python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 20 -a ' -a 3318 ' -s datou_3318 -M 0 -S 0 -U 95,95,120 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/caffe_cuda8_python3/python', '/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', '/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 : 3310860 load datou : 3318 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( 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 : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig 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 : 3318, datou_cur_ids : ['3674031'] with mtr_portfolio_ids : ['26604831'] and first list_photo_ids : [] new path : /proc/3310860/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, crop_condition, rle_unique_nms_with_priority, ventilate_hashtags_in_portfolio, final, blur_detection, brightness, velours_tree, send_mail_cod, split_time_score over limit max, limiting to limit_max 40 list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 3 ; length of list_pids : 3 ; length of list_args : 3 time to download the photos : 0.35797905921936035 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 : 10 step1:mask_detect Sat Sep 6 10:30:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 : 10599 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-09-06 10:30:32.803391: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-09-06 10:30:32.828483: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-09-06 10:30:32.830496: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fbc3c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-09-06 10:30:32.830544: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-09-06 10:30:32.834121: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-09-06 10:30:33.010583: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xe3511d0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-09-06 10:30:33.010630: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-09-06 10:30:33.012101: 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 2025-09-06 10:30:33.012538: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-06 10:30:33.026139: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-06 10:30:33.028985: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-06 10:30:33.030250: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-06 10:30:33.033467: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-06 10:30:33.035238: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-06 10:30:33.040832: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-06 10:30:33.042478: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-06 10:30:33.042547: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-06 10:30:33.043292: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-06 10:30:33.043306: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-06 10:30:33.043314: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-06 10:30:33.045240: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9818 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. 2025-09-06 10:30:33.370122: 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 2025-09-06 10:30:33.370203: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-06 10:30:33.370224: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-06 10:30:33.370242: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-06 10:30:33.370260: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-06 10:30:33.370278: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-06 10:30:33.370295: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-06 10:30:33.370313: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-06 10:30:33.371873: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-06 10:30:33.373218: 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 2025-09-06 10:30:33.373259: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-06 10:30:33.373280: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-06 10:30:33.373301: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-06 10:30:33.373320: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-06 10:30:33.373340: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-06 10:30:33.373359: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-06 10:30:33.373379: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-06 10:30:33.374930: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-06 10:30:33.374960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-06 10:30:33.374971: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-06 10:30:33.374980: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-06 10:30:33.376617: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9818 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-09-06 10:30:41.251876: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-06 10:30:41.489838: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 3 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 30.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 1920.00000 nb d'objets trouves : 10 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 17.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 1920.00000 nb d'objets trouves : 4 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 22.