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 : 1957539 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 : ['4022497'] with mtr_portfolio_ids : ['28352799'] and first list_photo_ids : [] new path : /proc/1957539/ 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 , BFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 8 ; length of list_pids : 8 ; length of list_args : 8 time to download the photos : 1.1077466011047363 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 Nov 8 11:40:29 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 2025-11-08 11:40:32.646319: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-11-08 11:40:32.670421: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-11-08 11:40:32.672460: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f2050000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-11-08 11:40:32.672510: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-11-08 11:40:32.676266: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-11-08 11:40:32.964128: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x16c18840 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-11-08 11:40:32.964172: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-11-08 11:40:32.965633: 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 2025-11-08 11:40:32.966020: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-08 11:40:32.973268: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-08 11:40:32.976604: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-08 11:40:32.976974: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-08 11:40:32.983133: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-08 11:40:32.984857: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-08 11:40:32.992625: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-08 11:40:32.994391: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-08 11:40:32.994464: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-08 11:40:32.995408: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-08 11:40:32.995426: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-08 11:40:32.995582: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-08 11:40:32.997331: 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. 2025-11-08 11:40:33.269488: 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 2025-11-08 11:40:33.269565: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-08 11:40:33.269585: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-08 11:40:33.269603: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-08 11:40:33.269621: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-08 11:40:33.269638: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-08 11:40:33.269655: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-08 11:40:33.269673: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-08 11:40:33.271270: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-08 11:40:33.272575: 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 2025-11-08 11:40:33.272609: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-08 11:40:33.272628: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-08 11:40:33.272645: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-08 11:40:33.272662: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-08 11:40:33.272679: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-08 11:40:33.272695: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-08 11:40:33.272712: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-08 11:40:33.274313: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-08 11:40:33.274345: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-08 11:40:33.274356: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-08 11:40:33.274365: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-08 11:40:33.275920: 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 : 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 : [] 2025-11-08 11:40:40.727077: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-08 11:40:40.918003: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-08 11:40:42.668860: E tensorflow/core/kernels/gpu_utils.cc:85] Detected cudnn out-of-bounds write in convolution buffer! This is likely a cudnn bug. We will skip this algorithm in the future, but your GPU state may already be corrupted, leading to incorrect results. Within Google, no action is needed on your part. Outside of Google, please ensure you're running the latest version of cudnn. If that doesn't fix the problem, please file a bug with this full error message and we'll contact nvidia. 2025-11-08 11:40:42.668926: E tensorflow/core/kernels/gpu_utils.cc:93] Redzone mismatch in LHS redzone of buffer 0x7f1e57200000 at offset 3426840; expected ffffffffffffffff but was ffffffff3eb4c952. 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 : 8 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 34.00000 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 : 2 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 26.00000 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 : 9 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 27.00000 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: 29.00000 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 : 1 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 21.00000 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 : 6 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 18.00000 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: 34.00000 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: 31.00000 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 Detection mask done ! Trying to reset tf kernel 1958193 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 4907 tf kernel not reseted sub process len(results) : 8 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 8 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 : 10180 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 : 0.00021076202392578125 nb_pixel_total : 6437 time to create 1 rle with old method : 0.0071485042572021484 length of segment : 131 