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 : 1296127 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 : ['2537953'] with mtr_portfolio_ids : ['20144254'] and first list_photo_ids : [] new path : /proc/1296127/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.24817490577697754 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 Sat Feb 1 19:20:31 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10774 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-01 19:20:34.413050: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-01 19:20:34.443459: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493020000 Hz 2025-02-01 19:20:34.445279: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f3510000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-01 19:20:34.445334: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-01 19:20:34.448522: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-01 19:20:34.663194: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3a2a1dd0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-01 19:20:34.663247: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-01 19:20:34.664721: 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 2025-02-01 19:20:34.665156: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 19:20:34.668275: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 19:20:34.671295: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 19:20:34.671833: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 19:20:34.674706: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 19:20:34.676105: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 19:20:34.681820: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 19:20:34.683794: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 19:20:34.683885: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 19:20:34.684763: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-01 19:20:34.684777: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-01 19:20:34.684787: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-01 19:20:34.686048: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-02-01 19:20:34.951492: 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 2025-02-01 19:20:34.951634: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 19:20:34.951667: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 19:20:34.951698: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 19:20:34.951727: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 19:20:34.951756: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 19:20:34.951783: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 19:20:34.951812: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 19:20:34.953144: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 19:20:34.954301: 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 2025-02-01 19:20:34.954334: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 19:20:34.954349: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 19:20:34.954363: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 19:20:34.954377: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 19:20:34.954391: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 19:20:34.954404: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 19:20:34.954418: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 19:20:34.955652: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 19:20:34.955690: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-01 19:20:34.955699: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-01 19:20:34.955707: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-01 19:20:34.957019: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-01 19:20:41.725331: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 19:20:41.887811: 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 : 2 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.64141 max: 150.15469 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0008783340454101562 length of segment : 25 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.0001633167266845703 length of segment : 30 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.0016896724700927734 length of segment : 39 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00036644935607910156 length of segment : 12 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 1640 time to create 1 rle with old method : 0.0030088424682617188 length of segment : 54 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.0002589225769042969 length of segment : 32 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 864 time to create 1 rle with old method : 0.0016427040100097656 length of segment : 36 time for calcul the mask position with numpy : 0.0002760887145996094 nb_pixel_total : 5754 time to create 1 rle with old method : 0.009743690490722656 length of segment : 134 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00022125244140625 length of segment : 24 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 529 time to create 1 rle with old method : 0.0007779598236083984 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.31719 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 : 4.38690185546875e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.0008149147033691406 length of segment : 32 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 2772 time to create 1 rle with old method : 0.003360271453857422 length of segment : 58 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 2793 time to create 1 rle with old method : 0.003538370132446289 length of segment : 58 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 2854 time to create 1 rle with old method : 0.0035305023193359375 length of segment : 61 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.20391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00015807151794433594 nb_pixel_total : 6335 time to create 1 rle with old method : 0.010736227035522461 length of segment : 102 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 962 time to create 1 rle with old method : 0.0016720294952392578 length of segment : 44 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.60234 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 : 0.00025582313537597656 nb_pixel_total : 11963 time to create 1 rle with old method : 0.016231298446655273 length of segment : 155 time for calcul the mask position with numpy : 0.00016951560974121094 nb_pixel_total : 8492 time to create 1 rle with old method : 0.010577678680419922 length of segment : 146 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1263 time to create 1 rle with old method : 0.0016701221466064453 length of segment : 51 time for calcul the mask position with numpy : 0.00023555755615234375 nb_pixel_total : 14173 time to create 1 rle with old method : 0.016051292419433594 length of segment : 178 time for calcul the mask position with numpy : 0.0003268718719482422 nb_pixel_total : 12 time to create 1 rle with old method : 0.00014209747314453125 length of segment : 2 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.0012569427490234375 length of segment : 25 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0002827644348144531 length of segment : 15 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001678466796875 length of segment : 18 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002465248107910156 length of segment : 10 length of segment : 0 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: 149.44375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 726 time to create 1 rle with old method : 0.0009396076202392578 length of segment : 82 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 577 time to create 1 rle with old method : 0.0007226467132568359 length of segment : 72 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005586147308349609 length of segment : 17 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 1175 time to create 1 rle with old method : 0.0015230178833007812 length of segment : 37 time for calcul the mask position with numpy : 0.0005614757537841797 nb_pixel_total : 45351 time to create 1 rle with old method : 0.05177879333496094 length of segment : 269 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 802 time to create 1 rle with old method : 0.0009903907775878906 length of segment : 66 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 1076 time to create 1 rle with old method : 0.0012693405151367188 length of segment : 34 time for calcul the mask position with numpy : 0.0005505084991455078 nb_pixel_total : 47178 time to create 1 rle with old method : 0.051337480545043945 length of segment : 302 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.0001857280731201172 length of segment : 10 Processing 1 images image shape: (400, 400, 3) min: 14.00000 max: 214.00000 molded_images shape: (1, 640, 640, 3) min: -83.32891 max: 91.84063 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.91875 max: 150.76016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 34 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 1032 time to create 1 rle with old method : 0.0013422966003417969 length of segment : 40 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0005035400390625 length of segment : 23 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 626 time to create 1 rle with old method : 0.0009436607360839844 length of segment : 24 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 54 time to create 1 rle with old method : 0.00010204315185546875 length of segment : 13 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003898143768310547 length of segment : 19 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0005326271057128906 length of segment : 37 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.000789642333984375 length of segment : 17 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0008847713470458984 length of segment : 25 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001704692840576172 length of segment : 11 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.00025343894958496094 length of segment : 12 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 62 time to create 1 rle with old method : 0.00015044212341308594 length of segment : 7 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00018453598022460938 length of segment : 10 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.00041866302490234375 length of segment : 20 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.00036406517028808594 length of segment : 20 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.0002307891845703125 length of segment : 22 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.000255584716796875 length of segment : 15 time for calcul the mask position with numpy : 0.00037288665771484375 nb_pixel_total : 20573 time to create 1 rle with old method : 0.023714780807495117 length of segment : 143 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00026154518127441406 length of segment : 10 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 126 time to create 1 rle with old method : 0.00019311904907226562 length of segment : 17 time for calcul the mask position with numpy : 2.7894973754882812e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.00022411346435546875 length of segment : 14 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.00044536590576171875 length of segment : 24 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0005741119384765625 length of segment : 21 time for calcul the mask position with numpy : 2.5033950805664062e-05 nb_pixel_total : 4 time to create 1 rle with old method : 2.8133392333984375e-05 length of segment : 3 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.00012922286987304688 length of segment : 15 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0006918907165527344 length of segment : 29 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00031256675720214844 length of segment : 15 time for calcul the mask position with numpy : 0.00031256675720214844 nb_pixel_total : 20378 time to create 1 rle with old method : 0.0222017765045166 length of segment : 146 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 10 time to create 1 rle with old method : 0.0001316070556640625 length of segment : 4 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 19 time to create 1 rle with old method : 7.05718994140625e-05 length of segment : 8 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0004138946533203125 length of segment : 18 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 24 time to create 1 rle with old method : 5.459785461425781e-05 length of segment : 7 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002155303955078125 length of segment : 11 time for calcul the mask position