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 3804210' -s carac_4877 -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 : 2034942 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 : 4877, datou_cur_ids : ['3804210'] with mtr_portfolio_ids : ['27391869'] and first list_photo_ids : [] new path : /proc/2034942/ 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 ! 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 13611 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13613 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 13613 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 13614 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 13614 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 13615 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13615 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 13621 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13621 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 13617 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13617 ventilate_hashtags_in_portfolio have less outputs used (0) than in the step definition (1) : some outputs may be not used ! 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 13611 doesn't seem to be define in the database( WARNING : type of input 2 of step 13613 doesn't seem to be define in the database( WARNING : output 1 of step 13611 have datatype=2 whereas input 1 of step 13614 have datatype=7 WARNING : type of output 2 of step 13614 doesn't seem to be define in the database( WARNING : type of input 1 of step 13615 doesn't seem to be define in the database( WARNING : type of output 3 of step 13614 doesn't seem to be define in the database( WARNING : type of input 1 of step 13617 doesn't seem to be define in the database( WARNING : type of input 2 of step 13621 doesn't seem to be define in the database( WARNING : output 1 of step 13615 have datatype=7 whereas input 2 of step 13621 have datatype=None WARNING : type of output 3 of step 13621 doesn't seem to be define in the database( WARNING : type of input 2 of step 13617 doesn't seem to be define in the database( WARNING : output 0 of step 13614 have datatype=1 whereas input 0 of step 13615 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, tfhub_classification2, argmax over limit max, limiting to limit_max 20 list_input_json : [] origin We have 1 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.6451923847198486 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 : 9 step1:mask_detect Wed Oct 1 08:47:41 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 : 10138 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-10-01 08:47:44.215552: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-10-01 08:47:44.244554: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-10-01 08:47:44.246665: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f0d28000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-10-01 08:47:44.246731: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-10-01 08:47:44.250903: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-10-01 08:47:44.403796: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2f70b200 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-10-01 08:47:44.403854: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-10-01 08:47:44.405307: 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 2025-10-01 08:47:44.405907: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-01 08:47:44.409131: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-01 08:47:44.411647: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-01 08:47:44.412038: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-01 08:47:44.415356: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-01 08:47:44.416771: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-01 08:47:44.422838: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-01 08:47:44.424271: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-01 08:47:44.424384: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-01 08:47:44.425182: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-01 08:47:44.425199: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-01 08:47:44.425209: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-01 08:47:44.426523: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9387 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. 2025-10-01 08:47:44.869506: 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 2025-10-01 08:47:44.869622: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-01 08:47:44.869650: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-01 08:47:44.869674: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-01 08:47:44.869720: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-01 08:47:44.869745: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-01 08:47:44.869769: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-01 08:47:44.869792: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-01 08:47:44.871947: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-01 08:47:44.876817: 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 2025-10-01 08:47:44.876922: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-01 08:47:44.876948: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-01 