origin masks : 2.0608954429626465 time for calcul the mask position with numpy : 0.02138972282409668 nb_pixel_total : 1639315 time to create 1 rle with new method : 0.054653167724609375 time for calcul the mask position with numpy : 0.008504390716552734 nb_pixel_total : 2354 time to create 1 rle with old method : 0.002629995346069336 time for calcul the mask position with numpy : 0.010300397872924805 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002841949462890625 time for calcul the mask position with numpy : 0.010384082794189453 nb_pixel_total : 1292 time to create 1 rle with old method : 0.0015103816986083984 time for calcul the mask position with numpy : 0.010413646697998047 nb_pixel_total : 3995 time to create 1 rle with old method : 0.004551410675048828 time for calcul the mask position with numpy : 0.010938405990600586 nb_pixel_total : 63154 time to create 1 rle with old method : 0.06769895553588867 time for calcul the mask position with numpy : 0.010411739349365234 nb_pixel_total : 572 time to create 1 rle with old method : 0.0006692409515380859 time for calcul the mask position with numpy : 0.010257482528686523 nb_pixel_total : 12 time to create 1 rle with old method : 3.5762786865234375e-05 time for calcul the mask position with numpy : 0.006043910980224609 nb_pixel_total : 81 time to create 1 rle with old method : 0.0001246929168701172 time for calcul the mask position with numpy : 0.0059719085693359375 nb_pixel_total : 17 time to create 1 rle with old method : 5.173683166503906e-05 time for calcul the mask position with numpy : 0.005954742431640625 nb_pixel_total : 824 time to create 1 rle with old method : 0.0009603500366210938 time for calcul the mask position with numpy : 0.00593113899230957 nb_pixel_total : 92 time to create 1 rle with old method : 0.0001895427703857422 time for calcul the mask position with numpy : 0.0059964656829833984 nb_pixel_total : 175 time to create 1 rle with old method : 0.00021886825561523438 time for calcul the mask position with numpy : 0.005955934524536133 nb_pixel_total : 119 time to create 1 rle with old method : 0.0001537799835205078 time for calcul the mask position with numpy : 0.0059850215911865234 nb_pixel_total : 807 time to create 1 rle with old method : 0.0009474754333496094 time for calcul the mask position with numpy : 0.006017208099365234 nb_pixel_total : 122 time to create 1 rle with old method : 0.0001659393310546875 time for calcul the mask position with numpy : 0.00597691535949707 nb_pixel_total : 1174 time to create 1 rle with old method : 0.0013189315795898438 time for calcul the mask position with numpy : 0.005968332290649414 nb_pixel_total : 1536 time to create 1 rle with old method : 0.0016987323760986328 time for calcul the mask position with numpy : 0.006010770797729492 nb_pixel_total : 914 time to create 1 rle with old method : 0.0010519027709960938 time for calcul the mask position with numpy : 0.006126880645751953 nb_pixel_total : 239 time to create 1 rle with old method : 0.00029206275939941406 time for calcul the mask position with numpy : 0.006067514419555664 nb_pixel_total : 861 time to create 1 rle with old method : 0.000980377197265625 time for calcul the mask position with numpy : 0.005990266799926758 nb_pixel_total : 17 time to create 1 rle with old method : 6.318092346191406e-05 time for calcul the mask position with numpy : 0.006079673767089844 nb_pixel_total : 3558 time to create 1 rle with old method : 0.0040781497955322266 time for calcul the mask position with numpy : 0.006052732467651367 nb_pixel_total : 710 time to create 1 rle with old method : 0.0008549690246582031 time for calcul the mask position with numpy : 0.006239414215087891 nb_pixel_total : 451 time to create 1 rle with old method : 0.0005698204040527344 time for calcul the mask position with numpy : 0.006219148635864258 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002849102020263672 time for calcul the mask position with numpy : 0.006089925765991211 nb_pixel_total : 338 time to create 1 rle with old method : 0.0004048347473144531 time for calcul the mask position with numpy : 0.010422468185424805 nb_pixel_total : 6196 time to create 1 rle with old method : 0.0067632198333740234 time for calcul the mask position with numpy : 0.010447978973388672 nb_pixel_total : 2182 time to create 1 rle with old method : 0.0025322437286376953 time for calcul the mask position with numpy : 0.010234355926513672 nb_pixel_total : 966 time to create 1 rle with old method : 0.0011169910430908203 time for calcul the mask position with numpy : 0.008781909942626953 nb_pixel_total : 17 time to create 1 rle with old method : 7.605552673339844e-05 time for calcul the mask position with numpy : 0.006084918975830078 nb_pixel_total : 1488 time to create 1 rle with old method : 0.0016918182373046875 time for calcul the mask position with numpy : 0.006067514419555664 nb_pixel_total : 548 time to create 1 rle with old method : 0.0006594657897949219 time for calcul the mask position with numpy : 0.00707244873046875 nb_pixel_total : 149624 time to create 1 rle with old method : 0.16350483894348145 time for calcul the mask position with numpy : 0.006530284881591797 nb_pixel_total : 588 time to create 1 rle with old method : 0.0006787776947021484 time for calcul the mask position with numpy : 0.00626063346862793 nb_pixel_total : 795 time to create 1 rle with old method : 0.0009124279022216797 time for calcul the mask position with numpy : 0.006175041198730469 nb_pixel_total : 1344 time to create 1 rle with old method : 0.0015287399291992188 time for calcul the mask position with numpy : 0.0062520503997802734 nb_pixel_total : 29 time to create 1 rle with old method : 7.748603820800781e-05 time for calcul the mask position with numpy : 0.00627589225769043 nb_pixel_total : 156 time to create 1 rle with old method : 0.00020384788513183594 time for calcul the mask position with numpy : 0.0062389373779296875 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002722740173339844 time for calcul the mask position with numpy : 0.006242513656616211 nb_pixel_total : 1956 time to create 1 rle with old method : 0.0022077560424804688 time for calcul the mask position with numpy : 0.00632929801940918 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006380081176757812 time for calcul the mask position with numpy : 0.00626063346862793 nb_pixel_total : 987 time to create 1 rle with old method : 0.0011553764343261719 time for calcul the mask position with numpy : 0.006442070007324219 nb_pixel_total : 1888 time to create 1 rle with old method : 0.0021522045135498047 time for calcul the mask position with numpy : 0.006292581558227539 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003266334533691406 time for calcul the mask position with numpy : 0.0062558650970458984 nb_pixel_total : 698 time to create 1 rle with old method : 0.0008063316345214844 time for calcul the mask position with numpy : 0.007225751876831055 nb_pixel_total : 287 time to create 1 rle with old method : 0.0004322528839111328 time for calcul the mask position with numpy : 0.0073854923248291016 nb_pixel_total : 215 time to create 1 rle with old method : 0.000308990478515625 time for calcul the mask position with numpy : 0.006569623947143555 nb_pixel_total : 173 time to create 1 rle with old method : 0.00023055076599121094 time for calcul the mask position with numpy : 0.006147146224975586 nb_pixel_total : 1720 time to create 1 rle with old method : 0.0018579959869384766 time for calcul the mask position with numpy : 0.0061147212982177734 nb_pixel_total : 281 time to create 1 rle with old method : 0.00031876564025878906 time for calcul the mask position with numpy : 0.006075620651245117 nb_pixel_total : 1017 time to create 1 rle with old method : 0.0012133121490478516 time for calcul the mask position with numpy : 0.006076812744140625 nb_pixel_total : 407 time to create 1 rle with old method : 0.0004725456237792969 time for calcul the mask position with numpy : 0.006130218505859375 nb_pixel_total : 2445 time to create 1 rle with old method : 0.0026597976684570312 time for calcul the mask position with numpy : 0.006103992462158203 nb_pixel_total : 241 time to create 1 rle with old method : 0.00030422210693359375 time for calcul the mask position with numpy : 0.006053924560546875 nb_pixel_total : 946 time to create 1 rle with old method : 0.0010738372802734375 time for calcul the mask position with numpy : 0.006186723709106445 nb_pixel_total : 536 time to create 1 rle with old method : 0.0006308555603027344 time for calcul the mask position with numpy : 0.006232261657714844 nb_pixel_total : 1703 time to create 1 rle with old method : 0.0019609928131103516 time for calcul the mask position with numpy : 0.006203174591064453 nb_pixel_total : 394 time to create 1 rle with old method : 0.00045561790466308594 time for calcul the mask position with numpy : 0.006109952926635742 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0011823177337646484 time for calcul the mask position with numpy : 0.005997419357299805 nb_pixel_total : 285 time to create 1 rle with old method : 0.0003361701965332031 time for calcul the mask position with numpy : 0.006036996841430664 nb_pixel_total : 1288 time to create 1 rle with old method : 0.001493215560913086 time for calcul the mask position with numpy : 0.006516456604003906 nb_pixel_total : 106476 time to create 1 rle with old method : 0.11414599418640137 time for calcul the mask position with numpy : 0.006298065185546875 nb_pixel_total : 3621 time to create 1 rle with old method : 0.004178524017333984 time for calcul the mask position with numpy : 0.006116390228271484 nb_pixel_total : 283 time to create 1 rle with old method : 0.0003337860107421875 time for calcul the mask position with numpy : 0.006241321563720703 nb_pixel_total : 14 time to create 1 rle with old method : 4.2438507080078125e-05 time for calcul the mask position with numpy : 0.010056495666503906 nb_pixel_total : 39507 time to create 1 rle with old method : 0.04209303855895996 time for calcul the mask position with numpy : 0.006222248077392578 nb_pixel_total : 2883 time to create 1 rle with old method : 0.0030870437622070312 time for calcul the mask position with numpy : 0.006102085113525391 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005280971527099609 time for calcul the mask position with numpy : 0.006296396255493164 nb_pixel_total : 312 time to create 1 rle with old method : 0.0003600120544433594 time for calcul the mask position with numpy : 0.006078958511352539 nb_pixel_total : 952 time to create 1 rle with old method : 0.0011200904846191406 time for calcul the mask position with numpy : 0.006167411804199219 nb_pixel_total : 508 time to create 1 rle with old method : 0.0006048679351806641 time for calcul the mask position with numpy : 0.006230831146240234 nb_pixel_total : 3284 time to create 1 rle with old method : 0.0037577152252197266 time for calcul the mask position with numpy : 0.0064432621002197266 nb_pixel_total : 93 time to create 1 rle with old method : 0.00020599365234375 time for calcul the mask position with numpy : 0.006267070770263672 nb_pixel_total : 819 time to create 1 rle with old method : 0.0009067058563232422 time for calcul the mask position with numpy : 0.006246805191040039 nb_pixel_total : 207 time to create 1 rle with old method : 0.0002663135528564453 time for calcul the mask position with numpy : 0.00640416145324707 nb_pixel_total : 444 time to create 1 rle with old method : 0.0007326602935791016 time for calcul the mask position with numpy : 0.00663304328918457 nb_pixel_total : 319 time to create 1 rle with old method : 0.0005319118499755859 time for calcul the mask position with numpy : 0.006680965423583984 nb_pixel_total : 346 time to create 1 rle with old method : 0.0005941390991210938 time for calcul the mask position with numpy : 0.006686210632324219 nb_pixel_total : 1185 time to create 1 rle with old method : 0.001959085464477539 time for calcul the mask position with numpy : 0.006402015686035156 nb_pixel_total : 340 time to create 1 rle with old method : 0.00041365623474121094 time for calcul the mask position with numpy : 0.006147623062133789 nb_pixel_total : 294 time to create 1 rle with old method : 0.00035381317138671875 time for calcul the mask position with numpy : 0.006170511245727539 nb_pixel_total : 53 time to create 1 rle with old method : 8.344650268554688e-05 time for calcul the mask position with numpy : 0.008427143096923828 nb_pixel_total : 672 time to create 1 rle with old method : 0.0007987022399902344 time for calcul the mask position with numpy : 0.008933305740356445 nb_pixel_total : 1470 time to create 1 rle with old method : 0.002476215362548828 time for calcul the mask position with numpy : 0.010127544403076172 nb_pixel_total : 1 time to create 1 rle with old method : 2.3365020751953125e-05 time for calcul the mask position with numpy : 0.009170293807983398 nb_pixel_total : 59 time to create 1 rle with old method : 8.535385131835938e-05 time for calcul the mask position with numpy : 0.008647680282592773 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002300739288330078 time for calcul the mask position with numpy : 0.008556604385375977 nb_pixel_total : 11 time to create 1 rle with old method : 4.172325134277344e-05 time for calcul the mask