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 3910988' -s traitement_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 : 4075019 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 : ['3910988'] with mtr_portfolio_ids : ['27666880'] and first list_photo_ids : [] new path : /proc/4075019/ 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 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.34398341178894043 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 Fri Oct 10 09:09:09 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 : 7216 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-10-10 09:09:11.966989: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-10-10 09:09:11.990506: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-10-10 09:09:11.992039: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f7e2c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-10-10 09:09:11.992085: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-10-10 09:09:11.994573: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-10-10 09:09:12.109058: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x10c09a50 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-10-10 09:09:12.109093: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-10-10 09:09:12.109846: 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 2025-10-10 09:09:12.110117: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:09:12.112126: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:09:12.114065: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:09:12.114384: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:09:12.116417: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:09:12.117363: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:09:12.121457: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:09:12.122688: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:09:12.122757: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:09:12.123392: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-10 09:09:12.123407: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-10 09:09:12.123416: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-10 09:09:12.124485: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6640 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. 2025-10-10 09:09:12.532785: 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 2025-10-10 09:09:12.532898: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:09:12.532914: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:09:12.532928: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:09:12.532957: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:09:12.532971: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:09:12.532983: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:09:12.532997: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:09:12.533980: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:09:12.535136: 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 2025-10-10 09:09:12.535170: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:09:12.535185: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:09:12.535199: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:09:12.535212: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:09:12.535226: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:09:12.535240: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:09:12.535253: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:09:12.536247: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:09:12.536280: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-10 09:09:12.536288: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-10 09:09:12.536295: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-10 09:09:12.537319: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6640 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 : [] 2025-10-10 09:09:18.770628: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:09:18.929005: 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 : 2 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 : 3 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 : 3 Detection mask done ! Trying to reset tf kernel 4075744 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1927 tf kernel not reseted sub process len(results) : 2 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 2 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 : 7216 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 : 0.014140605926513672 nb_pixel_total : 1022401 time to create 1 rle with new method : 0.031033992767333984 length of segment : 1767 time for calcul the mask position with numpy : 0.0016155242919921875 nb_pixel_total : 121086 time to create 1 rle with old method : 0.13038277626037598 length of segment : 358 time for calcul the mask position with numpy : 0.013489961624145508 nb_pixel_total : 1032992 time to create 1 rle with new method : 0.023847103118896484 length of segment : 1770 time for calcul the mask position with numpy : 0.0020072460174560547 nb_pixel_total : 121092 time to create 1 rle with old method : 0.18918061256408691 length of segment : 357 time spent for convertir_results : 1.6596002578735352 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 4 chid ids of type : 3663 Number RLEs to save : 4252 save missing photos in datou_result : time spend for datou_step_exec : 17.06851363182068 time