with numpy : 2.7894973754882812e-05 nb_pixel_total : 26 time to create 1 rle with old method : 6.4849853515625e-05 length of segment : 7 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.0001285076141357422 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.68438 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 : 3.981590270996094e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003905296325683594 length of segment : 19 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0004391670227050781 length of segment : 22 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00028252601623535156 length of segment : 14 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.00033283233642578125 length of segment : 34 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.000286102294921875 length of segment : 24 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0010533332824707031 length of segment : 36 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 651 time to create 1 rle with old method : 0.0009388923645019531 length of segment : 64 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0009753704071044922 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.80156 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 626 time to create 1 rle with old method : 0.0008702278137207031 length of segment : 44 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 3149 time to create 1 rle with old method : 0.003960609436035156 length of segment : 68 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00028967857360839844 length of segment : 18 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1783 time to create 1 rle with old method : 0.002256631851196289 length of segment : 127 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1227 time to create 1 rle with old method : 0.001560211181640625 length of segment : 40 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 2219 time to create 1 rle with old method : 0.0030596256256103516 length of segment : 51 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 3506 time to create 1 rle with old method : 0.004647493362426758 length of segment : 78 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 841 time to create 1 rle with old method : 0.0011591911315917969 length of segment : 39 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0004076957702636719 length of segment : 24 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 1866 time to create 1 rle with old method : 0.002458810806274414 length of segment : 38 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 2608 time to create 1 rle with old method : 0.0033991336822509766 length of segment : 38 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0004062652587890625 length of segment : 20 time for calcul the mask position with numpy : 0.00011491775512695312 nb_pixel_total : 5399 time to create 1 rle with old method : 0.006499767303466797 length of segment : 96 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: 145.39687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005664825439453125 length of segment : 36 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1269 time to create 1 rle with old method : 0.0015718936920166016 length of segment : 54 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1252 time to create 1 rle with old method : 0.0016279220581054688 length of segment : 53 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.0006344318389892578 length of segment : 40 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1540 time to create 1 rle with old method : 0.0019371509552001953 length of segment : 78 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00015115737915039062 length of segment : 26 time for calcul the mask position with numpy : 0.0001842975616455078 nb_pixel_total : 4602 time to create 1 rle with old method : 0.005858898162841797 length of segment : 249 time for calcul the mask position with numpy : 0.00025653839111328125 nb_pixel_total : 3662 time to create 1 rle with old method : 0.00529026985168457 length of segment : 174 Processing 1 images image shape: (280, 400, 3) min: 12.00000 max: 203.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 75.65313 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0007424354553222656 length of segment : 53 time for calcul the mask position with numpy : 0.0009944438934326172 nb_pixel_total : 106769 time to create 1 rle with old method : 0.11945891380310059 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: 149.08437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1589 time to create 1 rle with old method : 0.002080202102661133 length of segment : 85 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002880096435546875 length of segment : 27 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1874 time to create 1 rle with old method : 0.0023725032806396484 length of segment : 80 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.00046372413635253906 length of segment : 35 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.00030159950256347656 length of segment : 19 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003783702850341797 length of segment : 16 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.00048804283142089844 length of segment : 30 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00036835670471191406 length of segment : 17 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001399517059326172 length of segment : 16 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 : 49 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006144046783447266 length of segment : 25 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.0003161430358886719 length of segment : 20 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.00040221214294433594 length of segment : 15 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0006010532379150391 length of segment : 22 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.0001652240753173828 length of segment : 7 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002543926239013672 length of segment : 15 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005605220794677734 length of segment : 22 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.00030732154846191406 length of segment : 19 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0004086494445800781 length of segment : 13 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0003159046173095703 length of segment : 15 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 25 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 252 time to create 1 rle with old method : 0.00037670135498046875 length of segment : 17 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1629 time to create 1 rle with old method : 0.002073526382446289 length of segment : 56 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 825 time to create 1 rle with old method : 0.001049041748046875 length of segment : 37 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1463 time to create 1 rle with old method : 0.0018768310546875 length of segment : 61 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.0010902881622314453 length of segment : 39 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1068 time to create 1 rle with old method : 0.0014867782592773438 length of segment : 21 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006499290466308594 length of segment : 27 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 61 time to create 1 rle with old method : 0.00011777877807617188 length of segment : 8 time for calcul the mask position with numpy : 0.0001373291015625 nb_pixel_total : 2316 time to create 1 rle with old method : 0.0028548240661621094 length of segment : 126 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0003285408020019531 length of segment : 16 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.0004496574401855469 length of segment : 17 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.00036215782165527344 length of segment : 22 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.00016236305236816406 length of segment : 11 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.00013065338134765625 length of segment : 13 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00036835670471191406 length of segment : 16 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 719 time to create 1 rle with old method : 0.0010132789611816406 length of segment : 34 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0004038810729980469 length of segment : 22 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1530 time to create 1 rle with old method : 0.001867055892944336 length of segment : 56 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0011668205261230469 length of segment : 16 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.0001838207244873047 length of segment : 9 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00012493133544921875 length of segment : 9 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.0003635883331298828 length of segment : 23 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0006892681121826172 length of segment : 27 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00041747093200683594 length of segment : 18 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0007402896881103516 length of segment : 38 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 34 time to create 1 rle with old method : 8.821487426757812e-05 length of segment : 9 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00034999847412109375 length of segment : 25 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00035858154296875 length of segment : 15 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.0002655982971191406 length of segment : 13 time for calcul the mask position with numpy : 2.574920654296875e-05 nb_pixel_total : 28 time to create 1 rle with old method : 6.532669067382812e-05 length of segment : 5 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003342628479003906 length of segment : 22 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 53 time to create 1 rle with old method : 0.00011014938354492188 length of segment : 8 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00028061866760253906 length of segment : 27 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002493858337402344 length of segment : 16 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.000179290771484375 length of segment : 14 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 37 time to create 1 rle with old method : 7.891654968261719e-05 length of segment : 8 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.00044345855712890625 length of segment : 16 time for calcul the mask position with numpy : 0.0001342296600341797 nb_pixel_total : 2541 time to create 1 rle with old method : 0.0031082630157470703 length of segment : 137 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: 150.22891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0010242462158203125 length of segment : 34 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007395744323730469 length of segment : 31 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 2892 time to create 1 rle with old method : 0.0037169456481933594 length of segment : 119 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.001173257827758789 length of segment : 29 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 726 time to create 1 rle with old method : 0.0010972023010253906 length of segment : 17 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0004851818084716797 length of segment : 44 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 668 time to create 1 rle with old method : 0.000885009765625 length of segment : 49 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 584 time to create 1 rle with old method : 0.0009121894836425781 length of segment : 30 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003788471221923828 length of segment : 24 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.00034737586975097656 length of segment : 50 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00019311904907226562 length of segment : 11 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.00033354759216308594 length of segment : 43 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: -115.64141 max: 149.81875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006282329559326172 length of segment : 26 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 50 time to create 1 rle with old method : 9.34600830078125e-05 length of segment : 19 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00018906593322753906 length of segment : 29 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 822 time to