python /home/admin/mtr/script_for_cron.py -j default -m 20 -a 'python3 ~/workarea/git/Velours/python/prod/datou.py -j batch_current -C 2529344' -s traitement_4234 -M 0 -S 0 -U 100,80,95 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/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', '/home/admin/workarea/git/apy', '/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 : 2950268 load datou : 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) 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 : step 0 init_dummy_multi_datou is not linked in the step_by_step architecture ! WARNING : step 1294 init_dummy_multi_datou is not linked in the step_by_step architecture ! 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 ! 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 : (photo_id, hashtag_id, score_max) was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? load thcls load pdts 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 : ['2529344'] with mtr_portfolio_ids : ['20068969'] and first list_photo_ids : [] new path : /proc/2950268/ 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 over limit max, limiting to limit_max 21 list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 1 ; length of list_pids : 1 ; length of list_args : 1 time to download the photos : 0.18355846405029297 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Wed Feb 12 10:48:02 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 : 10332 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-12 10:48:06.187274: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-12 10:48:06.219217: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-12 10:48:06.221141: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f0344000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-12 10:48:06.221176: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-12 10:48:06.225065: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-12 10:48:06.474370: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x287adbb0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-12 10:48:06.474424: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-12 10:48:06.478208: 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 2025-02-12 10:48:06.479699: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 10:48:06.482828: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 10:48:06.485151: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 10:48:06.485778: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 10:48:06.490115: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 10:48:06.492060: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 10:48:06.501595: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 10:48:06.504282: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 10:48:06.504389: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 10:48:06.505206: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-12 10:48:06.505222: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-12 10:48:06.505231: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-12 10:48:06.506662: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9570 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. 2025-02-12 10:48:06.823846: 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 2025-02-12 10:48:06.823983: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 10:48:06.824013: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 10:48:06.824037: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 10:48:06.824077: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 10:48:06.824100: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 10:48:06.824124: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 10:48:06.824150: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 10:48:06.825812: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 10:48:06.827576: 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 2025-02-12 10:48:06.827661: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 10:48:06.827691: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 10:48:06.827716: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 10:48:06.827739: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 10:48:06.827764: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 10:48:06.827787: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 10:48:06.827810: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 10:48:06.829464: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 10:48:06.829557: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-12 10:48:06.829570: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-12 10:48:06.829582: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-12 10:48:06.831539: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9570 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 : [] 2025-02-12 10:48:16.120267: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 10:48:16.313499: 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 : 1 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.59453 max: 148.45156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 32 time to create 1 rle with old method : 0.00015163421630859375 length of segment : 10 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0006463527679443359 length of segment : 31 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0005497932434082031 length of segment : 36 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.0003540515899658203 length of segment : 31 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00023794174194335938 length of segment : 22 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.0003306865692138672 length of segment : 28 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00032782554626464844 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: -119.03984 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004849433898925781 length of segment : 30 time for calcul the mask position with numpy : 0.00015282630920410156 nb_pixel_total : 3485 time to create 1 rle with old method : 0.0047075748443603516 length of segment : 115 time for calcul the mask position with numpy : 0.00014352798461914062 nb_pixel_total : 2571 time to create 1 rle with old method : 0.0034668445587158203 length of segment : 84 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 24 time to create 1 rle with old method : 7.414817810058594e-05 length of segment : 6 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 817 time to create 1 rle with old method : 0.0012009143829345703 length of segment : 50 time for calcul the mask position with numpy : 0.0001251697540283203 nb_pixel_total : 3155 time to create 1 rle with old method : 0.0040361881256103516 length of segment : 115 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.00013184547424316406 length of segment : 16 