spend to save output : 0.6328549385070801 total time spend for step 1 : 17.70136857032776 step2:crop_condition Fri Oct 10 09:09:26 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : 2 ! batch 1 Loaded 4 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 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 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 begin to crop the class : cartonnette param for this class : {'min_score': 0.5} filtre for class : cartonnette hashtag_id of this class : 702398920 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 begin to crop the class : plastique param for this class : {'min_score': 0.5} filtre for class : plastique hashtag_id of this class : 492725882 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 [1388569600, 1388569399] Looping around the photos to save general results len do output : 0 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, '3910988') ('4877', '27666880', '1388569600', None, None, None, None, None, '3910988') ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569399', None, None, None, None, None, '3910988') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.03734254837036133 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.3701655864715576 time spend to save output : 0.037543535232543945 total time spend for step 2 : 0.40770912170410156 step3:thcl Fri Oct 10 09:09:27 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure No keys ! Beginning of datou step Thcl ! no input Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos [1388569600, 1388569399] Looping around the photos to save general results len do output : 0 before output type Managing all output in save final without adding information in the mtr_datou_result ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569600', None, None, None, None, None, '3910988') ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569399', None, None, None, None, None, '3910988') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.03833508491516113 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.1460094451904297 time spend to save output : 0.03847551345825195 total time spend for step 3 : 0.18448495864868164 step4:merge_mask_thcl_custom Fri Oct 10 09:09:27 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 4 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 [1388569600, 1388569399] Looping around the photos to save general results len do output : 2 /1388569600Didn't retrieve data .Didn't retrieve data . /1388569399Didn'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, '3910988') ('4877', '27666880', '1388569600', None, None, None, None, None, '3910988') ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569399', None, None, None, None, None, '3910988') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.03691434860229492 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.17388343811035156 time spend to save output : 0.0371394157409668 total time spend for step 4 : 0.21102285385131836 step5:rle_unique_nms_with_priority Fri Oct 10 09:09:27 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms nb_obj : 2 nb_hashtags : 1 time to prepare the origin masks : 0.1748337745666504 time for calcul the mask position with numpy : 0.011458396911621094 nb_pixel_total : 721499 time to create 1 rle with new method : 0.03927946090698242 time for calcul the mask position with numpy : 0.006447315216064453 nb_pixel_total : 18942 time to create 1 rle with old method : 0.023325443267822266 time for calcul the mask position with numpy : 0.014624357223510742 nb_pixel_total : 1022119 time to create 1 rle with new method : 0.03730463981628418 create new chi : 0.14223980903625488 time to delete rle : 0.15389227867126465 batch 1 Loaded 3 chid ids of type : 3726 Number RLEs to save : 4701 TO DO : save crop sub photo not yet done ! save time : 0.599461555480957 nb_obj : 2 nb_hashtags : 1 time to prepare the origin masks : 0.17719173431396484 time for calcul the mask position with numpy : 0.01172947883605957 nb_pixel_total : 712440 time to create 1 rle with new method : 0.041826725006103516 time for calcul the mask position with numpy : 0.005270719528198242 nb_pixel_total : 19266 time to create 1 rle with old method : 0.02103567123413086 time for calcul the mask position with numpy : 0.013410806655883789 nb_pixel_total : 1030854 time to create 1 rle with new method : 0.030694961547851562 create new chi : 0.13064932823181152 time to delete rle : 0.00042748451232910156 batch 1 Loaded 3 chid ids of type : 3726 Number RLEs to save : 4780 TO DO : save crop sub photo not yet done ! save time : 0.597930908203125 map_output_result : {1388569600: (0.0, 'Should be the crop_list due to order', 0.0), 1388569399: (0.0, 'Should be the crop_list due to order', 0.0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1388569600, 1388569399] Looping around the photos to save general results len do output : 2 /1388569600.Didn't retrieve data . /1388569399.Didn't retrieve data . before output type Used above Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569600', None, None, None, None, None, '3910988') ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569399', None, None, None, None, None, '3910988') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.03713250160217285 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.09576678276062 time spend to save output : 0.037431955337524414 total time spend for step 5 : 