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 3911023' -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 : 4112958 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 : ['3911023'] with mtr_portfolio_ids : ['27666953'] and first list_photo_ids : [] new path : /proc/4112958/ 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 , BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 0.848353385925293 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 09:23:57 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 : 10998 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-10-10 09:24:00.142403: 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 09:24:00.166390: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-10-10 09:24:00.167830: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f8564000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-10-10 09:24:00.167884: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-10-10 09:24:00.171279: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-10-10 09:24:00.470236: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x6e48b30 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-10-10 09:24:00.470293: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-10-10 09:24:00.471646: 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 09:24:00.472009: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:24:00.474862: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:24:00.477336: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:24:00.477792: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:24:00.480264: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:24:00.481153: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:24:00.484992: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:24:00.486363: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:24:00.486412: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:24:00.487130: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-10 09:24:00.487144: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-10 09:24:00.487152: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-10 09:24:00.488428: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 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 09:24:00.884978: 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 09:24:00.885058: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:24:00.885079: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:24:00.885098: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:24:00.885130: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:24:00.885148: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:24:00.885166: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:24:00.885184: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:24:00.886785: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:24:00.888217: 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 09:24:00.888250: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:24:00.888269: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:24:00.888287: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:24:00.888304: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:24:00.888321: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:24:00.888338: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:24:00.888355: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:24:00.889927: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:24:00.889963: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-10 09:24:00.889974: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-10 09:24:00.889983: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-10 09:24:00.891661: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 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 09:24:07.295067: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:24:07.451363: 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 : 5 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 : 11 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: 143.83868 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 11 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: 146.07264 image_metas shape: (1, 18) min: 0.00000 max: 1632.00000 nb d'objets trouves : 10 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 : 13 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 Detection mask done ! Trying to reset tf kernel 4113060 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5706 tf kernel not reseted sub process len(results) : 5 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 5 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 : 10998 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 : 0.0002810955047607422 nb_pixel_total : 8945 time to create 1 rle with old method : 0.010443687438964844 length of segment : 153 time for calcul the mask position with numpy : 0.0002238750457763672 nb_pixel_total : 11722 time to create 1 rle with old method : 0.013720035552978516 length of segment : 131 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004608631134033203 length of segment : 21 time for calcul the mask position with numpy : 0.0012280941009521484 nb_pixel_total : 91133 time to create 1 rle with old method : 0.10143113136291504 length of segment : 437 time for calcul the mask position with numpy : 0.00012373924255371094 nb_pixel_total : 4596 time to create 1 rle with old method : 0.005135536193847656 length of segment : 107 time for calcul the mask position with numpy : 0.007021903991699219 nb_pixel_total : 346835 time to create 1 rle with new method : 0.020550251007080078 length of segment : 1401 time for calcul the mask position with numpy : 0.0005893707275390625 nb_pixel_total : 40277 time to create 1 rle with old method : 0.04554247856140137 length of segment : 205 time for calcul the mask