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 2474 time to create 1 rle with old method : 0.002849578857421875 length of segment : 51 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 3737 time to create 1 rle with old method : 0.004402637481689453 length of segment : 81 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 3673 time to create 1 rle with old method : 0.004285097122192383 length of segment : 59 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 2329 time to create 1 rle with old method : 0.0027663707733154297 length of segment : 49 time for calcul the mask position with numpy : 0.0002734661102294922 nb_pixel_total : 16257 time to create 1 rle with old method : 0.017774581909179688 length of segment : 170 time for calcul the mask position with numpy : 0.0018510818481445312 nb_pixel_total : 122589 time to create 1 rle with old method : 0.13645648956298828 length of segment : 509 time for calcul the mask position with numpy : 0.011586189270019531 nb_pixel_total : 787416 time to create 1 rle with new method : 0.029537677764892578 length of segment : 1036 time for calcul the mask position with numpy : 0.0012133121490478516 nb_pixel_total : 100049 time to create 1 rle with old method : 0.10952138900756836 length of segment : 513 time spent for convertir_results : 0.9986109733581543 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 9 chid ids of type : 3594 Number RLEs to save : 2599 save missing photos in datou_result : time spend for datou_step_exec : 21.48636507987976 time spend to save output : 0.23767971992492676 total time spend for step 1 : 21.724044799804688 step2:crop_condition Sat Nov 8 11:40:51 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 : 8 ! batch 1 Loaded 9 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 ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3736932 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1762598452_1957539 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(1762598452), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157480_0.png', 0, 58, 51, 0, 1762598452,'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(1762598452), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157479_0.png', 0, 93, 131, 0, 1762598452,'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(1762598452), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157483_0.png', 0, 66, 48, 0, 1762598452,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 3 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.9996359348297119 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 ! 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 : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3736932 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1762598453_1957539 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(1762598454), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157481_0.png', 0, 58, 81, 0, 1762598454,'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(1762598454), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396588_e327d56add6c2eb8eff1eff7fa67931b_rle_crop_4027157482_0.png', 0, 86, 59, 0, 1762598454,'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(1762598454), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157484_0.png', 0, 136, 169, 0, 1762598454,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 3 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.0172083377838135 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 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 ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3736932 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1762598458_1957539 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(1762598459), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157486_0.png', 0, 1136, 992, 0, 1762598459,'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(1762598459), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157485_0.png', 0, 403, 504, 0, 1762598459,'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(1762598459), 0.0, 0.0, 14, '', 0, 0, '1762598428_1957539_1393396585_89208ad2f3dee012ca5e21e1cf834463_rle_crop_4027157487_0.png', 0, 328, 510, 0, 1762598459,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 3 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.3968980312347412 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 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 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 [1393396590, 1393396589, 1393396588, 1393396587, 1393396586, 1393396585, 1393396495, 1393396494] Looping around the photos to save general results len do output : 9 /1393397805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393397806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393397807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393397808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393397809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393397810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393397812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393397813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393397814Didn'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, '4022497') ('3318', '28352799', '1393396590', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396589', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396588', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396587', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396586', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396585', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396495', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396494', None, None, None, None, None, '4022497') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 35 time used for this insertion : 0.017319679260253906 save_final save missing photos in datou_result : time spend for datou_step_exec : 8.15322756767273 time spend to save output : 0.01790142059326172 total time spend for step 2 : 8.171128988265991 step3:rle_unique_nms_with_priority Sat Nov 8 11:40:59 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 