python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 10 -a ' -a 4234 -l 5 ' -s datou_current_4234 -M 0 -S 0 -U 95,95,80 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 : 597117 load datou : 4234 # 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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 ? 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 ? 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 ? [ (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 ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl 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 ? 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)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 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 : 4234, datou_cur_ids : ['2657890'] with mtr_portfolio_ids : ['21280472'] and first list_photo_ids : [] new path : /proc/597117/ 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 0.6176493167877197 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 : 11 step1:mask_detect Tue Mar 11 12:20:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3160 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-11 12:20:33.985841: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-11 12:20:34.011164: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-11 12:20:34.013636: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f73fc000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-11 12:20:34.013690: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-11 12:20:34.019311: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-11 12:20:34.312456: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1be88240 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-11 12:20:34.312516: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-11 12:20:34.313695: 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 2025-03-11 12:20:34.314249: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-11 12:20:34.317790: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-11 12:20:34.321378: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-11 12:20:34.322292: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-11 12:20:34.325335: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-11 12:20:34.326745: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-11 12:20:34.332357: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-11 12:20:34.333482: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-11 12:20:34.333558: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-11 12:20:34.334116: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-11 12:20:34.334132: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-11 12:20:34.334141: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-11 12:20:34.335753: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2708 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. 2025-03-11 12:20:34.804130: 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 2025-03-11 12:20:34.804308: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-11 12:20:34.804355: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-11 12:20:34.804392: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-11 12:20:34.804438: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-11 12:20:34.804480: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-11 12:20:34.804517: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-11 12:20:34.804550: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-11 12:20:34.805773: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-11 12:20:34.807028: 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 2025-03-11 12:20:34.807138: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-11 12:20:34.807162: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-11 12:20:34.807184: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-11 12:20:34.807425: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-11 12:20:34.807466: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-11 12:20:34.807486: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-11 12:20:34.807506: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-11 12:20:34.808609: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-11 12:20:34.808654: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-11 12:20:34.808665: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-11 12:20:34.808675: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-11 12:20:34.809805: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2708 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 : [] 2025-03-11 12:20:43.319084: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-11 12:20:43.619557: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-11 12:20:45.819468: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.819546: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.820151: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.820169: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.827347: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.827375: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.827952: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.827968: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.834592: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.834617: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.835201: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.835218: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.866514: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.866545: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.867164: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.867184: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.873129: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.873157: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.873741: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.873758: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 12:20:45.909952: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.910559: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.912436: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.913018: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.959006: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.959608: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.988682: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.989285: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.990810: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:45.991409: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.023315: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.023926: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.025607: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.026187: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.031964: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.032580: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.034083: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.034664: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.063417: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.064081: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.064647: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.065191: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.069025: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.069571: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.085442: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.086086: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.086670: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.087263: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.100527: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.101155: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.101738: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.102317: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.106966: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.107603: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.112532: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.113150: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.125528: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.126173: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.130444: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.131062: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.131648: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.132228: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.133159: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.133749: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.144784: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.145419: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.146022: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.146601: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.147214: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.147799: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.163367: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.164259: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.197879: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.197937: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-03-11 