position with numpy : 0.0017943382263183594 nb_pixel_total : 130948 time to create 1 rle with old method : 0.13924503326416016 length of segment : 603 time for calcul the mask position with numpy : 0.0014274120330810547 nb_pixel_total : 100376 time to create 1 rle with old method : 0.10483789443969727 length of segment : 513 time for calcul the mask position with numpy : 0.0013155937194824219 nb_pixel_total : 97337 time to create 1 rle with old method : 0.10460233688354492 length of segment : 471 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 372 time to create 1 rle with old method : 0.0007708072662353516 length of segment : 26 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 1738 time to create 1 rle with old method : 0.0030448436737060547 length of segment : 79 time for calcul the mask position with numpy : 0.006047725677490234 nb_pixel_total : 339728 time to create 1 rle with new method : 0.014837503433227539 length of segment : 770 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 867 time to create 1 rle with old method : 0.0011470317840576172 length of segment : 43 time for calcul the mask position with numpy : 0.0012454986572265625 nb_pixel_total : 116826 time to create 1 rle with old method : 0.12635040283203125 length of segment : 369 time for calcul the mask position with numpy : 0.0003306865692138672 nb_pixel_total : 9714 time to create 1 rle with old method : 0.011450767517089844 length of segment : 198 time for calcul the mask position with numpy : 0.00020122528076171875 nb_pixel_total : 13145 time to create 1 rle with old method : 0.015191078186035156 length of segment : 99 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 7210 time to create 1 rle with old method : 0.008214712142944336 length of segment : 142 time for calcul the mask position with numpy : 0.0002231597900390625 nb_pixel_total : 10440 time to create 1 rle with old method : 0.011759281158447266 length of segment : 258 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0005130767822265625 length of segment : 33 time for calcul the mask position with numpy : 0.00018215179443359375 nb_pixel_total : 11819 time to create 1 rle with old method : 0.013235330581665039 length of segment : 149 time for calcul the mask position with numpy : 0.004190683364868164 nb_pixel_total : 324905 time to create 1 rle with new method : 0.01166081428527832 length of segment : 780 time for calcul the mask position with numpy : 0.0002422332763671875 nb_pixel_total : 3023 time to create 1 rle with old method : 0.003642559051513672 length of segment : 117 time for calcul the mask position with numpy : 0.0007021427154541016 nb_pixel_total : 47326 time to create 1 rle with old method : 0.052149295806884766 length of segment : 525 time for calcul the mask position with numpy : 0.00041556358337402344 nb_pixel_total : 4379 time to create 1 rle with old method : 0.004913330078125 length of segment : 124 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00037932395935058594 length of segment : 20 time for calcul the mask position with numpy : 0.00037789344787597656 nb_pixel_total : 15424 time to create 1 rle with old method : 0.016740083694458008 length of segment : 119 time for calcul the mask position with numpy : 0.0008893013000488281 nb_pixel_total : 22973 time to create 1 rle with old method : 0.025768041610717773 length of segment : 472 time for calcul the mask position with numpy : 0.0006456375122070312 nb_pixel_total : 23928 time to create 1 rle with old method : 0.02700042724609375 length of segment : 177 time for calcul the mask position with numpy : 0.0019021034240722656 nb_pixel_total : 117125 time to create 1 rle with old method : 0.12180137634277344 length of segment : 382 time for calcul the mask position with numpy : 0.0001628398895263672 nb_pixel_total : 3390 time to create 1 rle with old method : 0.0043392181396484375 length of segment : 43 time for calcul the mask position with numpy : 0.0002243518829345703 nb_pixel_total : 3472 time to create 1 rle with old method : 0.004191398620605469 length of segment : 107 time for calcul the mask position with numpy : 0.0018455982208251953 nb_pixel_total : 80789 time to create 1 rle with old method : 0.08804464340209961 length of segment : 508 time for calcul the mask position with numpy : 0.00017404556274414062 nb_pixel_total : 1609 time to create 1 rle with old method : 0.001775503158569336 length of segment : 97 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 2204 time to create 1 rle with old method : 0.002593994140625 length of segment : 54 time for calcul the mask position with numpy : 0.00025343894958496094 nb_pixel_total : 3920 time to create 1 rle with old method : 0.0044901371002197266 length of segment : 98 time for calcul the mask position with numpy : 0.00016641616821289062 nb_pixel_total : 2409 time to create 1 rle with old method : 0.0030198097229003906 length of segment : 115 time for calcul the mask position with numpy : 0.0005371570587158203 nb_pixel_total : 11832 time to create 1 rle with old method : 0.013768196105957031 length of segment : 205 time for calcul the mask position with numpy : 0.009603023529052734 nb_pixel_total : 379218 time to create 1 rle with new method : 0.02083754539489746 length of segment : 1057 time for calcul the mask position with numpy : 0.00032806396484375 nb_pixel_total : 5402 time to create 1 rle with old method : 0.0065648555755615234 length of segment : 82 time for calcul the mask position with numpy : 0.0014581680297851562 nb_pixel_total : 114721 time to create 1 rle with old method : 0.12882542610168457 length of segment : 349 time for calcul the mask position with numpy : 0.0002613067626953125 nb_pixel_total : 5229 time to create 1 rle with old method : 0.006143331527709961 length of segment : 109 time for calcul the mask position with numpy : 0.0010488033294677734 nb_pixel_total : 59452 time to create 1 rle with old method : 0.07186579704284668 length of segment : 337 time for calcul the mask position with numpy : 0.00045561790466308594 nb_pixel_total : 9044 time to create 1 rle with old method : 0.01012420654296875 length of segment : 189 time for calcul the mask position with numpy : 0.0003437995910644531 nb_pixel_total : 12799 time to create 1 rle with old method : 0.014304399490356445 length of segment : 115 time for calcul the mask position with numpy : 0.0001201629638671875 nb_pixel_total : 695 time to create 1 rle with old method : 0.0008900165557861328 length of segment : 47 time for calcul the mask position with numpy : 0.00072479248046875 nb_pixel_total : 16345 time to create 1 rle with old method : 0.018947601318359375 length of segment : 192 time for calcul the mask position with numpy : 0.00039076805114746094 nb_pixel_total : 11958 time to create 1 rle with old method : 0.013668537139892578 length of segment : 127 time for calcul the mask position with numpy : 0.00017499923706054688 nb_pixel_total : 5673 time to create 1 rle with old method : 0.00798177719116211 length of segment : 92 time for calcul the mask position with numpy : 0.00037741661071777344 nb_pixel_total : 6886 time to create 1 rle with old method : 0.008213520050048828 length of segment : 143 time for calcul the mask position with numpy : 0.003966331481933594 nb_pixel_total : 115356 time to create 1 rle with old method : 0.1295938491821289 length of segment : 661 time for calcul the mask position with numpy : 0.0003204345703125 nb_pixel_total : 8948 time to create 1 rle with old method : 0.010724067687988281 length of segment : 163 time for calcul the mask position with numpy : 0.0015766620635986328 nb_pixel_total : 71898 time to create 1 rle with old method : 0.0809319019317627 length of segment : 429 time for calcul the mask position with numpy : 0.001332998275756836 nb_pixel_total : 94372 time to create 1 rle with old method : 0.10380029678344727 length of segment : 327 time for calcul the mask position with numpy : 0.006639003753662109 nb_pixel_total : 349834 time to create 1 rle with new method : 0.01294088363647461 length of segment : 1080 time for calcul the mask position with numpy : 0.0006685256958007812 nb_pixel_total : 31035 time to create 1 rle with old method : 0.03461861610412598 length of segment : 231 time for calcul the mask position with numpy : 0.00020933151245117188 nb_pixel_total : 4988 time to create 1 rle with old method : 0.006155729293823242 length of segment : 187 time spent for convertir_results : 4.336045980453491 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 57 chid ids of type : 3663 Number RLEs to save : 16068 save missing photos in datou_result : time spend for datou_step_exec : 20.9997239112854 time spend to save output : 1.8854036331176758 total time spend for step 1 : 22.885127544403076 step2:crop_condition Fri Oct 10 09:24:20 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 ! 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 : 5 ! batch 1 Loaded 57 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 ! 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 : 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 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 ! 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_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 ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! we have finished the crop for the class : cartonnette begin to crop the class : carton_brun param for this class : {'min_score': 0.7} filtre for class : carton_brun hashtag_id of this class : 2107753024 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 5 About to insert : list_path_to_insert length 5 new photo from crops ! we have finished the crop for the class : 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 [1388574720, 1388574602, 1388574600, 1388574597, 1388574595] Looping around the photos to save general results len do output : 29 /-3991837028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3991837040Didn'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, '3911023') ('4877', '27666953', '1388574720', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574602', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574600', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574597', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574595', None, None, None, None, None, '3911023') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 92 time used for this insertion : 0.039998531341552734 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.6940248012542725 time spend to save output : 0.04119706153869629 total time spend for step 2 : 5.735221862792969 step3:thcl Fri Oct 10 09:24:26 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure 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 : 0.009389162063598633 time to convert the images to numpy array : 0.023137569427490234 time to import caffe and check if the image exist : 0.007889032363891602 time to convert the images to numpy array : 0.0337834358215332 time to import caffe and check if the image exist : 0.0077877044677734375 time to convert the images to numpy array : 0.039727210998535156 time to import caffe and check if the image exist : 0.006728410720825195 time to convert the images to numpy array : 0.04311966896057129 time to import caffe and check if the image exist : 0.012549161911010742 time to convert the images to numpy array : 0.03803825378417969 time to import caffe and check if the image exist : 0.009971857070922852 time to convert the images to numpy array : 0.04216718673706055 time to import caffe and check if the image exist : 0.008917570114135742 time to convert the images to numpy array : 0.04590940475463867 time to import caffe and check if the image exist : 0.007984638214111328 time to