08:47:44.876972: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-01 08:47:44.876995: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-01 08:47:44.877018: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-01 08:47:44.877042: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-01 08:47:44.877065: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-01 08:47:44.879051: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-01 08:47:44.879115: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-01 08:47:44.879134: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-01 08:47:44.879148: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-01 08:47:44.881489: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9387 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 : [] 2025-10-01 08:47:52.889546: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-01 08:47:53.064625: 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 : 4 NEW PHOTO Processing 1 images image shape: (1080, 1632, 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: 1632.00000 nb d'objets trouves : 15 NEW PHOTO Processing 1 images image shape: (1080, 1632, 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: 1632.00000 nb d'objets trouves : 16 NEW PHOTO Processing 1 images image shape: (1080, 1632, 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: 1632.00000 nb d'objets trouves : 14 NEW PHOTO Processing 1 images image shape: (1080, 1632, 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: 1632.00000 nb d'objets trouves : 17 Detection mask done ! Trying to reset tf kernel 2035048 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 4849 tf kernel not reseted sub process len(results) : 4 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 4 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 : 10138 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 : 0.0002167224884033203 nb_pixel_total : 3701 time to create 1 rle with old method : 0.004495143890380859 length of segment : 113 time for calcul the mask position with numpy : 0.0016951560974121094 nb_pixel_total : 103151 time to create 1 rle with old method : 0.1209406852722168 length of segment : 371 time for calcul the mask position with numpy : 0.00017261505126953125 nb_pixel_total : 4820 time to create 1 rle with old method : 0.006043195724487305 length of segment : 84 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 671 time to create 1 rle with old method : 0.0009515285491943359 length of segment : 50 time for calcul the mask position with numpy : 0.0005724430084228516 nb_pixel_total : 33547 time to create 1 rle with old method : 0.0376584529876709 length of segment : 256 time for calcul the mask position with numpy : 0.00017070770263671875 nb_pixel_total : 6730 time to create 1 rle with old method : 0.007730245590209961 length of segment : 99 time for calcul the mask position with numpy : 0.0004971027374267578 nb_pixel_total : 32802 time to create 1 rle with old method : 0.03598332405090332 length of segment : 315 time for calcul the mask position with numpy : 0.0003285408020019531 nb_pixel_total : 7072 time to create 1 rle with old method : 0.008526086807250977 length of segment : 240 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 606 time to create 1 rle with old method : 0.0007717609405517578 length of segment : 66 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0009071826934814453 length of segment : 19 time for calcul the mask position with numpy : 0.0035927295684814453 nb_pixel_total : 135191 time to create 1 rle with old method : 0.14998173713684082 length of segment : 806 time for calcul the mask position with numpy : 0.0001780986785888672 nb_pixel_total : 8063 time to create 1 rle with old method : 0.010300159454345703 length of segment : 83 time for calcul the mask position with numpy : 0.00015473365783691406 nb_pixel_total : 2032 time to create 1 rle with old method : 0.0029435157775878906 length of segment : 99 time for calcul the mask position with numpy : 0.0016179084777832031 nb_pixel_total : 108667 time to create 1 rle with old method : 0.11957144737243652 length of segment : 449 time for calcul the mask position with numpy : 0.00013494491577148438 nb_pixel_total : 4626 time to create 1 rle with old method : 0.005208730697631836 length of segment : 91 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 2582 time to create 1 rle with old method : 0.0030214786529541016 length of segment : 72 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.00037598609924316406 length of segment : 48 time for calcul the mask position with numpy : 0.005296230316162109 nb_pixel_total : 322983 time to create 1 rle with new method : 0.018625974655151367 length of segment : 1159 time for calcul the mask position with numpy : 0.00021648406982421875 nb_pixel_total : 10875 time to create 1 rle with old method : 0.012118816375732422 length of segment : 139 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 2451 time to create 1 rle with old method : 0.002964496612548828 length of segment : 37 time for calcul the mask position with numpy : 0.00032711029052734375 nb_pixel_total : 17738 time to create 1 rle with old method : 0.019278764724731445 length of segment : 166 time for calcul the mask position with numpy : 0.001575469970703125 nb_pixel_total : 103197 time to create 1 rle with