2.1331987380981445 step6:crop_condition Fri Oct 10 09:09:29 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 every photo are already treated, don't need to treat again Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')' at line 1") no crop found some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 3726 Loading chi in step crop for list_pids : 2 ! batch 1 Loaded 6 chid ids of type : 3726 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 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 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 begin to crop the class : cartonnette param for this class : {'min_score': 0.5} filtre for class : cartonnette hashtag_id of this class : 702398920 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 begin to crop the class : plastique param for this class : {'min_score': 0.5} filtre for class : plastique hashtag_id of this class : 492725882 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 [1388569600, 1388569399] Looping around the photos to save general results len do output : 0 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, '3910988') ('4877', '27666880', '1388569600', None, None, None, None, None, '3910988') ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569399', None, None, None, None, None, '3910988') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.03620600700378418 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.9159190654754639 time spend to save output : 0.03637075424194336 total time spend for step 6 : 0.9522898197174072 step7:ventilate_hashtags_in_portfolio Fri Oct 10 09:09:30 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 ! VR 22-3-18 : For now we do not clean correctly the datou structure beginning of datou step ventilate_hashtags_in_portfolio : To implement ! To do loadFromThcl(), then load ParamDescType : thcl2725 thcls : [{'id': 2725, 'mtr_user_id': 31, 'name': 'learn_qualipapia_rle_210302_2', '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': '3460440,3460441,3460446,3460434,3460439,3467416,3460442,3460443,3486028,3460445', 'photo_hashtag_type': 3410, 'photo_desc_type': 5186, 'type_classification': 'caffe', 'hashtag_id_list': '2107753024,2107753020,2107752385,2107752406,702398920,493012381,493202403,492628673,492668766,492725882'}] thcl {'id': 2725, 'mtr_user_id': 31, 'name': 'learn_qualipapia_rle_210302_2', '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': '3460440,3460441,3460446,3460434,3460439,3467416,3460442,3460443,3486028,3460445', 'photo_hashtag_type': 3410, 'photo_desc_type': 5186, 'type_classification': 'caffe', 'hashtag_id_list': '2107753024,2107753020,2107752385,2107752406,702398920,493012381,493202403,492628673,492668766,492725882'} Update svm_hashtag_type_desc : 5186 Iterating over portfolio : 27666880 get user id for portfolio 27666880 SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=27666880 AND mptpi.`type`=3726 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Teint_Dans_La_Masse','flou','autre_refus','plastique','environnement','mal_croppe','Carton_gris','kraft','metal','papier','cartonnette','Carton_brun')) AND mptpi.`min_score`=0.5 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=27666880 AND mptpi.`type`=3726 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Teint_Dans_La_Masse','flou','autre_refus','plastique','environnement','mal_croppe','Carton_gris','kraft','metal','papier','cartonnette','Carton_brun')) AND mptpi.`min_score`=0.5 To do To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=27666880 AND mptpi.`type`=4417 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Teint_Dans_La_Masse','flou','autre_refus','plastique','environnement','mal_croppe','Carton_gris','kraft','metal','papier','cartonnette','Carton_brun')) AND mptpi.`min_score`=0.5 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=27666880 AND mptpi.`type`=4417 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Teint_Dans_La_Masse','flou','autre_refus','plastique','environnement','mal_croppe','Carton_gris','kraft','metal','papier','cartonnette','Carton_brun')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://marlene.fotonower.com/velours/27684052,27684053,27684054,27684055,27684056,27684057,27684058,27684059,27684060,27684061,27684063,27684064?tags=Teint_Dans_La_Masse,flou,autre_refus,plastique,environnement,mal_croppe,Carton_gris,kraft,metal,papier,cartonnette,Carton_brun Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1388569600, 1388569399] Looping around the photos to save general results len do output : 1 /27666880. before output type 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, '3910988') ('4877', '27666880', '1388569600', None, None, None, None, None, '3910988') ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569399', None, None, None, None, None, '3910988') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.03653526306152344 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.4724645614624023 time spend to save output : 0.0367434024810791 total time spend for step 7 : 3.5092079639434814 step8:tfhub_classification2 Fri Oct 10 09:09:34 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 TFHub with tf2 ! nombre de thcls : 3 we are using the classfication for multi_thcl [3513, 3379, 3847] begin to check gpu status inside check gpu memory 2025-10-10 09:09:36.811145: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-10-10 09:09:36.862489: 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 