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1541 time to create 1 rle with old method : 0.002062559127807617 length of segment : 68 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00042510032653808594 length of segment : 46 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 16 time to create 1 rle with old method : 6.341934204101562e-05 length of segment : 3 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0013933181762695312 length of segment : 44 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 2001 time to create 1 rle with old method : 0.002664327621459961 length of segment : 65 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.00122833251953125 length of segment : 39 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.51250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00011491775512695312 nb_pixel_total : 3155 time to create 1 rle with old method : 0.006100654602050781 length of segment : 103 time for calcul the mask position with numpy : 0.00012826919555664062 nb_pixel_total : 1835 time to create 1 rle with old method : 0.004424095153808594 length of segment : 44 time for calcul the mask position with numpy : 0.00013685226440429688 nb_pixel_total : 1757 time to create 1 rle with old method : 0.0037283897399902344 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.99688 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.0002262592315673828 nb_pixel_total : 11199 time to create 1 rle with old method : 0.021399736404418945 length of segment : 89 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0005047321319580078 length of segment : 17 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00027942657470703125 length of segment : 14 time for calcul the mask position with numpy : 0.0002410411834716797 nb_pixel_total : 5544 time to create 1 rle with old method : 0.010444164276123047 length of segment : 136 time for calcul the mask position with numpy : 0.000194549560546875 nb_pixel_total : 5310 time to create 1 rle with old method : 0.00958871841430664 length of segment : 126 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.64687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0004181861877441406 length of segment : 16 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.00026607513427734375 length of segment : 11 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.0013604164123535156 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 26.00000 max: 237.00000 molded_images shape: (1, 640, 640, 3) min: -79.01250 max: 108.25078 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: -113.57891 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 : 6.413459777832031e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00039958953857421875 length of segment : 25 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0005481243133544922 length of segment : 15 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1178 time to create 1 rle with old method : 0.0018191337585449219 length of segment : 50 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00017571449279785156 length of segment : 11 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0005714893341064453 length of segment : 15 time for calcul the mask position with numpy : 0.0001227855682373047 nb_pixel_total : 3212 time to create 1 rle with old method : 0.005147695541381836 length of segment : 56 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.00017380714416503906 length of segment : 9 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00027298927307128906 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: -121.21172 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 : 6.4849853515625e-05 nb_pixel_total : 882 time to create 1 rle with old method : 0.0014543533325195312 length of segment : 39 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0007023811340332031 length of segment : 18 time for calcul the mask position with numpy : 0.00019288063049316406 nb_pixel_total : 11652 time to create 1 rle with old method : 0.014100313186645508 length of segment : 97 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0016312599182128906 length of segment : 28 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0009462833404541016 length of segment : 21 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 568 time to create 1 rle with old method : 0.0012111663818359375 length of segment : 26 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1137 time to create 1 rle with old method : 0.0018208026885986328 length of segment : 38 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0010383129119873047 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.25078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0009434223175048828 length of segment : 47 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.0001652240753173828 length of segment : 11 time for calcul the mask position with numpy : 0.0002124309539794922 nb_pixel_total : 10625 time to create 1 rle with old method : 0.01299142837524414 length of segment : 183 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.0006134510040283203 length of segment : 25 time for calcul the mask position with numpy : 0.00017547607421875 nb_pixel_total : 508 time to create 1 rle with old method : 0.0012416839599609375 length of segment : 35 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 886 time to create 1 rle with old method : 0.0013620853424072266 length of segment : 29 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 738 time to create 1 rle with old method : 0.0009613037109375 length of segment : 36 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 730 time to create 1 rle with old method : 0.0010564327239990234 length of segment : 74 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 2594 time to create 1 rle with old method : 0.0034208297729492188 length of segment : 82 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0009036064147949219 length of segment : 104 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 862 time to create 1 rle with old method : 0.0016820430755615234 length of segment : 26 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.18594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1469 time to create 1 rle with old method : 0.001873016357421875 length of segment : 63 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 871 time to create 1 rle with old method : 0.0011768341064453125 length of segment : 47 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0007157325744628906 length of segment : 39 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007481575012207031 length of segment : 54 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0006883144378662109 length of segment : 27 time for calcul the mask position with numpy : 0.00016951560974121094 nb_pixel_total : 2652 time to create 1 rle with old method : 0.003245115280151367 length of segment : 183 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1137 time to create 1 rle with old method : 0.0014312267303466797 length of segment : 71 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0004839897155761719 length of segment : 36 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.00047206878662109375 length of segment : 70 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1681 time to create 1 rle with old method : 0.0020864009857177734 length of segment : 81 Processing 1 images image shape: (280, 400, 3) min: 20.00000 max: 213.