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 2525220' -s traitement_3459 -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 : 3966550 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 : 3459, datou_cur_ids : ['2525220'] with mtr_portfolio_ids : ['20036989'] and first list_photo_ids : [] new path : /proc/3966550/ 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, crop_condition, thcl, merge_mask_thcl_custom, rle_unique_nms_with_priority, crop_condition, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score over limit max, limiting to limit_max 20 list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 20 ; length of list_pids : 20 ; length of list_args : 20 time to download the photos : 3.244170904159546 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 5 14:21:48 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 : 5485 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-05 14:21:51.416686: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-05 14:21:51.443220: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-05 14:21:51.445337: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f2f24000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-05 14:21:51.445383: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-05 14:21:51.449135: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-05 14:21:51.599221: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3e73ee00 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-05 14:21:51.599265: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-05 14:21:51.600357: 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 2025-02-05 14:21:51.600742: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 14:21:51.603775: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 14:21:51.606521: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 14:21:51.606856: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 14:21:51.610644: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 14:21:51.612235: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 14:21:51.619829: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 14:21:51.621194: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 14:21:51.621271: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 14:21:51.621904: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-05 14:21:51.621919: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-05 14:21:51.621939: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-05 14:21:51.623051: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5013 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. 2025-02-05 14:21:51.936607: 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 2025-02-05 14:21:51.936690: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 14:21:51.936711: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 14:21:51.936728: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 14:21:51.936745: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 14:21:51.936761: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 14:21:51.936777: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 14:21:51.936794: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 14:21:51.937764: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 14:21:51.938773: 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 2025-02-05 14:21:51.938803: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 14:21:51.938818: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 14:21:51.938832: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 14:21:51.938846: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 14:21:51.938860: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 14:21:51.938873: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 14:21:51.938887: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 14:21:51.939878: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 14:21:51.939908: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-05 14:21:51.939917: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-05 14:21:51.939924: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-05 14:21:51.940944: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5013 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 : thcl2896 thcls : [{'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5309 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5309, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 16384, 25088, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 5, 10, 19, 20, 46), datetime.datetime(2021, 5, 10, 19, 20, 46)) {'thcl': {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'], 'list_hashtags_csv': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'svm_hashtag_type_desc': 5309, 'photo_desc_type': 5309, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', '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_convoyeur_qualipapia_nantes_poly_100521_1 NUM_CLASSES 10 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_convoyeur_qualipapia_nantes_poly_100521_1 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-05 14:22:00.416264: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 