2025-10-10 09:09:36.862761: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:09:36.864608: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:09:36.866207: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:09:36.866504: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:09:36.868382: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:09:36.869309: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:09:36.873229: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:09:36.874660: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:09:36.875041: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-10-10 09:09:36.902478: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-10-10 09:09:36.904112: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f7d6c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-10-10 09:09:36.904147: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-10-10 09:09:37.164670: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x11c04c30 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-10-10 09:09:37.164734: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-10-10 09:09:37.166500: 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 2025-10-10 09:09:37.166651: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:09:37.166689: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:09:37.166724: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:09:37.166757: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:09:37.166791: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:09:37.166824: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:09:37.166858: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:09:37.169254: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:09:37.169403: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:09:37.170696: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-10 09:09:37.170732: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-10 09:09:37.170746: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-10 09:09:37.173252: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3096 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) l 3637 free memory gpu now : 10998 max_wait_temp : 1 max_wait : 5 1 Physical GPUs, 1 Logical GPUs tagging for thcl : 3513 To do loadFromThcl(), then load ParamDescType : thcl3513 thcls : [{'id': 3513, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2_tf', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 4557, 'photo_desc_type': 5767, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] thcl {'id': 3513, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2_tf', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 4557, 'photo_desc_type': 5767, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'} Update svm_hashtag_type_desc : 5767 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5767, 'Rungis_amount_dechets_fall_2018_v2_tf', 2048, 2048, 'Rungis_amount_dechets_fall_2018_v2_tf', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 3, 16, 15, 52, 10), datetime.datetime(2023, 3, 16, 15, 52, 10)) model_name : Rungis_amount_dechets_fall_2018_v2_tf model_param file didn't exist model_name : Rungis_amount_dechets_fall_2018_v2_tf model_type : tf_classification2 list file need : ['Confusion_Matrix.png', 'Precision_Recall_05102018_Papier_non_papier_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_peu_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_presque_vide.jpg', 'Precision_Recall_05102018_Papier_non_papier_tres_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_tres_peu_dense.jpg', 'Result_Summary.txt', 'checkpoint', 'model_checkpoint.ckpt.data-00000-of-00001', 'model_checkpoint.ckpt.data-00000-of-00002', 'model_checkpoint.ckpt.data-00001-of-00002', 'model_checkpoint.ckpt.index', 'model_weights.h5'] file exist in s3 : ['Confusion_Matrix.png', 'Precision_Recall_05102018_Papier_non_papier_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_peu_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_presque_vide.jpg', 'Precision_Recall_05102018_Papier_non_papier_tres_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_tres_peu_dense.jpg', 'Result_Summary.txt', 'checkpoint', 'model_checkpoint.ckpt.data-00000-of-00001', 'model_checkpoint.ckpt.data-00000-of-00002', 'model_checkpoint.ckpt.data-00001-of-00002', 'model_checkpoint.ckpt.index', 'model_weights.h5'] file manque in s3 : [] local folder : /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Confusion_Matrix.png size_local : 67810 size in s3 : 67810 create time local : 2023-10-30 16:21:37 create time in s3 : 2023-10-30 14:09:29 Confusion_Matrix.png already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_dense.jpg size_local : 73949 size in s3 : 73949 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:30 Precision_Recall_05102018_Papier_non_papier_dense.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_peu_dense.jpg size_local : 85572 size in s3 : 85572 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:39 Precision_Recall_05102018_Papier_non_papier_peu_dense.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_presque_vide.jpg size_local : 72361 size in s3 : 72361 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:37 Precision_Recall_05102018_Papier_non_papier_presque_vide.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_tres_dense.jpg size_local : 83567 size in s3 : 83567 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:48 Precision_Recall_05102018_Papier_non_papier_tres_dense.