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 88.21328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009779930114746094 nb_pixel_total : 106494 time to create 1 rle with old method : 0.14023780822753906 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0007648468017578125 length of segment : 24 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00038123130798339844 length of segment : 16 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0005280971527099609 length of segment : 30 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1606 time to create 1 rle with old method : 0.0021190643310546875 length of segment : 41 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.0001761913299560547 length of segment : 12 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0006768703460693359 length of segment : 41 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 4867 time to create 1 rle with old method : 0.006011247634887695 length of segment : 81 time for calcul the mask position with numpy : 0.0001163482666015625 nb_pixel_total : 4886 time to create 1 rle with old method : 0.005826473236083984 length of segment : 126 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1303 time to create 1 rle with old method : 0.0016472339630126953 length of segment : 54 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005037784576416016 length of segment : 28 time for calcul the mask position with numpy : 0.00014400482177734375 nb_pixel_total : 4676 time to create 1 rle with old method : 0.005577564239501953 length of segment : 140 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1580 time to create 1 rle with old method : 0.001960277557373047 length of segment : 54 time for calcul the mask position with numpy : 0.00013446807861328125 nb_pixel_total : 3263 time to create 1 rle with old method : 0.0041561126708984375 length of segment : 133 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1507 time to create 1 rle with old method : 0.002034425735473633 length of segment : 53 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 : 36 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00042819976806640625 length of segment : 16 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0011343955993652344 length of segment : 51 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00031065940856933594 length of segment : 20 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.0010654926300048828 length of segment : 39 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 3527 time to create 1 rle with old method : 0.004358053207397461 length of segment : 78 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005323886871337891 length of segment : 31 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 914 time to create 1 rle with old method : 0.0012433528900146484 length of segment : 39 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00018644332885742188 length of segment : 17 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002391338348388672 length of segment : 18 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005660057067871094 length of segment : 29 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.00024366378784179688 length of segment : 15 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1485 time to create 1 rle with old method : 0.001918792724609375 length of segment : 62 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.00037407875061035156 length of segment : 16 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1790 time to create 1 rle with old method : 0.0021822452545166016 length of segment : 80 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.00044608116149902344 length of segment : 31 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002474784851074219 length of segment : 12 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002562999725341797 length of segment : 18 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004372596740722656 length of segment : 31 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005772113800048828 length of segment : 24 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 673 time to create 1 rle with old method : 0.0008685588836669922 length of segment : 35 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0007758140563964844 length of segment : 44 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1898 time to create 1 rle with old method : 0.0024566650390625 length of segment : 61 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00039577484130859375 length of segment : 22 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1302 time to create 1 rle with old method : 0.0016956329345703125 length of segment : 45 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003821849822998047 length of segment : 17 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0005810260772705078 length of segment : 19 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1877 time to create 1 rle with old method : 0.002357006072998047 length of segment : 61 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1236 time to create 1 rle with old method : 0.001592397689819336 length of segment : 51 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1007 time to create 1 rle with old method : 0.0013325214385986328 length of segment : 81 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 2025 time to create 1 rle with old method : 0.0024788379669189453 length of segment : 82 time for calcul the mask position with numpy : 0.00010967254638671875 nb_pixel_total : 3373 time to create 1 rle with old method : 0.004044055938720703 length of segment : 79 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 3115 time to create 1 rle with old method : 0.003854513168334961 length of segment : 83 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1965 time to create 1 rle with old method : 0.00240325927734375 length of segment : 61 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002562999725341797 length of segment : 14 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 847 time to create 1 rle with old method : 0.0012054443359375 length of segment : 37 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002295970916748047 length of segment : 14 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0016813278198242188 