create 1 rle with old method : 0.0011394023895263672 length of segment : 40 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0011086463928222656 length of segment : 34 time for calcul the mask position with numpy : 0.00022411346435546875 nb_pixel_total : 7792 time to create 1 rle with old method : 0.009769439697265625 length of segment : 201 length of segment : 0 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003101825714111328 length of segment : 12 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1267 time to create 1 rle with old method : 0.001735687255859375 length of segment : 79 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1667 time to create 1 rle with old method : 0.002238035202026367 length of segment : 52 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.98125 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 : 6.175041198730469e-05 nb_pixel_total : 585 time to create 1 rle with old method : 0.001092672348022461 length of segment : 29 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.0007238388061523438 length of segment : 16 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 2425 time to create 1 rle with old method : 0.007493019104003906 length of segment : 53 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0007271766662597656 length of segment : 16 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.0002338886260986328 length of segment : 15 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 2027 time to create 1 rle with old method : 0.003252744674682617 length of segment : 57 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 838 time to create 1 rle with old method : 0.0011713504791259766 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.08672 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 6546 time to create 1 rle with old method : 0.008336782455444336 length of segment : 98 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0013561248779296875 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.79375 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 : 4.696846008300781e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 15 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0013952255249023438 length of segment : 55 time for calcul the mask position with numpy : 0.00017714500427246094 nb_pixel_total : 7742 time to create 1 rle with old method : 0.010002613067626953 length of segment : 139 time for calcul the mask position with numpy : 0.0002739429473876953 nb_pixel_total : 13914 time to create 1 rle with old method : 0.01873159408569336 length of segment : 177 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.000270843505859375 length of segment : 17 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 1209 time to create 1 rle with old method : 0.0018453598022460938 length of segment : 31 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 618 time to create 1 rle with old method : 0.0007567405700683594 length of segment : 60 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1789 time to create 1 rle with old method : 0.0022020339965820312 length of segment : 54 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00022673606872558594 length of segment : 11 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.0002532005310058594 length of segment : 11 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: 148.92812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1123 time to create 1 rle with old method : 0.0015032291412353516 length of segment : 41 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1083 time to create 1 rle with old method : 0.0012996196746826172 length of segment : 88 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1384 time to create 1 rle with old method : 0.001707315444946289 length of segment : 108 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.000789642333984375 length of segment : 20 time for calcul the mask position with numpy : 0.0005292892456054688 nb_pixel_total : 43966 time to create 1 rle with old method : 0.05065131187438965 length of segment : 265 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001995563507080078 length of segment : 10 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006389617919921875 length of segment : 68 time for calcul the mask position with numpy : 0.0001304149627685547 nb_pixel_total : 7087 time to create 1 rle with old method : 0.00876474380493164 length of segment : 61 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1002 time to create 1 rle with old method : 0.0012199878692626953 length of segment : 77 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1368 time to create 1 rle with old method : 0.0017991065979003906 length of segment : 39 time for calcul the mask position with numpy : 0.0001513957977294922 nb_pixel_total : 7721 time to create 1 rle with old method : 0.013146400451660156 length of segment : 66 Processing 1 images image shape: (400, 400, 3) min: 16.00000 max: 218.00000 molded_images shape: (1, 640, 640, 3) min: -87.08672 max: 95.54766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.07891 max: 151.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1160 time to create 1 rle with old method : 0.0015492439270019531 length of segment : 54 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0005216598510742188 length of segment : 26 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 766 time to create 1 rle with old method : 0.0010266304016113281 length of segment : 33 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00020456314086914062 length of segment : 13 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00020956993103027344 length of segment : 11 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1298 time to create 1 rle with old method : 0.001617431640625 length of segment : 46 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.0002334117889404297 length of segment : 12 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00016498565673828125 length of segment : 18 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002689361572265625 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.13359 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.00048422813415527344 length of segment : 26 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0003848075866699219 length of segment : 18 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 961 time to create 1 rle with old method : 0.0013360977172851562 length of segment : 51 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0003135204315185547 length of segment : 15 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.00034880638122558594 length of segment : 32 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003838539123535156 length of segment : 23 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00048613548278808594 length of segment : 24 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0007927417755126953 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.93828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.0008389949798583984 length of segment : 46 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 1962 time to create 1 rle with old method : 0.0024852752685546875 length of segment : 132 time for calcul the mask position with numpy : 0.00010371208190917969 nb_pixel_total : 2903 time to create 1 rle with old method : 0.003887653350830078 length of segment : 68 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.000308990478515625 length of segment : 19 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 2087 time to create 1 rle with old method : 0.0027649402618408203 length of segment : 47 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 2235 time to create 1 rle with old method : 0.003137350082397461 length of segment : 49 time for calcul the mask position with numpy : 0.00010967254638671875 nb_pixel_total : 3794 time to create 1 rle with old method : 0.004731893539428711 length of segment : 78 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0016808509826660156 length of segment : 83 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 817 time to create 1 rle with old method : 0.0010957717895507812 length of segment : 37 time for calcul the mask position with numpy : 0.00012540817260742188 nb_pixel_total : 4469 time to create 1 rle with old method : 0.005536317825317383 length of segment : 72 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1243 time to create 1 rle with old method : 0.0015735626220703125 length of segment : 37 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0007615089416503906 length of segment : 19 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0006506443023681641 length of segment : 18 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 754 time to create 1 rle with old method : 0.0009286403656005859 length of segment : 35 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1375 time to create 1 rle with old method : 0.0018374919891357422 length of segment : 44 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: 143.24062 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005691051483154297 length of segment : 36 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0007169246673583984 length of segment : 38 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1468 time to create 1 rle with old method : 0.0018682479858398438 length of segment : 74 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1244 time to create 1 rle with old method : 0.0015306472778320312 length of segment : 54 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 868 time to create 1 rle with old method : 0.0011239051818847656 length of segment : 38 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 671 time to create 1 rle with old method : 0.0008585453033447266 length of segment : 45 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1187 time to create 1 rle with old method : 0.0015244483947753906 length of segment : 52 time for calcul the mask position with numpy : 0.0001957416534423828 nb_pixel_total : 2635 time to create 1 rle with old method : 0.003441333770751953 length of segment : 171 time for calcul the mask position with numpy : 0.00012922286987304688 nb_pixel_total : 2314 time to create 1 rle with old method : 0.002977132797241211 length of segment : 142 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1133 time to create 1 rle with old method : 0.001430511474609375 length of segment : 51 Processing 1 images image shape: (280, 400, 3) min: 5.00000 max: 204.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 74.74688 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 609 time to create 1 rle with old method : 0.0008225440979003906 length of segment : 63 time for calcul the mask position with numpy : 0.000919342041015625 nb_pixel_total : 106585 time to create 1 rle with old method : 0.12116050720214844 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: 149.22109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1614 time to create 1 rle with old method : 0.001959085464477539 length of segment : 87 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00030684471130371094 length of segment : 28 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0002605915069580078 length of segment : 20 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1569 time to create 1 rle with old method : 0.0019314289093017578 length of segment : 44 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003941059112548828 length of segment : 16 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.00044727325439453125 length of segment : 33 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 1865 time to create 1 rle with old method : 0.0022749900817871094 length of segment : 82 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.00012755393981933594 length of segment : 19 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.0002586841583251953 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 : 40 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0009109973907470703 length of segment : 28 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0004417896270751953 length of segment : 20 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0003495216369628906 length of segment : 16 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0005314350128173828 length of segment : 18 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0005590915679931641 length of segment : 15 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0007495880126953125 length of segment : 21 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0006947517395019531 length of segment : 15 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1484 time to create 1 rle with old method : 0.0025484561920166016 length of segment : 51 