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 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 9 chid ids of type : 3594 +++++++++++ No data in photo_id : 1393396590 nb_obj : 3 nb_hashtags : 2 time to prepare the origin masks : 0.2626464366912842 time for calcul the mask position with numpy : 0.1447293758392334 nb_pixel_total : 2060952 time to create 1 rle with new method : 0.25188326835632324 time for calcul the mask position with numpy : 0.006508827209472656 nb_pixel_total : 3737 time to create 1 rle with old method : 0.0043947696685791016 time for calcul the mask position with numpy : 0.007120609283447266 nb_pixel_total : 2474 time to create 1 rle with old method : 0.0027952194213867188 time for calcul the mask position with numpy : 0.0065844058990478516 nb_pixel_total : 6437 time to create 1 rle with old method : 0.007528066635131836 create new chi : 0.44184398651123047 time to delete rle : 0.031670331954956055 batch 1 Loaded 7 chid ids of type : 3594 +++Number RLEs to save : 1606 TO DO : save crop sub photo not yet done ! save time : 0.14547085762023926 nb_obj : 1 nb_hashtags : 1 time to prepare the origin masks : 0.1430222988128662 time for calcul the mask position with numpy : 0.07024192810058594 nb_pixel_total : 2069927 time to create 1 rle with new method : 0.16956853866577148 time for calcul the mask position with numpy : 0.009552478790283203 nb_pixel_total : 3673 time to create 1 rle with old method : 0.004357814788818359 create new chi : 0.2539811134338379 time to delete rle : 0.00032019615173339844 batch 1 Loaded 3 chid ids of type : 3594 +Number RLEs to save : 1198 TO DO : save crop sub photo not yet done ! save time : 0.11857485771179199 No data in photo_id : 1393396587 nb_obj : 4 nb_hashtags : 3 time to prepare the origin masks : 0.21328520774841309 time for calcul the mask position with numpy : 0.13205814361572266 nb_pixel_total : 1147103 time to create 1 rle with new method : 0.13159632682800293 time for calcul the mask position with numpy : 0.017281055450439453 nb_pixel_total : 785322 time to create 1 rle with new method : 0.29260849952697754 time for calcul the mask position with numpy : 0.007415294647216797 nb_pixel_total : 122589 time to create 1 rle with old method : 0.13892412185668945 time for calcul the mask position with numpy : 0.006064891815185547 nb_pixel_total : 16257 time to create 1 rle with old method : 0.018424510955810547 time for calcul the mask position with numpy : 0.006293058395385742 nb_pixel_total : 2329 time to create 1 rle with old method : 0.002663850784301758 create new chi : 0.7728908061981201 time to delete rle : 0.0004544258117675781 batch 1 Loaded 9 chid ids of type : 3594 ++++++Number RLEs to save : 4469 TO DO : save crop sub photo not yet done ! save time : 0.2951817512512207 nb_obj : 1 nb_hashtags : 1 time to prepare the origin masks : 0.03484153747558594 time for calcul the mask position with numpy : 0.01981496810913086 nb_pixel_total : 1973551 time to create 1 rle with new method : 0.0552518367767334 time for calcul the mask position with numpy : 0.006969928741455078 nb_pixel_total : 100049 time to create 1 rle with old method : 0.11134815216064453 create new chi : 0.19370317459106445 time to delete rle : 0.0002722740173339844 batch 1 Loaded 3 chid ids of type : 3594 +Number RLEs to save : 2106 TO DO : save crop sub photo not yet done ! save time : 0.18085193634033203 No data in photo_id : 1393396495 No data in photo_id : 1393396494 map_output_result : {1393396590: (0.0, 'Should be the crop_list due to order', 0.0), 1393396589: (0.0, 'Should be the crop_list due to order', 0), 1393396588: (0.0, 'Should be the crop_list due to order', 0), 1393396587: (0.0, 'Should be the crop_list due to order', 0.0), 1393396586: (0.0, 'Should be the crop_list due to order', 0), 1393396585: (0.0, 'Should be the crop_list due to order', 0), 1393396495: (0.0, 'Should be the crop_list due to order', 0.0), 1393396494: (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 [1393396590, 1393396589, 1393396588, 1393396587, 1393396586, 1393396585, 1393396495, 1393396494] Looping around the photos to save general results len do output : 8 /1393396590.Didn't retrieve data . /1393396589.Didn't retrieve data . /1393396588.Didn't retrieve data . /1393396587.Didn't retrieve data . /1393396586.Didn't retrieve data . /1393396585.Didn't retrieve data . /1393396495.Didn't retrieve data . /1393396494.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, '4022497') ('3318', '28352799', '1393396590', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396589', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396588', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396587', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396586', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396585', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396495', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396494', None, None, None, None, None, '4022497') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 24 time used for this insertion : 0.01322793960571289 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.2766799926757812 time spend to save output : 0.013570308685302734 total time spend for step 3 : 3.290250301361084 step4:ventilate_hashtags_in_portfolio Sat Nov 8 11:41:03 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 : 28352799 get user id for portfolio 28352799 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`=28352799 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pehd','autre','flou','pet_fonce','environnement','papier','pet_clair','background','metal','carton','mal_croppe')) 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`=28352799 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pehd','autre','flou','pet_fonce','environnement','papier','pet_clair','background','metal','carton','mal_croppe')) AND mptpi.