14:22:00.736342: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_convoyeur_qualipapia_nantes_poly_100521_1 /data/models_weight/learn_convoyeur_qualipapia_nantes_poly_100521_1/mask_model.h5 size_local : 256031040 size in s3 : 256031040 create time local : 2021-08-09 05:45:48 create time in s3 : 2021-08-06 18:59:51 mask_model.h5 already exist and didn't need to update list_images length : 20 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 3 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 10 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 9 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 15 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 9 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 15 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 9 Detection mask done ! Trying to reset tf kernel 3966832 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 196 tf kernel not reseted sub process len(results) : 20 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 20 len(list_Values) 0 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5485 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2896 Catched exception ! Connect or reconnect ! thcls : [{'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5309 ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'] time for calcul the mask position with numpy : 0.01730966567993164 nb_pixel_total : 790746 time to create 1 rle with new method : 0.06698274612426758 length of segment : 1245 time for calcul the mask position with numpy : 0.0006794929504394531 nb_pixel_total : 39635 time to create 1 rle with old method : 0.04143500328063965 length of segment : 401 time for calcul the mask position with numpy : 0.0009245872497558594 nb_pixel_total : 58382 time to create 1 rle with old method : 0.06083250045776367 length of segment : 523 time for calcul the mask position with numpy : 0.0010209083557128906 nb_pixel_total : 63962 time to create 1 rle with old method : 0.06682896614074707 length of segment : 471 time for calcul the mask position with numpy : 0.005288839340209961 nb_pixel_total : 297576 time to create 1 rle with new method : 0.010886907577514648 length of segment : 974 time for calcul the mask position with numpy : 0.00030422210693359375 nb_pixel_total : 12413 time to create 1 rle with old method : 0.013127326965332031 length of segment : 181 time for calcul the mask position with numpy : 0.00036072731018066406 nb_pixel_total : 15488 time to create 1 rle with old method : 0.016603946685791016 length of segment : 195 time for calcul the mask position with numpy : 0.0003840923309326172 nb_pixel_total : 15024 time to create 1 rle with old method : 0.016000986099243164 length of segment : 234 time for calcul the mask position with numpy : 0.00016736984252929688 nb_pixel_total : 7956 time to create 1 rle with old method : 0.008704185485839844 length of segment : 85 time for calcul the mask position with numpy : 0.007658481597900391 nb_pixel_total : 460297 time to create 1 rle with new method : 0.020190954208374023 length of segment : 1317 time for calcul the mask position with numpy : 0.0010995864868164062 nb_pixel_total : 39650 time to create 1 rle with old method : 0.042249202728271484 length of segment : 371 time for calcul the mask position with numpy : 0.0015556812286376953 nb_pixel_total : 93323 time to create 1 rle with old method : 0.1001882553100586 length of segment : 598 time for calcul the mask position with numpy : 0.026064157485961914 nb_pixel_total : 1109197 time to create 1 rle with new method : 0.06768584251403809 length of segment : 1345 time for calcul the mask position with numpy : 0.0021944046020507812 nb_pixel_total : 121788 time to create 1 rle with old method : 0.16704010963439941 length of segment : 526 time for calcul the mask position with numpy : 0.001184701919555664 nb_pixel_total : 81080 time to create 1 rle with old method : 0.08901262283325195 length of segment : 395 time for calcul the mask position with numpy : 0.00025844573974609375 nb_pixel_total : 9582 time to create 1 rle with old method : 0.011114358901977539 length of segment : 147 time for calcul the mask position with numpy : 0.0003266334533691406 nb_pixel_total : 12126 time to create 1 rle with old method : 0.013754844665527344 length of segment : 398 time for calcul the mask position with numpy : 0.0001933574676513672 nb_pixel_total : 4372 time to create 1 rle with old method : 0.005347728729248047 length of segment : 75 time for calcul the mask position with numpy : 0.023075580596923828 nb_pixel_total : 1017203 time to create 1 rle with new method : 0.04108428955078125 length of segment : 1224 time for calcul the mask position with numpy : 0.002655029296875 nb_pixel_total : 154710 time to create 1 rle with new method : 0.006983041763305664 length of segment : 439 time for calcul the mask position with numpy : 0.0005047321319580078 nb_pixel_total : 9709 time to create 1 rle with old method : 0.010946273803710938 length of segment : 240 time for calcul the mask position with numpy : 0.006333827972412109 nb_pixel_total : 355473 time to create 1 rle with new method : 0.015420913696289062 length of segment : 1066 time for calcul the mask position with numpy : 0.013064861297607422 nb_pixel_total : 528849 time