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_tres_peu_dense.jpg size_local : 71611 size in s3 : 71611 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:29 Precision_Recall_05102018_Papier_non_papier_tres_peu_dense.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Result_Summary.txt size_local : 1058 size in s3 : 1058 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:30 Result_Summary.txt already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/checkpoint size_local : 99 size in s3 : 99 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:36 checkpoint already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_checkpoint.ckpt.data-00000-of-00001 size_local : 188538519 size in s3 : 188538519 create time local : 2023-10-30 16:21:41 create time in s3 : 2023-10-30 14:09:40 model_checkpoint.ckpt.data-00000-of-00001 already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_checkpoint.ckpt.data-00000-of-00002 size_local : 216572 size in s3 : 216572 create time local : 2023-10-30 16:21:41 create time in s3 : 2023-03-16 14:52:09 model_checkpoint.ckpt.data-00000-of-00002 already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_checkpoint.ckpt.data-00001-of-00002 size_local : 32279708 size in s3 : 32279708 create time local : 2023-10-30 16:21:42 create time in s3 : 2023-03-16 14:52:07 model_checkpoint.ckpt.data-00001-of-00002 already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_checkpoint.ckpt.index size_local : 28001 size in s3 : 28001 create time local : 2023-10-30 16:21:42 create time in s3 : 2023-10-30 14:09:30 model_checkpoint.ckpt.index already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_weights.h5 size_local : 94501976 size in s3 : 94501976 create time local : 2023-10-30 16:21:44 create time in s3 : 2023-10-30 14:09:37 model_weights.h5 already exist and didn't need to update desc size : 2048 Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= module (KerasLayer) (None, 2048) 23561152 _________________________________________________________________ Rungis_amount_dechets_fall_2 (None, 5) 10245 ================================================================= Total params: 23,571,397 Trainable params: 10,245 Non-trainable params: 23,561,152 _________________________________________________________________ Loading Weights... time used to create the model : 7.200063467025757 time used to load_weights : 0.12804841995239258 0it [00:00, ?it/s] 2it [00:00, 3749.94it/s]2025-10-10 09:09:46.330141: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:09:46.508168: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 temp/1760080148_4075019_1388569600_975212c891b7bf32e112f412595542fb.jpg temp/1760080148_4075019_1388569399_4493a71f0993213fff64940a147323a3.jpg Found 2 images belonging to 1 classes. begin to do the prediction : time used to do the prediction : 2.1212785243988037 (2,) (2, 5) (2, 2048) shape of features : (2, 2048) shape of new features : (1, 2, 2048) save descriptor for thcl : 3513 time to traite the descriptors : 0.02424335479736328 storage_type for insertDescriptorsMulti : 3 To insert : 1388569600 To insert : 1388569399 Catched exception ! Connect or reconnect ! time to insert the descriptors : 2.0772545337677 tagging for thcl : 3379 To do loadFromThcl(), then load ParamDescType : thcl3379 thcls : [{'id': 3379, 'mtr_user_id': 31, 'name': 'learn_classif_flux_maj_generique_effnet_v2_s_02062022', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'aluminium,ela,film_pedb,flux_dev,jrm,pcm,pcnc,pehd_pp,pet_clair,refus,tapis_vide', 'svm_portfolios_learning': '5515864,5515840,5515844,5515850,6244400,6237996,6237998,5515847,5515841,5515868,5515866', 'photo_hashtag_type': 4374, 'photo_desc_type': 5680, 'type_classification': 'tf_classification2', 'hashtag_id_list': '493546845,492741797,2107760237,2107760238,495916461,560181804,1284539308,2107760239,2107755846,538914404,2107748999'}] thcl {'id': 3379, 'mtr_user_id': 31, 'name': 'learn_classif_flux_maj_generique_effnet_v2_s_02062022', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'aluminium,ela,film_pedb,flux_dev,jrm,pcm,pcnc,pehd_pp,pet_clair,refus,tapis_vide', 'svm_portfolios_learning': '5515864,5515840,5515844,5515850,6244400,6237996,6237998,5515847,5515841,5515868,5515866', 'photo_hashtag_type': 4374, 'photo_desc_type': 5680, 'type_classification': 'tf_classification2', 'hashtag_id_list': '493546845,492741797,2107760237,2107760238,495916461,560181804,1284539308,2107760239,2107755846,538914404,2107748999'} Update svm_hashtag_type_desc : 5680 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5680, 'learn_classif_flux_maj_generique_effnet_v2_s_02062022', 1280, 1280, 'learn_classif_flux_maj_generique_effnet_v2_s_02062022', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2022, 6, 4, 1, 31, 10), datetime.datetime(2022, 6, 4, 1, 31, 10)) model_name : learn_classif_flux_maj_generique_effnet_v2_s_02062022 model_param file didn't exist model_name : learn_classif_flux_maj_generique_effnet_v2_s_02062022 model_type : tf_classification2 list file need : ['Confusion_Matrix.png', 'Precision_Recall_aluminium.jpg', 'Precision_Recall_ela.jpg', 'Precision_Recall_film_pedb.jpg', 'Precision_Recall_flux_dev.jpg', 'Precision_Recall_jrm.jpg', 'Precision_Recall_pcm.jpg', 'Precision_Recall_pcnc.jpg', 'Precision_Recall_pehd_pp.jpg', 'Precision_Recall_pet_clair.jpg', 