`min_score`=0.5 To do Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") 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`=28352799 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pehd','autre','flou','pet_fonce','environnement','papier','pet_clair','background','metal','carton','mal_croppe')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://marlene.fotonower.com/velours/28352925,28352926,28352927,28352928,28352929,28352930,28352931,28352932,28352933,28352934,28352935?tags=pehd,autre,flou,pet_fonce,environnement,papier,pet_clair,background,metal,carton,mal_croppe Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1393396590, 1393396589, 1393396588, 1393396587, 1393396586, 1393396585, 1393396495, 1393396494] Looping around the photos to save general results len do output : 1 /28352799. 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, '4022497') ('3318', '28352799', '1393396590', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396589', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396588', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396587', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396586', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396585', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396495', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396494', None, None, None, None, None, '4022497') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.014510869979858398 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.6642498970031738 time spend to save output : 0.014751672744750977 total time spend for step 4 : 1.6790015697479248 step5:final Sat Nov 8 11:41:04 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 : {1393396590: ('0.06286572868441358',), 1393396589: ('0.06286572868441358',), 1393396588: ('0.06286572868441358',), 1393396587: ('0.06286572868441358',), 1393396586: ('0.06286572868441358',), 1393396585: ('0.06286572868441358',), 1393396495: ('0.06286572868441358',), 1393396494: ('0.06286572868441358',)} new output for save of step final : {1393396590: ('0.06286572868441358',), 1393396589: ('0.06286572868441358',), 1393396588: ('0.06286572868441358',), 1393396587: ('0.06286572868441358',), 1393396586: ('0.06286572868441358',), 1393396585: ('0.06286572868441358',), 1393396495: ('0.06286572868441358',), 1393396494: ('0.06286572868441358',)} [1393396590, 1393396589, 1393396588, 1393396587, 1393396586, 1393396585, 1393396495, 1393396494] Looping around the photos to save general results len do output : 8 /1393396590.Didn't retrieve data . /1393396589.Didn't retrieve data . /1393396588.Didn't retrieve data . /1393396587.Didn't retrieve data . /1393396586.Didn't retrieve data . /1393396585.Didn't retrieve data . /1393396495.Didn't retrieve data . /1393396494.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, '4022497') ('3318', '28352799', '1393396590', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396589', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396588', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396587', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396586', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396585', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396495', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396494', None, None, None, None, None, '4022497') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 24 time used for this insertion : 0.015464067459106445 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11807560920715332 time spend to save output : 0.015877723693847656 total time spend for step 5 : 0.13395333290100098 step6:blur_detection Sat Nov 8 11:41:04 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 inside step blur_detection methode: ratio et variance treat image : temp/1762598428_1957539_1393396590_83616d291e62d3b96aaca49b1e02e079.jpg resize: (1080, 1920) 1393396590 -2.5539518858642123 treat image : temp/1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915.jpg resize: (1080, 1920) 1393396589 -2.243838939415677 treat image : temp/1762598428_1957539_1393396588_e327d56add6c2eb8eff1eff7fa67931b.jpg resize: (1080, 1920) 1393396588 -2.265615902992142 treat image : temp/1762598428_1957539_1393396587_81169ff5399e066e46aeb5de509181d4.jpg resize: (1080, 1920) 1393396587 -1.6344401843859893 treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea.jpg resize: (1080, 1920) 1393396586 -2.4250681262366736 treat image : temp/1762598428_1957539_1393396585_89208ad2f3dee012ca5e21e1cf834463.jpg resize: (1080, 1920) 1393396585 0.8926854924476793 treat image : temp/1762598428_1957539_1393396495_105d2d0d7170147e0822730783898eb2.jpg resize: (1080, 1920) 1393396495 -2.144875927043263 treat image : temp/1762598428_1957539_1393396494_ae10c37eac2bed64265e14e4235c4396.jpg resize: (1080, 1920) 1393396494 -2.441492844914161 treat image : temp/1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157480_0.png resize: (51, 58) 1393397805 4.635177771970166 treat image : temp/1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157479_0.png resize: (131, 93) 1393397806 -1.7627700191241658 treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157483_0.png resize: (48, 66) 1393397807 0.777091622722314 treat image : temp/1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157481_0.png resize: (81, 58) 1393397808 4.381441488652602 treat image : temp/1762598428_1957539_1393396588_e327d56add6c2eb8eff1eff7fa67931b_rle_crop_4027157482_0.png resize: (59, 86) 1393397809 -0.649086569531467 treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157484_0.png resize: (169, 136) 1393397810 -1.454728786921866 treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157486_0.png resize: (992, 1136) 1393397812 -0.5309274343739584 treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157485_0.png resize: (504, 403) 1393397813 -0.44850655431898867 treat image : temp/1762598428_1957539_1393396585_89208ad2f3dee012ca5e21e1cf834463_rle_crop_4027157487_0.png resize: (510, 328) 1393397814 0.24415238420448984 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 : 17 time used for this insertion : 0.01360321044921875 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 17 time used for this insertion : 0.01255345344543457 save missing photos in datou_result : time spend for datou_step_exec : 6.720806121826172 time spend to save output : 0.030831098556518555 