to create 1 rle with new method : 0.022478580474853516 length of segment : 1269 time for calcul the mask position with numpy : 0.0009603500366210938 nb_pixel_total : 53807 time to create 1 rle with old method : 0.06099843978881836 length of segment : 375 time for calcul the mask position with numpy : 0.0003612041473388672 nb_pixel_total : 8567 time to create 1 rle with old method : 0.010065317153930664 length of segment : 122 time for calcul the mask position with numpy : 0.000171661376953125 nb_pixel_total : 5918 time to create 1 rle with old method : 0.007028102874755859 length of segment : 65 time for calcul the mask position with numpy : 0.0013227462768554688 nb_pixel_total : 51174 time to create 1 rle with old method : 0.056745290756225586 length of segment : 348 time for calcul the mask position with numpy : 0.0045969486236572266 nb_pixel_total : 369793 time to create 1 rle with new method : 0.01099085807800293 length of segment : 1523 time for calcul the mask position with numpy : 0.0018846988677978516 nb_pixel_total : 107032 time to create 1 rle with old method : 0.11953020095825195 length of segment : 364 time for calcul the mask position with numpy : 0.0031485557556152344 nb_pixel_total : 84835 time to create 1 rle with old method : 0.09709787368774414 length of segment : 534 time for calcul the mask position with numpy : 0.0002295970916748047 nb_pixel_total : 6550 time to create 1 rle with old method : 0.007520914077758789 length of segment : 143 time for calcul the mask position with numpy : 0.013884782791137695 nb_pixel_total : 644727 time to create 1 rle with new method : 0.02794957160949707 length of segment : 1629 time for calcul the mask position with numpy : 0.00020647048950195312 nb_pixel_total : 7496 time to create 1 rle with old method : 0.008478403091430664 length of segment : 119 time for calcul the mask position with numpy : 0.00016617774963378906 nb_pixel_total : 7130 time to create 1 rle with old method : 0.008420944213867188 length of segment : 105 time for calcul the mask position with numpy : 0.0013091564178466797 nb_pixel_total : 52694 time to create 1 rle with old method : 0.09126424789428711 length of segment : 265 time for calcul the mask position with numpy : 0.008014202117919922 nb_pixel_total : 168969 time to create 1 rle with new method : 0.0287017822265625 length of segment : 1009 time for calcul the mask position with numpy : 0.0027866363525390625 nb_pixel_total : 73709 time to create 1 rle with old method : 0.13835740089416504 length of segment : 316 time for calcul the mask position with numpy : 0.0012569427490234375 nb_pixel_total : 30471 time to create 1 rle with old method : 0.04772782325744629 length of segment : 465 time for calcul the mask position with numpy : 0.03642988204956055 nb_pixel_total : 1232479 time to create 1 rle with new method : 0.05713152885437012 length of segment : 1666 time for calcul the mask position with numpy : 0.0006871223449707031 nb_pixel_total : 19960 time to create 1 rle with old method : 0.03727316856384277 length of segment : 149 time for calcul the mask position with numpy : 0.008398056030273438 nb_pixel_total : 304798 time to create 1 rle with new method : 0.013038873672485352 length of segment : 998 time for calcul the mask position with numpy : 0.004503726959228516 nb_pixel_total : 185195 time to create 1 rle with new method : 0.00894308090209961 length of segment : 738 time for calcul the mask position with numpy : 0.019104719161987305 nb_pixel_total : 1223863 time to create 1 rle with new method : 0.03764152526855469 length of segment : 1531 time for calcul the mask position with numpy : 0.017342567443847656 nb_pixel_total : 1042345 time to create 1 rle with new method : 0.027281522750854492 length of segment : 1579 time for calcul the mask position with numpy : 0.003734111785888672 nb_pixel_total : 207948 time to create 1 rle with new method : 0.0104522705078125 length of segment : 943 time for calcul the mask position with numpy : 0.0005352497100830078 nb_pixel_total : 24815 time to create 1 rle with old method : 0.029675006866455078 length of segment : 127 time for calcul the mask position with numpy : 0.0003337860107421875 nb_pixel_total : 7599 time to create 1 rle with old method : 0.008906364440917969 length of segment : 133 time for calcul the mask position with numpy : 0.007897615432739258 nb_pixel_total : 377665 time to create 1 rle with new method : 0.014518976211547852 length of segment : 1008 time for calcul the mask position with numpy : 0.01730656623840332 nb_pixel_total : 928519 time to create 1 rle with new method : 0.0387575626373291 length of segment : 1632 time for calcul the mask position with numpy : 0.004524946212768555 nb_pixel_total : 123174 time to create 1 rle with old method : 0.13229155540466309 length of segment : 699 time for calcul the mask position with numpy : 0.012277841567993164 nb_pixel_total : 591951 time to create 1 rle with new method : 0.022112607955932617 length of segment : 1107 time for calcul the mask position with numpy : 0.00018167495727539062 nb_pixel_total : 7555 time to create 1 rle with old method : 0.008895635604858398 length of segment : 81 time for calcul the mask position with numpy : 