'Precision_Recall_refus.jpg', 'Precision_Recall_tapis_vide.jpg', 'Result_Summary.txt', 'checkpoint', 'model_checkpoint.ckpt.data-00000-of-00002', 'model_checkpoint.ckpt.data-00001-of-00002', 'model_checkpoint.ckpt.index', 'model_weights.h5'] file exist in s3 : ['Confusion_Matrix.png', 'Precision_Recall_aluminium.jpg', 'Precision_Recall_ela.jpg', 'Precision_Recall_film_pedb.jpg', 'Precision_Recall_flux_dev.jpg', 'Precision_Recall_jrm.jpg', 'Precision_Recall_pcm.jpg', 'Precision_Recall_pcnc.jpg', 'Precision_Recall_pehd_pp.jpg', 'Precision_Recall_pet_clair.jpg', 'Precision_Recall_refus.jpg', 'Precision_Recall_tapis_vide.jpg', 'Result_Summary.txt', 'checkpoint', 'model_checkpoint.ckpt.data-00000-of-00002', 'model_checkpoint.ckpt.data-00001-of-00002', 'model_checkpoint.ckpt.index', 'model_weights.h5'] file manque in s3 : [] local folder : /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022 /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Confusion_Matrix.png size_local : 82527 size in s3 : 82527 create time local : 2022-06-06 13:01:24 create time in s3 : 2022-06-03 23:31:09 Confusion_Matrix.png already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_aluminium.jpg size_local : 67602 size in s3 : 67602 create time local : 2022-06-06 13:01:24 create time in s3 : 2022-06-03 23:23:41 Precision_Recall_aluminium.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_ela.jpg size_local : 67189 size in s3 : 67189 create time local : 2022-06-06 13:01:25 create time in s3 : 2022-06-03 23:26:13 Precision_Recall_ela.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_film_pedb.jpg size_local : 71280 size in s3 : 71280 create time local : 2022-06-06 13:01:25 create time in s3 : 2022-06-03 23:26:14 Precision_Recall_film_pedb.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_flux_dev.jpg size_local : 59936 size in s3 : 59936 create time local : 2022-06-06 13:01:25 create time in s3 : 2022-06-03 23:23:41 Precision_Recall_flux_dev.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_jrm.jpg size_local : 67657 size in s3 : 67657 create time local : 2022-06-06 13:01:25 create time in s3 : 2022-06-03 23:31:06 Precision_Recall_jrm.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_pcm.jpg size_local : 83042 size in s3 : 83042 create time local : 2022-06-06 13:01:25 create time in s3 : 2022-06-03 23:23:40 Precision_Recall_pcm.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_pcnc.jpg size_local : 69972 size in s3 : 69972 create time local : 2022-06-06 13:01:27 create time in s3 : 2022-06-03 23:31:05 Precision_Recall_pcnc.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_pehd_pp.jpg size_local : 67313 size in s3 : 67313 create time local : 2022-06-06 13:01:27 create time in s3 : 2022-06-03 23:23:45 Precision_Recall_pehd_pp.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_pet_clair.jpg size_local : 67320 size in s3 : 67320 create time local : 2022-06-06 13:01:27 create time in s3 : 2022-06-03 23:31:04 Precision_Recall_pet_clair.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_refus.jpg size_local : 59936 size in s3 : 59936 create time local : 2022-06-06 13:01:27 create time in s3 : 2022-06-03 23:31:08 Precision_Recall_refus.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Precision_Recall_tapis_vide.jpg size_local : 80244 size in s3 : 80244 create time local : 2022-06-06 13:01:27 create time in s3 : 2022-06-03 23:23:45 Precision_Recall_tapis_vide.jpg already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/Result_Summary.txt size_local : 1018 size in s3 : 1018 create time local : 2022-06-06 13:01:27 create time in s3 : 2022-06-03 23:31:08 Result_Summary.txt already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/checkpoint size_local : 99 size in s3 : 99 create time local : 2022-06-06 13:01:27 create time in s3 : 2022-06-03 23:31:06 checkpoint already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/model_checkpoint.ckpt.data-00000-of-00002 size_local : 216640 size in s3 : 216640 create time local : 2022-06-06 13:01:27 create time in s3 : 2022-06-03 23:23:43 model_checkpoint.ckpt.data-00000-of-00002 already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/model_checkpoint.ckpt.data-00001-of-00002 size_local : 32341196 size in s3 : 32341196 create time local : 2022-06-06 13:01:28 create time in s3 : 2022-06-03 23:26:15 model_checkpoint.ckpt.data-00001-of-00002 already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/model_checkpoint.ckpt.index size_local : 43546 size in s3 : 43546 create time local : 2022-06-06 13:01:28 create time in s3 : 2022-06-03 23:26:13 model_checkpoint.ckpt.index already exist and didn't need to update /data/models_weight/learn_classif_flux_maj_generique_effnet_v2_s_02062022/model_weights.h5 size_local : 16531224 size in s3 : 16531224 create time local : 2022-06-06 13:01:29 create time in s3 : 2022-06-03 23:23:46 model_weights.h5 already exist and didn't need to update desc size : 1280 Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= module (KerasLayer) (None, 1280) 4049564 _________________________________________________________________ learn_classif_flux_maj_gener (None, 11) 14091 ================================================================= Total params: 4,063,655 Trainable params: 14,091 Non-trainable params: 4,049,564 _________________________________________________________________ Loading Weights... time used to create the model : 6.735360622406006 time