total time spend for step 6 : 6.75163722038269 step7:brightness Sat Nov 8 11:41:11 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/1762598428_1957539_1393396590_83616d291e62d3b96aaca49b1e02e079.jpg treat image : temp/1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915.jpg treat image : temp/1762598428_1957539_1393396588_e327d56add6c2eb8eff1eff7fa67931b.jpg treat image : temp/1762598428_1957539_1393396587_81169ff5399e066e46aeb5de509181d4.jpg treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea.jpg treat image : temp/1762598428_1957539_1393396585_89208ad2f3dee012ca5e21e1cf834463.jpg treat image : temp/1762598428_1957539_1393396495_105d2d0d7170147e0822730783898eb2.jpg treat image : temp/1762598428_1957539_1393396494_ae10c37eac2bed64265e14e4235c4396.jpg treat image : temp/1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157480_0.png treat image : temp/1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157479_0.png treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157483_0.png treat image : temp/1762598428_1957539_1393396589_1781db3454dbf5a1aee1bf401dc22915_rle_crop_4027157481_0.png treat image : temp/1762598428_1957539_1393396588_e327d56add6c2eb8eff1eff7fa67931b_rle_crop_4027157482_0.png treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157484_0.png treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157486_0.png treat image : temp/1762598428_1957539_1393396586_f1ad97cddd0b21d8096cf35ce7b023ea_rle_crop_4027157485_0.png treat image : temp/1762598428_1957539_1393396585_89208ad2f3dee012ca5e21e1cf834463_rle_crop_4027157487_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 : 17 time used for this insertion : 0.01581597328186035 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 17 time used for this insertion : 0.014657974243164062 save missing photos in datou_result : time spend for datou_step_exec : 1.8704724311828613 time spend to save output : 0.034859418869018555 total time spend for step 7 : 1.9053318500518799 step8:velours_tree Sat Nov 8 11:41:13 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 : 0.1218099594116211 time spend to save output : 3.24249267578125e-05 total time spend for step 8 : 0.1218423843383789 step9:send_mail_cod Sat Nov 8 11:41:13 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_P28352799_08-11-2025_11_41_13.pdf 28352925 imagette283529251762598473 28352926 imagette283529261762598473 28352927 imagette283529271762598473 28352928 imagette283529281762598473 28352930 change filename to text .change filename to text .change filename to text .imagette283529301762598473 28352931 change filename to text .change filename to text .change filename to text .imagette283529311762598474 28352932 imagette283529321762598474 28352933 imagette283529331762598474 28352934 change filename to text .change filename to text .change filename to text .imagette283529341762598474 28352935 imagette283529351762598474 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=28352799 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://marlene.fotonower.com/velours/28352925,28352926,28352927,28352928,28352929,28352930,28352931,28352932,28352933,28352934,28352935?tags=pehd,autre,flou,pet_fonce,environnement,papier,pet_clair,background,metal,carton,mal_croppe args[1393396590] : ((1393396590, -2.5539518858642123, 492609224), (1393396590, 0.7095013659611548, 2107752395), '0.06286572868441358') We are sending mail with results at report@fotonower.com args[1393396589] : ((1393396589, -2.243838939415677, 492609224), (1393396589, 0.563941843613456, 2107752395), '0.06286572868441358') We are sending mail with results at report@fotonower.com args[1393396588] : ((1393396588, -2.265615902992142, 492609224), (1393396588, 0.46522568681978277, 2107752395), '0.06286572868441358') We are sending mail with results at report@fotonower.com args[1393396587] : ((1393396587, -1.6344401843859893, 492688767), (1393396587, 0.6503669524156008, 2107752395), '0.06286572868441358') We are sending mail with results at report@fotonower.com args[1393396586] : ((1393396586, -2.4250681262366736, 492609224), (1393396586, 0.3682132452427374, 2107752395), '0.06286572868441358') We are sending mail with results at report@fotonower.com args[1393396585] : ((1393396585, 0.8926854924476793, 492688767), (1393396585, 0.1970837460100433, 2107752395), '0.06286572868441358') We are sending mail with results at report@fotonower.com args[1393396495] : ((1393396495, -2.144875927043263, 492609224), (1393396495, 0.5537968976923835, 2107752395), '0.06286572868441358') We are sending mail with results at report@fotonower.com args[1393396494] : ((1393396494, -2.441492844914161, 492609224), (1393396494, 0.7157890800075662, 2107752395), '0.06286572868441358') We are sending mail with results at report@fotonower.com refus_total : 0.06286572868441358 2022-04-13 10:29:59 0 SELECT ph.photo_id,ph.url,ph.username,ph.uploaded_at,ph.text FROM MTRBack.photos_view ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=28352799 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_P28352799_08-11-2025_11_41_13.pdf results_Auto_P28352799_08-11-2025_11_41_13.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28352799_08-11-2025_11_41_13.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','28352799','results_Auto_P28352799_08-11-2025_11_41_13.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28352799_08-11-2025_11_41_13.pdf','pdf','','0.17','0.06286572868441358') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/28352799

https://www.fotonower.com/image?json=false&list_photos_id=1393396590
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1393396589
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1393396588
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1393396587
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1393396586
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1393396585
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1393396495
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1393396494
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 6.29%
Veuillez trouver les photos des contaminants.