old method : 0.1352684497833252 length of segment : 357 time for calcul the mask position with numpy : 0.0006055831909179688 nb_pixel_total : 44916 time to create 1 rle with old method : 0.04831886291503906 length of segment : 298 time for calcul the mask position with numpy : 0.00036835670471191406 nb_pixel_total : 20776 time to create 1 rle with old method : 0.023066282272338867 length of segment : 147 time for calcul the mask position with numpy : 0.001562356948852539 nb_pixel_total : 128068 time to create 1 rle with old method : 0.14560270309448242 length of segment : 478 time for calcul the mask position with numpy : 0.00023651123046875 nb_pixel_total : 3916 time to create 1 rle with old method : 0.004811286926269531 length of segment : 103 time for calcul the mask position with numpy : 0.0003268718719482422 nb_pixel_total : 9680 time to create 1 rle with old method : 0.011143207550048828 length of segment : 104 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004897117614746094 length of segment : 20 time for calcul the mask position with numpy : 0.00015926361083984375 nb_pixel_total : 1404 time to create 1 rle with old method : 0.0016188621520996094 length of segment : 76 time for calcul the mask position with numpy : 0.00042700767517089844 nb_pixel_total : 4931 time to create 1 rle with old method : 0.0060384273529052734 length of segment : 150 time for calcul the mask position with numpy : 0.00035643577575683594 nb_pixel_total : 12823 time to create 1 rle with old method : 0.015002012252807617 length of segment : 112 time for calcul the mask position with numpy : 0.00024318695068359375 nb_pixel_total : 4753 time to create 1 rle with old method : 0.005661725997924805 length of segment : 90 time for calcul the mask position with numpy : 0.0005991458892822266 nb_pixel_total : 24390 time to create 1 rle with old method : 0.027919292449951172 length of segment : 356 time for calcul the mask position with numpy : 0.009463787078857422 nb_pixel_total : 362177 time to create 1 rle with new method : 0.019821882247924805 length of segment : 891 time for calcul the mask position with numpy : 0.002496004104614258 nb_pixel_total : 108196 time to create 1 rle with old method : 0.13609075546264648 length of segment : 325 time for calcul the mask position with numpy : 0.00011873245239257812 nb_pixel_total : 2356 time to create 1 rle with old method : 0.0028624534606933594 length of segment : 46 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.0009930133819580078 length of segment : 24 time for calcul the mask position with numpy : 0.0005841255187988281 nb_pixel_total : 19638 time to create 1 rle with old method : 0.022954940795898438 length of segment : 252 time for calcul the mask position with numpy : 0.00021314620971679688 nb_pixel_total : 8953 time to create 1 rle with old method : 0.010216474533081055 length of segment : 90 time for calcul the mask position with numpy : 0.0004203319549560547 nb_pixel_total : 13010 time to create 1 rle with old method : 0.015697717666625977 length of segment : 165 time for calcul the mask position with numpy : 0.0006127357482910156 nb_pixel_total : 39257 time to create 1 rle with old method : 0.04737114906311035 length of segment : 300 time for calcul the mask position with numpy : 0.0003910064697265625 nb_pixel_total : 13450 time to create 1 rle with old method : 0.016733169555664062 length of segment : 122 time for calcul the mask position with numpy : 0.0004858970642089844 nb_pixel_total : 5995 time to create 1 rle with old method : 0.007502555847167969 length of segment : 140 time for calcul the mask position with numpy : 0.00030112266540527344 nb_pixel_total : 3553 time to create 1 rle with old method : 0.004270076751708984 length of segment : 129 time for calcul the mask position with numpy : 0.0069735050201416016 nb_pixel_total : 260642 time to create 1 rle with new method : 0.012262344360351562 length of segment : 907 time for calcul the mask position with numpy : 0.0005619525909423828 nb_pixel_total : 16837 time to create 1 rle with old method : 0.020648956298828125 length of segment : 239 time for calcul the mask position with numpy : 0.0011737346649169922 nb_pixel_total : 25445 time to create 1 rle with old method : 0.029047489166259766 length of segment : 318 time for calcul the mask position with numpy : 0.0015599727630615234 nb_pixel_total : 96044 time to create 1 rle with old method : 0.10804128646850586 length of segment : 346 time for calcul the mask position with numpy : 0.0001697540283203125 nb_pixel_total : 2675 time to create 1 rle with old method : 0.003484964370727539 length of segment : 56 time for calcul the mask position with numpy : 0.0013227462768554688 nb_pixel_total : 96690 time to create 1 rle with old method : 0.10963988304138184 length of segment : 362 time for calcul the mask position with numpy : 0.0009446144104003906 nb_pixel_total : 70179 time to create 1 rle with old method : 0.08106064796447754 length of segment : 336 time for calcul the mask position with numpy : 0.0002484321594238281 nb_pixel_total : 5603 time to create 1 rle with old method : 0.006778240203857422 length of segment : 101 time for calcul the mask position with numpy : 0.00040221214294433594 nb_pixel_total : 12146 time to create 1 rle with old method : 0.01571822166442871 length