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0007531642913818359 length of segment : 20 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0010967254638671875 length of segment : 37 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004258155822753906 length of segment : 27 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002923011779785156 length of segment : 16 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 2593 time to create 1 rle with old method : 0.003194570541381836 length of segment : 150 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 730 time to create 1 rle with old method : 0.0009870529174804688 length of segment : 31 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.0003330707550048828 length of segment : 16 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.00042748451232910156 length of segment : 16 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0004639625549316406 length of segment : 19 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002932548522949219 length of segment : 17 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 881 time to create 1 rle with old method : 0.0011513233184814453 length of segment : 46 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002899169921875 length of segment : 30 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00016689300537109375 length of segment : 8 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1130 time to create 1 rle with old method : 0.0016531944274902344 length of segment : 20 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 70 time to create 1 rle with old method : 0.00013518333435058594 length of segment : 19 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1636 time to create 1 rle with old method : 0.002100229263305664 length of segment : 75 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004439353942871094 length of segment : 25 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0003139972686767578 length of segment : 22 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003185272216796875 length of segment : 22 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 991 time to create 1 rle with old method : 0.001379251480102539 length of segment : 18 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002295970916748047 length of segment : 13 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003662109375 length of segment : 21 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.00013518333435058594 length of segment : 11 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003380775451660156 length of segment : 22 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00016617774963378906 length of segment : 11 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.000530242919921875 length of segment : 23 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003628730773925781 length of segment : 15 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.00032210350036621094 length of segment : 14 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003418922424316406 length of segment : 15 time for calcul the mask position with numpy : 0.0001049041748046875 nb_pixel_total : 2151 time to create 1 rle with old method : 0.0027496814727783203 length of segment : 120 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.0003764629364013672 length of segment : 22 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 857 time to create 1 rle with old method : 0.0011780261993408203 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: 149.58437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 742 time to create 1 rle with old method : 0.0009837150573730469 length of segment : 33 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 668 time to create 1 rle with old method : 0.0009167194366455078 length of segment : 35 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 895 time to create 1 rle with old method : 0.0012257099151611328 length of segment : 31 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 809 time to create 1 rle with old method : 0.0011477470397949219 length of segment : 19 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 3455 time to create 1 rle with old method : 0.004415035247802734 length of segment : 92 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003991127014160156 length of segment : 55 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.001043558120727539 length of segment : 57 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 929 time to create 1 rle with old method : 0.00139617919921875 length of segment : 35 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 58 time to create 1 rle with old method : 0.00010704994201660156 length of segment : 10 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00028777122497558594 length of segment : 23 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0004611015319824219 length of segment : 25 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0005788803100585938 length of segment : 61 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002181529998779297 length of segment : 14 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1172 time to create 1 rle with old method : 0.001748800277709961 length of segment : 41 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 254.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0007240772247314453 length of segment : 105 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004696846008300781 length of segment : 68 time for calcul the mask position with numpy : 0.0004165172576904297 nb_pixel_total : 37456 time to create 1 rle with old method : 0.04213356971740723 length of segment : 254 Detection mask done ! Trying to reset tf kernel 1296254 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 4686 tf kernel not reseted sub process len(results) : 320 len(list_Values) 320 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 320 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 : 5485 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 320 chid ids of type : 4228 Number RLEs to save : 14132 save missing photos in datou_result : time spend for datou_step_exec : 22.987472534179688 time spend to save output : 1.037123203277588 total time spend for step 1 : 24.024595737457275 step2:brightness Sat Feb 1 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/1738434031_1296127_1333764179_8896a990d8b4c3a91eb7c9496aa4c85c.jpg treat image : temp/1738434031_1296127_1333764086_0e0284aa921a6ce30e18047dfb88d1d7.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 2 time used for this insertion : 0.012542009353637695 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.012424945831298828 save missing photos in datou_result : time spend for datou_step_exec : 0.5206711292266846 time spend to save output : 0.030291080474853516 total time spend for step 2 : 0.5509622097015381 step3:blur_detection Sat Feb 1 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/1738434031_1296127_1333764179_8896a990d8b4c3a91eb7c9496aa4c85c.jpg resize: (1080, 1920) 1333764179 -8.193993554471637 treat image : temp/1738434031_1296127_1333764086_0e0284aa921a6ce30e18047dfb88d1d7.jpg resize: (1080, 1920) 1333764086 -8.19460520633695 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 2 time used for this insertion : 0.012702226638793945 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.011873960494995117 save missing photos in datou_result : time spend for datou_step_exec : 1.9684381484985352 time spend to save output : 0.029695749282836914 total time spend for step 3 : 1.998133897781372 step4:rle_unique_nms_with_priority Sat Feb 1 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 320 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 167 nb_hashtags : 6 time to prepare the origin masks : 1.0608201026916504 time for calcul the mask position with numpy : 0.1638350486755371 nb_pixel_total : 1778170 time to create 1 rle with new method : 0.08670449256896973 time for calcul the mask position with numpy : 0.00798797607421875 nb_pixel_total : 45351 time to create 1 rle with old method : 0.05213809013366699 time for calcul the mask position with numpy : 0.008266925811767578 nb_pixel_total : 4748 time to create 1 rle with old method : 0.006211042404174805 time for calcul the mask position with numpy : 0.00792694091796875 nb_pixel_total : 1263 time to create 1 rle with old method : 0.0015101432800292969 time for calcul the mask position with numpy : 0.008055925369262695 nb_pixel_total : 69 time to create 1 rle with old method : 0.00010013580322265625 time for calcul the mask position with numpy : 0.008140325546264648 nb_pixel_total : 173 time to create 1 rle with old method : 0.00023436546325683594 time for calcul the mask position with numpy : 0.008000373840332031 nb_pixel_total : 129 time to create 1 rle with old method : 0.00016927719116210938 time for calcul the mask position with numpy : 0.00802302360534668 nb_pixel_total : 903 time to create 1 rle with old method : 0.0010728836059570312 time for calcul the mask position with numpy : 0.007938623428344727 nb_pixel_total : 78 time to create 1 rle with old method : 0.00011682510375976562 time for calcul the mask position with numpy : 0.008209228515625 nb_pixel_total : 16 time to create 1 rle with old method : 5.173683166503906e-05 time for calcul the mask position with numpy : 0.008300065994262695 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005614757537841797 time for calcul the mask position with numpy : 0.00835728645324707 nb_pixel_total : 1640 time to create 1 rle with old method : 0.0021736621856689453 time for calcul the mask position with numpy : 0.008441686630249023 nb_pixel_total : 59 time to create 1 rle with old method : 0.0001537799835205078 time for calcul the mask position with numpy : 0.008473396301269531 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001621246337890625 time for calcul the mask position with numpy : 0.008449316024780273 nb_pixel_total : 2772 time to create 1 rle with old method : 0.003581523895263672 time for calcul the mask position with numpy : 0.008545398712158203 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006346702575683594 time for calcul the mask position with numpy : 0.008486270904541016 nb_pixel_total : 962 time to create 1 rle with old method : 0.0012369155883789062 time for calcul the mask position with numpy : 0.00847005844116211 nb_pixel_total : 5754 time to create 1 rle with old method : 0.007393360137939453 time for calcul the mask position with numpy : 0.008780241012573242 nb_pixel_total : 184 time to create 1 rle with old method : 0.0002560615539550781 time for calcul the mask position with numpy : 0.009220361709594727 nb_pixel_total : 577 time to create 1 rle with old method : 0.0008020401000976562 time for calcul the mask position with numpy : 0.008876562118530273 nb_pixel_total : 2339 time to create 1 rle with old method : 0.0030333995819091797 time for calcul the mask position with numpy : 0.008936882019042969 nb_pixel_total : 11963 time to create 1 rle with old method : 0.015294551849365234 time for calcul the mask position with numpy : 0.007965326309204102 nb_pixel_total : 726 time to create 1 rle with old method : 0.0008871555328369141 time for calcul the mask position with numpy : 0.00835871696472168 nb_pixel_total : 164 time to create 1 rle with old method : 0.00024247169494628906 time for calcul the mask position with numpy : 0.008289813995361328 nb_pixel_total : 6335 time to create 1 rle with old method : 0.007657051086425781 time for calcul the mask position with numpy : 0.007791042327880859 nb_pixel_total : 8492 time to create 1 rle with old method : 0.00946664810180664 time for calcul the mask position with numpy : 0.008244037628173828 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002009868621826172 time for calcul the mask position with numpy : 0.008492708206176758 nb_pixel_total : 94 time to create 1 rle with old method : 0.00013065338134765625 time for calcul the mask position with numpy : 0.0082855224609375 nb_pixel_total : 23 time to create 1 rle with old method : 4.982948303222656e-05 time for calcul the mask position with numpy : 0.008189916610717773 nb_pixel_total : 1175 time to create 1 rle with old method : 0.0012631416320800781 time for calcul the mask position with numpy : 0.008803606033325195 nb_pixel_total : 524 time to create 1 rle with old method : 0.0006172657012939453 time for calcul the mask position with numpy : 0.008933782577514648 nb_pixel_total : 386 time to create 1 rle with old method : 0.00048422813415527344 time for calcul the mask position with numpy : 0.009181022644042969 nb_pixel_total : 478 time to create 1 rle with old method : 0.0005764961242675781 time for calcul the mask position with numpy : 0.008913755416870117 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001533031463623047 