convert the images to numpy array : 0.04844546318054199 time to import caffe and check if the image exist : 0.008214712142944336 time to convert the images to numpy array : 0.05301189422607422 time to import caffe and check if the image exist : 0.008621454238891602 time to convert the images to numpy array : 0.05420327186584473 total time to convert the images to numpy array : 0.3460562229156494 list photo_ids error: [] list photo_ids correct : [-3991837069, -3991837040, -3991837078, -3991837070, -3991837023, -3991837057, -3991837054, -3991837052, -3991837028, -3991837045, -3991837044, -3991837072, -3991837067, -3991837073, -3991837046, -3991837053, -3991837068, -3991837062, -3991837075, -3991837066, -3991837038, -3991837039, -3991837036, -3991837048, -3991837051, -3991837064, -3991837074, -3991837031, -3991837025] number of photos to traite : 29 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 : 10998 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 : 10776 max_wait_temp : 1 max_wait : 0 dict_keys(['prob']) time used to do the prepocess of the images : 0.28809165954589844 time used to do the prediction : 0.08583879470825195 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 : 10774 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 : 10774 max_wait_temp : 1 max_wait : 0 dict_keys(['prob']) time used to do the prepocess of the images : 0.22492289543151855 time used to do the prediction : 0.06732630729675293 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 : 1.2636184692382812e-05 save missing photos in datou_result : time spend for datou_step_exec : 8.045724153518677 time spend to save output : 0.0002751350402832031 total time spend for step 3 : 8.04599928855896 step4:merge_mask_thcl_custom Fri Oct 10 09:24:34 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 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 57 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 [1388574720, 1388574602, 1388574600, 1388574597, 1388574595] Looping around the photos to save general results len do output : 5 /1388574720Didn't retrieve data .Didn't retrieve data . /1388574602Didn't retrieve data .Didn't retrieve data . /1388574600Didn't retrieve data .Didn't retrieve data . /1388574597Didn't retrieve data .Didn't retrieve data . /1388574595Didn'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, '3911023') ('4877', '27666953', '1388574720', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574602', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574600', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574597', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574595', None, None, None, None, None, '3911023') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.038346052169799805 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.1888575553894043 time spend to save output : 0.038687944412231445 total time spend for step 4 : 0.22754549980163574 step5:rle_unique_nms_with_priority Fri Oct 10 09:24:34 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 Begin step rle-unique-nms nb_obj : 8 nb_hashtags : 4 time to prepare the origin masks : 0.6108014583587646 time for calcul the mask position with numpy : 0.016062021255493164 nb_pixel_total : 1235303 time to create 1 rle with new method : 0.03818988800048828 time for calcul the mask position with numpy : 0.005525827407836914 nb_pixel_total : 33114 time to create 1 rle with old method : 0.03659868240356445 time for calcul the mask position with numpy : 0.005088329315185547 nb_pixel_total : 23019 time to create 1 rle with old method : 0.0254058837890625 time for calcul the mask position with numpy : 0.005018949508666992 nb_pixel_total : 11683 time to create 1 rle with old method : 0.01278066635131836 time for calcul the mask position with numpy : 0.007153987884521484 nb_pixel_total : 354484 time to create 1 rle with new method : 0.03309464454650879 time for calcul the mask position with numpy : 0.005155801773071289 nb_pixel_total : 4584 time to create 1 rle with old method : 0.005150556564331055 time for calcul the mask position with numpy : 0.005441188812255859 nb_pixel_total : 91192 time to create 1 rle with old method : 0.09682464599609375 time for calcul the mask position with numpy : 0.005083560943603516 nb_pixel_total : 320 time to create 1 rle with old method : 0.0003883838653564453 time for calcul the mask position with numpy : 0.004799842834472656 nb_pixel_total : 8861 time to create 1 rle with old method : 0.009801149368286133 create new chi : 0.3209397792816162 time to delete rle : 0.06754589080810547 batch 1 Loaded 9 chid ids of type : 3726 Number RLEs to save : 6144 TO DO : save crop sub photo not yet done ! save time : 0.7363367080688477 nb_obj : 9 nb_hashtags : 4 time to prepare the origin masks : 0.6124539375305176 time for calcul the mask position with numpy : 0.014456987380981445 nb_pixel_total : 1265282 time to create 1 rle with new method : 0.03246879577636719 time for calcul the mask position with numpy : 0.005518436431884766 nb_pixel_total : 114374 time to create 1 rle with old method : 0.12312436103820801 time for calcul the mask position with numpy : 0.005853891372680664 nb_pixel_total : 373 time to create 1 rle with old method : 0.0004220008850097656 time for calcul the mask position with numpy : 0.005315065383911133 nb_pixel_total : 7188 time to create 1 rle with old method : 0.007809162139892578 time for calcul the mask position with numpy : 0.0051288604736328125 nb_pixel_total : 13066 time to create 1 rle with old method : 0.014225244522094727 time for calcul the mask position with numpy : 0.004998683929443359 nb_pixel_total : 9651 time to create 1 rle with old method : 0.010775327682495117 time for calcul the mask position with numpy : 0.0049800872802734375 nb_pixel_total : 861 time to create 1 rle with old method : 0.0009891986846923828 time for calcul the mask position