0.0007507801055908203 nb_pixel_total : 58423 time to create 1 rle with old method : 0.0660402774810791 length of segment : 319 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 5390 time to create 1 rle with old method : 0.006325244903564453 length of segment : 80 time for calcul the mask position with numpy : 0.0014088153839111328 nb_pixel_total : 132380 time to create 1 rle with old method : 0.17153286933898926 length of segment : 394 time for calcul the mask position with numpy : 0.0004258155822753906 nb_pixel_total : 14265 time to create 1 rle with old method : 0.015835285186767578 length of segment : 123 time for calcul the mask position with numpy : 0.0007319450378417969 nb_pixel_total : 33785 time to create 1 rle with old method : 0.03640246391296387 length of segment : 273 time for calcul the mask position with numpy : 0.0009722709655761719 nb_pixel_total : 23661 time to create 1 rle with old method : 0.025619029998779297 length of segment : 495 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 1849 time to create 1 rle with old method : 0.0021245479583740234 length of segment : 52 time for calcul the mask position with numpy : 0.012047052383422852 nb_pixel_total : 605058 time to create 1 rle with new method : 0.022472381591796875 length of segment : 1433 time for calcul the mask position with numpy : 0.0008544921875 nb_pixel_total : 41563 time to create 1 rle with old method : 0.044989824295043945 length of segment : 273 time for calcul the mask position with numpy : 0.00036072731018066406 nb_pixel_total : 9185 time to create 1 rle with old method : 0.010334491729736328 length of segment : 132 time for calcul the mask position with numpy : 0.014172554016113281 nb_pixel_total : 811579 time to create 1 rle with new method : 0.028321266174316406 length of segment : 1779 time for calcul the mask position with numpy : 0.0015718936920166016 nb_pixel_total : 94398 time to create 1 rle with old method : 0.10326743125915527 length of segment : 595 time for calcul the mask position with numpy : 0.00021386146545410156 nb_pixel_total : 3129 time to create 1 rle with old method : 0.004080057144165039 length of segment : 131 time for calcul the mask position with numpy : 0.004221439361572266 nb_pixel_total : 291274 time to create 1 rle with new method : 0.01060175895690918 length of segment : 952 time for calcul the mask position with numpy : 0.002004384994506836 nb_pixel_total : 103111 time to create 1 rle with old method : 0.11714029312133789 length of segment : 397 time for calcul the mask position with numpy : 0.0013229846954345703 nb_pixel_total : 35391 time to create 1 rle with old method : 0.0391695499420166 length of segment : 387 time for calcul the mask position with numpy : 0.005391836166381836 nb_pixel_total : 192835 time to create 1 rle with new method : 0.011687517166137695 length of segment : 800 time for calcul the mask position with numpy : 0.014831304550170898 nb_pixel_total : 516622 time to create 1 rle with new method : 0.02947092056274414 length of segment : 1378 time for calcul the mask position with numpy : 0.0014843940734863281 nb_pixel_total : 69007 time to create 1 rle with old method : 0.07663297653198242 length of segment : 583 time for calcul the mask position with numpy : 0.0003223419189453125 nb_pixel_total : 10656 time to create 1 rle with old method : 0.012346029281616211 length of segment : 196 time for calcul the mask position with numpy : 0.0047740936279296875 nb_pixel_total : 309185 time to create 1 rle with new method : 0.011771917343139648 length of segment : 1189 time for calcul the mask position with numpy : 0.0002808570861816406 nb_pixel_total : 13778 time to create 1 rle with old method : 0.015596389770507812 length of segment : 164 time for calcul the mask position with numpy : 0.0008594989776611328 nb_pixel_total : 46749 time to create 1 rle with old method : 0.05026054382324219 length of segment : 325 time for calcul the mask position with numpy : 0.00016951560974121094 nb_pixel_total : 4914 time to create 1 rle with old method : 0.008090496063232422 length of segment : 193 time for calcul the mask position with numpy : 0.0002913475036621094 nb_pixel_total : 12191 time to create 1 rle with old method : 0.020023822784423828 length of segment : 151 time for calcul the mask position with numpy : 0.00019741058349609375 nb_pixel_total : 4459 time to create 1 rle with old method : 0.005063295364379883 length of segment : 63 time for calcul the mask position with numpy : 0.011826753616333008 nb_pixel_total : 352164 time to create 1 rle with new method : 0.02777266502380371 length of segment : 1121 time for calcul the mask position with numpy : 0.003934144973754883 nb_pixel_total : 184019 time to create 1 rle with new method : 0.012617349624633789 length of segment : 1269 time for calcul the mask position with numpy : 0.005816936492919922 nb_pixel_total : 370334 time to create 1 rle with new method : 0.013559103012084961 length of segment : 1335 time for calcul the mask position with numpy : 0.0006520748138427734 nb_pixel_total : 32883 time to create 1 rle with old method : 0.03621959686279297 length of segment : 208 time for calcul the mask position with numpy : 0.00014972686767578125 