exemples de contaminants: papier: https://www.fotonower.com/view/28352930?limit=200
exemples de contaminants: pet_clair: https://www.fotonower.com/view/28352931?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/28352934?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28352799_08-11-2025_11_41_13.pdf.

Lien vers velours :https://marlene.fotonower.com/velours/28352925,28352926,28352927,28352928,28352929,28352930,28352931,28352932,28352933,28352934,28352935?tags=pehd,autre,flou,pet_fonce,environnement,papier,pet_clair,background,metal,carton,mal_croppe.


L'équipe Fotonower 202 b'' Date: Sat, 08 Nov 2025 10:41:15 GMT Content-Length: 0 Connection: close Server: nginx X-Message-Id: -vXedZsLSvOosapIU223GQ 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 [1393396590, 1393396589, 1393396588, 1393396587, 1393396586, 1393396585, 1393396495, 1393396494] 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, '4022497') ('3318', '28352799', '1393396590', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396589', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396588', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396587', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396586', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396585', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396495', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396494', None, None, None, None, None, '4022497') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 8 time used for this insertion : 0.01626133918762207 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.226844072341919 time spend to save output : 0.016453981399536133 total time spend for step 9 : 2.243298053741455 step10:split_time_score Sat Nov 8 11:41:16 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'}] (('11', 8),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 08112025 28352799 Nombre de photos uploadées : 8 / 23040 (0%) 08112025 28352799 Nombre de photos taguées (types de déchets): 0 / 8 (0%) 08112025 28352799 Nombre de photos taguées (volume) : 0 / 8 (0%) elapsed_time : load_data_split_time_score 1.6689300537109375e-06 elapsed_time : order_list_meta_photo_and_scores 5.0067901611328125e-06 ???????? elapsed_time : fill_and_build_computed_from_old_data 0.0004150867462158203 Catched exception ! Connect or reconnect ! Catched exception ! Connect or reconnect ! elapsed_time : insert_dashboard_record_day_entry 0.21504664421081543 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 : 0.09208728780864198 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28348936_08-11-2025_11_01_31.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 28348936 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`=28348936 AND mptpi.`type`=3594 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 28352790 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 28352791 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 28352794 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 28352797 order by id desc limit 1 Qualite : 0.06286572868441358 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28352799_08-11-2025_11_41_13.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 28352799 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`=28352799 AND mptpi.`type`=3594 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'08112025': {'nb_upload': 8, '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 [1393396590, 1393396589, 1393396588, 1393396587, 1393396586, 1393396585, 1393396495, 1393396494] Looping around the photos to save general results len do output : 1 /28352799Didn'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, '4022497') ('3318', '28352799', '1393396590', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396589', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396588', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396587', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396586', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396585', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396495', None, None, None, None, None, '4022497') ('3318', None, None, None, None, None, None, None, '4022497') ('3318', '28352799', '1393396494', None, None, None, None, None, '4022497') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.014426469802856445 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.150175333023071 time spend to save output : 0.014606714248657227 total time spend for step 10 : 5.1647820472717285 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 8 set_done_treatment 27.80user 15.74system 0:56.68elapsed 76%CPU (0avgtext+0avgdata 2630592maxresident)k 623752inputs+10184outputs (1561major+1068448minor)pagefaults 0swaps