length of segment : 42 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0004677772521972656 length of segment : 31 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003943443298339844 length of segment : 19 time for calcul the mask position with numpy : 0.00021338462829589844 nb_pixel_total : 9790 time to create 1 rle with old method : 0.01846027374267578 length of segment : 111 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.0007176399230957031 length of segment : 25 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0006856918334960938 length of segment : 33 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.00013303756713867188 length of segment : 20 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 823 time to create 1 rle with old method : 0.0011129379272460938 length of segment : 58 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0006265640258789062 length of segment : 24 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.00026226043701171875 length of segment : 22 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002989768981933594 length of segment : 21 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.00036525726318359375 length of segment : 35 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00024080276489257812 length of segment : 16 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 855 time to create 1 rle with old method : 0.0011365413665771484 length of segment : 55 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 2062 time to create 1 rle with old method : 0.0026023387908935547 length of segment : 67 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0008766651153564453 length of segment : 17 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.0003559589385986328 length of segment : 30 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.00027441978454589844 length of segment : 8 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0005285739898681641 length of segment : 28 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 3350 time to create 1 rle with old method : 0.005128622055053711 length of segment : 116 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00017571449279785156 length of segment : 11 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004010200500488281 length of segment : 36 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0007145404815673828 length of segment : 32 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: 129.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0007257461547851562 length of segment : 53 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.0008134841918945312 length of segment : 51 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002875328063964844 length of segment : 12 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.0001361370086669922 length of segment : 9 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.000911712646484375 length of segment : 37 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.00016689300537109375 length of segment : 9 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 26 time to create 1 rle with old method : 7.796287536621094e-05 length of segment : 7 Detection mask done ! Trying to reset tf kernel 2950619 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5043 tf kernel not reseted sub process len(results) : 149 len(list_Values) 149 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 149 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 : 10332 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 149 chid ids of type : 4228 Number RLEs to save : 6890 save missing photos in datou_result : time spend for datou_step_exec : 22.661420822143555 time spend to save output : 1.0817461013793945 total time spend for step 1 : 23.74316692352295 step2:brightness Wed Feb 12 10:48:26 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/1739353682_2950268_1332932991_7395647e4f4c8caeb6614d483b219216.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 : 1 time used for this insertion : 0.11337423324584961 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.1460099220275879 save missing photos in datou_result : time spend for datou_step_exec : 0.5352883338928223 time spend to save output : 0.26399827003479004 total time spend for step 2 : 0.7992866039276123 step3:blur_detection Wed Feb 12 10:48:27 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/1739353682_2950268_1332932991_7395647e4f4c8caeb6614d483b219216.jpg resize: (1080, 1920) 1332932991 -8.086102535375112 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 : 1 time used for this insertion : 0.29271483421325684 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.010997772216796875 save missing photos in datou_result : time spend for datou_step_exec : 1.0813710689544678 time spend to save output : 0.3079705238342285 total time spend for step 3 : 1.3893415927886963 step4:rle_unique_nms_with_priority Wed Feb 12 10:48:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 149 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 148 nb_hashtags : 7 time to prepare the origin masks : 1.1364386081695557 time for calcul the mask position with numpy : 0.07321476936340332 nb_pixel_total : 1810329 time to create 1 rle with new method : 0.3645768165588379 time for calcul the mask position with numpy : 0.008882999420166016 nb_pixel_total : 2001 time to create 1 rle with old method : 0.002418994903564453 time for calcul the mask position with numpy : 0.008667707443237305 nb_pixel_total : 3485 time to create 1 rle with old method : 0.004025936126708984 time for calcul the mask position with numpy : 0.008649826049804688 nb_pixel_total : 26 time to create 1 rle with old method : 0.00011610984802246094 time for calcul the mask position with numpy : 0.008592367172241211 nb_pixel_total : 2571 time to create 1 rle with old method : 0.002826690673828125 time for calcul the mask position with numpy : 0.008821487426757812 nb_pixel_total : 271 time to create 1 rle with old method : 0.0003292560577392578 time for calcul the mask position with numpy : 0.009238243103027344 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004286766052246094 time for calcul the mask position with numpy : 0.008501291275024414 nb_pixel_total : 32 time to create 1 rle with old method : 6.341934204101562e-05 time for calcul the mask position with numpy : 0.008826732635498047 nb_pixel_total : 64 time to create 1 rle with old method : 8.702278137207031e-05 time for calcul the mask position with numpy : 0.008514642715454102 nb_pixel_total : 76 time to create 1 rle with old method : 0.00020265579223632812 time for calcul the mask position with numpy : 0.008462190628051758 nb_pixel_total : 332 time to create 1 rle with old method : 0.0003821849822998047 time for calcul the mask position with numpy : 0.008463859558105469 nb_pixel_total : 170 time to create 1 rle with