nb_pixel_total : 6983 time to create 1 rle with old method : 0.00832819938659668 length of segment : 61 time for calcul the mask position with numpy : 0.0009963512420654297 nb_pixel_total : 63101 time to create 1 rle with old method : 0.0699613094329834 length of segment : 334 time for calcul the mask position with numpy : 0.0010104179382324219 nb_pixel_total : 48828 time to create 1 rle with old method : 0.053667306900024414 length of segment : 273 time for calcul the mask position with numpy : 0.00015544891357421875 nb_pixel_total : 2173 time to create 1 rle with old method : 0.0026001930236816406 length of segment : 46 time for calcul the mask position with numpy : 0.00033283233642578125 nb_pixel_total : 4437 time to create 1 rle with old method : 0.0052373409271240234 length of segment : 150 time for calcul the mask position with numpy : 0.0007543563842773438 nb_pixel_total : 17561 time to create 1 rle with old method : 0.019823074340820312 length of segment : 293 time for calcul the mask position with numpy : 0.010482072830200195 nb_pixel_total : 456251 time to create 1 rle with new method : 0.01917123794555664 length of segment : 1554 time for calcul the mask position with numpy : 0.0008599758148193359 nb_pixel_total : 22359 time to create 1 rle with old method : 0.026499271392822266 length of segment : 194 time for calcul the mask position with numpy : 0.0004982948303222656 nb_pixel_total : 21602 time to create 1 rle with old method : 0.02439141273498535 length of segment : 228 time for calcul the mask position with numpy : 0.0012433528900146484 nb_pixel_total : 51512 time to create 1 rle with old method : 0.0585935115814209 length of segment : 407 time for calcul the mask position with numpy : 0.00027942657470703125 nb_pixel_total : 7160 time to create 1 rle with old method : 0.00849771499633789 length of segment : 97 time for calcul the mask position with numpy : 0.00020384788513183594 nb_pixel_total : 2814 time to create 1 rle with old method : 0.003361225128173828 length of segment : 69 time for calcul the mask position with numpy : 0.014716148376464844 nb_pixel_total : 545317 time to create 1 rle with new method : 0.02598261833190918 length of segment : 1503 time for calcul the mask position with numpy : 0.00010824203491210938 nb_pixel_total : 1838 time to create 1 rle with old method : 0.002193927764892578 length of segment : 88 time for calcul the mask position with numpy : 0.0010459423065185547 nb_pixel_total : 50608 time to create 1 rle with old method : 0.05739927291870117 length of segment : 223 time for calcul the mask position with numpy : 0.0001652240753173828 nb_pixel_total : 4153 time to create 1 rle with old method : 0.004775285720825195 length of segment : 95 time for calcul the mask position with numpy : 0.00035190582275390625 nb_pixel_total : 5819 time to create 1 rle with old method : 0.007509708404541016 length of segment : 154 time for calcul the mask position with numpy : 0.0005726814270019531 nb_pixel_total : 31693 time to create 1 rle with old method : 0.035280704498291016 length of segment : 166 time for calcul the mask position with numpy : 0.00077056884765625 nb_pixel_total : 20139 time to create 1 rle with old method : 0.023959636688232422 length of segment : 239 time for calcul the mask position with numpy : 0.0005872249603271484 nb_pixel_total : 21040 time to create 1 rle with old method : 0.023641347885131836 length of segment : 153 time for calcul the mask position with numpy : 0.019021034240722656 nb_pixel_total : 814937 time to create 1 rle with new method : 0.031754493713378906 length of segment : 1539 time for calcul the mask position with numpy : 0.0005755424499511719 nb_pixel_total : 20249 time to create 1 rle with old method : 0.032446861267089844 length of segment : 237 time for calcul the mask position with numpy : 0.001026153564453125 nb_pixel_total : 38987 time to create 1 rle with old method : 0.04217672348022461 length of segment : 494 time for calcul the mask position with numpy : 0.002132892608642578 nb_pixel_total : 51240 time to create 1 rle with old method : 0.05852532386779785 length of segment : 832 time for calcul the mask position with numpy : 0.024735212326049805 nb_pixel_total : 591512 time to create 1 rle with new method : 0.03276348114013672 length of segment : 1194 time for calcul the mask position with numpy : 0.0006036758422851562 nb_pixel_total : 12543 time to create 1 rle with old method : 0.014757633209228516 length of segment : 191 time for calcul the mask position with numpy : 0.0003941059112548828 nb_pixel_total : 16986 time to create 1 rle with old method : 0.02049851417541504 length of segment : 161 time for calcul the mask position with numpy : 0.002547025680541992 nb_pixel_total : 51664 time to create 1 rle with old method : 0.0578310489654541 length of segment : 342 time for calcul the mask position with numpy : 0.0004394054412841797 nb_pixel_total : 12301 time to create 1 rle with old method : 0.017262935638427734 length of segment : 116 time for calcul the mask position with numpy : 0.00061798095703125 nb_pixel_total : 16903 time to create 1 rle with old method : 0.01929497718811035 length of segment : 307 time for calcul the mask position with numpy : 0.0021631717681884766 nb_pixel_total : 46817 time to create 1 rle with old method : 0.05209755897521973 length of segment : 602 time for calcul the mask position with numpy : 0.004883766174316406 nb_pixel_total : 294730 time to create 1 rle with new method : 0.013290643692016602 length of segment : 1100 time for calcul the mask position with numpy : 0.00028586387634277344 nb_pixel_total : 4466 time to create 1 rle with old method : 0.00513911247253418 length of segment : 84 time for calcul the mask position with numpy : 0.0004253387451171875 nb_pixel_total : 10425 time to create 1 rle with old method : 0.011681556701660156 length of segment : 144 time for calcul the mask position with numpy : 0.0012865066528320312 nb_pixel_total : 45180 time to create 1 rle with old method : 0.05004167556762695 length of segment : 288 time for calcul the mask position with numpy : 0.0012063980102539062 nb_pixel_total : 62137 time to create 1 rle with old method : 0.06775975227355957 length of segment : 213 time for calcul the mask position with numpy : 0.00027298927307128906 nb_pixel_total : 13419 time to create 1 rle with old method : 0.016025066375732422 length of segment : 117 time for calcul the mask position with numpy : 0.00417637825012207 nb_pixel_total : 98688 time to create 1 rle with old method : 0.10800480842590332 length of segment : 530 time for calcul the mask position with numpy : 0.020566463470458984 nb_pixel_total : 668804 time to create 1 rle with new method : 0.04016375541687012 length of segment : 1361 time for calcul the mask position with numpy : 0.0006406307220458984 nb_pixel_total : 33091 time to create 1 rle with old method : 0.036813974380493164 length of segment : 171 time for calcul the mask position with numpy : 0.0007874965667724609 nb_pixel_total : 24055 time to create 1 rle with old method : 0.027668476104736328 length of segment : 210 time for calcul the mask position with numpy : 0.004166126251220703 nb_pixel_total : 292797 time to create 1 rle with new method : 0.011996030807495117 length of segment : 906 time for calcul the mask position with numpy : 0.00030303001403808594 nb_pixel_total : 5469 time to create 1 rle with old method : 0.006636142730712891 length of segment : 59 time for calcul the mask position with numpy : 0.001859903335571289 nb_pixel_total : 70988 time to create 1 rle with old method : 0.07705974578857422 length of segment : 361 time for calcul the mask position with numpy : 0.00011444091796875 nb_pixel_total : 770 time to create 1 rle with old method : 0.0009679794311523438 length of segment : 41 time for calcul the mask position with numpy : 0.012207984924316406 nb_pixel_total : 324762 time to create 1 rle with new method : 0.021969318389892578 length of segment : 2087 time for calcul the mask position with numpy : 0.00045490264892578125 nb_pixel_total : 6095 time to create 1 rle with old method : 0.010209798812866211 length of segment : 87 time for calcul the mask position with numpy : 0.000396728515625 nb_pixel_total : 10053 time to create 1 rle with old method : 0.011629343032836914 length of segment : 86 time for calcul the mask position with numpy : 0.0024869441986083984 nb_pixel_total : 95943 time to create 1 rle with old method : 0.10588884353637695 length of segment : 289 time for calcul the mask position with numpy : 0.00014209747314453125 nb_pixel_total : 2049 time to create 1 rle with old method : 0.0024559497833251953 length of segment : 45 time for calcul the mask position with numpy : 0.0006227493286132812 nb_pixel_total : 28263 time to create 1 rle with old method : 0.03213214874267578 length of segment : 300 time for calcul the mask position with numpy : 0.00035071372985839844 nb_pixel_total : 15661 time to create 1 rle with old method : 0.017566919326782227 length of segment : 206 time for calcul the mask position with numpy : 0.0007548332214355469 nb_pixel_total : 22219 time to create 1 rle with old method : 0.02474236488342285 length of segment : 220 time for calcul the mask position with numpy : 0.0008389949798583984 nb_pixel_total : 34991 time to create 1 rle with old method : 0.039461374282836914 length of segment : 142 time for calcul the mask position with numpy : 0.00024175643920898438 nb_pixel_total : 5249 time to create 1 rle with old method : 0.006334543228149414 length of segment : 89 time for calcul the mask position with numpy : 0.00042366981506347656 nb_pixel_total : 17695 time to create 1 rle with old method : 0.020084142684936523 length of segment : 244 time for calcul the mask position with numpy : 0.0004892349243164062 nb_pixel_total : 10541 time to create 1 rle with old method : 0.012183666229248047 length of segment : 164 time for calcul the mask position with numpy : 0.00049591064453125 nb_pixel_total : 9313 time to create 1 rle with old method : 0.010716676712036133 length of segment : 226 time for calcul the mask position with numpy : 0.019811630249023438 nb_pixel_total : 716135 time to create 1 rle with new method : 0.03358912467956543 length of segment : 1316 time for calcul the mask position with numpy : 0.00013899803161621094 nb_pixel_total : 1087 time to create 1 rle with old method : 0.0013706684112548828 length of segment : 62 time for