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 1920.00000 nb d'objets trouves : 10 Detection mask done ! Trying to reset tf kernel 3311333 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1126 tf kernel not reseted sub process len(results) : 3 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 3 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 : 6021 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2847 Catched exception ! Connect or reconnect ! thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] time for calcul the mask position with numpy : 0.00045800209045410156 nb_pixel_total : 15855 time to create 1 rle with old method : 0.01843738555908203 length of segment : 290 time for calcul the mask position with numpy : 0.00023865699768066406 nb_pixel_total : 11198 time to create 1 rle with old method : 0.013020753860473633 length of segment : 188 time for calcul the mask position with numpy : 0.0019462108612060547 nb_pixel_total : 107330 time to create 1 rle with old method : 0.11974024772644043 length of segment : 509 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 3124 time to create 1 rle with old method : 0.003734588623046875 length of segment : 79 time for calcul the mask position with numpy : 0.00011491775512695312 nb_pixel_total : 5637 time to create 1 rle with old method : 0.006483793258666992 length of segment : 113 time for calcul the mask position with numpy : 0.00012731552124023438 nb_pixel_total : 6247 time to create 1 rle with old method : 0.007423877716064453 length of segment : 133 time for calcul the mask position with numpy : 0.0001690387725830078 nb_pixel_total : 9725 time to create 1 rle with old method : 0.011493444442749023 length of segment : 136 time for calcul the mask position with numpy : 0.0001938343048095703 nb_pixel_total : 12505 time to create 1 rle with old method : 0.014552593231201172 length of segment : 130 time for calcul the mask position with numpy : 0.00014710426330566406 nb_pixel_total : 5926 time to create 1 rle with old method : 0.006934404373168945 length of segment : 124 time for calcul the mask position with numpy : 0.00023651123046875 nb_pixel_total : 9806 time to create 1 rle with old method : 0.01165151596069336 length of segment : 140 time for calcul the mask position with numpy : 0.0002276897430419922 nb_pixel_total : 11886 time to create 1 rle with old method : 0.014131546020507812 length of segment : 105 time for calcul the mask position with numpy : 0.00022339820861816406 nb_pixel_total : 11080 time to create 1 rle with old method : 0.013036727905273438 length of segment : 208 time for calcul the mask position with numpy : 0.012854337692260742 nb_pixel_total : 735108 time to create 1 rle with new method : 0.05195045471191406 length of segment : 870 time spent for convertir_results : 1.089200735092163 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 13 chid ids of type : 3594 Number RLEs to save : 3025 save missing photos in datou_result : time spend for datou_step_exec : 19.617876291275024 time spend to save output : 0.3973398208618164 total time spend for step 1 : 20.01521611213684 step2:crop_condition Sat Sep 6 10:30:50 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 : 3594 Loading chi in step crop for list_pids : 3 ! batch 1 Loaded 13 chid ids of type : 3594 +++++++++++++ begin to crop the class : papier param for this class : {'min_score': 0.7} filtre for class : papier hashtag_id of this class : 492668766 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 : 8 About to insert : list_path_to_insert length 8 new photo from crops ! About to upload 8 photos upload in portfolio : 3736932 init cache_photo without model_param we have 8 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757147450_3310860 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 8 photos in the portfolio 3736932 time of upload the photos Elapsed time : 2.4613356590270996 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.7} filtre for class : carton hashtag_id of this class : 492774966 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 ! About to upload 1 photos upload in portfolio : 3736932 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757147453_3310860 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.7350966930389404 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.7} filtre for class : metal hashtag_id of this class : 492628673 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 ! About to upload 1 photos upload in portfolio : 3736932 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757147454_3310860 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.824383020401001 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.7} filtre for class : pet_clair hashtag_id of this class : 2107755846 we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 3736932 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757147459_3310860 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 2 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.0039162635803223 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.7} filtre for class : autre hashtag_id of this class : 494826614 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 ! About to upload 1 photos upload in portfolio : 3736932 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757147460_3310860 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.956709623336792 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.7} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.7} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles from all chi we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1381995886, 1381995825, 1381995810] Looping around the photos to save general results len do output : 13 /1382010844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1382010856Didn'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 ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995886', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995825', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995810', None, None, None, None, None, '3674031') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 42 time used for this insertion : 0.024553537368774414 save_final save missing photos in datou_result : time spend for datou_step_exec : 10.81856083869934 time spend to save output : 0.025372028350830078 total time spend for step 2 : 10.843932867050171 step3:rle_unique_nms_with_priority Sat Sep 6 10:31:00 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 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 13 chid ids of type : 3594 +++++++++++++nb_obj : 7 nb_hashtags : 4 time to prepare the origin masks : 0.5065438747406006 time for calcul the mask position with numpy : 0.0686943531036377 nb_pixel_total : 1919961 time to create 1 rle with new method : 0.09320282936096191 time for calcul the mask position with numpy : 0.006635189056396484 nb_pixel_total : 9725 time to create 1 rle with old method : 0.010943889617919922 time for calcul the mask position with numpy : 0.006565570831298828 nb_pixel_total : 6247 time to create 1 rle with old method : 0.006986141204833984 time for calcul the mask position with numpy : 0.006586551666259766 nb_pixel_total : 160 time to create 1 rle with old method : 0.000438690185546875 time for calcul the mask position with numpy : 0.006632566452026367 nb_pixel_total : 3124 time to create 1 rle with old method : 0.0035254955291748047 time for calcul the mask position with numpy : 0.0072956085205078125 nb_pixel_total : 107330 time to create 1 rle with old method : 0.11870288848876953 time for calcul the mask position with numpy : 0.006822824478149414 nb_pixel_total : 11198 time to create 1 rle with old method : 0.012648582458496094 time for calcul the mask position with numpy : 0.0070002079010009766 nb_pixel_total : 15855 time to create 1 rle with old method : 0.017769813537597656 create new chi : 0.39066600799560547 time to delete rle : 0.021410465240478516 batch 1 Loaded 15 chid ids of type : 3594 +++++++Number RLEs to save : 3814 TO DO : save crop sub photo not yet done ! save time : 0.8534979820251465 nb_obj : 1 nb_hashtags : 1 time to prepare the origin masks : 0.07437658309936523 time for calcul the mask position with numpy : 0.035245418548583984 nb_pixel_total : 2061095 time to create 1 rle with new method : 0.09383559226989746 time for calcul the mask position with numpy : 0.007374286651611328 nb_pixel_total : 12505 time to create 1 rle with old method : 0.014160633087158203 create new chi : 0.15096616744995117 time to delete rle : 0.0003561973571777344 batch 1 Loaded 3 chid ids of type : 3594 +Number RLEs to save : 1340 TO DO : save crop sub photo not yet done ! save time : 0.14218640327453613 nb_obj : 5 nb_hashtags : 2 time to prepare the origin masks : 0.12208294868469238 time for calcul the mask position with numpy : 0.03204846382141113 nb_pixel_total : 1299794 time to create 1 rle with new method : 0.06959676742553711 time for calcul the mask position with numpy : 0.01196908950805664 nb_pixel_total : 735108 time to create 1 rle with new method : 0.03019547462463379 time for calcul the mask position with numpy : 0.006646871566772461 nb_pixel_total : 11080 time to create 1 rle with old method : 0.012662649154663086 time for calcul the mask position with numpy : 0.006517887115478516 nb_pixel_total : 11886 time to create 1 rle with old method : 0.013454675674438477 time for calcul the mask position with numpy : 0.006893157958984375 nb_pixel_total : 9806 time to create 1 rle with old method : 0.011011123657226562 time for calcul the mask position with numpy : 0.0069391727447509766 nb_pixel_total : 5926 time to create 1 rle with old method : 0.006735563278198242 create new chi : 0.21536803245544434 time to delete rle : 0.0004787445068359375 batch 1 Loaded 11 chid ids of type : 3594 +++++Number RLEs to save : 3974 TO DO : save crop sub photo not yet done ! save time : 0.7150051593780518 map_output_result : {1381995886: (0.0, 'Should be the crop_list due to order', 0), 1381995825: (0.0, 'Should be the crop_list due to order', 0), 1381995810: (0.0, 'Should be the crop_list due to order', 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 [1381995886, 1381995825, 1381995810] Looping around the photos to save general results len do output : 3 /1381995886.Didn't retrieve data . /1381995825.Didn't retrieve data . /1381995810.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 ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995886', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995825', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995810', None, None, None, None, None, '3674031') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.015864849090576172 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.41554594039917 time spend to save output : 0.016176939010620117 total time spend for step 3 : 3.43172287940979 step4:ventilate_hashtags_in_portfolio Sat Sep 6 10:31:04 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 ! Iterating over portfolio : 26604831 get user id for portfolio 26604831 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`=26604831 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('background','flou','carton','metal','pet_clair','pet_fonce','mal_croppe','papier','environnement','autre','pehd')) 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`=26604831 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('background','flou','carton','metal','pet_clair','pet_fonce','mal_croppe','papier','environnement','autre','pehd')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://marlene.fotonower.com/velours/26605156,26605157,26605158,26605159,26605160,26605161,26605162,26605163,26605164,26605165,26605166?tags=background,flou,pet_clair,autre,mal_croppe,carton,pehd,papier,metal,environnement,pet_fonce Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1381995886, 1381995825, 1381995810] Looping around the photos to save general results len do output : 1 /26604831. 