of segment : 152 time for calcul the mask position with numpy : 0.0003886222839355469 nb_pixel_total : 20390 time to create 1 rle with old method : 0.024639606475830078 length of segment : 229 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 561 time to create 1 rle with old method : 0.0008525848388671875 length of segment : 18 time for calcul the mask position with numpy : 0.00023937225341796875 nb_pixel_total : 3953 time to create 1 rle with old method : 0.005095243453979492 length of segment : 128 time spent for convertir_results : 3.9682295322418213 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 56 chid ids of type : 3663 Number RLEs to save : 12729 save missing photos in datou_result : time spend for datou_step_exec : 23.76203680038452 time spend to save output : 1.5026299953460693 total time spend for step 1 : 25.26466679573059 step2:crop_condition Wed Oct 1 08:48:06 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 : 4 ! batch 1 Loaded 56 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 ! 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 : 6 About to insert : list_path_to_insert length 6 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 ! 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 : 9 About to insert : list_path_to_insert length 9 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 ! 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 : 6 About to insert : list_path_to_insert length 6 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 ! map_result returned by crop_photo_return_map_crop : length : 14 About to insert : list_path_to_insert length 14 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 ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 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 ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 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 [1387083785, 1387083672, 1387083669, 1387083666] Looping around the photos to save general results len do output : 37 /-3981871913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3981871901Didn'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 ('4877', None, None, None, None, None, None, None, '3804210') ('4877', '27391869', '1387083785', None, None, None, None, None, '3804210') ('4877', None, None, None, None, None, None, None, '3804210') ('4877', '27391869', '1387083672', None, None, None, None, None, '3804210') ('4877', None, None, None, None, None, None, None, '3804210') ('4877', '27391869', '1387083669', None, None, None, None, None, '3804210') ('4877', None, None, None, None, None, None, None, '3804210') ('4877', '27391869', '1387083666', None, None, None, None, None, '3804210') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 115 time used for this insertion : 0.042138099670410156 save_final save missing photos in datou_result : time spend for datou_step_exec : 6.248581647872925 time spend to save output : 0.04353690147399902 total time spend for step 2 : 6.292118549346924 step3:thcl Wed Oct 1 08:48:12 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 : 0.005833864212036133 time to convert the images to numpy array : 0.009944677352905273 time to import caffe and check if the image exist : 0.0037708282470703125 time to convert the images to numpy array : 0.018301963806152344 time to import caffe and check if the image exist : 0.008258581161499023 time to convert the images to numpy array : 0.01888751983642578 time to import caffe and check if the image exist : 0.008563756942749023 time to convert the images to numpy array : 0.02343153953552246 time to import caffe and check if the image exist : 0.00958704948425293 time to convert the images to numpy array : 0.023107528686523438 time to import caffe and check if the image exist : 0.0055010318756103516 time to convert the images to numpy array : 0.032521724700927734 time to import caffe and check if the image exist : 0.0061495304107666016 time to convert the images to numpy array : 0.0338442325592041 time to import caffe and check if the image exist : 0.008059501647949219 time to convert the images to numpy array : 0.03319096565246582 time to import caffe and check if the image exist : 0.011232614517211914 time to convert the images to numpy array : 0.03020000457763672 time to import caffe and check if the image exist : 0.009684562683105469 time to convert the images to numpy array : 0.036870479583740234 total time to convert the images to numpy array : 0.26343560218811035 list photo_ids error: [] list photo_ids correct : [-3981871901, -3981871949, -3981871899, -3981871900, -3981871906, -3981871914, -3981871926, -3981871933, -3981871930, -3981871945, -3981871936, -3981871897, -3981871907, -3981871913, -3981871927, -3981871925, -3981871940, -3981871896, -3981871895, -3981871915, -3981871917, -3981871916, -3981871918, -3981871932, -3981871935, -3981871948, -3981871946, -3981871943, -3981871908, -3981871929, -3981871947, -3981871942, -3981871941, -3981871902, -3981871919, -3981871934, -3981871944] number of photos to traite : 37 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 : 10138 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'] 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 l 3637 free memory gpu now : 9919 max_wait_temp : 1 max_wait : 0 dict_keys(['prob']) time used to do