12:20:46.198985: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.200004: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.207144: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.207887: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.216174: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.216832: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.235942: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.236731: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.237541: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.238263: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.242274: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.242819: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.243398: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.243981: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.245948: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.255069: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.255663: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.265379: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.266199: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.266796: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.267387: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.268002: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 12:20:46.268601: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.15G (2304638976 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 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 : 5 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.78984 max: 145.05703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0003857612609863281 length of segment : 40 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 34 time to create 1 rle with old method : 9.846687316894531e-05 length of segment : 10 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.0014617443084716797 length of segment : 52 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 692 time to create 1 rle with old method : 0.0013659000396728516 length of segment : 45 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.00018310546875 length of segment : 19 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1779 time to create 1 rle with old method : 0.003278970718383789 length of segment : 65 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 2042 time to create 1 rle with old method : 0.0038323402404785156 length of segment : 50 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.62969 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 830 time to create 1 rle with old method : 0.0011594295501708984 length of segment : 38 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 1286 time to create 1 rle with old method : 0.0020825862884521484 length of segment : 35 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 2712 time to create 1 rle with old method : 0.0037491321563720703 length of segment : 87 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0015518665313720703 length of segment : 74 Processing 1 images image shape: (400, 400, 3) min: 33.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -88.10234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 2406 time to create 1 rle with old method : 0.0035762786865234375 length of segment : 47 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.50078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00013589859008789062 nb_pixel_total : 5395 time to create 1 rle with old method : 0.007999897003173828 length of segment : 150 time for calcul the mask position with numpy : 0.00017118453979492188 nb_pixel_total : 5184 time to create 1 rle with old method : 0.006452083587646484 length of segment : 140 Processing 1 images image shape: (400, 320, 3) min: 0.00000 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: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0008285045623779297 length of segment : 17 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.00047969818115234375 length of segment : 29 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1441 time to create 1 rle with old method : 0.0020589828491210938 length of segment : 101 time for calcul the mask position with numpy : 0.0007545948028564453 nb_pixel_total : 63257 time to create 1 rle with old method : 0.08091306686401367 length of segment : 316 time for calcul the mask position with numpy : 0.0008966922760009766 nb_pixel_total : 67692 time to create 1 rle with old method : 0.09861493110656738 length of segment : 307 Processing 1 images image shape: (400, 400, 3) min: 22.00000 max: 200.00000 molded_images shape: (1, 640, 640, 3) min: -91.09844 max: 77.01016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 253.00000 molded_images shape: (1, 640, 640, 3) min: -116.92266 max: 131.87734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0005486011505126953 length of segment : 21 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0006077289581298828 length of segment : 22 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 1831 time to create 1 rle with old method : 0.004098415374755859 length of segment : 38 time for calcul the mask position with numpy : 0.0005388259887695312 nb_pixel_total : 23050 time to create 1 rle with old method : 0.032523155212402344 length of segment : 251 time for calcul the mask position with numpy : 0.00019931793212890625 nb_pixel_total : 3038 time to create 1 rle with old method : 0.005218505859375 length of segment : 61 Processing 1 images image shape: (400, 400, 3) min: 8.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.03594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.0005104541778564453 length of segment : 16 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00031638145446777344 length of segment : 8 time for calcul the mask position with numpy : 0.0001270771026611328 nb_pixel_total : 1807 time to create 1 rle with old method : 0.012778520584106445 length of segment : 45 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00040221214294433594 length of segment : 15 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.001073598861694336 length of segment : 17 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0011668205261230469 length of segment : 27 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0011112689971923828 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.36797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0003380775451660156 length of segment : 16 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001952648162841797 length of segment : 9 time for calcul the mask position with numpy : 0.000255584716796875 nb_pixel_total : 14575 time to create 1 rle with old method : 0.01704859733581543 length of segment : 129 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1118 time to create 1 rle with old method : 0.0014507770538330078 length of segment : 44 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1497 time to create 1 rle with old method : 0.0020961761474609375 length of segment : 27 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1304 time to create 1 rle with old method : 0.0016655921936035156 length of segment : 39 time for calcul the mask position with numpy : 0.00010895729064941406 nb_pixel_total : 1576 time to create 1 rle with old method : 0.0020825862884521484 length of segment : 99 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.0002913475036621094 length of segment : 13 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 1410 time to create 1 rle with old method : 0.0018346309661865234 length of segment : 44 time for calcul the mask position with numpy : 0.00021457672119140625 nb_pixel_total : 12382 time to create 1 rle with old method : 0.015371322631835938 length of segment : 172 time for calcul the mask position with numpy : 0.000301361083984375 nb_pixel_total : 6560 time to create 1 rle with old method : 0.010254383087158203 length of segment : 144 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 387 time to create 1 rle with old method : 0.0006115436553955078 length of segment : 23 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0007009506225585938 length of segment : 20 time for calcul the mask position with numpy : 0.000354766845703125 nb_pixel_total : 8098 time to create 1 rle with old method : 0.011555910110473633 length of segment : 239 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0005779266357421875 length of segment : 17 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.22891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 2200 time to create 1 rle with old method : 0.002744436264038086 length of segment : 133 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 1578 time to create 1 rle with old method : 0.002279043197631836 length of segment : 73 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.0008821487426757812 length of segment : 47 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.0002586841583251953 length of segment : 16 time for calcul the mask position with numpy : 0.00011968612670898438 nb_pixel_total : 1618 time to create 1 rle with old method : 0.002666950225830078 length of segment : 143 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0007464885711669922 length of segment : 44 time for calcul the mask position with numpy : 0.00018215179443359375 nb_pixel_total : 3353 time to create 1 rle with old method : 0.005845069885253906 length of segment : 209 time for calcul the mask position with numpy : 0.00022935867309570312 nb_pixel_total : 4110 time to create 1 rle with old method : 0.0057675838470458984 length of segment : 212 Processing 1 images image shape: (280, 400, 3) min: 13.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 76.00234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0013747215270996094 nb_pixel_total : 104209 time to create 1 rle with old method : 0.15001296997070312 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.64297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0004703998565673828 length of segment : 23 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0004687309265136719 length of segment : 41 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0013213157653808594 length of segment : 68 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 784 time to create 1 rle with old method : 0.0010457038879394531 length of segment : 62 time for calcul the mask position with numpy : 0.000156402587890625 nb_pixel_total : 8010 time to create 1 rle with old method : 0.009844541549682617 length of segment : 114 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005919933319091797 length of segment : 31 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 918 time to create 1 rle with old method : 0.0012497901916503906 length of segment : 28 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1320 time to create 1 rle with old method : 0.0018658638000488281 length of segment : 40 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1187 time to create 1 rle with old method : 0.0021719932556152344 length of segment : 36 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.93984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0014026165008544922 length of segment : 31 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0005497932434082031 length of segment : 18 time for calcul the mask position with numpy : 0.00011491775512695312 nb_pixel_total : 868 time to create 1 rle with old method : 0.0021424293518066406 length of segment : 36 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.00028324127197265625 length of segment : 12 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.0003521442413330078 length of segment : 18 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.000606536865234375 length of segment : 43 time for calcul the mask position with numpy : 9.036064147949219e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0004608631134033203 length of segment : 14 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0005354881286621094 length of segment : 18 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.0003821849822998047 length of segment : 9 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0008180141448974609 length of segment : 24 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.0002238750457763672 length of segment : 9 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0012221336364746094 length of segment : 46 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.70156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0004687309265136719 length of segment : 16 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0005645751953125 length of segment : 31 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0004229545593261719 length of segment : 14 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1607 time to create 1 rle with old method : 0.0022182464599609375 length of segment : 71 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0011832714080810547 length of segment : 36 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 615 time to create 1 rle with old method : 0.0012521743774414062 length of segment : 35 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 129.85000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 369 time to create 1 rle with old method : 0.0005476474761962891 length of segment : 79 time for calcul the mask position with numpy : 0.0005986690521240234 nb_pixel_total : 24354 time to create 1 rle with old method : 0.032701969146728516 length of segment : 238 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.39531 max: 145.55312 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.0002810955047607422 length of segment : 34 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0018432140350341797 length of segment : 54 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 818 time to create 1 rle with old method : 0.0012347698211669922 length of segment : 54 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 34 time to create 1 rle with old method : 7.414817810058594e-05 length of segment : 9 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.00013017654418945312 length of segment : 20 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1998 time to create 1 rle with old method : 0.002615690231323242 length of segment : 52 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.0013675689697265625 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.30156 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 824 time to create 1 rle with old method : 0.001918792724609375 length of segment : 35 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 916 time to create 1 rle with old method : 0.0012788772583007812 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 22.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -91.88359 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.0001049041748046875 nb_pixel_total : 2884 time to create 1 rle with old method : 0.0040280818939208984 length of segment : 53 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1019 time to create 1 rle with old method : 0.0016965866088867188 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 16.