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 ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995886', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995825', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995810', None, None, None, None, None, '3674031') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.06293320655822754 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.439608097076416 time spend to save output : 0.06326103210449219 total time spend for step 4 : 0.5028691291809082 step5:final Sat Sep 6 10:31:04 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 ! complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step final ! Catched exception ! Connect or reconnect ! Inside saveOutput : final : False verbose : 0 original output for save of step final : {1381995886: ('0.059952582184898066',), 1381995825: ('0.059952582184898066',), 1381995810: ('0.059952582184898066',)} new output for save of step final : {1381995886: ('0.059952582184898066',), 1381995825: ('0.059952582184898066',), 1381995810: ('0.059952582184898066',)} [1381995886, 1381995825, 1381995810] Looping around the photos to save general results len do output : 3 /1381995886.Didn't retrieve data . /1381995825.Didn't retrieve data . /1381995810.Didn't retrieve data . before output type Used above Used above Managing all output in save final without adding information in the mtr_datou_result ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995886', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995825', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995810', None, None, None, None, None, '3674031') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.020956039428710938 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12107276916503906 time spend to save output : 0.021245718002319336 total time spend for step 5 : 0.1423184871673584 step6:blur_detection Sat Sep 6 10:31:05 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 inside step blur_detection methode: ratio et variance treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4.jpg resize: (1080, 1920) 1381995886 0.2344827821742732 treat image : temp/1757147429_3310860_1381995825_a347cde458eca02b08c190fe8eebfd1c.jpg resize: (1080, 1920) 1381995825 1.1521603795082034 treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c.jpg resize: (1080, 1920) 1381995810 -0.4699907621944244 treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742549_0.png resize: (187, 80) 1382010844 -0.3753855446640931 treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742548_0.png resize: (290, 107) 1382010845 -2.065800927536419 treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742552_0.png resize: (112, 71) 1382010846 -1.0122292314880472 treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742553_0.png resize: (103, 76) 1382010847 -0.3678699945935288 treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742558_0.png resize: (105, 160) 1382010848 -0.015696095174736593 treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742557_0.png resize: (139, 115) 1382010849 -2.3507405997071134 treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742559_0.png resize: (208, 73) 1382010850 -1.1256244426693798 treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742556_0.png resize: (121, 74) 1382010851 -1.4317186959647406 treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742551_0.png resize: (79, 55) 1382010852 0.6233051531953386 treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742554_0.png resize: (104, 127) 1382010853 -1.0382257080253945 treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742550_0.png resize: (504, 353) 1382010854 -0.22069509150763458 treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742560_0.png resize: (858, 1110) 1382010855 -0.02407633574635032 treat image : temp/1757147429_3310860_1381995825_a347cde458eca02b08c190fe8eebfd1c_rle_crop_3947742555_0.png resize: (123, 136) 1382010856 -2.1114974811872864 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 16 time used for this insertion : 0.015327930450439453 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 16 time used for this insertion : 0.038135528564453125 save missing photos in datou_result : time spend for datou_step_exec : 2.798983097076416 time spend to save output : 0.058129310607910156 total time spend for step 6 : 2.857112407684326 step7:brightness Sat Sep 6 10:31:07 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 inside step calcul brightness treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4.jpg treat image : temp/1757147429_3310860_1381995825_a347cde458eca02b08c190fe8eebfd1c.jpg treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c.jpg treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742549_0.png treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742548_0.png treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742552_0.png treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742553_0.png treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742558_0.png treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742557_0.png treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742559_0.png treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742556_0.png treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742551_0.png treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742554_0.png treat image : temp/1757147429_3310860_1381995886_244ae3b5666dfceb2c4d272b0f7f09e4_rle_crop_3947742550_0.png treat image : temp/1757147429_3310860_1381995810_e477cf4843011458dad2b5970ab6045c_rle_crop_3947742560_0.png treat image : temp/1757147429_3310860_1381995825_a347cde458eca02b08c190fe8eebfd1c_rle_crop_3947742555_0.png Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 16 time used for this insertion : 0.016737699508666992 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 16 time used for this insertion : 0.022639989852905273 save missing photos in datou_result : time spend for datou_step_exec : 0.8962774276733398 time spend to save output : 0.043682098388671875 total time spend for step 7 : 0.9399595260620117 step8:velours_tree Sat Sep 6 10:31:08 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 can't find the photo_desc_type Inside saveOutput : final : False verbose : 0 ouput is None No outpout to save, returning out of save general time spend for datou_step_exec : 0.1572263240814209 time spend to save output : 3.361701965332031e-05 total time spend for step 8 : 0.15725994110107422 step9:send_mail_cod Sat Sep 6 10:31:08 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 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 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 3 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 dans la step send mail cod work_area: /home/admin/workarea/git/Velours/python in order to get the selector url, please entre the license of selector results_Auto_P26604831_06-09-2025_10_31_08.pdf 26605156 imagette266051561757147468 26605157 imagette266051571757147468 26605158 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette266051581757147468 26605159 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette266051591757147470 26605160 imagette266051601757147471 26605161 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette266051611757147471 26605162 change filename to text .change filename to text .change filename to text .imagette266051621757147472 26605163 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette266051631757147472 26605164 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette266051641757147473 26605166 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette266051661757147473 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=26604831 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://marlene.fotonower.com/velours/26605156,26605157,26605158,26605159,26605160,26605161,26605162,26605163,26605164,26605165,26605166?tags=background,flou,pet_clair,autre,mal_croppe,carton,pehd,papier,metal,environnement,pet_fonce args[1381995886] : ((1381995886, 0.2344827821742732, 492688767), (1381995886, 0.5116984414951056, 2107752395), '0.059952582184898066') We are sending mail with results at report@fotonower.com args[1381995825] : ((1381995825, 1.1521603795082034, 492688767), (1381995825, 0.2663131264229947, 2107752395), '0.059952582184898066') We are sending mail with results at report@fotonower.com args[1381995810] : ((1381995810, -0.4699907621944244, 492688767), (1381995810, 0.77431701733197, 2107752395), '0.059952582184898066') We are sending mail with results at report@fotonower.com refus_total : 0.059952582184898066 2022-04-13 10:29:59 0 SELECT ph.photo_id,ph.url,ph.username,ph.uploaded_at,ph.text FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=26604831 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26604831_06-09-2025_10_31_08.pdf results_Auto_P26604831_06-09-2025_10_31_08.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26604831_06-09-2025_10_31_08.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('3318','26604831','results_Auto_P26604831_06-09-2025_10_31_08.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26604831_06-09-2025_10_31_08.pdf','pdf','','0.36','0.059952582184898066') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/26604831

https://www.fotonower.com/image?json=false&list_photos_id=1381995886
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1381995825
La photo est trop floue, merci de reprendre une photo.(avec le score = 1.1521603795082034)
https://www.fotonower.com/image?json=false&list_photos_id=1381995810
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 6.00%
Veuillez trouver les photos des contaminants.

exemples de contaminants: pet_clair: https://www.fotonower.com/view/26605158?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/26605159?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/26605161?limit=200
exemples de contaminants: pehd: https://www.fotonower.com/view/26605162?limit=200
exemples de contaminants: papier: https://www.fotonower.com/view/26605163?limit=200
exemples de contaminants: metal: https://www.fotonower.com/view/26605164?limit=200
exemples de contaminants: pet_fonce: https://www.fotonower.com/view/26605166?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26604831_06-09-2025_10_31_08.pdf.

Lien vers velours :https://marlene.fotonower.com/velours/26605156,26605157,26605158,26605159,26605160,26605161,26605162,26605163,26605164,26605165,26605166?tags=background,flou,pet_clair,autre,mal_croppe,carton,pehd,papier,metal,environnement,pet_fonce.