time for calcul the mask position with numpy : 0.008390188217163086 nb_pixel_total : 11 time to create 1 rle with old method : 1.7642974853515625e-05 time for calcul the mask position with numpy : 0.00898122787475586 nb_pixel_total : 1032 time to create 1 rle with old method : 0.001329660415649414 time for calcul the mask position with numpy : 0.008532047271728516 nb_pixel_total : 3149 time to create 1 rle with old method : 0.0034842491149902344 time for calcul the mask position with numpy : 0.00780797004699707 nb_pixel_total : 663 time to create 1 rle with old method : 0.0008232593536376953 time for calcul the mask position with numpy : 0.00784611701965332 nb_pixel_total : 841 time to create 1 rle with old method : 0.0009093284606933594 time for calcul the mask position with numpy : 0.010153532028198242 nb_pixel_total : 15 time to create 1 rle with old method : 3.981590270996094e-05 time for calcul the mask position with numpy : 0.008255720138549805 nb_pixel_total : 62 time to create 1 rle with old method : 7.62939453125e-05 time for calcul the mask position with numpy : 0.007900714874267578 nb_pixel_total : 80 time to create 1 rle with old method : 0.00010275840759277344 time for calcul the mask position with numpy : 0.007884979248046875 nb_pixel_total : 1227 time to create 1 rle with old method : 0.0013413429260253906 time for calcul the mask position with numpy : 0.008040904998779297 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005843639373779297 time for calcul the mask position with numpy : 0.007973432540893555 nb_pixel_total : 321 time to create 1 rle with old method : 0.0003693103790283203 time for calcul the mask position with numpy : 0.00783228874206543 nb_pixel_total : 688 time to create 1 rle with old method : 0.0008134841918945312 time for calcul the mask position with numpy : 0.007925033569335938 nb_pixel_total : 244 time to create 1 rle with old method : 0.00028324127197265625 time for calcul the mask position with numpy : 0.008301734924316406 nb_pixel_total : 485 time to create 1 rle with old method : 0.0005459785461425781 time for calcul the mask position with numpy : 0.008516311645507812 nb_pixel_total : 126 time to create 1 rle with old method : 0.0001571178436279297 time for calcul the mask position with numpy : 0.008512496948242188 nb_pixel_total : 550 time to create 1 rle with old method : 0.0006518363952636719 time for calcul the mask position with numpy : 0.008535623550415039 nb_pixel_total : 150 time to create 1 rle with old method : 0.00018286705017089844 time for calcul the mask position with numpy : 0.00844573974609375 nb_pixel_total : 4292 time to create 1 rle with old method : 0.005016803741455078 time for calcul the mask position with numpy : 0.008459806442260742 nb_pixel_total : 1783 time to create 1 rle with old method : 0.002139568328857422 time for calcul the mask position with numpy : 0.008423805236816406 nb_pixel_total : 276 time to create 1 rle with old method : 0.00034880638122558594 time for calcul the mask position with numpy : 0.008518695831298828 nb_pixel_total : 19 time to create 1 rle with old method : 3.790855407714844e-05 time for calcul the mask position with numpy : 0.00822305679321289 nb_pixel_total : 168 time to create 1 rle with old method : 0.000244140625 time for calcul the mask position with numpy : 0.008618593215942383 nb_pixel_total : 94 time to create 1 rle with old method : 0.0001251697540283203 time for calcul the mask position with numpy : 0.008333444595336914 nb_pixel_total : 54 time to create 1 rle with old method : 6.4849853515625e-05 time for calcul the mask position with numpy : 0.008258581161499023 nb_pixel_total : 235 time to create 1 rle with old method : 0.0003292560577392578 time for calcul the mask position with numpy : 0.008449316024780273 nb_pixel_total : 130 time to create 1 rle with old method : 0.00017404556274414062 time for calcul the mask position with numpy : 0.008705615997314453 nb_pixel_total : 291 time to create 1 rle with old method : 0.00035881996154785156 time for calcul the mask position with numpy : 0.00836944580078125 nb_pixel_total : 1252 time to create 1 rle with old method : 0.0014922618865966797 time for calcul the mask position with numpy : 0.008531332015991211 nb_pixel_total : 167 time to create 1 rle with old method : 0.00021505355834960938 time for calcul the mask position with numpy : 0.008476972579956055 nb_pixel_total : 303 time to create 1 rle with old method : 0.0003936290740966797 time for calcul the mask position with numpy : 0.008492708206176758 nb_pixel_total : 53 time to create 1 rle with old method : 8.916854858398438e-05 time for calcul the mask position with numpy : 0.008538961410522461 nb_pixel_total : 26 time to create 1 rle with old method : 5.1021575927734375e-05 time for calcul the mask position with numpy : 0.00813603401184082 nb_pixel_total : 221 time to create 1 rle with old method : 0.0002579689025878906 time for calcul the mask position with numpy : 0.008220672607421875 nb_pixel_total : 787 time to create 1 rle with old method : 0.0009510517120361328 time for calcul the mask position with numpy : 0.008112907409667969 nb_pixel_total : 258 time to create 1 rle with old method : 0.0002887248992919922 time for calcul the mask position with numpy : 0.007961750030517578 nb_pixel_total : 3506 time to create 1 rle with old method : 0.003779172897338867 time for calcul the mask position with numpy : 0.007820367813110352 nb_pixel_total : 308 time to create 1 rle with old method : 0.00034356117248535156 time for calcul the mask position with numpy : 0.00797724723815918 nb_pixel_total : 20503 time to create 1 rle with old method : 0.022226572036743164 time for calcul the mask position with numpy : 0.00820469856262207 nb_pixel_total : 172 time to create 1 rle with old method : 0.0003154277801513672 time for calcul the mask position with numpy : 0.008054494857788086 nb_pixel_total : 135 time to create 1 rle with old method : 0.000156402587890625 time for calcul the mask position with numpy : 0.007860422134399414 nb_pixel_total : 247 time to create 1 rle with old method : 0.00028061866760253906 time for calcul the mask position with numpy : 0.007845163345336914 nb_pixel_total : 1269 time to create 1 rle with old method : 0.001377105712890625 time for calcul the mask position with numpy : 0.008135557174682617 nb_pixel_total : 79 time to create 1 rle with old method : 9.512901306152344e-05 time for calcul the mask position with numpy : 0.008223295211791992 nb_pixel_total : 341 time to create 1 rle with old method : 0.00039649009704589844 time for calcul the mask position with numpy : 0.008462905883789062 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001342296600341797 time for calcul the mask position with numpy : 0.008568763732910156 nb_pixel_total : 4 time to create 1 rle with old method : 1.5974044799804688e-05 time for calcul the mask position with numpy : 0.008109807968139648 nb_pixel_total : 5399 time to create 1 rle with old method : 0.006386995315551758 time for calcul the mask position with numpy : 0.008446455001831055 nb_pixel_total : 1540 time to create 1 rle with old method : 0.0017993450164794922 time for calcul the mask position with numpy : 0.008456707000732422 nb_pixel_total : 237 time to create 1 rle with old method : 0.0002899169921875 time for calcul the mask position with numpy : 0.008514165878295898 nb_pixel_total : 626 time to create 1 rle with old method : 0.0007157325744628906 time for calcul the mask position with numpy : 0.008520841598510742 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001327991485595703 time for calcul the mask position with numpy : 0.008520841598510742 nb_pixel_total : 10 time to create 1 rle with old method : 3.886222839355469e-05 time for calcul the mask position with numpy : 0.008442401885986328 nb_pixel_total : 202 time to create 1 rle with old method : 0.00024175643920898438 time for calcul the mask position with numpy : 0.008471250534057617 nb_pixel_total : 170 time to create 1 rle with old method : 0.0002465248107910156 time for calcul the mask position with numpy : 0.008608102798461914 nb_pixel_total : 218 time to create 1 rle with old method : 0.00029158592224121094 time for calcul the mask position with numpy : 0.008500814437866211 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004253387451171875 time for calcul the mask position with numpy : 0.008491277694702148 nb_pixel_total : 113 time to create 1 rle with old method : 0.00020241737365722656 time for calcul the mask position with numpy : 0.008514881134033203 nb_pixel_total : 2219 time to create 1 rle with old method : 0.0026814937591552734 time for calcul the mask position with numpy : 0.008671045303344727 nb_pixel_total : 584 time to create 1 rle with old method : 0.0007610321044921875 time for calcul the mask position with numpy : 0.008532047271728516 nb_pixel_total : 176 time to create 1 rle with old method : 0.00022077560424804688 time for calcul the mask position with numpy : 0.008226394653320312 nb_pixel_total : 392 time to create 1 rle with old method : 0.0004830360412597656 time for calcul the mask position with numpy : 0.008437633514404297 nb_pixel_total : 626 time to create 1 rle with old method : 0.0007374286651611328 time for calcul the mask position with numpy : 0.008654117584228516 nb_pixel_total : 63 time to create 1 rle with old method : 7.915496826171875e-05 time for calcul the mask position with numpy : 0.009299278259277344 nb_pixel_total : 106264 time to create 1 rle with old method : 0.15013504028320312 time for calcul the mask position with numpy : 0.008789300918579102 nb_pixel_total : 104 time to create 1 rle with old method : 0.0002181529998779297 time for calcul the mask position with numpy : 0.008692264556884766 nb_pixel_total : 726 time to create 1 rle with old method : 0.000911712646484375 time for calcul the mask position with numpy : 0.00873708724975586 nb_pixel_total : 337 time to create 1 rle with old method : 0.0004913806915283203 time for calcul the mask position with numpy : 0.008778810501098633 nb_pixel_total : 2892 time to create 1 rle with old method : 0.0033829212188720703 time for calcul the mask position with numpy : 0.008819818496704102 nb_pixel_total : 224 time to create 1 rle with old method : 0.0002987384796142578 time for calcul the mask position with numpy : 0.008709907531738281 nb_pixel_total : 668 time to create 1 rle with old method : 0.0008795261383056641 time for calcul the mask position with numpy : 0.008646011352539062 nb_pixel_total : 173 time to create 1 rle with old method : 0.0003592967987060547 time for calcul the mask position with numpy : 0.015172004699707031 nb_pixel_total : 95 time to create 1 rle with old method : 0.0002498626708984375 time for calcul the mask position with numpy : 0.012109518051147461 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003285408020019531 time for calcul the mask position with numpy : 0.008613824844360352 nb_pixel_total : 242 time to create 1 rle with old method : 0.00030517578125 time for calcul the mask position with numpy : 0.008628129959106445 nb_pixel_total : 229 time to create 1 rle with old method : 0.00030231475830078125 time for calcul the mask position with numpy : 0.009106874465942383 nb_pixel_total : 392 time to create 1 rle with old method : 0.0010268688201904297 time for calcul the mask position with numpy : 0.010147809982299805 nb_pixel_total : 254 time to create 1 rle with old method : 0.00047707557678222656 time for calcul the mask position with numpy : 0.010134220123291016 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002951622009277344 time for calcul the mask position with numpy : 0.010030508041381836 nb_pixel_total : 403 time to create 1 rle with old method : 0.0006902217864990234 time for calcul the mask position with numpy : 0.010201454162597656 nb_pixel_total : 278 time to create 1 rle with old method : 0.0005035400390625 time for calcul the mask position with numpy : 0.01009368896484375 nb_pixel_total : 269 time to create 1 rle with old method : 0.0004627704620361328 time for calcul the mask position with numpy : 0.009648799896240234 nb_pixel_total : 229 time to create 1 rle with old method : 0.0003230571746826172 time for calcul the mask position with numpy : 0.008699417114257812 nb_pixel_total : 210 time to create 1 rle with old method : 0.00027823448181152344 time for calcul the mask position with numpy : 0.008900642395019531 nb_pixel_total : 257 time to create 1 rle with old method : 0.00037789344787597656 time for calcul the mask position with numpy : 0.008767366409301758 nb_pixel_total : 740 time to create 1 rle with old method : 0.0009200572967529297 time for calcul the mask position with numpy : 0.008635282516479492 nb_pixel_total : 300 time to create 1 rle with old method : 