position with numpy : 0.009656190872192383 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001456737518310547 time for calcul the mask position with numpy : 0.009680986404418945 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003001689910888672 time for calcul the mask position with numpy : 0.009621381759643555 nb_pixel_total : 1073 time to create 1 rle with old method : 0.001725912094116211 time for calcul the mask position with numpy : 0.009614706039428711 nb_pixel_total : 629 time to create 1 rle with old method : 0.0010399818420410156 time for calcul the mask position with numpy : 0.00968170166015625 nb_pixel_total : 11 time to create 1 rle with old method : 7.700920104980469e-05 time for calcul the mask position with numpy : 0.009659767150878906 nb_pixel_total : 189 time to create 1 rle with old method : 0.00032329559326171875 time for calcul the mask position with numpy : 0.009618759155273438 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003345012664794922 create new chi : 1.2399005889892578 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 : 0.001756429672241211 batch 1 Loaded 96 chid ids of type : 4230 Number RLEs to save : 10129 TO DO : save crop sub photo not yet done ! save time : 0.5941300392150879 nb_obj : 80 nb_hashtags : 7 time to prepare the origin masks : 1.5211503505706787 time for calcul the mask position with numpy : 0.018932580947875977 nb_pixel_total : 1652793 time to create 1 rle with new method : 0.04038047790527344 time for calcul the mask position with numpy : 0.006785392761230469 nb_pixel_total : 115 time to create 1 rle with old method : 0.00015687942504882812 time for calcul the mask position with numpy : 0.006272792816162109 nb_pixel_total : 850 time to create 1 rle with old method : 0.0010097026824951172 time for calcul the mask position with numpy : 0.007275104522705078 nb_pixel_total : 63378 time to create 1 rle with old method : 0.06781268119812012 time for calcul the mask position with numpy : 0.006318330764770508 nb_pixel_total : 401 time to create 1 rle with old method : 0.00045371055603027344 time for calcul the mask position with numpy : 0.006270885467529297 nb_pixel_total : 123 time to create 1 rle with old method : 0.00019550323486328125 time for calcul the mask position with numpy : 0.006274223327636719 nb_pixel_total : 110 time to create 1 rle with old method : 0.00014257431030273438 time for calcul the mask position with numpy : 0.0061528682708740234 nb_pixel_total : 24 time to create 1 rle with old method : 4.863739013671875e-05 time for calcul the mask position with numpy : 0.006174325942993164 nb_pixel_total : 801 time to create 1 rle with old method : 0.0009448528289794922 time for calcul the mask position with numpy : 0.006245613098144531 nb_pixel_total : 24 time to create 1 rle with old method : 5.4836273193359375e-05 time for calcul the mask position with numpy : 0.0060918331146240234 nb_pixel_total : 61 time to create 1 rle with old method : 9.1552734375e-05 time for calcul the mask position with numpy : 0.007099151611328125 nb_pixel_total : 3364 time to create 1 rle with old method : 0.00490117073059082 time for calcul the mask position with numpy : 0.006655454635620117 nb_pixel_total : 241 time to create 1 rle with old method : 0.0002961158752441406 time for calcul the mask position with numpy : 0.0061528682708740234 nb_pixel_total : 784 time to create 1 rle with old method : 0.0008704662322998047 time for calcul the mask position with numpy : 0.00604248046875 nb_pixel_total : 99 time to create 1 rle with old method : 0.00013136863708496094 time for calcul the mask position with numpy : 0.006354808807373047 nb_pixel_total : 481 time to create 1 rle with old method : 0.0005884170532226562 time for calcul the mask position with numpy : 0.0064122676849365234 nb_pixel_total : 259 time to create 1 rle with old method : 0.0003209114074707031 time for calcul the mask position with numpy : 0.006182193756103516 nb_pixel_total : 6266 time to create 1 rle with old method : 0.007093906402587891 time for calcul the mask position with numpy : 0.0064830780029296875 nb_pixel_total : 185 time to create 1 rle with old method : 0.00024199485778808594 time for calcul the mask position with numpy : 0.006572246551513672 nb_pixel_total : 194 time to create 1 rle with old method : 0.0003361701965332031 time for calcul the mask position with numpy : 0.00649261474609375 nb_pixel_total : 1983 time to create 1 rle with