used to load_weights : 0.11209654808044434 0it [00:00, ?it/s] 2it [00:00, 3898.05it/s]temp/1760080148_4075019_1388569600_975212c891b7bf32e112f412595542fb.jpg temp/1760080148_4075019_1388569399_4493a71f0993213fff64940a147323a3.jpg Found 2 images belonging to 1 classes. begin to do the prediction : time used to do the prediction : 0.9667067527770996 (2,) (2, 11) (2, 1280) shape of features : (2, 1280) shape of new features : (1, 2, 1280) save descriptor for thcl : 3379 time to traite the descriptors : 0.029922008514404297 storage_type for insertDescriptorsMulti : 3 To insert : 1388569600 To insert : 1388569399 time to insert the descriptors : 0.8198120594024658 tagging for thcl : 3847 To do loadFromThcl(), then load ParamDescType : thcl3847 thcls : [{'id': 3847, 'mtr_user_id': 31, 'name': 'learn_MM_generique_050224', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'aluminium,ela,emr,film_pedb,flux_dev,jrm,pcm,pcnc,pehd_pp,pet_clair,refus,tapis_vide', 'svm_portfolios_learning': '13096157,13096155,13096163,13096159,13301956,13095886,13096162,13096160,13358264,13096158,5515868,13276803', 'photo_hashtag_type': 4932, 'photo_desc_type': 6032, 'type_classification': 'tf_classification2', 'hashtag_id_list': '493546845,492741797,616987804,2107760237,2107760238,495916461,560181804,1284539308,2107760239,2107755846,538914404,2107748999'}] thcl {'id': 3847, 'mtr_user_id': 31, 'name': 'learn_MM_generique_050224', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'aluminium,ela,emr,film_pedb,flux_dev,jrm,pcm,pcnc,pehd_pp,pet_clair,refus,tapis_vide', 'svm_portfolios_learning': '13096157,13096155,13096163,13096159,13301956,13095886,13096162,13096160,13358264,13096158,5515868,13276803', 'photo_hashtag_type': 4932, 'photo_desc_type': 6032, 'type_classification': 'tf_classification2', 'hashtag_id_list': '493546845,492741797,616987804,2107760237,2107760238,495916461,560181804,1284539308,2107760239,2107755846,538914404,2107748999'} Update svm_hashtag_type_desc : 6032 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (6032, 'learn_MM_generique_050224', 1280, 1280, 'learn_MM_generique_050224', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2024, 2, 5, 21, 42, 4), datetime.datetime(2024, 2, 5, 21, 42, 4)) model_name : learn_MM_generique_050224 model_param file didn't exist model_name : learn_MM_generique_050224 model_type : tf_classification2 list file need : ['Confusion_Matrix.png', 'Precision_Recall_aluminium.jpg', 'Precision_Recall_ela.jpg', 'Precision_Recall_emr.jpg', 'Precision_Recall_film_pedb.jpg', 'Precision_Recall_flux_dev.jpg', 'Precision_Recall_jrm.jpg', 'Precision_Recall_pcm.jpg', 'Precision_Recall_pcnc.jpg', 'Precision_Recall_pehd_pp.jpg', 'Precision_Recall_pet_clair.jpg', 'Precision_Recall_refus.jpg', 'Precision_Recall_tapis_vide.jpg', 'Result_Summary.txt', 'checkpoint', 'model_checkpoint.ckpt.data-00000-of-00001', 'model_checkpoint.ckpt.index', 'model_weights.h5'] file exist in s3 : ['Confusion_Matrix.png', 'Precision_Recall_aluminium.jpg', 'Precision_Recall_ela.jpg', 'Precision_Recall_emr.jpg', 'Precision_Recall_film_pedb.jpg', 'Precision_Recall_flux_dev.jpg', 'Precision_Recall_jrm.jpg', 'Precision_Recall_pcm.jpg', 'Precision_Recall_pcnc.jpg', 'Precision_Recall_pehd_pp.jpg', 'Precision_Recall_pet_clair.jpg', 'Precision_Recall_refus.jpg', 'Precision_Recall_tapis_vide.jpg', 'Result_Summary.txt', 'checkpoint', 'model_checkpoint.ckpt.data-00000-of-00001', 'model_checkpoint.ckpt.index', 'model_weights.h5'] file manque in s3 : [] local folder : /data/models_weight/learn_MM_generique_050224 /data/models_weight/learn_MM_generique_050224/Confusion_Matrix.png size_local : 88145 size in s3 : 88145 create time local : 2024-04-08 09:17:48 create time in s3 : 2024-02-05 20:41:54 Confusion_Matrix.png already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_aluminium.jpg size_local : 67983 size in s3 : 67983 create time local : 2024-04-08 09:17:48 create time in s3 : 2024-02-05 20:42:02 Precision_Recall_aluminium.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_ela.jpg size_local : 68484 size in s3 : 68484 create time local : 2024-04-08 09:17:48 create time in s3 : 2024-02-05 20:42:04 Precision_Recall_ela.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_emr.jpg size_local : 77930 size in s3 : 77930 create time local : 2024-04-08 09:17:48 create time in s3 : 2024-02-05 20:41:55 Precision_Recall_emr.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_film_pedb.jpg size_local : 66701 size in s3 : 66701 create time local : 2024-04-08 09:17:48 create time in s3 : 2024-02-05 20:41:55 Precision_Recall_film_pedb.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_flux_dev.jpg size_local : 59936 size in s3 : 59936 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:42:04 Precision_Recall_flux_dev.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_jrm.jpg size_local : 72890 size in s3 : 72890 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:42:04 Precision_Recall_jrm.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_pcm.jpg size_local : 93916 size in s3 : 93916 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:42:02 Precision_Recall_pcm.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_pcnc.jpg size_local : 74701 size in s3 : 74701 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:42:04 Precision_Recall_pcnc.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_pehd_pp.jpg size_local : 68765 size in s3 : 68765 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:42:03 Precision_Recall_pehd_pp.