calcul the mask position with numpy : 0.0011124610900878906 nb_pixel_total : 52471 time to create 1 rle with old method : 0.05774402618408203 length of segment : 406 time for calcul the mask position with numpy : 0.005898237228393555 nb_pixel_total : 390376 time to create 1 rle with new method : 0.012772560119628906 length of segment : 990 time for calcul the mask position with numpy : 0.0003986358642578125 nb_pixel_total : 16540 time to create 1 rle with old method : 0.018433570861816406 length of segment : 196 time for calcul the mask position with numpy : 0.0007944107055664062 nb_pixel_total : 26552 time to create 1 rle with old method : 0.029804468154907227 length of segment : 329 time spent for convertir_results : 17.604884147644043 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 146 chid ids of type : 3663 Number RLEs to save : 75693 save missing photos in datou_result : time spend for datou_step_exec : 48.40368604660034 time spend to save output : 5.694729566574097 total time spend for step 1 : 54.09841561317444 step2:crop_condition Wed Feb 5 14:22:42 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 Loading chi in step crop with photo_hashtag_type : 3663 Loading chi in step crop for list_pids : 20 ! batch 1 Loaded 146 chid ids of type : 3663 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ begin to crop the class : teint_dans_la_masse param for this class : {'min_score': 0.7} filtre for class : teint_dans_la_masse hashtag_id of this class : 2107752385 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! we have finished the crop for the class : teint_dans_la_masse begin to crop the class : autre_refus param for this class : {'min_score': 0.5} filtre for class : autre_refus hashtag_id of this class : 2107752406 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 5 About to insert : list_path_to_insert length 5 new photo from crops ! we have finished the crop for the class : autre_refus begin to crop the class : carton_gris param for this class : {'min_score': 0.5} filtre for class : carton_gris hashtag_id of this class : 2107753020 we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! we have finished the crop for the class : carton_gris begin to crop the class : cartonnette param for this class : {'min_score': 0.5} filtre for class : cartonnette hashtag_id of this class : 702398920 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 21 About to insert : list_path_to_insert length 21 new photo from crops ! we have finished the crop for the class : cartonnette begin to crop the class : carton_brun param for this class : {'min_score': 0.7} filtre for class : carton_brun hashtag_id of this class : 2107753024 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 10 About to insert : list_path_to_insert length 10 new photo from crops ! we have finished the crop for the class : carton_brun begin to crop the class : plastique param for this class : {'min_score': 0.5} filtre for class : plastique hashtag_id of this class : 492725882 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 5 About to insert : list_path_to_insert length 5 new photo from crops ! we have finished the crop for the class : plastique begin to crop the class : kraft param for this class : {'min_score': 0.5} filtre for class : kraft hashtag_id of this class : 493202403 begin to crop the class : metal param for this class : {'min_score': 0.5} filtre for class : metal hashtag_id of this class : 492628673 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1332557805, 1332557794, 1332557777, 1332557774, 1332557760, 1332557754, 1332557749, 1332557743, 1332557735, 1332557658, 1332557613, 1332557558, 1332557547, 1332557518, 1332557461, 1332557455, 1332557305, 1332557242, 1332557227, 1332557160] Looping around the photos to save general results len do output : 47 /-3656058909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656058974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3656059033Didn'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 ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557805', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557794', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557777', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557774', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557760', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557754', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557749', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557743', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557735', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557658', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557613', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557558', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557547', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557518', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557461', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557455', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557305', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557242', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557227', None, None, None, None, None, '2525220') ('3459', None, None, None, None, None, None, None, '2525220') ('3459', None, '1332557160', None, None, None, None, None, '2525220') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 