old method : 0.0022814273834228516 time for calcul the mask position with numpy : 0.006220102310180664 nb_pixel_total : 1296 time to create 1 rle with old method : 0.0015714168548583984 time for calcul the mask position with numpy : 0.006300687789916992 nb_pixel_total : 548 time to create 1 rle with old method : 0.0006644725799560547 time for calcul the mask position with numpy : 0.006939888000488281 nb_pixel_total : 149251 time to create 1 rle with old method : 0.1627960205078125 time for calcul the mask position with numpy : 0.007218837738037109 nb_pixel_total : 643 time to create 1 rle with old method : 0.0007457733154296875 time for calcul the mask position with numpy : 0.0063381195068359375 nb_pixel_total : 2466 time to create 1 rle with old method : 0.0028045177459716797 time for calcul the mask position with numpy : 0.006411314010620117 nb_pixel_total : 769 time to create 1 rle with old method : 0.0008482933044433594 time for calcul the mask position with numpy : 0.006443500518798828 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005116462707519531 time for calcul the mask position with numpy : 0.006407499313354492 nb_pixel_total : 1359 time to create 1 rle with old method : 0.001537322998046875 time for calcul the mask position with numpy : 0.0064389705657958984 nb_pixel_total : 4215 time to create 1 rle with old method : 0.00480198860168457 time for calcul the mask position with numpy : 0.006403207778930664 nb_pixel_total : 629 time to create 1 rle with old method : 0.0007462501525878906 time for calcul the mask position with numpy : 0.006238222122192383 nb_pixel_total : 505 time to create 1 rle with old method : 0.0005857944488525391 time for calcul the mask position with numpy : 0.006253480911254883 nb_pixel_total : 82 time to create 1 rle with old method : 0.00014972686767578125 time for calcul the mask position with numpy : 0.006842613220214844 nb_pixel_total : 1154 time to create 1 rle with old method : 0.0013589859008789062 time for calcul the mask position with numpy : 0.0061779022216796875 nb_pixel_total : 2032 time to create 1 rle with old method : 0.002359628677368164 time for calcul the mask position with numpy : 0.0062291622161865234 nb_pixel_total : 154 time to create 1 rle with old method : 0.00026297569274902344 time for calcul the mask position with numpy : 0.007124662399291992 nb_pixel_total : 471 time to create 1 rle with old method : 0.0005633831024169922 time for calcul the mask position with numpy : 0.006517887115478516 nb_pixel_total : 227 time to create 1 rle with old method : 0.0002837181091308594 time for calcul the mask position with numpy : 0.006365060806274414 nb_pixel_total : 4855 time to create 1 rle with old method : 0.005590200424194336 time for calcul the mask position with numpy : 0.006349325180053711 nb_pixel_total : 266 time to create 1 rle with old method : 0.00033283233642578125 time for calcul the mask position with numpy : 0.0068454742431640625 nb_pixel_total : 84 time to create 1 rle with old method : 0.00012683868408203125 time for calcul the mask position with numpy : 0.0066416263580322266 nb_pixel_total : 1848 time to create 1 rle with old method : 0.0021033287048339844 time for calcul the mask position with numpy : 0.006278514862060547 nb_pixel_total : 429 time to create 1 rle with old method : 0.0004990100860595703 time for calcul the mask position with numpy : 0.006218671798706055 nb_pixel_total : 2387 time to create 1 rle with old method : 0.0026421546936035156 time for calcul the mask position with numpy : 0.006171226501464844 nb_pixel_total : 468 time to create 1 rle with old method : 0.0005254745483398438 time for calcul the mask position with numpy : 0.006241559982299805 nb_pixel_total : 1767 time to create 1 rle with old method : 0.0019207000732421875 time for calcul the mask position with numpy : 0.006173610687255859 nb_pixel_total : 399 time to create 1 rle with old method : 0.0004775524139404297 time for calcul the mask position with numpy : 0.006104707717895508 nb_pixel_total : 262 time to create 1 rle with old method : 0.000354766845703125 time for calcul the mask position with numpy : 0.006146669387817383 nb_pixel_total : 1211 time to create 1 rle with old method : 0.0013892650604248047 time for calcul the mask position with numpy : 0.006753683090209961 nb_pixel_total : 106328 time to create 1 rle with old method : 0.11331343650817871 time for calcul the mask position with numpy : 0.006317615509033203 