0.0003762245178222656 time for calcul the mask position with numpy : 0.00838780403137207 nb_pixel_total : 116 time to create 1 rle with old method : 0.00015664100646972656 time for calcul the mask position with numpy : 0.008598566055297852 nb_pixel_total : 2 time to create 1 rle with old method : 4.076957702636719e-05 time for calcul the mask position with numpy : 0.008311271667480469 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003371238708496094 time for calcul the mask position with numpy : 0.008119583129882812 nb_pixel_total : 169 time to create 1 rle with old method : 0.000232696533203125 time for calcul the mask position with numpy : 0.008046388626098633 nb_pixel_total : 375 time to create 1 rle with old method : 0.0004897117614746094 time for calcul the mask position with numpy : 0.00812530517578125 nb_pixel_total : 532 time to create 1 rle with old method : 0.0006606578826904297 time for calcul the mask position with numpy : 0.008037328720092773 nb_pixel_total : 184 time to create 1 rle with old method : 0.00022983551025390625 time for calcul the mask position with numpy : 0.008296966552734375 nb_pixel_total : 53 time to create 1 rle with old method : 7.62939453125e-05 time for calcul the mask position with numpy : 0.008273839950561523 nb_pixel_total : 34 time to create 1 rle with old method : 5.7697296142578125e-05 time for calcul the mask position with numpy : 0.008315563201904297 nb_pixel_total : 566 time to create 1 rle with old method : 0.0006814002990722656 time for calcul the mask position with numpy : 0.008438587188720703 nb_pixel_total : 2316 time to create 1 rle with old method : 0.0026416778564453125 time for calcul the mask position with numpy : 0.008468151092529297 nb_pixel_total : 223 time to create 1 rle with old method : 0.00030159950256347656 time for calcul the mask position with numpy : 0.008590936660766602 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002684593200683594 time for calcul the mask position with numpy : 0.008566856384277344 nb_pixel_total : 246 time to create 1 rle with old method : 0.00030994415283203125 time for calcul the mask position with numpy : 0.008677005767822266 nb_pixel_total : 913 time to create 1 rle with old method : 0.001129150390625 time for calcul the mask position with numpy : 0.009289741516113281 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003376007080078125 time for calcul the mask position with numpy : 0.008681535720825195 nb_pixel_total : 12 time to create 1 rle with old method : 5.030632019042969e-05 time for calcul the mask position with numpy : 0.008748292922973633 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006079673767089844 time for calcul the mask position with numpy : 0.008725166320800781 nb_pixel_total : 195 time to create 1 rle with old method : 0.00025725364685058594 time for calcul the mask position with numpy : 0.008701324462890625 nb_pixel_total : 1589 time to create 1 rle with old method : 0.00191497802734375 time for calcul the mask position with numpy : 0.009564638137817383 nb_pixel_total : 28 time to create 1 rle with old method : 7.271766662597656e-05 time for calcul the mask position with numpy : 0.010222673416137695 nb_pixel_total : 583 time to create 1 rle with old method : 0.000986337661743164 time for calcul the mask position with numpy : 0.009993553161621094 nb_pixel_total : 268 time to create 1 rle with old method : 0.0004565715789794922 time for calcul the mask position with numpy : 0.009530067443847656 nb_pixel_total : 68 time to create 1 rle with old method : 0.00012254714965820312 time for calcul the mask position with numpy : 0.009454011917114258 nb_pixel_total : 294 time to create 1 rle with old method : 0.00047850608825683594 time for calcul the mask position with numpy : 0.009497642517089844 nb_pixel_total : 584 time to create 1 rle with old method : 0.0009367465972900391 time for calcul the mask position with numpy : 0.008664369583129883 nb_pixel_total : 252 time to create 1 rle with old method : 0.0003781318664550781 time for calcul the mask position with numpy : 0.00928640365600586 nb_pixel_total : 1874 time to create 1 rle with old method : 0.002919912338256836 time for calcul the mask position with numpy : 0.011579513549804688 nb_pixel_total : 1463 time to create 1 rle with old method : 0.0021500587463378906 time for calcul the mask position with numpy : 0.008780956268310547 nb_pixel_total : 662 time to create 1 rle with old method : 0.0008006095886230469 time for calcul the mask position with numpy : 0.00824427604675293 nb_pixel_total : 217 time to create 1 rle with old method : 0.0002512931823730469 time for calcul the mask position with numpy : 0.008061647415161133 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002701282501220703 time for calcul the mask position with numpy : 0.008048057556152344 nb_pixel_total : 86 time to create 1 rle with old method : 0.00010561943054199219 time for calcul the mask position with numpy : 0.00800180435180664 nb_pixel_total : 35 time to create 1 rle with old method : 6.628036499023438e-05 time for calcul the mask position with numpy : 0.008402347564697266 nb_pixel_total : 825 time to create 1 rle with old method : 0.0009918212890625 time for calcul the mask position with numpy : 0.008563995361328125 nb_pixel_total : 1629 time to create 1 rle with old method : 0.0018737316131591797 time for calcul the mask position with numpy : 0.008359670639038086 nb_pixel_total : 547 time to create 1 rle with old method : 0.0006036758422851562 time for calcul the mask position with numpy : 0.008486032485961914 nb_pixel_total : 39 time to create 1 rle with old method : 7.677078247070312e-05 time for calcul the mask position with numpy : 0.008348226547241211 nb_pixel_total : 71 time to create 1 rle with old method : 9.107589721679688e-05 time for calcul the mask position with numpy : 0.008180618286132812 nb_pixel_total : 88 time to create 1 rle with old method : 0.00011229515075683594 time for calcul the mask position with numpy : 0.008295059204101562 nb_pixel_total : 263 time to create 1 rle with old method : 0.00030875205993652344 time for calcul the mask position with numpy : 0.008121967315673828 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005946159362792969 time for calcul the mask position with numpy : 0.008464574813842773 nb_pixel_total : 186 time to create 1 rle with old method : 0.00023865699768066406 time for calcul the mask position with numpy : 0.008303403854370117 nb_pixel_total : 37 time to create 1 rle with old method : 5.2928924560546875e-05 time for calcul the mask position with numpy : 0.008402109146118164 nb_pixel_total : 311 time to create 1 rle with old method : 0.0003306865692138672 time for calcul the mask position with numpy : 0.008333921432495117 nb_pixel_total : 1068 time to create 1 rle with old method : 0.0012581348419189453 time for calcul the mask position with numpy : 0.008390665054321289 nb_pixel_total : 93 time to create 1 rle with old method : 0.00011730194091796875 time for calcul the mask position with numpy : 0.008217096328735352 nb_pixel_total : 31 time to create 1 rle with old method : 4.458427429199219e-05 create new chi : 2.0808422565460205 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 : 0.010803937911987305 batch 1 Loaded 168 chid ids of type : 4230 Number RLEs to save : 13428 TO DO : save crop sub photo not yet done ! save time : 0.8669018745422363 nb_obj : 149 nb_hashtags : 7 time to prepare the origin masks : 2.564059257507324 time for calcul the mask position with numpy : 0.04087114334106445 nb_pixel_total : 1754933 time to create 1 rle with new method : 0.0700676441192627 time for calcul the mask position with numpy : 0.006298542022705078 nb_pixel_total : 1384 time to create 1 rle with old method : 0.0016145706176757812 time for calcul the mask position with numpy : 0.008280038833618164 nb_pixel_total : 1789 time to create 1 rle with old method : 0.002137422561645508 time for calcul the mask position with numpy : 0.010290861129760742 nb_pixel_total : 50 time to create 1 rle with old method : 8.463859558105469e-05 time for calcul the mask position with numpy : 0.010446786880493164 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002474784851074219 time for calcul the mask position with numpy : 0.010173797607421875 nb_pixel_total : 137 time to create 1 rle with old method : 0.00018143653869628906 time for calcul the mask position with numpy : 0.00645756721496582 nb_pixel_total : 822 time to create 1 rle with old method : 0.0009634494781494141 time for calcul the mask position with numpy : 0.006577968597412109 nb_pixel_total : 1267 time to create 1 rle with old method : 0.001497030258178711 time for calcul the mask position with numpy : 0.006684780120849609 nb_pixel_total : 462 time to create 1 rle with old method : 0.0005393028259277344 time for calcul the mask position with numpy : 0.0075223445892333984 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006134510040283203 time for calcul the mask position with numpy : 0.007817506790161133 nb_pixel_total : 43966 time to create 1 rle with old method : 0.04693865776062012 time for calcul the mask position with numpy : 0.006024599075317383 nb_pixel_total : 52 time to create 1 rle with old method : 0.0001049041748046875 time for calcul the mask position with numpy : 0.006008148193359375 nb_pixel_total : 2425 time to create 1 rle with old method : 0.0027174949645996094 time for calcul the mask position with numpy : 0.009069681167602539 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003485679626464844 time for calcul the mask position with numpy : 0.007950782775878906 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0011444091796875 time for calcul the mask position with numpy : 0.008349180221557617 nb_pixel_total : 924 time to create 1 rle with old method : 0.0010080337524414062 time for calcul the mask position with numpy : 0.007969856262207031 nb_pixel_total : 7792 time to create 1 rle with old method : 0.009051799774169922 time for calcul the mask position with numpy : 0.008872509002685547 nb_pixel_total : 838 time to create 1 rle with old method : 0.0009250640869140625 time for calcul the mask position with numpy : 0.006604194641113281 nb_pixel_total : 585 time to create 1 rle with old method : 0.0007219314575195312 time for calcul the mask position with numpy : 0.0068624019622802734 nb_pixel_total : 207 time to create 1 rle with old method : 0.000255584716796875 time for calcul the mask position with numpy : 0.006379604339599609 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006344318389892578 time for calcul the mask position with numpy : 0.0064084529876708984 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005230903625488281 time for calcul the mask position with numpy : 0.006258249282836914 nb_pixel_total : 116 time to create 1 rle with old method : 0.0001590251922607422 time for calcul the mask position with numpy : 0.007662057876586914 nb_pixel_total : 13914 time to create 1 rle with old method : 0.015684127807617188 time for calcul the mask position with numpy : 0.010362863540649414 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.006296396255493164 nb_pixel_total : 637 time to create 1 rle with old method : 0.0008981227874755859 time for calcul the mask position with numpy : 0.006498813629150391 nb_pixel_total : 7087 time to create 1 rle with old method : 0.008395910263061523 time for calcul the mask position with numpy : 0.006616830825805664 nb_pixel_total : 1083 time to create 1 rle with old method : 0.0012426376342773438 time for calcul the mask position with numpy : 0.006261587142944336 nb_pixel_total : 6546 time to create 1 rle with old method : 0.007378101348876953 time for calcul the mask position with numpy : 0.0062122344970703125 nb_pixel_total : 7742 time to create 1 rle with old method : 0.00911855697631836 time for calcul the mask position with numpy : 0.006338596343994141 nb_pixel_total : 5 time to create 1 rle with old method : 3.1948089599609375e-05 time for calcul the mask position with numpy : 0.006594419479370117 nb_pixel_total : 109 time to create 1 rle with old method : 0.00016236305236816406 time for calcul the mask position with numpy : 0.008846282958984375 nb_pixel_total : 22 time to create 1 rle with old method : 8.58306884765625e-05 time for calcul the mask position with numpy : 0.006966114044189453 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002014636993408203 time for calcul the mask position with numpy : 0.006988048553466797 nb_pixel_total : 278 time to create 1 rle with old method : 0.00042819976806640625 time for calcul the mask position with numpy : 0.006993293762207031 nb_pixel_total : 1123 time to create 1 rle with old method : 0.0012602806091308594 time for calcul the mask position with numpy : 0.007938861846923828 nb_pixel_total : 739 time