with numpy : 0.0069789886474609375 nb_pixel_total : 339565 time to create 1 rle with new method : 0.02859187126159668 time for calcul the mask position with numpy : 0.008823871612548828 nb_pixel_total : 1736 time to create 1 rle with old method : 0.0019066333770751953 time for calcul the mask position with numpy : 0.0060994625091552734 nb_pixel_total : 10464 time to create 1 rle with old method : 0.011491537094116211 create new chi : 0.30347704887390137 time to delete rle : 0.00047135353088378906 batch 1 Loaded 10 chid ids of type : 3726 Number RLEs to save : 4867 TO DO : save crop sub photo not yet done ! save time : 0.6018872261047363 nb_obj : 10 nb_hashtags : 3 time to prepare the origin masks : 0.8163137435913086 time for calcul the mask position with numpy : 0.012836456298828125 nb_pixel_total : 1261883 time to create 1 rle with new method : 0.03081536293029785 time for calcul the mask position with numpy : 0.004959821701049805 nb_pixel_total : 107 time to create 1 rle with old method : 0.000186920166015625 time for calcul the mask position with numpy : 0.0048558712005615234 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002503395080566406 time for calcul the mask position with numpy : 0.005055665969848633 nb_pixel_total : 4346 time to create 1 rle with old method : 0.004845142364501953 time for calcul the mask position with numpy : 0.005399465560913086 nb_pixel_total : 23706 time to create 1 rle with old method : 0.02619194984436035 time for calcul the mask position with numpy : 0.005187034606933594 nb_pixel_total : 2776 time to create 1 rle with old method : 0.0030660629272460938 time for calcul the mask position with numpy : 0.0050716400146484375 nb_pixel_total : 285 time to create 1 rle with old method : 0.0003809928894042969 time for calcul the mask position with numpy : 0.00555729866027832 nb_pixel_total : 116865 time to create 1 rle with old method : 0.12697267532348633 time for calcul the mask position with numpy : 0.0066967010498046875 nb_pixel_total : 325261 time to create 1 rle with new method : 0.026413679122924805 time for calcul the mask position with numpy : 0.004879474639892578 nb_pixel_total : 11796 time to create 1 rle with old method : 0.01269674301147461 time for calcul the mask position with numpy : 0.004980802536010742 nb_pixel_total : 15375 time to create 1 rle with old method : 0.01694321632385254 create new chi : 0.3169727325439453 time to delete rle : 0.0004506111145019531 batch 1 Loaded 11 chid ids of type : 3726 Number RLEs to save : 4773 TO DO : save crop sub photo not yet done ! save time : 0.6000528335571289 nb_obj : 13 nb_hashtags : 4 time to prepare the origin masks : 0.8075394630432129 time for calcul the mask position with numpy : 0.013813018798828125 nb_pixel_total : 1153180 time to create 1 rle with new method : 0.03790783882141113 time for calcul the mask position with numpy : 0.005173206329345703 nb_pixel_total : 3911 time to create 1 rle with old method : 0.004285573959350586 time for calcul the mask position with numpy : 0.005011081695556641 nb_pixel_total : 36499 time to create 1 rle with old method : 0.038133859634399414 time for calcul the mask position with numpy : 0.004775285720825195 nb_pixel_total : 5198 time to create 1 rle with old method : 0.005517244338989258 time for calcul the mask position with numpy : 0.004918813705444336 nb_pixel_total : 5168 time to create 1 rle with old method : 0.005822658538818359 time for calcul the mask position with numpy : 0.007150173187255859 nb_pixel_total : 393787 time to create 1 rle with new method : 0.03033304214477539 time for calcul the mask position with numpy : 0.004885435104370117 nb_pixel_total : 3374 time to create 1 rle with old method : 0.0037026405334472656 time for calcul the mask position with numpy : 0.004889011383056641 nb_pixel_total : 11663 time to create 1 rle with old method : 0.012805700302124023 time for calcul the mask position with numpy : 0.004865407943725586 nb_pixel_total : 1817 time to create 1 rle with old method : 0.0020897388458251953 time for calcul the mask position with numpy : 0.005225658416748047 nb_pixel_total : 81367 time to create 1 rle with old method : 0.08487105369567871 time for calcul the mask position with numpy : 0.0048863887786865234 nb_pixel_total : 2192 time to create 1 rle with old method : 0.002283334732055664 time for calcul the mask position with numpy : 0.004580497741699219 nb_pixel_total : 1601 time to create 1 rle with old method : 0.0016894340515136719 time for calcul the mask position with numpy : 0.00465703010559082 nb_pixel_total : 3465 time to create 1 rle with old method : 0.0037615299224853516 time for calcul the mask position with numpy : 0.005019426345825195 nb_pixel_total : 59338 time to create 1 rle with old method : 0.06200599670410156 create new chi : 0.38041043281555176 time to delete rle : 0.0006859302520751953 batch 1 Loaded 14 chid ids of type : 3726 Number RLEs to save : 6598 TO DO : save crop sub photo not yet done ! save time : 0.7969775199890137 nb_obj : 13 nb_hashtags : 6 time to prepare the origin masks : 1.0583772659301758 time for calcul the mask position with numpy : 0.015368461608886719 nb_pixel_total : 1194094 time to create 1 rle with new method : 0.033094167709350586 time for calcul the mask position with numpy : 0.005400180816650391 nb_pixel_total : 14921 time to create 1 rle with old method : 0.01622176170349121 time for calcul the mask position with numpy : 0.005692958831787109 nb_pixel_total : 15035 time to create 1 rle with old method : 0.024555683135986328 time for calcul the mask position with numpy : 0.005533695220947266 nb_pixel_total : 5651 time to create 1 rle with old method : 0.009286165237426758 time for calcul the mask position with numpy : 0.0056612491607666016 nb_pixel_total : 19898 time to create 1 rle with old method : 0.032683372497558594 time for calcul the mask