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_pet_clair.jpg size_local : 69649 size in s3 : 69649 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:42:03 Precision_Recall_pet_clair.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_refus.jpg size_local : 59936 size in s3 : 59936 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:41:59 Precision_Recall_refus.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Precision_Recall_tapis_vide.jpg size_local : 71529 size in s3 : 71529 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:41:54 Precision_Recall_tapis_vide.jpg already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/Result_Summary.txt size_local : 1076 size in s3 : 1076 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:41:55 Result_Summary.txt already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/checkpoint size_local : 99 size in s3 : 99 create time local : 2024-04-08 09:17:49 create time in s3 : 2024-02-05 20:42:00 checkpoint already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/model_checkpoint.ckpt.data-00000-of-00001 size_local : 32591049 size in s3 : 32591049 create time local : 2024-04-08 09:17:50 create time in s3 : 2024-02-05 20:42:02 model_checkpoint.ckpt.data-00000-of-00001 already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/model_checkpoint.ckpt.index size_local : 42495 size in s3 : 42495 create time local : 2024-04-08 09:17:50 create time in s3 : 2024-02-05 20:41:55 model_checkpoint.ckpt.index already exist and didn't need to update /data/models_weight/learn_MM_generique_050224/model_weights.h5 size_local : 16536200 size in s3 : 16536200 create time local : 2024-04-08 09:17:50 create time in s3 : 2024-02-05 20:42:00 model_weights.h5 already exist and didn't need to update desc size : 1280 Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= module (KerasLayer) (None, 1280) 4049564 _________________________________________________________________ learn_MM_generique_050224den (None, 12) 15372 ================================================================= Total params: 4,064,936 Trainable params: 15,372 Non-trainable params: 4,049,564 _________________________________________________________________ Loading Weights... time used to create the model : 7.04290771484375 time used to load_weights : 0.11216115951538086 0it [00:00, ?it/s] 2it [00:00, 3429.52it/s]temp/1760080148_4075019_1388569600_975212c891b7bf32e112f412595542fb.jpg temp/1760080148_4075019_1388569399_4493a71f0993213fff64940a147323a3.jpg Found 2 images belonging to 1 classes. begin to do the prediction : time used to do the prediction : 0.8387317657470703 (2,) (2, 12) (2, 1280) shape of features : (2, 1280) shape of new features : (1, 2, 1280) save descriptor for thcl : 3847 time to traite the descriptors : 0.041306495666503906 storage_type for insertDescriptorsMulti : 3 To insert : 1388569600 To insert : 1388569399 time to insert the descriptors : 1.1916468143463135 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : tfhub_classification2 we use saveGeneral [1388569600, 1388569399] Looping around the photos to save general results len do output : 2 /1388569600Didn't retrieve data . /1388569399Didn't retrieve data . before output type 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, '3910988') ('4877', '27666880', '1388569600', None, None, None, None, None, '3910988') ('4877', None, None, None, None, None, None, None, '3910988') ('4877', '27666880', '1388569399', None, None, None, None, None, '3910988') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.03474855422973633 save_final save missing photos in datou_result : time spend for datou_step_exec : 37.92538094520569 time spend to save output : 0.034951210021972656 total time spend for step 8 : 37.96033215522766 step9:argmax Fri Oct 10 09:10:12 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 Argmax ! Inside saveOutput : final : True verbose : 0 photo_id : 1388569600 output[photo_id] : [[(1388569600, '05102018_Papier_non_papier_presque_vide', 0.33165148, 4557, 3513), (1388569600, 'jrm', 0.3161899, 4374, 3379), (1388569600, 'tapis_vide', 0.42020315, 4932, 3847)], 'temp/1760080148_4075019_1388569600_975212c891b7bf32e112f412595542fb.jpg'] photo_id : 1388569399 output[photo_id] : [[(1388569399, '05102018_Papier_non_papier_presque_vide', 0.3315066, 4557, 3513), (1388569399, 'jrm', 0.31631353, 4374, 3379), (1388569399, 'tapis_vide', 0.42033798, 4932, 3847)], 'temp/1760080148_4075019_1388569399_4493a71f0993213fff64940a147323a3.jpg'] begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 6 time used for this insertion : 0.03577566146850586 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 6 time used for this insertion : 0.036826133728027344 len list_finale : 6, len picture : 2 begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.03704690933227539 saving photo_ids in datou_result begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.03519392013549805 save missing photos in datou_result : time spend for datou_step_exec : 0.01710987091064453 time spend to save output : 0.19560956954956055 total time spend for step 9 : 0.21271944046020508 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 2 set_done_treatment 41.40user 11.73system 1:08.33elapsed 77%CPU (0avgtext+0avgdata 2865356maxresident)k 16inputs+3176outputs (14major+2034140minor)pagefaults 0swaps