old method : 0.00032711029052734375 time for calcul the mask position with numpy : 0.008673667907714844 nb_pixel_total : 35 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.008869171142578125 nb_pixel_total : 290 time to create 1 rle with old method : 0.0003650188446044922 time for calcul the mask position with numpy : 0.008539438247680664 nb_pixel_total : 16 time to create 1 rle with old method : 3.361701965332031e-05 time for calcul the mask position with numpy : 0.008669376373291016 nb_pixel_total : 17 time to create 1 rle with old method : 7.987022399902344e-05 time for calcul the mask position with numpy : 0.008849620819091797 nb_pixel_total : 24 time to create 1 rle with old method : 4.5299530029296875e-05 time for calcul the mask position with numpy : 0.008421897888183594 nb_pixel_total : 1541 time to create 1 rle with old method : 0.0018072128295898438 time for calcul the mask position with numpy : 0.008578777313232422 nb_pixel_total : 3155 time to create 1 rle with old method : 0.0034623146057128906 time for calcul the mask position with numpy : 0.008409500122070312 nb_pixel_total : 817 time to create 1 rle with old method : 0.0009474754333496094 time for calcul the mask position with numpy : 0.008948326110839844 nb_pixel_total : 5544 time to create 1 rle with old method : 0.0060727596282958984 time for calcul the mask position with numpy : 0.008469343185424805 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004341602325439453 time for calcul the mask position with numpy : 0.008623838424682617 nb_pixel_total : 216 time to create 1 rle with old method : 0.0002651214599609375 time for calcul the mask position with numpy : 0.008578300476074219 nb_pixel_total : 1835 time to create 1 rle with old method : 0.0022792816162109375 time for calcul the mask position with numpy : 0.008865594863891602 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0011749267578125 time for calcul the mask position with numpy : 0.008594989776611328 nb_pixel_total : 1757 time to create 1 rle with old method : 0.0020787715911865234 time for calcul the mask position with numpy : 0.008564472198486328 nb_pixel_total : 11199 time to create 1 rle with old method : 0.012612104415893555 time for calcul the mask position with numpy : 0.00845646858215332 nb_pixel_total : 118 time to create 1 rle with old method : 0.0001556873321533203 time for calcul the mask position with numpy : 0.009287595748901367 nb_pixel_total : 781 time to create 1 rle with old method : 0.0014069080352783203 time for calcul the mask position with numpy : 0.008547782897949219 nb_pixel_total : 116 time to create 1 rle with old method : 0.00014734268188476562 time for calcul the mask position with numpy : 0.008405447006225586 nb_pixel_total : 222 time to create 1 rle with old method : 0.00025463104248046875 time for calcul the mask position with numpy : 0.008374214172363281 nb_pixel_total : 1137 time to create 1 rle with old method : 0.001367807388305664 time for calcul the mask position with numpy : 0.008379697799682617 nb_pixel_total : 508 time to create 1 rle with old method : 0.0006885528564453125 time for calcul the mask position with numpy : 0.008432388305664062 nb_pixel_total : 77 time to create 1 rle with old method : 0.00010251998901367188 time for calcul the mask position with numpy : 0.008411884307861328 nb_pixel_total : 297 time to create 1 rle with old method : 0.0003769397735595703 time for calcul the mask position with numpy : 0.008360624313354492 nb_pixel_total : 10625 time to create 1 rle with old method : 0.01201939582824707 time for calcul the mask position with numpy : 0.008415699005126953 nb_pixel_total : 738 time to create 1 rle with old method : 0.0008630752563476562 time for calcul the mask position with numpy : 0.008962154388427734 nb_pixel_total : 243 time to create 1 rle with old method : 0.00029754638671875 time for calcul the mask position with numpy : 0.008476734161376953 nb_pixel_total : 130 time to create 1 rle with old method : 0.00018525123596191406 time for calcul the mask position with numpy : 0.008486747741699219 nb_pixel_total : 871 time to create 1 rle with old method : 0.0010492801666259766 time for calcul the mask position with numpy : 0.008430719375610352 nb_pixel_total : 730 time to create 1 rle with old method : 0.0008137226104736328 time for calcul the mask position with numpy : 0.008422136306762695 nb_pixel_total : 36 time to create 1 rle with old method : 6.341934204101562e-05 time for calcul the mask position with numpy : 0.008624076843261719 nb_pixel_total : 11652 time to create 1 rle with old method : 0.013602256774902344 time for calcul the mask position with numpy : 0.008758783340454102 nb_pixel_total : 501 time to create 1 rle with old method : 0.0009481906890869141 time for calcul the mask position with numpy : 0.009076356887817383 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005598068237304688 time for calcul the mask position with numpy : 0.008647918701171875 nb_pixel_total : 2652 time to create 1 rle with old method : 0.0035331249237060547 time for calcul the mask position with numpy : 0.00974893569946289 nb_pixel_total : 540 time to create 1 rle with old method : 0.00092315673828125 time for calcul the mask position with numpy : 0.00973653793334961 nb_pixel_total : 1178 time to create 1 rle with old method : 0.0019986629486083984 time for calcul the mask position with numpy : 0.009809017181396484 nb_pixel_total : 92 time to create 1 rle with old method : 0.0001800060272216797 time for calcul the mask position with numpy : 0.009782552719116211 nb_pixel_total : 3212 time to create 1 rle with old method : 0.005198240280151367 time for calcul the mask position with numpy : 0.009757518768310547 nb_pixel_total : 248 time to create 1 rle with old method : 0.00044465065002441406 time for calcul the mask position with numpy : 0.00978708267211914 nb_pixel_total : 1469 time to create 1 rle with old method : 0.0024094581604003906 time for calcul the mask position with numpy : 0.00952768325805664 nb_pixel_total : 1481 time to create 1 rle with old method : 0.0017483234405517578 time for calcul the mask position with numpy : 0.008534908294677734 nb_pixel_total : 120 time to create 1 rle with old method : 0.00022864341735839844 time for calcul the mask position with numpy : 0.008462667465209961 nb_pixel_total : 568 time to create 1 rle with old method : 0.0006611347198486328 time for calcul the mask position with numpy : 0.008708953857421875 nb_pixel_total : 46 time to create 1 rle with old method : 0.00011658668518066406 time for calcul the mask position with numpy : 0.008459806442260742 nb_pixel_total : 111 time to create 1 rle with old method : 0.00019240379333496094 time for calcul the mask position with numpy : 0.008399486541748047 nb_pixel_total : 886 time to create 1 rle with old method : 0.0010585784912109375 time for calcul the mask position