to create 1 rle with old method : 0.0008742809295654297 time for calcul the mask position with numpy : 0.007360219955444336 nb_pixel_total : 512 time to create 1 rle with old method : 0.0006320476531982422 time for calcul the mask position with numpy : 0.00707244873046875 nb_pixel_total : 48 time to create 1 rle with old method : 0.00010967254638671875 time for calcul the mask position with numpy : 0.00722813606262207 nb_pixel_total : 343 time to create 1 rle with old method : 0.0004222393035888672 time for calcul the mask position with numpy : 0.007927656173706055 nb_pixel_total : 2903 time to create 1 rle with old method : 0.0030472278594970703 time for calcul the mask position with numpy : 0.007689476013183594 nb_pixel_total : 1298 time to create 1 rle with old method : 0.0015685558319091797 time for calcul the mask position with numpy : 0.0072612762451171875 nb_pixel_total : 495 time to create 1 rle with old method : 0.0005671977996826172 time for calcul the mask position with numpy : 0.007546663284301758 nb_pixel_total : 26 time to create 1 rle with old method : 7.05718994140625e-05 time for calcul the mask position with numpy : 0.007017374038696289 nb_pixel_total : 817 time to create 1 rle with old method : 0.0009102821350097656 time for calcul the mask position with numpy : 0.006964683532714844 nb_pixel_total : 1243 time to create 1 rle with old method : 0.0013031959533691406 time for calcul the mask position with numpy : 0.007020473480224609 nb_pixel_total : 671 time to create 1 rle with old method : 0.0007536411285400391 time for calcul the mask position with numpy : 0.0070629119873046875 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002455711364746094 time for calcul the mask position with numpy : 0.0063953399658203125 nb_pixel_total : 401 time to create 1 rle with old method : 0.0004582405090332031 time for calcul the mask position with numpy : 0.005822896957397461 nb_pixel_total : 1160 time to create 1 rle with old method : 0.0013959407806396484 time for calcul the mask position with numpy : 0.006093025207519531 nb_pixel_total : 868 time to create 1 rle with old method : 0.0010344982147216797 time for calcul the mask position with numpy : 0.006415843963623047 nb_pixel_total : 504 time to create 1 rle with old method : 0.0005893707275390625 time for calcul the mask position with numpy : 0.006394386291503906 nb_pixel_total : 2635 time to create 1 rle with old method : 0.003215312957763672 time for calcul the mask position with numpy : 0.0062906742095947266 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0015578269958496094 time for calcul the mask position with numpy : 0.006224632263183594 nb_pixel_total : 1962 time to create 1 rle with old method : 0.002240419387817383 time for calcul the mask position with numpy : 0.006177425384521484 nb_pixel_total : 116 time to create 1 rle with old method : 0.00020051002502441406 time for calcul the mask position with numpy : 0.006223440170288086 nb_pixel_total : 101 time to create 1 rle with old method : 0.00014138221740722656 time for calcul the mask position with numpy : 0.006173610687255859 nb_pixel_total : 282 time to create 1 rle with old method : 0.00035762786865234375 time for calcul the mask position with numpy : 0.0061147212982177734 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002474784851074219 time for calcul the mask position with numpy : 0.006366252899169922 nb_pixel_total : 1187 time to create 1 rle with old method : 0.0013589859008789062 time for calcul the mask position with numpy : 0.006174564361572266 nb_pixel_total : 6 time to create 1 rle with old method : 3.790855407714844e-05 time for calcul the mask position with numpy : 0.006706953048706055 nb_pixel_total : 218 time to create 1 rle with old method : 0.00026607513427734375 time for calcul the mask position with numpy : 0.006205320358276367 nb_pixel_total : 359 time to create 1 rle with old method : 0.0003991127014160156 time for calcul the mask position with numpy : 0.006028890609741211 nb_pixel_total : 3794 time to create 1 rle with old method : 0.004117488861083984 time for calcul the mask position with numpy : 0.006865739822387695 nb_pixel_total : 131 time to create 1 rle with old method : 0.0001823902130126953 time for calcul the mask position with numpy : 0.006008625030517578 nb_pixel_total : 1244 time to create 1 rle with old method : 0.0013773441314697266 time for calcul the mask position with numpy : 0.0060482025146484375 nb_pixel_total : 248 time to create 1 rle with old method : 0.00031447410583496094 time for calcul the mask position with numpy : 0.006637096405029297 nb_pixel_total : 19 time to create 1 rle with old method : 8.678436279296875e-05 time for calcul the mask position with numpy : 0.006270170211791992 nb_pixel_total : 174 time to create 1 rle with old method : 0.00021791458129882812 time for calcul the mask position with numpy : 0.005771636962890625 nb_pixel_total : 124 time to create 1 rle with old method : 0.00018072128295898438 time for calcul the mask position with numpy : 0.005883932113647461 nb_pixel_total : 4469 time to create 1 rle with old method : 0.005404233932495117 time for calcul the mask position with numpy : 0.0063323974609375 nb_pixel_total : 1468 time to create 1 rle with old method : 0.0017590522766113281 time for calcul the mask position with numpy : 0.005967140197753906 nb_pixel_total : 646 time to create 1 rle with old method : 0.0007643699645996094 time for calcul the mask position with numpy : 0.0058515071868896484 nb_pixel_total : 214 time to create 1 rle with old method : 0.0003006458282470703 time for calcul the mask position with numpy : 0.005738973617553711 nb_pixel_total : 139 time to create 1 rle with old method : 0.0001819133758544922 time for calcul the mask position with numpy : 0.0056149959564208984 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004153251647949219 time for calcul the mask position with numpy : 0.005630016326904297 nb_pixel_total : 225 time to create 1 rle with old method : 0.00025963783264160156 time for calcul the mask position with numpy : 0.005965471267700195 nb_pixel_total : 2087 time to create 1 rle with old method : 0.0022754669189453125 time for calcul the mask position with numpy : 0.00602412223815918 nb_pixel_total : 961 time to create 1 rle with old method : 0.0011353492736816406 time for calcul the mask position with numpy : 0.005913734436035156 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003638267517089844 time for calcul the mask position with numpy : 0.0058002471923828125 nb_pixel_total : 84 time to create 1 rle with old method : 0.00011944770812988281 time for calcul the mask position with numpy : 0.006455659866333008 nb_pixel_total : 766 time to create 1 rle with old method : 0.0012979507446289062 time for calcul the mask position with numpy : 0.007520437240600586 nb_pixel_total : 106172 time to create 1 rle with old method : 0.12064647674560547 time for calcul the mask position with numpy : 0.007092475891113281 nb_pixel_total : 809 time to create 1 rle with old method : 0.0009353160858154297 time for calcul the mask position with numpy : 0.006808757781982422 nb_pixel_total : 85 time to create 1 rle with old method : 0.00012493133544921875 time for calcul the mask position with numpy : 0.006888389587402344 nb_pixel_total : 1569 time to create 1 rle with old method : 0.001659393310546875 time for calcul the mask position with numpy : 0.007677793502807617 nb_pixel_total : 3455 time to create 1 rle with old method : 0.0039048194885253906 time for calcul the mask position with numpy : 0.007109880447387695 nb_pixel_total : 164 time to create 1 rle with old method : 0.0002295970916748047 time for calcul the mask position with numpy : 0.006946563720703125 nb_pixel_total : 119 time to create 1 rle with old method : 0.00019788742065429688 time for calcul the mask position with numpy : 0.00695490837097168 nb_pixel_total : 495 time to create 1 rle with old method : 0.0006005764007568359 time for calcul the mask position with numpy : 0.006861209869384766 nb_pixel_total : 799 time to create 1 rle with old method : 0.0010821819305419922 time for calcul the mask position with numpy : 0.007111310958862305 nb_pixel_total : 37456 time to create 1 rle with old method : 0.0385594367980957 time for calcul the mask position with numpy : 0.006793022155761719 nb_pixel_total : 217 time to create 1 rle with old method : 0.00029587745666503906 time for calcul the mask position with numpy : 0.011518478393554688 nb_pixel_total : 397 time to create 1 rle with old method : 0.0004634857177734375 time for calcul the mask position with numpy : 0.009473800659179688 nb_pixel_total : 260 time to create 1 rle with old method : 0.00033736228942871094 time for calcul the mask position with numpy : 0.010065317153930664 nb_pixel_total : 156 time to create 1 rle with old method : 0.000209808349609375 time for calcul the mask position with numpy : 0.010113000869750977 nb_pixel_total : 383 time to create 1 rle with old method : 0.00047659873962402344 time for calcul the mask position with numpy : 0.01002955436706543 nb_pixel_total : 245 time to create 1 rle with old method : 0.00030875205993652344 time for calcul the mask position with numpy : 0.01020050048828125 nb_pixel_total : 292 time to create 1 rle with old method : 0.0003693103790283203 time for calcul the mask position with numpy : 0.010163068771362305 nb_pixel_total : 29 time to create 1 rle with old method : 7.319450378417969e-05 time for calcul the mask position with numpy : 0.01013946533203125 nb_pixel_total : 215 time to create 1 rle with old method : 0.00027942657470703125 time for calcul the mask position with numpy : 0.010418176651000977 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003681182861328125 time for calcul the mask position with numpy : 0.006959438323974609 nb_pixel_total : 341 time to create 1 rle with old method : 0.0004291534423828125 time for calcul the mask position with numpy : 0.006965160369873047 nb_pixel_total : 145 time to create 1 rle with old method : 0.00018167495727539062 time for calcul the mask position with numpy : 0.006493091583251953 nb_pixel_total : 287 time to create 1 rle with old method : 0.0003228187561035156 time for calcul the mask position with numpy : 0.0057773590087890625 nb_pixel_total : 742 time to create 1 rle with old method : 0.0008220672607421875 time for calcul the mask position with numpy : 0.005795955657958984 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003025531768798828 time for calcul the mask position with numpy : 0.006662130355834961 nb_pixel_total : 2593 time to create 1 rle with old method : 0.0028095245361328125 time for calcul the mask position with numpy : 0.006007671356201172 nb_pixel_total : 184 time to create 1 rle with old method : 0.00020956993103027344 time for calcul the mask position with numpy : 0.005846977233886719 nb_pixel_total : 70 time to create 1 rle with old method : 0.00010633468627929688 time for calcul the mask position with numpy : 0.006672382354736328 nb_pixel_total : 115 time to create 1 rle with old method : 0.0003333091735839844 time for calcul the mask position with numpy : 0.006822347640991211 nb_pixel_total : 668 time to create 1 rle with old method : 0.0007736682891845703 time for calcul the mask position with numpy : 0.006625175476074219 nb_pixel_total : 228 time to create 1 rle with old method : 0.00041961669921875 time for calcul the mask position with numpy : 0.006420135498046875 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003676414489746094 time for calcul the mask position with numpy : 0.006455898284912109 nb_pixel_total : 221 time to create 1 rle with old method : 0.00038504600524902344 time for calcul the mask position with numpy : 0.00641322135925293 nb_pixel_total : 11 time to create 1 rle with old method : 5.269050598144531e-05 time for calcul the mask position with numpy : 0.006152153015136719 nb_pixel_total : 240 time to create 1 rle with old method : 0.00029921531677246094 time for calcul the mask position with numpy : 0.00620722770690918 nb_pixel_total : 2 time to create 1 rle with old method : 3.123283386230469e-05 time for calcul the mask position with numpy : 0.0060291290283203125 nb_pixel_total : 895 time to create 1 rle with old method : 0.0010371208190917969 time for calcul the mask position with numpy : 0.006753444671630859 nb_pixel_total : 189 time to create 1 rle with old method : 0.00023794174194335938 time for calcul the mask position with numpy : 0.0060100555419921875 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002334117889404297 time for calcul the mask position with numpy : 0.006384849548339844 nb_pixel_total : 1614 time to create 1 rle with old method : 0.0018398761749267578 time for calcul the mask position with numpy : 0.006123542785644531 nb_pixel_total : 