161 time used for this insertion : 0.03696465492248535 save_final save missing photos in datou_result : time spend for datou_step_exec : 10.562754154205322 time spend to save output : 0.03882551193237305 total time spend for step 2 : 10.601579666137695 step3:thcl Wed Feb 5 14:22:52 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 ! nombre de thcls : 2 we are using the classfication for multi_thcl [2456, 2868] time to import caffe and check if the image exist : 0.013909101486206055 time to convert the images to numpy array : 0.03437685966491699 time to import caffe and check if the image exist : 0.008233070373535156 time to convert the images to numpy array : 0.05463075637817383 time to import caffe and check if the image exist : 0.012250423431396484 time to convert the images to numpy array : 0.07179927825927734 time to import caffe and check if the image exist : 0.01315617561340332 time to convert the images to numpy array : 0.07790017127990723 time to import caffe and check if the image exist : 0.00945138931274414 time to convert the images to numpy array : 0.09133481979370117 time to import caffe and check if the image exist : 0.016771554946899414 time to convert the images to numpy array : 0.09820151329040527 time to import caffe and check if the image exist : 0.015352725982666016 time to convert the images to numpy array : 0.12660646438598633 time to import caffe and check if the image exist : 0.013927221298217773 time to convert the images to numpy array : 0.13930845260620117 time to import caffe and check if the image exist : 0.014370441436767578 time to convert the images to numpy array : 0.15308761596679688 time to import caffe and check if the image exist : 0.013730764389038086 time to convert the images to numpy array : 0.15714144706726074 total time to convert the images to numpy array : 0.6024904251098633 list photo_ids error: [] list photo_ids correct : [-3656058932, -3656058985, -3656059000, -3656058993, -3656059005, -3656059007, -3656059033, -3656059042, -3656059052, -3656058916, -3656058928, -3656058933, -3656058909, -3656059003, -3656059017, -3656059019, -3656058954, -3656058978, -3656058982, -3656058979, -3656058981, -3656058991, -3656058953, -3656058962, -3656058968, -3656058969, -3656058964, -3656059023, -3656059039, -3656058941, -3656058940, -3656058974, -3656058960, -3656059012, -3656059016, -3656059015, -3656058989, -3656059004, -3656059018, -3656059024, -3656059030, -3656059038, -3656059022, -3656058911, -3656058918, -3656058927, -3656058947] number of photos to traite : 47 try to delete the photos incorrect in DB tagging for thcl : 2456 To do loadFromThcl(), then load ParamDescType : thcl2456 thcls : [{'id': 2456, 'mtr_user_id': 31, 'name': 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'papier,refus', 'svm_portfolios_learning': '3028087,3028251', 'photo_hashtag_type': 3049, 'photo_desc_type': 4999, 'type_classification': 'caffe', 'hashtag_id_list': '492668766,538914404'}] thcl {'id': 2456, 'mtr_user_id': 31, 'name': 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'papier,refus', 'svm_portfolios_learning': '3028087,3028251', 'photo_hashtag_type': 3049, 'photo_desc_type': 4999, 'type_classification': 'caffe', 'hashtag_id_list': '492668766,538914404'} Update svm_hashtag_type_desc : 4999 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) To loadFromThcl() : net_4999 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 4376 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_qualipapia_papier_refus_from_vlg_data_aug 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_qualipapia_papier_refus_from_vlg_data_aug 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'] WARNING: Logging before InitGoogleLogging() is written to STDERR E0205 14:22:55.879833 3966550 common.cpp:114] Cannot create Cublas handle. Cublas won't be available. E0205 14:22:55.885455 3966550 common.cpp:121] Cannot create Curand generator. Curand won't be available. local folder : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/caffemodel size_local : 44972172 size in s3 : 44972172 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 caffemodel already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/deploy.prototxt size_local : 17311 size in s3 : 17311 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:51 mean.npy already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/synset_words.txt size_local : 57 size in s3 : 57 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 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_qualipapia_papier_refus_from_vlg_data_aug/deploy.prototxt caffemodel_filename : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 7 wait 20 seconds F0205 14:23:17.563010 3966550 math_functions.cu:26] Check failed: status == CUBLAS_STATUS_SUCCESS (1 vs. 0) CUBLAS_STATUS_NOT_INITIALIZED *** Check failure stack trace: *** Command terminated by signal 6 46.10user 25.21system 1:35.51elapsed 74%CPU (0avgtext+0avgdata 2978080maxresident)k 440672inputs+15600outputs (4011major+1759817minor)pagefaults 0swaps