position with numpy : 0.005384683609008789 nb_pixel_total : 11906 time to create 1 rle with old method : 0.012689352035522461 time for calcul the mask position with numpy : 0.006797313690185547 nb_pixel_total : 368979 time to create 1 rle with new method : 0.026691913604736328 time for calcul the mask position with numpy : 0.004850625991821289 nb_pixel_total : 3877 time to create 1 rle with old method : 0.004334688186645508 time for calcul the mask position with numpy : 0.0049457550048828125 nb_pixel_total : 12649 time to create 1 rle with old method : 0.01338958740234375 time for calcul the mask position with numpy : 0.005345821380615234 nb_pixel_total : 94101 time to create 1 rle with old method : 0.0989830493927002 time for calcul the mask position with numpy : 0.004875898361206055 nb_pixel_total : 6829 time to create 1 rle with old method : 0.007303476333618164 time for calcul the mask position with numpy : 0.005013465881347656 nb_pixel_total : 684 time to create 1 rle with old method : 0.0008273124694824219 time for calcul the mask position with numpy : 0.005131721496582031 nb_pixel_total : 8994 time to create 1 rle with old method : 0.009967327117919922 time for calcul the mask position with numpy : 0.005435943603515625 nb_pixel_total : 4942 time to create 1 rle with old method : 0.00556492805480957 create new chi : 0.38485217094421387 time to delete rle : 0.0006346702575683594 batch 1 Loaded 14 chid ids of type : 3726 Number RLEs to save : 7102 TO DO : save crop sub photo not yet done ! save time : 0.8205051422119141 map_output_result : {1388574720: (0.0, 'Should be the crop_list due to order', 0.0), 1388574602: (0.0, 'Should be the crop_list due to order', 0.0), 1388574600: (0.0, 'Should be the crop_list due to order', 0.0), 1388574597: (0.0, 'Should be the crop_list due to order', 0.0), 1388574595: (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 [1388574720, 1388574602, 1388574600, 1388574597, 1388574595] Looping around the photos to save general results len do output : 5 /1388574720.Didn't retrieve data . /1388574602.Didn't retrieve data . /1388574600.Didn't retrieve data . /1388574597.Didn't retrieve data . /1388574595.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, '3911023') ('4877', '27666953', '1388574720', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574602', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574600', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574597', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574595', None, None, None, None, None, '3911023') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.034555673599243164 save_final save missing photos in datou_result : time spend for datou_step_exec : 9.41588282585144 time spend to save output : 0.03494977951049805 total time spend for step 5 : 9.450832605361938 step6:crop_condition Fri Oct 10 09:24:43 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 3726 Loading chi in step crop for list_pids : 5 ! batch 1 Loaded 58 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 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1760081085_4112958 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1760081086), 0.0, 0.0, 14, '', 0, 0, '1760081036_4112958_1388574600_26d666dff14f745a51d9dce46c0fb9ee_rle_crop_3991837604_0.png', 0, 107, 124, 0, 1760081086,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 2.015159845352173 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 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1760081087_4112958 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1760081087), 0.0, 0.0, 14, '', 0, 0, '1760081036_4112958_1388574595_813948b1c2b2ee1ea0dfc9e45648b58d_rle_crop_3991837760_0.png', 0, 144, 105, 0, 1760081087,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.6063508987426758 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 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1760081087_4112958 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1760081088), 0.0, 0.0, 14, '', 0, 0, '1760081036_4112958_1388574602_d6e60370fad33580e4f6168c29b9100b_rle_crop_3991837595_0.png', 0, 206, 83, 0, 1760081088,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1760081088), 0.0, 0.0, 14, '', 0, 0, '1760081036_4112958_1388574597_e8a0d735f9bd67ca47c44e13de00906f_rle_crop_3991837729_0.png', 0, 122, 43, 0, 1760081088,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.8459651470184326 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 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1760081089_4112958 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1760081089), 0.0, 0.0, 14, '', 0, 0, '1760081036_4112958_1388574720_4966c44a385f17ee94d5617edb9b262d_rle_crop_3991837585_0.png', 0, 119, 131, 0, 1760081089,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.7555677890777588 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 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 [1388574720, 1388574602, 1388574600, 1388574597, 1388574595] Looping around the photos to save general results len do output : 5 /1388630997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1388630998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1388630999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1388631000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1388631001Didn'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, '3911023') ('4877', '27666953', '1388574720', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574602', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574600', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574597', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574595', None, None, None, None, None, '3911023') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 20 time used for this insertion : 0.0432744026184082 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.768362522125244 time spend to save output : 0.04372882843017578 total time spend for step 6 : 5.81209135055542 step7:ventilate_hashtags_in_portfolio Fri Oct 10 09:24:49 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 : 27666953 get user id for portfolio 27666953 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`=27666953 AND mptpi.