nb_pixel_total : 3640 time to create 1 rle with old method : 0.0041735172271728516 time for calcul the mask position with numpy : 0.006669044494628906 nb_pixel_total : 192 time to create 1 rle with old method : 0.00024437904357910156 time for calcul the mask position with numpy : 0.006292104721069336 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003299713134765625 time for calcul the mask position with numpy : 0.006437063217163086 nb_pixel_total : 36092 time to create 1 rle with old method : 0.03841352462768555 time for calcul the mask position with numpy : 0.006914615631103516 nb_pixel_total : 3040 time to create 1 rle with old method : 0.0037479400634765625 time for calcul the mask position with numpy : 0.007720470428466797 nb_pixel_total : 64 time to create 1 rle with old method : 9.489059448242188e-05 time for calcul the mask position with numpy : 0.007071971893310547 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003032684326171875 time for calcul the mask position with numpy : 0.006993293762207031 nb_pixel_total : 2384 time to create 1 rle with old method : 0.002761363983154297 time for calcul the mask position with numpy : 0.007179737091064453 nb_pixel_total : 37 time to create 1 rle with old method : 0.00013494491577148438 time for calcul the mask position with numpy : 0.008337020874023438 nb_pixel_total : 518 time to create 1 rle with old method : 0.0009176731109619141 time for calcul the mask position with numpy : 0.013796806335449219 nb_pixel_total : 771 time to create 1 rle with old method : 0.0013761520385742188 time for calcul the mask position with numpy : 0.013031959533691406 nb_pixel_total : 81 time to create 1 rle with old method : 0.00011777877807617188 time for calcul the mask position with numpy : 0.011960029602050781 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003094673156738281 time for calcul the mask position with numpy : 0.011459827423095703 nb_pixel_total : 360 time to create 1 rle with old method : 0.00043010711669921875 time for calcul the mask position with numpy : 0.011281490325927734 nb_pixel_total : 320 time to create 1 rle with old method : 0.00042939186096191406 time for calcul the mask position with numpy : 0.010626554489135742 nb_pixel_total : 1510 time to create 1 rle with old method : 0.0017473697662353516 time for calcul the mask position with numpy : 0.011889934539794922 nb_pixel_total : 292 time to create 1 rle with old method : 0.000370025634765625 time for calcul the mask position with numpy : 0.011957406997680664 nb_pixel_total : 299 time to create 1 rle with old method : 0.0003654956817626953 time for calcul the mask position with numpy : 0.010622739791870117 nb_pixel_total : 168 time to create 1 rle with old method : 0.0002071857452392578 time for calcul the mask position with numpy : 0.010607004165649414 nb_pixel_total : 680 time to create 1 rle with old method : 0.0008068084716796875 time for calcul the mask position with numpy : 0.01073312759399414 nb_pixel_total : 799 time to create 1 rle with old method : 0.0009627342224121094 time for calcul the mask position with numpy : 0.0107574462890625 nb_pixel_total : 21 time to create 1 rle with old method : 7.414817810058594e-05 time for calcul the mask position with numpy : 0.01072072982788086 nb_pixel_total : 166 time to create 1 rle with old method : 0.00020837783813476562 time for calcul the mask position with numpy : 0.011649370193481445 nb_pixel_total : 302 time to create 1 rle with old method : 0.0003769397735595703 time for calcul the mask position with numpy : 0.0062160491943359375 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005183219909667969 time for calcul the mask position with numpy : 0.006482601165771484 nb_pixel_total : 59 time to create 1 rle with old method : 0.00020194053649902344 time for calcul the mask position with numpy : 0.006640434265136719 nb_pixel_total : 190 time to create 1 rle with old method : 0.0003275871276855469 time for calcul the mask position with numpy : 0.0065653324127197266 nb_pixel_total : 673 time to create 1 rle with old method : 0.0010945796966552734 time for calcul the mask position with numpy : 0.0066432952880859375 nb_pixel_total : 253 time to create 1 rle with old method : 0.00045490264892578125 time for calcul the mask position with numpy : 0.00649571418762207 nb_pixel_total : 222 time to create 1 rle with old method : 0.00038433074951171875 time for calcul the mask position with numpy : 0.0066547393798828125 nb_pixel_total : 170 time to create 1 rle with old method : 0.0003044605255126953 create new chi : 1.1159899234771729 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 : 0.0018377304077148438 batch 1 Loaded 81 chid ids of type : 4230 Number RLEs to save : 10013 TO DO : save crop sub photo not yet done ! save time : 0.5843143463134766 map_output_result : {1337396817: (0.0, 'Should be the crop_list due to order', 0.0), 1337396814: (0.0, 'Should be the crop_list due to order', 0.0), 1337396812: (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 [1337396817, 1337396814, 1337396812] Looping around the photos to save general results len do output : 3 /1337396817.Didn't retrieve data . /1337396814.Didn't retrieve data . /1337396812.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, '2582951') ('4234', '20513076', '1337396817', None, None, None, None, None, '2582951') ('4234', None, None, None, None, None, None, None, '2582951') ('4234', '20513076', '1337396814', None, None, None, None, None, '2582951') ('4234', None, None, None, None, None, None, None, '2582951') ('4234', '20513076', '1337396812', None, None, None, None, None, '2582951') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.014319419860839844 save_final save missing photos in datou_result : time spend for datou_step_exec : 10.434691429138184 time spend to save output : 0.014584064483642578 total time spend for step 4 : 10.449275493621826 step5:crop_condition Thu Feb 13 19:21:09 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 260 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 ! map_result returned by crop_photo_return_map_crop : length : 86 About to insert : list_path_to_insert length 86 new photo from crops ! About to upload 86 photos upload in portfolio : 4869462 init cache_photo without model_param we have 86 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739470870_1251291 we have uploaded 86 photos in the portfolio 4869462 time of upload the photos Elapsed time : 20.392332792282104 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 ! map_result returned by crop_photo_return_map_crop : length : 20 About to insert : list_path_to_insert length 20 new photo from crops ! About to upload 20 photos upload in portfolio : 4869462 init cache_photo without model_param we have 20 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739470891_1251291 we have uploaded 20 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.854180097579956 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 ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739470896_1251291 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.5562312602996826 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 ! map_result returned by crop_photo_return_map_crop : length : 11 About to insert : list_path_to_insert length 11 new photo from crops ! About to upload 11 photos upload in portfolio : 4869462 init cache_photo without model_param we have 11 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739470897_1251291 we have uploaded 11 photos in the portfolio 4869462 time of upload the photos Elapsed time : 2.4095120429992676 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 44 About to insert : list_path_to_insert length 44 new photo from crops ! About to upload 44 photos upload in portfolio : 4869462 init cache_photo without model_param we have 44 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739470901_1251291 we have uploaded 44 photos in the portfolio 4869462 time of upload the photos Elapsed time : 9.63695502281189 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 Next one ! 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/1739470911_1251291 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.7593684196472168 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1337396817, 1337396814, 1337396812] Looping around the photos to save general results len do output : 164 /1337425798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337425996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337426058Didn'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, '2582951') ('4234', '20513076', '1337396817', None, None, None, None, None, '2582951') ('4234', None, None, None, None, None, None, None, '2582951') ('4234', '20513076', '1337396814', None, None, None, None, None, '2582951') ('4234', None, None, None, None, None, None, None, '2582951') ('4234', '20513076', '1337396812', None, None, None, None, None, '2582951') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 