143 time to create 1 rle with old method : 0.00019168853759765625 time for calcul the mask position with numpy : 0.0069997310638427734 nb_pixel_total : 322 time to create 1 rle with old method : 0.00037860870361328125 time for calcul the mask position with numpy : 0.006151437759399414 nb_pixel_total : 318 time to create 1 rle with old method : 0.0003821849822998047 time for calcul the mask position with numpy : 0.0064585208892822266 nb_pixel_total : 301 time to create 1 rle with old method : 0.00047206878662109375 time for calcul the mask position with numpy : 0.006361722946166992 nb_pixel_total : 929 time to create 1 rle with old method : 0.0010504722595214844 time for calcul the mask position with numpy : 0.006292581558227539 nb_pixel_total : 355 time to create 1 rle with old method : 0.0004379749298095703 time for calcul the mask position with numpy : 0.006100177764892578 nb_pixel_total : 265 time to create 1 rle with old method : 0.0003197193145751953 time for calcul the mask position with numpy : 0.0063016414642333984 nb_pixel_total : 730 time to create 1 rle with old method : 0.0008387565612792969 time for calcul the mask position with numpy : 0.006090879440307617 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004341602325439453 time for calcul the mask position with numpy : 0.006062507629394531 nb_pixel_total : 1861 time to create 1 rle with old method : 0.002098560333251953 time for calcul the mask position with numpy : 0.006070137023925781 nb_pixel_total : 174 time to create 1 rle with old method : 0.000213623046875 time for calcul the mask position with numpy : 0.0062410831451416016 nb_pixel_total : 216 time to create 1 rle with old method : 0.00028228759765625 time for calcul the mask position with numpy : 0.0060274600982666016 nb_pixel_total : 58 time to create 1 rle with old method : 8.988380432128906e-05 time for calcul the mask position with numpy : 0.006150245666503906 nb_pixel_total : 1105 time to create 1 rle with old method : 0.0012819766998291016 time for calcul the mask position with numpy : 0.006249666213989258 nb_pixel_total : 609 time to create 1 rle with old method : 0.0007245540618896484 time for calcul the mask position with numpy : 0.007337808609008789 nb_pixel_total : 90 time to create 1 rle with old method : 0.00014591217041015625 time for calcul the mask position with numpy : 0.007258892059326172 nb_pixel_total : 834 time to create 1 rle with old method : 0.000978708267211914 time for calcul the mask position with numpy : 0.0073435306549072266 nb_pixel_total : 881 time to create 1 rle with old method : 0.0010328292846679688 time for calcul the mask position with numpy : 0.007230997085571289 nb_pixel_total : 27 time to create 1 rle with old method : 8.988380432128906e-05 time for calcul the mask position with numpy : 0.007249593734741211 nb_pixel_total : 1484 time to create 1 rle with old method : 0.001760244369506836 time for calcul the mask position with numpy : 0.0072672367095947266 nb_pixel_total : 79 time to create 1 rle with old method : 0.0001456737518310547 time for calcul the mask position with numpy : 0.0076029300689697266 nb_pixel_total : 80 time to create 1 rle with old method : 0.00020766258239746094 time for calcul the mask position with numpy : 0.007246494293212891 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006802082061767578 time for calcul the mask position with numpy : 0.007241487503051758 nb_pixel_total : 187 time to create 1 rle with old method : 0.00024700164794921875 time for calcul the mask position with numpy : 0.0062906742095947266 nb_pixel_total : 313 time to create 1 rle with old method : 0.0003921985626220703 time for calcul the mask position with numpy : 0.0061817169189453125 nb_pixel_total : 44 time to create 1 rle with old method : 0.00011539459228515625 time for calcul the mask position with numpy : 0.006231069564819336 nb_pixel_total : 1130 time to create 1 rle with old method : 0.0014009475708007812 time for calcul the mask position with numpy : 0.006192207336425781 nb_pixel_total : 1 time to create 1 rle with old method : 2.2411346435546875e-05 create new chi : 1.515387773513794 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 : 0.0016865730285644531 batch 1 Loaded 150 chid ids of type : 4230 Number RLEs to save : 13616 TO DO : save crop sub photo not yet done ! save time : 0.7894914150238037 map_output_result : {1333764179: (0.0, 'Should be the crop_list due to order', 0.0), 1333764086: (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 [1333764179, 1333764086] Looping around the photos to save general results len do output : 2 /1333764179.Didn't retrieve data . /1333764086.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, '2537953') ('4234', '20144254', '1333764179', None, None, None, None, None, '2537953') ('4234', None, None, None, None, None, None, None, '2537953') ('4234', '20144254', '1333764086', None, None, None, None, None, '2537953') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.01420450210571289 save_final save missing photos in datou_result : time spend for datou_step_exec : 9.330261945724487 time spend to save output : 0.014398574829101562 total time spend for step 4 : 9.344660520553589 step5:crop_condition Sat Feb 1 19:21:07 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 2 ! batch 1 Loaded 318 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 142 About to insert : list_path_to_insert length 142 new photo from crops ! About to upload 142 photos upload in portfolio : 4869462 init cache_photo without model_param we have 142 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738434069_1296127 we have uploaded 142 photos in the portfolio 4869462 time of upload the photos Elapsed time : 29.59893774986267 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 29 About to insert : list_path_to_insert length 29 new photo from crops ! About to upload 29 photos upload in portfolio : 4869462 init cache_photo without model_param we have 29 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738434100_1296127 we have uploaded 29 photos in the portfolio 4869462 time of upload the photos Elapsed time : 6.73569393157959 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/1738434106_1296127 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.5381283760070801 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 12 About to insert : list_path_to_insert length 12 new photo from crops ! About to upload 12 photos upload in portfolio : 4869462 init cache_photo without model_param we have 12 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738434107_1296127 we have uploaded 12 photos in the portfolio 4869462 time of upload the photos Elapsed time : 2.349781036376953 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 ! map_result returned by crop_photo_return_map_crop : length : 31 About to insert : list_path_to_insert length 31 new photo from crops ! About to upload 31 photos upload in portfolio : 4869462 init cache_photo without model_param we have 31 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738434110_1296127 we have uploaded 31 photos in the portfolio 4869462 time of upload the photos Elapsed time : 7.630777835845947 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1333764179, 1333764086] Looping around the photos to save general results len do output : 215 /1333767431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767460Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767474Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767494Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1333767655Didn'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, '2537953') ('4234', '20144254', '1333764179', None, None, None, None, None, '2537953') ('4234', None, None, None, None, None, None, None, '2537953') ('4234', '20144254', '1333764086', None, None, None, None, None, '2537953') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 647 time used for this insertion : 0.6168577671051025 save_final save missing photos in datou_result : time spend for datou_step_exec : 50.60580015182495 time spend to save output : 0.6231644153594971 total time spend for step 5 : 51.22896456718445 step6:thcl Sat Feb 1 19:21:58 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 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 : 0.010181188583374023 time to convert the images to numpy array : 0.06640768051147461 time to import caffe and check if the image exist : 0.02716541290283203 time to convert the images to numpy array : 0.053029775619506836 time to import caffe and check if the image exist : 0.015401124954223633 time to convert the images to numpy array : 0.06942152976989746 time to import caffe and check if the image exist : 0.014611482620239258 time to convert the images to numpy array : 0.0732271671295166 time to import caffe and check if the image exist : 0.016654014587402344 time to convert the images to numpy array : 0.07224225997924805 time to import caffe and check if the image exist : 0.02551102638244629 time to convert the images to numpy array : 0.06788516044616699 time to import caffe and check if the image exist : 0.016226768493652344 time to convert the images to numpy array : 0.07757687568664551 time to import caffe and check if the image exist : 0.021552324295043945 time to convert the images to numpy array : 0.07283234596252441 time to import caffe and check if the image exist : 0.017648935317993164 time to convert the images to numpy array : 0.07912540435791016 time to import caffe and check if the image exist : 0.026801586151123047 time to convert the images to numpy array : 0.06993556022644043 total time to convert the images to numpy array : 0.29744625091552734 list photo_ids error: [] list photo_ids correct : [1333767431, 1333767432, 1333767433, 1333767434, 1333767435, 1333767436, 1333767437, 1333767438, 1333767439, 1333767440, 1333767441, 1333767442, 1333767443, 1333767444, 1333767445, 1333767446, 1333767447, 1333767448, 1333767449, 1333767450, 1333767451, 1333767452, 1333767453, 1333767454, 1333767455, 1333767456, 1333767457, 1333767458, 1333767459, 1333767460, 1333767461, 1333767462, 1333767463, 1333767464, 1333767465, 1333767466, 1333767467, 1333767468, 1333767469, 1333767470, 1333767471, 1333767472, 1333767473, 1333767474, 1333767639, 1333767640, 1333767641, 1333767642, 1333767643, 1333767644, 1333767645, 1333767646, 1333767647, 1333767648, 1333767649, 1333767650, 1333767651, 1333767652, 1333767653, 1333767654, 1333767655, 1333767520, 1333767521, 1333767522, 1333767523, 1333767524, 1333767525, 1333767526, 1333767527, 1333767528, 1333767529, 1333767530, 1333767531, 1333767532, 1333767533, 1333767535, 1333767536, 1333767537, 1333767538, 1333767539, 1333767540, 1333767541, 1333767542, 1333767543, 1333767544, 1333767545, 1333767546, 1333767547, 1333767548, 1333767549, 1333767550, 1333767551, 1333767552, 1333767553, 1333767554, 1333767555, 1333767556, 1333767557, 1333767558, 1333767559, 1333767560, 1333767561, 1333767562, 1333767563, 1333767564, 1333767475, 1333767476, 1333767477, 1333767478, 1333767479, 1333767480, 1333767481, 1333767482, 1333767483, 1333767484, 1333767485, 1333767486, 1333767487, 1333767488, 1333767489, 1333767490, 1333767491, 1333767492, 1333767493, 1333767494, 1333767495, 1333767496, 1333767615, 1333767616, 1333767617, 1333767618, 1333767619, 1333767620, 1333767621, 1333767622, 1333767624, 1333767625, 1333767626, 1333767627, 1333767629, 1333767630, 1333767631, 1333767632, 1333767633, 1333767634, 1333767635, 1333767636, 1333767637, 1333767638, 1333767591, 1333767592, 1333767593, 1333767594, 1333767595, 1333767596, 1333767597, 1333767598, 1333767599, 1333767600, 1333767601, 1333767602, 1333767603, 1333767604, 1333767605, 1333767606, 1333767607, 1333767610, 1333767611, 1333767612, 1333767613, 1333767614, 1333767565, 1333767566, 1333767567, 1333767568, 1333767569, 1333767570, 1333767571, 1333767572, 1333767573, 1333767574, 1333767579, 1333767580, 1333767581, 1333767582, 1333767583, 1333767584, 1333767585, 1333767586, 1333767587, 1333767588, 1333767589, 1333767590, 1333767497, 1333767498, 1333767499, 1333767500, 1333767501, 1333767502, 1333767503, 1333767504, 1333767505, 1333767506, 1333767507, 1333767508, 1333767509, 1333767510, 1333767511, 1333767512, 1333767513, 1333767514, 1333767516, 1333767517, 1333767518, 1333767519] number of photos to traite : 215 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 : 10998 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 F0201 19:22:04.310925 1296127 math_functions.cu:79] Check failed: error == cudaSuccess (715 vs. 0) an illegal instruction was encountered *** Check failure stack trace: *** Command terminated by signal 6 31.98user 24.34system 1:39.38elapsed 56%CPU (0avgtext+0avgdata 2929244maxresident)k 689864inputs+8576outputs (8major+2409528minor)pagefaults 0swaps