`type`=3726 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre_refus','papier','Carton_brun','Teint_Dans_La_Masse','flou','Carton_gris','plastique','cartonnette','mal_croppe','environnement','metal','kraft')) 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`=27666953 AND mptpi.`type`=3726 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre_refus','papier','Carton_brun','Teint_Dans_La_Masse','flou','Carton_gris','plastique','cartonnette','mal_croppe','environnement','metal','kraft')) 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`=27666953 AND mptpi.`type`=4417 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre_refus','papier','Carton_brun','Teint_Dans_La_Masse','flou','Carton_gris','plastique','cartonnette','mal_croppe','environnement','metal','kraft')) 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`=27666953 AND mptpi.`type`=4417 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre_refus','papier','Carton_brun','Teint_Dans_La_Masse','flou','Carton_gris','plastique','cartonnette','mal_croppe','environnement','metal','kraft')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://marlene.fotonower.com/velours/27685671,27685672,27685673,27685674,27685675,27685676,27685677,27685678,27685679,27685680,27685681,27685682?tags=autre_refus,papier,Carton_brun,Teint_Dans_La_Masse,flou,Carton_gris,plastique,cartonnette,mal_croppe,environnement,metal,kraft Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1388574720, 1388574602, 1388574600, 1388574597, 1388574595] Looping around the photos to save general results len do output : 1 /27666953. 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, '3911023') ('4877', '27666953', '1388574720', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574602', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574600', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574597', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574595', None, None, None, None, None, '3911023') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.03770852088928223 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.4729270935058594 time spend to save output : 0.037903547286987305 total time spend for step 7 : 3.5108306407928467 step8:tfhub_classification2 Fri Oct 10 09:24:53 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 09:24:55.749508: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-10-10 09:24:55.750399: 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 09:24:55.750460: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:24:55.750506: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:24:55.752186: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:24:55.752240: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:24:55.753800: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:24:55.754417: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:24:55.757338: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:24:55.758832: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:24:55.759192: 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 09:24:55.782562: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-10-10 09:24:55.784159: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f845c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-10-10 09:24:55.784202: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-10-10 09:24:55.787567: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x12b2b460 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-10-10 09:24:55.787598: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-10-10 09:24:55.789052: 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 09:24:55.789130: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:24:55.789161: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:24:55.789253: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-10-10 09:24:55.789288: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-10-10 09:24:55.789333: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-10-10 09:24:55.789381: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-10-10 09:24:55.789431: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-10-10 09:24:55.791647: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-10-10 09:24:55.791715: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-10-10 09:24:55.791770: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-10-10 09:24:55.791786: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-10-10 09:24:55.791799: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-10-10 09:24:55.794005: 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 : 10774 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 : 7.3782057762146 time used to load_weights : 0.12880420684814453 0it [00:00, ?it/s] 5it [00:00, 2903.44it/s]2025-10-10 09:25:05.168528: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-10-10 09:25:05.191116: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 temp/1760081036_4112958_1388574720_4966c44a385f17ee94d5617edb9b262d.jpg temp/1760081036_4112958_1388574602_d6e60370fad33580e4f6168c29b9100b.jpg temp/1760081036_4112958_1388574600_26d666dff14f745a51d9dce46c0fb9ee.jpg temp/1760081036_4112958_1388574597_e8a0d735f9bd67ca47c44e13de00906f.jpg temp/1760081036_4112958_1388574595_813948b1c2b2ee1ea0dfc9e45648b58d.jpg Found 5 images belonging to 1 classes. begin to do the prediction : time used to do the prediction : 2.1597495079040527 (5,) (5, 5) (5, 2048) shape of features : (5, 2048) shape of new features : (1, 5, 2048) save descriptor for thcl : 3513 time to traite the descriptors : 0.04230332374572754 storage_type for insertDescriptorsMulti : 3 To insert : 1388574720 To insert : 1388574602 To insert : 1388574600 To insert : 1388574597 To insert : 1388574595 Catched exception ! Connect or reconnect ! time to insert the descriptors : 2.559147357940674 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 : 6.742186546325684 time used to load_weights : 0.11125349998474121 0it [00:00, ?it/s] 5it [00:00, 2785.43it/s]temp/1760081036_4112958_1388574720_4966c44a385f17ee94d5617edb9b262d.jpg temp/1760081036_4112958_1388574602_d6e60370fad33580e4f6168c29b9100b.jpg temp/1760081036_4112958_1388574600_26d666dff14f745a51d9dce46c0fb9ee.jpg temp/1760081036_4112958_1388574597_e8a0d735f9bd67ca47c44e13de00906f.jpg temp/1760081036_4112958_1388574595_813948b1c2b2ee1ea0dfc9e45648b58d.jpg Found 5 images belonging to 1 classes. begin to do the prediction : time used to do the prediction : 1.0583951473236084 (5,) (5, 11) (5, 1280) shape of features : (5, 1280) shape of new features : (1, 5, 1280) save descriptor for thcl : 3379 time to traite the descriptors : 0.04254961013793945 storage_type for insertDescriptorsMulti : 3 To insert : 1388574720 To insert : 1388574602 To insert : 1388574600 To insert : 1388574597 To insert : 1388574595 time to insert the descriptors : 1.3426969051361084 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 : 7.238481044769287 time used to load_weights : 0.11018753051757812 0it [00:00, ?it/s] 5it [00:00, 2539.23it/s]temp/1760081036_4112958_1388574720_4966c44a385f17ee94d5617edb9b262d.jpg temp/1760081036_4112958_1388574602_d6e60370fad33580e4f6168c29b9100b.jpg temp/1760081036_4112958_1388574600_26d666dff14f745a51d9dce46c0fb9ee.jpg temp/1760081036_4112958_1388574597_e8a0d735f9bd67ca47c44e13de00906f.jpg temp/1760081036_4112958_1388574595_813948b1c2b2ee1ea0dfc9e45648b58d.jpg Found 5 images belonging to 1 classes. begin to do the prediction : time used to do the prediction : 0.9177412986755371 (5,) (5, 12) (5, 1280) shape of features : (5, 1280) shape of new features : (1, 5, 1280) save descriptor for thcl : 3847 time to traite the descriptors : 0.059433937072753906 storage_type for insertDescriptorsMulti : 3 To insert : 1388574720 To insert : 1388574602 To insert : 1388574600 To insert : 1388574597 To insert : 1388574595 time to insert the descriptors : 1.2772858142852783 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : tfhub_classification2 we use saveGeneral [1388574720, 1388574602, 1388574600, 1388574597, 1388574595] Looping around the photos to save general results len do output : 5 /1388574720Didn't retrieve data . /1388574602Didn't retrieve data . /1388574600Didn't retrieve data . /1388574597Didn't retrieve data . /1388574595Didn'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, '3911023') ('4877', '27666953', '1388574720', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574602', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574600', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574597', None, None, None, None, None, '3911023') ('4877', None, None, None, None, None, None, None, '3911023') ('4877', '27666953', '1388574595', None, None, None, None, None, '3911023') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 10 time used for this insertion : 0.0353856086730957 save_final save missing photos in datou_result : time spend for datou_step_exec : 39.13276028633118 time spend to save output : 0.03575706481933594 total time spend for step 8 : 39.16851735115051 step9:argmax Fri Oct 10 09:25:32 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 : 1388574720 output[photo_id] : [[(1388574720, '05102018_Papier_non_papier_presque_vide', 0.41315523, 4557, 3513), (1388574720, 'jrm', 0.8446372, 4374, 3379), (1388574720, 'jrm', 0.8180736, 4932, 3847)], 'temp/1760081036_4112958_1388574720_4966c44a385f17ee94d5617edb9b262d.jpg'] photo_id : 1388574602 output[photo_id] : [[(1388574602, '05102018_Papier_non_papier_tres_dense', 0.56911665, 4557, 3513), (1388574602, 'jrm', 0.92410696, 4374, 3379), (1388574602, 'jrm', 0.8520832, 4932, 3847)], 'temp/1760081036_4112958_1388574602_d6e60370fad33580e4f6168c29b9100b.jpg'] photo_id : 1388574600 output[photo_id] : [[(1388574600, '05102018_Papier_non_papier_tres_dense', 0.47015962, 4557, 3513), (1388574600, 'jrm', 0.8841503, 4374, 3379), (1388574600, 'jrm', 0.8783991, 4932, 3847)], 'temp/1760081036_4112958_1388574600_26d666dff14f745a51d9dce46c0fb9ee.jpg'] photo_id : 1388574597 output[photo_id] : [[(1388574597, '05102018_Papier_non_papier_peu_dense', 0.6274054, 4557, 3513), (1388574597, 'jrm', 0.90293336, 4374, 3379), (1388574597, 'jrm', 0.8508274, 4932, 3847)], 'temp/1760081036_4112958_1388574597_e8a0d735f9bd67ca47c44e13de00906f.jpg'] photo_id : 1388574595 output[photo_id] : [[(1388574595, '05102018_Papier_non_papier_tres_dense', 0.2723086, 4557, 3513), (1388574595, 'jrm', 0.8223285, 4374, 3379), (1388574595, 'jrm', 0.77334535, 4932, 3847)], 'temp/1760081036_4112958_1388574595_813948b1c2b2ee1ea0dfc9e45648b58d.jpg'] begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 15 time used for this insertion : 0.03587627410888672 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 15 time used for this insertion : 0.03818917274475098 len list_finale : 15, len picture : 5 begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.03823375701904297 saving photo_ids in datou_result begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.03565645217895508 save missing photos in datou_result : time spend for datou_step_exec : 0.01732015609741211 time spend to save output : 0.21556591987609863 total time spend for step 9 : 0.23288607597351074 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 5 set_done_treatment 59.47user 19.30system 1:41.31elapsed 77%CPU (0avgtext+0avgdata 3026892maxresident)k 24inputs+17832outputs (13major+2431162minor)pagefaults 0swaps