L'équipe Fotonower 202 b'' Server: nginx Date: Sat, 06 Sep 2025 08:31:15 GMT Content-Length: 0 Connection: close X-Message-Id: f-DD9UV8Qe-WK8NFgszw2A Access-Control-Allow-Origin: https://sendgrid.api-docs.io Access-Control-Allow-Methods: POST Access-Control-Allow-Headers: Authorization, Content-Type, On-behalf-of, x-sg-elas-acl Access-Control-Max-Age: 600 X-No-CORS-Reason: https://sendgrid.com/docs/Classroom/Basics/API/cors.html Strict-Transport-Security: max-age=31536000; includeSubDomains Content-Security-Policy: frame-ancestors 'none' Cache-Control: no-cache X-Content-Type-Options: no-sniff Referrer-Policy: strict-origin-when-cross-origin Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1381995886, 1381995825, 1381995810] Looping around the photos to save general results len do output : 0 before output type Used above Managing all output in save final without adding information in the mtr_datou_result ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995886', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995825', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995810', None, None, None, None, None, '3674031') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.02745342254638672 save_final save missing photos in datou_result : time spend for datou_step_exec : 6.717053651809692 time spend to save output : 0.02764153480529785 total time spend for step 9 : 6.74469518661499 step10:split_time_score Sat Sep 6 10:31:15 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 VR 22-3-18 : For now we do not clean correctly the datou structure begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 861, 'mtr_user_id': 31, 'name': 'Rungis_class_dechets_1212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Rungis_Aluminium,Rungis_Carton,Rungis_Papier,Rungis_Plastique_clair,Rungis_Plastique_dur,Rungis_Plastique_fonce,Rungis_Tapis_vide,Rungis_Tetrapak', 'svm_portfolios_learning': '1160730,571842,571844,571839,571933,571840,571841,572307', 'photo_hashtag_type': 999, 'photo_desc_type': 3963, 'type_classification': 'caffe', 'hashtag_id_list': '2107751280,2107750907,2107750908,2107750909,2107750910,2107750911,2107750912,2107750913'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', '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': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('09', 43),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 06092025 26604831 Nombre de photos uploadées : 43 / 23040 (0%) 06092025 26604831 Nombre de photos taguées (types de déchets): 0 / 43 (0%) 06092025 26604831 Nombre de photos taguées (volume) : 0 / 43 (0%) elapsed_time : load_data_split_time_score 4.5299530029296875e-06 elapsed_time : order_list_meta_photo_and_scores 1.1444091796875e-05 ??????????????????????????????????????????? elapsed_time : fill_and_build_computed_from_old_data 0.0026025772094726562 Catched exception ! Connect or reconnect ! Catched exception ! Connect or reconnect ! elapsed_time : insert_dashboard_record_day_entry 0.20437359809875488 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.21615461033950617 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26601766_06-09-2025_07_41_58.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26601766 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? 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`=26601766 AND mptpi.`type`=3594 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26604828 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26604829 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26604830 order by id desc limit 1 Qualite : 0.05311668113425926 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26604831_06-09-2025_10_31_08.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26604831 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? 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`=26604831 AND mptpi.`type`=3594 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'06092025': {'nb_upload': 43, 'nb_taggue_class': 0, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1381995886, 1381995825, 1381995810] Looping around the photos to save general results len do output : 1 /26604831Didn'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 ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995886', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995825', None, None, None, None, None, '3674031') ('3318', None, None, None, None, None, None, None, '3674031') ('3318', None, '1381995810', None, None, None, None, None, '3674031') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.01617741584777832 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.5549309253692627 time spend to save output : 0.0163724422454834 total time spend for step 10 : 3.571303367614746 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 3 set_done_treatment 21.87user 12.24system 0:53.28elapsed 64%CPU (0avgtext+0avgdata 2579848maxresident)k 536072inputs+17240outputs (241major+1079830minor)pagefaults 0swaps