495 time used for this insertion : 0.03615093231201172 save_final save missing photos in datou_result : time spend for datou_step_exec : 42.65000534057617 time spend to save output : 0.042139530181884766 total time spend for step 5 : 42.69214487075806 step6:thcl Thu Feb 13 19:21:51 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 : 0.0050313472747802734 time to convert the images to numpy array : 0.022025108337402344 time to import caffe and check if the image exist : 0.005749940872192383 time to convert the images to numpy array : 0.03271007537841797 time to import caffe and check if the image exist : 0.019488811492919922 time to convert the images to numpy array : 0.045172929763793945 time to import caffe and check if the image exist : 0.026064157485961914 time to convert the images to numpy array : 0.0434718132019043 time to import caffe and check if the image exist : 0.01782369613647461 time to convert the images to numpy array : 0.054212331771850586 time to import caffe and check if the image exist : 0.01805591583251953 time to convert the images to numpy array : 0.05451655387878418 time to import caffe and check if the image exist : 0.02289128303527832 time to convert the images to numpy array : 0.05006718635559082 time to import caffe and check if the image exist : 0.024446725845336914 time to convert the images to numpy array : 0.05056309700012207 time to import caffe and check if the image exist : 0.030780315399169922 time to convert the images to numpy array : 0.044516801834106445 time to import caffe and check if the image exist : 0.020251989364624023 time to convert the images to numpy array : 0.05571484565734863 total time to convert the images to numpy array : 0.3122570514678955 list photo_ids error: [] list photo_ids correct : [1337426046, 1337426047, 1337426048, 1337426049, 1337426051, 1337426052, 1337426053, 1337426054, 1337426055, 1337426057, 1337426058, 1337425868, 1337425870, 1337425872, 1337425874, 1337425876, 1337425879, 1337425881, 1337425883, 1337425885, 1337425887, 1337425889, 1337425891, 1337425893, 1337425895, 1337425897, 1337425899, 1337425901, 1337425919, 1337425920, 1337425921, 1337425922, 1337425923, 1337425924, 1337425925, 1337425926, 1337425927, 1337425928, 1337425929, 1337425930, 1337425931, 1337425932, 1337425933, 1337425934, 1337425935, 1337425798, 1337425800, 1337425802, 1337425804, 1337425806, 1337425808, 1337425810, 1337425812, 1337425814, 1337425816, 1337425818, 1337425820, 1337425822, 1337425824, 1337425827, 1337425829, 1337425831, 1337425833, 1337425835, 1337425837, 1337425839, 1337425841, 1337425843, 1337425845, 1337425847, 1337425849, 1337425851, 1337425853, 1337425855, 1337425857, 1337425859, 1337425862, 1337425864, 1337425866, 1337425936, 1337425960, 1337425962, 1337425964, 1337425965, 1337425966, 1337425967, 1337425968, 1337425969, 1337425971, 1337425972, 1337425973, 1337425974, 1337425975, 1337425976, 1337425977, 1337425978, 1337425902, 1337425903, 1337425904, 1337425905, 1337425906, 1337425907, 1337425908, 1337425909, 1337425910, 1337425911, 1337425912, 1337425913, 1337425914, 1337425915, 1337425916, 1337425917, 1337425918, 1337425979, 1337425980, 1337425981, 1337425982, 1337425983, 1337425986, 1337425987, 1337425988, 1337425989, 1337425990, 1337425991, 1337425992, 1337425993, 1337425994, 1337425995, 1337425996, 1337426011, 1337426012, 1337426013, 1337426014, 1337426015, 1337426016, 1337426017, 1337426018, 1337426019, 1337426020, 1337426021, 1337426022, 1337426023, 1337426024, 1337426025, 1337426026, 1337426027, 1337426028, 1337426029, 1337426030, 1337426031, 1337426032, 1337426033, 1337426034, 1337426035, 1337426036, 1337426037, 1337426038, 1337426039, 1337426040, 1337426041, 1337426042, 1337426043, 1337426044, 1337426045] number of photos to traite : 164 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 l 3637 free memory gpu now : 5264 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 WARNING: Logging before InitGoogleLogging() is written to STDERR F0213 19:21:58.252578 1251291 math_functions.cu:26] Check failed: status == CUBLAS_STATUS_SUCCESS (14 vs. 0) CUBLAS_STATUS_INTERNAL_ERROR *** Check failure stack trace: *** Command terminated by signal 6 39.43user 22.98system 1:32.29elapsed 67%CPU (0avgtext+0avgdata 2485260maxresident)k 329336inputs+7712outputs (2049major+2100439minor)pagefaults 0swaps