with numpy : 0.00864863395690918 nb_pixel_total : 302 time to create 1 rle with old method : 0.0003581047058105469 time for calcul the mask position with numpy : 0.008391618728637695 nb_pixel_total : 2588 time to create 1 rle with old method : 0.0030405521392822266 time for calcul the mask position with numpy : 0.008619308471679688 nb_pixel_total : 460 time to create 1 rle with old method : 0.0005404949188232422 time for calcul the mask position with numpy : 0.008491039276123047 nb_pixel_total : 407 time to create 1 rle with old method : 0.0004725456237792969 time for calcul the mask position with numpy : 0.008435249328613281 nb_pixel_total : 628 time to create 1 rle with old method : 0.0006868839263916016 time for calcul the mask position with numpy : 0.008586406707763672 nb_pixel_total : 882 time to create 1 rle with old method : 0.0010197162628173828 time for calcul the mask position with numpy : 0.008463382720947266 nb_pixel_total : 74 time to create 1 rle with old method : 9.560585021972656e-05 time for calcul the mask position with numpy : 0.008392333984375 nb_pixel_total : 373 time to create 1 rle with old method : 0.00043582916259765625 time for calcul the mask position with numpy : 0.008442878723144531 nb_pixel_total : 183 time to create 1 rle with old method : 0.00026297569274902344 time for calcul the mask position with numpy : 0.008623123168945312 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0011515617370605469 time for calcul the mask position with numpy : 0.009027719497680664 nb_pixel_total : 106494 time to create 1 rle with old method : 0.13972020149230957 time for calcul the mask position with numpy : 0.009041786193847656 nb_pixel_total : 127 time to create 1 rle with old method : 0.0001895427703857422 time for calcul the mask position with numpy : 0.008519411087036133 nb_pixel_total : 26 time to create 1 rle with old method : 5.507469177246094e-05 time for calcul the mask position with numpy : 0.008474349975585938 nb_pixel_total : 81 time to create 1 rle with old method : 0.00010585784912109375 time for calcul the mask position with numpy : 0.008417367935180664 nb_pixel_total : 1877 time to create 1 rle with old method : 0.0021059513092041016 time for calcul the mask position with numpy : 0.008522510528564453 nb_pixel_total : 76 time to create 1 rle with old method : 0.00012969970703125 time for calcul the mask position with numpy : 0.010871171951293945 nb_pixel_total : 9790 time to create 1 rle with old method : 0.011310338973999023 time for calcul the mask position with numpy : 0.008439064025878906 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003170967102050781 time for calcul the mask position with numpy : 0.008236408233642578 nb_pixel_total : 3373 time to create 1 rle with old method : 0.0037107467651367188 time for calcul the mask position with numpy : 0.00827336311340332 nb_pixel_total : 148 time to create 1 rle with old method : 0.0001823902130126953 time for calcul the mask position with numpy : 0.008151531219482422 nb_pixel_total : 288 time to create 1 rle with old method : 0.00032973289489746094 time for calcul the mask position with numpy : 0.008364677429199219 nb_pixel_total : 196 time to create 1 rle with old method : 0.00019979476928710938 time for calcul the mask position with numpy : 0.007997274398803711 nb_pixel_total : 213 time to create 1 rle with old method : 0.00024247169494628906 time for calcul the mask position with numpy : 0.008147954940795898 nb_pixel_total : 364 time to create 1 rle with old method : 0.0003845691680908203 time for calcul the mask position with numpy : 0.008336067199707031 nb_pixel_total : 647 time to create 1 rle with old method : 0.000751495361328125 time for calcul the mask position with numpy : 0.008079290390014648 nb_pixel_total : 417 time to create 1 rle with old method : 0.0004622936248779297 time for calcul the mask position with numpy : 0.009181976318359375 nb_pixel_total : 1606 time to create 1 rle with old method : 0.0017802715301513672 time for calcul the mask position with numpy : 0.008059024810791016 nb_pixel_total : 1790 time to create 1 rle with old method : 0.0020105838775634766 time for calcul the mask position with numpy : 0.008096933364868164 nb_pixel_total : 156 time to create 1 rle with old method : 0.00019431114196777344 time for calcul the mask position with numpy : 0.00830078125 nb_pixel_total : 490 time to create 1 rle with old method : 0.0005486011505126953 time for calcul the mask position with numpy : 0.008695602416992188 nb_pixel_total : 350 time to create 1 rle with old method : 0.0004296302795410156 time for calcul the mask position with numpy : 0.008348464965820312 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.00816035270690918 nb_pixel_total : 146 time to create 1 rle with old method : 0.0001919269561767578 time for calcul the mask position with numpy : 0.008346319198608398 nb_pixel_total : 11 time to create 1 rle with old method : 5.1975250244140625e-05 time for calcul the mask position with numpy : 0.00835418701171875 nb_pixel_total : 2 time to create 1 rle with old method : 1.7404556274414062e-05 time for calcul the mask position with numpy : 0.008258342742919922 nb_pixel_total : 950 time to create 1 rle with old method : 0.001108407974243164 time for calcul the mask position with numpy : 0.008273839950561523 nb_pixel_total : 240 time to create 1 rle with old method : 0.00029587745666503906 time for calcul the mask position with numpy : 0.008289098739624023 nb_pixel_total : 550 time to create 1 rle with old method : 0.0006129741668701172 time for calcul the mask position with numpy : 0.008242607116699219 nb_pixel_total : 142 time to create 1 rle with old method : 0.0001850128173828125 time for calcul the mask position with numpy : 0.008186578750610352 nb_pixel_total : 823 time to create 1 rle with old method : 0.0008916854858398438 time for calcul the mask position with numpy : 0.007968664169311523 nb_pixel_total : 397 time to create 1 rle with old method : 0.0004124641418457031 time for calcul the mask position with numpy : 0.00798654556274414 nb_pixel_total : 2 time to create 1 rle with old method : 8.296966552734375e-05 time for calcul the mask position with numpy : 0.007969856262207031 nb_pixel_total : 157 time to create 1 rle with old method : 0.00016427040100097656 time for calcul the mask position with numpy : 0.007987499237060547 nb_pixel_total : 1236 time to create 1 rle with old method : 0.0014109611511230469 time for calcul the mask position with numpy : 0.007979154586791992 nb_pixel_total : 515 time to create 1 rle with old method : 0.0005955696105957031 time for calcul the mask position with numpy : 0.008060455322265625 nb_pixel_total : 205 time to create 1 rle with old method : 0.00023412704467773438 time for calcul the mask position with numpy : 0.007943868637084961 nb_pixel_total : 284 time to create 1 rle with old method : 0.00034046173095703125 time for calcul the mask position with numpy : 0.008882284164428711 nb_pixel_total : 2025 time to create 1 rle with old method : 0.004204511642456055 time for calcul the mask position with numpy : 0.010525703430175781 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002830028533935547 time for calcul the mask position with numpy : 0.009578943252563477 nb_pixel_total : 4781 time to create 1 rle with old method : 0.005270957946777344 time for calcul the mask position with numpy : 0.008214235305786133 nb_pixel_total : 11 time to create 1 rle with old method : 5.7697296142578125e-05 time for calcul the mask position with numpy : 0.008638381958007812 nb_pixel_total : 914 time to create 1 rle with old method : 0.0011010169982910156 time for calcul the mask position with numpy : 0.008614301681518555 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002086162567138672 time for calcul the mask position with numpy : 0.008921146392822266 nb_pixel_total : 145 time to create 1 rle with old method : 0.0001842975616455078 time for calcul the mask position with numpy : 0.00841665267944336 nb_pixel_total : 1302 time to create 1 rle with old method : 0.0014998912811279297 time for calcul the mask position with numpy : 0.008090496063232422 nb_pixel_total : 1485 time to create 1 rle with old method : 0.001661062240600586 time for calcul the mask position with numpy : 0.008062601089477539 nb_pixel_total : 129 time to create 1 rle with old method : 0.00016021728515625 time for calcul the mask position with numpy : 0.0079803466796875 nb_pixel_total : 888 time to create 1 rle with old method : 0.0009677410125732422 time for calcul the mask position with numpy : 0.007930994033813477 nb_pixel_total : 3263 time to create 1 rle with old method : 0.0034742355346679688 time for calcul the mask position with numpy : 0.008061885833740234 nb_pixel_total : 3350 time to create 1 rle with old method : 0.003652811050415039 time for calcul the mask position with numpy : 0.007841348648071289 nb_pixel_total : 835 time to create 1 rle with old method : 0.0009648799896240234 time for calcul the mask position with numpy : 0.008197546005249023 nb_pixel_total : 105 time to create 1 rle with old method : 0.00011444091796875 time for calcul the mask position with numpy : 0.0077970027923583984 nb_pixel_total : 263 time to create 1 rle with old method : 0.0003020763397216797 time for calcul the mask position with numpy : 0.007796049118041992 nb_pixel_total : 622 time to create 1 rle with old method : 0.0006377696990966797 time for calcul the mask position with numpy : 0.00794529914855957 nb_pixel_total : 532 time to create 1 rle with old method : 0.0005600452423095703 time for calcul the mask position with numpy : 0.007776975631713867 nb_pixel_total : 855 time to create 1 rle with old method : 0.0009510517120361328 time for calcul the mask position with numpy : 0.007958412170410156 nb_pixel_total : 543 time to create 1 rle with old method : 0.0006089210510253906 time for calcul the mask position with numpy : 0.007816314697265625 nb_pixel_total : 72 time to create 1 rle with old method : 8.487701416015625e-05 time for calcul the mask position with numpy : 0.0077517032623291016 nb_pixel_total : 2 time to create 1 rle with old method : 1.7642974853515625e-05 time for calcul the mask position with numpy : 0.007859468460083008 nb_pixel_total : 315 time to create 1 rle with old method : 0.0003552436828613281 time for calcul the mask position with numpy : 0.008136510848999023 nb_pixel_total : 28 time to create 1 rle with old method : 4.506111145019531e-05 time for calcul the mask position with numpy : 0.007924556732177734 nb_pixel_total : 172 time to create 1 rle with old method : 0.00020837783813476562 time for calcul the mask position with numpy : 0.007957696914672852 nb_pixel_total : 251 time to create 1 rle with old method : 0.000316619873046875 time for calcul the mask position with numpy : 0.008229255676269531 nb_pixel_total : 365 time to create 1 rle with old method : 0.0004146099090576172 time for calcul the mask position with numpy : 0.008616209030151367 nb_pixel_total : 1898 time to create 1 rle with old method : 0.0029587745666503906 time for calcul the mask position with numpy : 0.010066032409667969 nb_pixel_total : 89 time to create 1 rle with old method : 0.00024890899658203125 time for calcul the mask position with numpy : 0.010468244552612305 nb_pixel_total : 525 time to create 1 rle with old method : 0.0008833408355712891 time for calcul the mask position with numpy : 0.009905099868774414 nb_pixel_total : 334 time to create 1 rle with old method : 0.00042319297790527344 time for calcul the mask position with numpy : 0.008540868759155273 nb_pixel_total : 256 time to create 1 rle with old method : 0.00034689903259277344 time for calcul the mask position with numpy : 0.008906841278076172 nb_pixel_total : 4867 time to create 1 rle with old method : 0.005411386489868164 time for calcul the mask position with numpy : 0.008761882781982422 nb_pixel_total : 3527 time to create 1 rle with old method : 0.004131793975830078 time for calcul the mask position with numpy : 0.008691072463989258 nb_pixel_total : 448 time to create 1 rle with old method : 0.0005617141723632812 time for calcul the mask position with numpy : 0.008644342422485352 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001773834228515625 time for calcul the mask position with numpy : 0.008671998977661133 nb_pixel_total : 1933 time to create 1 rle with old method : 0.002248048782348633 time for calcul the mask position with numpy : 0.008659601211547852 nb_pixel_total : 1303 time to create 1 rle with old method : 0.001556396484375 time for calcul the mask position with numpy : 0.008641719818115234 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003237724304199219 time for calcul the mask position with numpy : 0.008705377578735352 nb_pixel_total : 1580 time to create 1 rle with old method : 0.0018610954284667969 time for calcul the mask position with numpy : 0.0086212158203125 nb_pixel_total : 5 time to create 1 rle with old method : 8.96453857421875e-05 time for calcul the mask position with numpy : 0.008632183074951172 nb_pixel_total : 1007 time to create 1 rle with old method : 0.0012242794036865234 time for calcul the mask position with numpy : 0.008828401565551758 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005359649658203125 time for calcul the mask position with numpy : 0.008751392364501953 nb_pixel_total : 673 time to create 1 rle with old method : 0.0008144378662109375 create new chi : 2.0542349815368652 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 : 0.01148843765258789 batch 1 Loaded 149 chid ids of type : 4230 Number RLEs to save : 13246 TO DO : save crop sub photo not yet done ! save time : 0.9524884223937988 map_output_result : {1332932991: (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 [1332932991] Looping around the photos to save general results len do output : 1 /1332932991.