the prepocess of the images : 0.3041861057281494 time used to do the prediction : 0.12648248672485352 we don't save the descriptors for this thcl 2456 tagging for thcl : 2868 To do loadFromThcl(), then load ParamDescType : thcl2868 thcls : [{'id': 2868, 'mtr_user_id': 31, 'name': 'learn_papier_nantes_300421', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton_brun,Carton_gris,Teint_Dans_La_Masse,autre_refus,cartonnette,environnement,kraft,metal,papier,plastique', 'svm_portfolios_learning': '3752117,3752118,3752123,3752106,3752116,3752124,3752119,3581575,3486029,3752122', 'photo_hashtag_type': 3632, 'photo_desc_type': 5288, 'type_classification': 'caffe', 'hashtag_id_list': '2107753024,2107753020,2107752385,2107752406,702398920,493012381,493202403,492628673,492668766,492725882'}] thcl {'id': 2868, 'mtr_user_id': 31, 'name': 'learn_papier_nantes_300421', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton_brun,Carton_gris,Teint_Dans_La_Masse,autre_refus,cartonnette,environnement,kraft,metal,papier,plastique', 'svm_portfolios_learning': '3752117,3752118,3752123,3752106,3752116,3752124,3752119,3581575,3486029,3752122', 'photo_hashtag_type': 3632, 'photo_desc_type': 5288, 'type_classification': 'caffe', 'hashtag_id_list': '2107753024,2107753020,2107752385,2107752406,702398920,493012381,493202403,492628673,492668766,492725882'} Update svm_hashtag_type_desc : 5288 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5288, 'learn_papier_nantes_300421', 512, 512, 'learn_papier_nantes_300421', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 30, 17, 9, 41), datetime.datetime(2021, 4, 30, 17, 9, 41)) To loadFromThcl() : net_5288 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 9917 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5288, 'learn_papier_nantes_300421', 512, 512, 'learn_papier_nantes_300421', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 30, 17, 9, 41), datetime.datetime(2021, 4, 30, 17, 9, 41)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_papier_nantes_300421 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_papier_nantes_300421 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_papier_nantes_300421 /data/models_weight/learn_papier_nantes_300421/caffemodel size_local : 44791983 size in s3 : 44791983 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:13 caffemodel already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/deploy.prototxt size_local : 17255 size in s3 : 17255 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:12 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:14 mean.npy already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/synset_words.txt size_local : 331 size in s3 : 331 create time local : 2021-08-09 05:56:00 create time in s3 : 2021-08-06 19:22:12 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_papier_nantes_300421/deploy.prototxt caffemodel_filename : /data/models_weight/learn_papier_nantes_300421/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 9917 max_wait_temp : 1 max_wait : 0 dict_keys(['prob']) time used to do the prepocess of the images : 0.2740175724029541 time used to do the prediction : 0.09251141548156738 we don't save the descriptors for this thcl 2868 Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos test new format of the output of the step_thcl begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 0 time used for this insertion : 1.0251998901367188e-05 save missing photos in datou_result : time spend for datou_step_exec : 8.085174798965454 time spend to save output : 0.0003185272216796875 total time spend for step 3 : 8.085493326187134 step4:merge_mask_thcl_custom Wed Oct 1 08:48:20 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 1 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step merge_mask_thcl_custom batch 1 Loaded 56 chid ids of type : 3663 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++As expected we have just one thcl present End of step merge_mask_thcl_custom Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : merge_mask_thcl_custom we use saveGeneral [1387083785, 1387083672, 1387083669, 1387083666] Looping around the photos to save general results len do output : 4 /1387083785Didn't retrieve data .Didn't retrieve data . /1387083672Didn't retrieve data .Didn't retrieve data . /1387083669Didn't retrieve data .Didn't retrieve data . /1387083666Didn'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 : Managing all output in save final without adding information in the mtr_datou_result ('4877', None, None, None, None, None, None, None, '3804210') ('4877', '27391869', '1387083785', None, None, None, None, None, '3804210') ('4877', None, None, None, None, None, None, None, '3804210') ('4877', '27391869', '1387083672', None, None, None, None, None, '3804210') ('4877', None, None, None, None, None, None, None, '3804210') ('4877', '27391869', '1387083669', None, None, None, None, None, '3804210') ('4877', None, None, None, None, None, None, None, '3804210') ('4877', '27391869', '1387083666', None, None, None, None, None, '3804210') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.0369112491607666 Command terminated by signal 15 27.01user 19.66system 0:48.99elapsed 95%CPU (0avgtext+0avgdata 2663868maxresident)k 154568inputs+7880outputs (406major+1258513minor)pagefaults 0swaps