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, '2529344') ('4234', None, '1332932991', None, None, None, None, None, '2529344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.012444019317626953 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.480895519256592 time spend to save output : 0.01282358169555664 total time spend for step 4 : 4.493719100952148 step5:crop_condition Wed Feb 12 10:48:33 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 : 1 ! batch 1 Loaded 149 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 ! map_result returned by crop_photo_return_map_crop : length : 63 About to insert : list_path_to_insert length 63 new photo from crops ! About to upload 63 photos upload in portfolio : 4869462 init cache_photo without model_param we have 63 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739353714_2950268 we have uploaded 63 photos in the portfolio 4869462 time of upload the photos Elapsed time : 15.480608224868774 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 ! map_result returned by crop_photo_return_map_crop : length : 14 About to insert : list_path_to_insert length 14 new photo from crops ! About to upload 14 photos upload in portfolio : 4869462 init cache_photo without model_param we have 14 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739353730_2950268 we have uploaded 14 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.951287269592285 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 20 About to insert : list_path_to_insert length 20 new photo from crops ! About to upload 20 photos upload in portfolio : 4869462 init cache_photo without model_param we have 20 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739353735_2950268 we have uploaded 20 photos in the portfolio 4869462 time of upload the photos Elapsed time : 5.82371711730957 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 ! map_result returned by crop_photo_return_map_crop : length : 20 About to insert : list_path_to_insert length 20 new photo from crops ! About to upload 20 photos upload in portfolio : 4869462 init cache_photo without model_param we have 20 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739353741_2950268 Catched exception ! Connect or reconnect ! we have uploaded 20 photos in the portfolio 4869462 time of upload the photos Elapsed time : 104.17472672462463 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 [1332932991] Looping around the photos to save general results len do output : 117 /1337062461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062474Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062494Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062578Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337062589Didn'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, '2529344') ('4234', None, '1332932991', None, None, None, None, None, '2529344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 352 time used for this insertion : 0.027181625366210938 save_final save missing photos in datou_result : time spend for datou_step_exec : 131.67224717140198 time spend to save output : 0.12827730178833008 total time spend for step 5 : 131.8005244731903 step6:thcl Wed Feb 12 10:50:45 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 : 0.005112648010253906 time to convert the images to numpy array : 0.016352415084838867 time to import caffe and check if the image exist : 0.010850906372070312 time to convert the images to numpy array : 0.027657270431518555 time to import caffe and check if the image exist : 0.0074002742767333984 time to convert the images to numpy array : 0.033025503158569336 time to import caffe and check if the image exist : 0.008165836334228516 time to convert the images to numpy array : 0.0325322151184082 time to import caffe and check if the image exist : 0.013481616973876953 time to convert the images to numpy array : 0.02877640724182129 time to import caffe and check if the image exist : 0.015834569931030273 time to convert the images to numpy array : 0.027251720428466797 time to import caffe and check if the image exist : 0.00880885124206543 time to convert the images to numpy array : 0.03525066375732422 time to import caffe and check if the image exist : 0.013887405395507812 time to convert the images to numpy array : 0.03128409385681152 time to import caffe and check if the image exist : 0.010304927825927734 time to convert the images to numpy array : 0.03514599800109863 time to import caffe and check if the image exist : 0.014248847961425781 time to convert the images to numpy array : 0.032360076904296875 total time to convert the images to numpy array : 0.3337712287902832 list photo_ids error: [] list photo_ids correct : [1337062581, 1337062582, 1337062583, 1337062584, 1337062585, 1337062586, 1337062587, 1337062588, 1337062589, 1337062473, 1337062474, 1337062475, 1337062477, 1337062478, 1337062479, 1337062480, 1337062481, 1337062482, 1337062483, 1337062484, 1337062485, 1337062461, 1337062462, 1337062463, 1337062464, 1337062465, 1337062466, 1337062467, 1337062468, 1337062469, 1337062470, 1337062471, 1337062472, 1337062522, 1337062524, 1337062525, 1337062527, 1337062528, 1337062529, 1337062530, 1337062531, 1337062532, 1337062533, 1337062534, 1337062535, 1337062498, 1337062499, 1337062500, 1337062501, 1337062502, 1337062503, 1337062504, 1337062505, 1337062506, 1337062507, 1337062508, 1337062509, 1337062567, 1337062570, 1337062571, 1337062572, 1337062573, 1337062574, 1337062575, 1337062576, 1337062577, 1337062578, 1337062579, 1337062580, 1337062486, 1337062487, 1337062488, 1337062489, 1337062490, 1337062491, 1337062492, 1337062493, 1337062494, 1337062495, 1337062496, 1337062497, 1337062536, 1337062537, 1337062538, 1337062539, 1337062540, 1337062544, 1337062545, 1337062546, 1337062547, 1337062548, 1337062549, 1337062550, 1337062551, 1337062552, 1337062553, 1337062556, 1337062559, 1337062560, 1337062561, 1337062562, 1337062563, 1337062564, 1337062565, 1337062566, 1337062510, 1337062511, 1337062512, 1337062513, 1337062514, 1337062515, 1337062516, 1337062517, 1337062518, 1337062519, 1337062520, 1337062521] number of photos to traite : 117 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 : 10111 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/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/:/home/admin/workarea/git/apy/ 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 F0212 10:50:50.695223 2950268 math_functions.cu:68] Check failed: status == CUBLAS_STATUS_SUCCESS (13 vs. 0) CUBLAS_STATUS_EXECUTION_FAILED *** Check failure stack trace: *** Command terminated by signal 6 25.39user 17.77system 2:50.73elapsed 25%CPU (0avgtext+0avgdata 2455572maxresident)k 574704inputs+4608outputs (665major+1562282minor)pagefaults 0swaps