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -101.20391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00013756752014160156 nb_pixel_total : 6076 time to create 1 rle with old method : 0.007490873336791992 length of segment : 150 Processing 1 images image shape: (400, 320, 3) min: 0.00000 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: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 541 time to create 1 rle with old method : 0.0010292530059814453 length of segment : 16 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0005080699920654297 length of segment : 32 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.001031637191772461 length of segment : 15 time for calcul the mask position with numpy : 0.0007646083831787109 nb_pixel_total : 58770 time to create 1 rle with old method : 0.08100557327270508 length of segment : 303 time for calcul the mask position with numpy : 0.0007941722869873047 nb_pixel_total : 73528 time to create 1 rle with old method : 0.08496761322021484 length of segment : 373 Processing 1 images image shape: (400, 400, 3) min: 23.00000 max: 194.00000 molded_images shape: (1, 640, 640, 3) min: -90.18438 max: 74.94766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0015683174133300781 nb_pixel_total : 154231 time to create 1 rle with new method : 0.002705812454223633 length of segment : 405 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 253.00000 molded_images shape: (1, 640, 640, 3) min: -109.10234 max: 129.32656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.00041937828063964844 length of segment : 23 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0005853176116943359 length of segment : 22 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1858 time to create 1 rle with old method : 0.003602266311645508 length of segment : 49 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.00043845176696777344 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -104.85625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002715587615966797 length of segment : 16 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 1812 time to create 1 rle with old method : 0.004232168197631836 length of segment : 45 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004668235778808594 length of segment : 27 time for calcul the mask position with numpy : 0.0004127025604248047 nb_pixel_total : 30347 time to create 1 rle with old method : 0.034987688064575195 length of segment : 210 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 1733 time to create 1 rle with old method : 0.002229928970336914 length of segment : 44 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 1413 time to create 1 rle with old method : 0.0029735565185546875 length of segment : 35 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00032019615173339844 length of segment : 9 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0011610984802246094 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.89922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0004889965057373047 length of segment : 16 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.00037670135498046875 length of segment : 9 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007426738739013672 length of segment : 49 time for calcul the mask position with numpy : 0.00055694580078125 nb_pixel_total : 14231 time to create 1 rle with old method : 0.021534442901611328 length of segment : 139 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 1690 time to create 1 rle with old method : 0.002604246139526367 length of segment : 28 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.000537872314453125 length of segment : 23 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 1639 time to create 1 rle with old method : 0.002070903778076172 length of segment : 106 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0017473697662353516 length of segment : 40 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00017952919006347656 length of segment : 19 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1005 time to create 1 rle with old method : 0.0017921924591064453 length of segment : 38 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 615 time to create 1 rle with old method : 0.0008533000946044922 length of segment : 55 time for calcul the mask position with numpy : 0.0003116130828857422 nb_pixel_total : 12414 time to create 1 rle with old method : 0.015291929244995117 length of segment : 165 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1429 time to create 1 rle with old method : 0.0017864704132080078 length of segment : 45 time for calcul the mask position with numpy : 0.000232696533203125 nb_pixel_total : 5461 time to create 1 rle with old method : 0.006965160369873047 length of segment : 137 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 254.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 2569 time to create 1 rle with old method : 0.004395246505737305 length of segment : 164 time for calcul the mask position with numpy : 9.775161743164062e-05 nb_pixel_total : 2079 time to create 1 rle with old method : 0.003556966781616211 length of segment : 133 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 1574 time to create 1 rle with old method : 0.0026998519897460938 length of segment : 77 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 820 time to create 1 rle with old method : 0.0014622211456298828 length of segment : 46 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006258487701416016 length of segment : 40 time for calcul the mask position with numpy : 0.00019812583923339844 nb_pixel_total : 3512 time to create 1 rle with old method : 0.00433349609375 length of segment : 210 time for calcul the mask position with numpy : 0.00027179718017578125 nb_pixel_total : 2861 time to create 1 rle with old method : 0.003583669662475586 length of segment : 168 time for calcul the mask position with numpy : 0.00024962425231933594 nb_pixel_total : 3284 time to create 1 rle with old method : 0.0045320987701416016 length of segment : 172 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.001607656478881836 length of segment : 45 Processing 1 images image shape: (280, 400, 3) min: 13.00000 max: 195.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 81.97500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0011930465698242188 nb_pixel_total : 104849 time to create 1 rle with old method : 0.1417372226715088 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.64297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.00046253204345703125 length of segment : 23 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1515 time to create 1 rle with old method : 0.0019729137420654297 length of segment : 110 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0004229545593261719 length of segment : 33 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1285 time to create 1 rle with old method : 0.0018546581268310547 length of segment : 40 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1149 time to create 1 rle with old method : 0.0016808509826660156 length of segment : 36 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.26250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0004317760467529297 length of segment : 18 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 575 time to create 1 rle with old method : 0.0007750988006591797 length of segment : 32 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 807 time to create 1 rle with old method : 0.0010590553283691406 length of segment : 36 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.00033736228942871094 length of segment : 17 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005071163177490234 length of segment : 29 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003838539123535156 length of segment : 28 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.0002377033233642578 length of segment : 14 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00019073486328125 length of segment : 13 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.0001499652862548828 length of segment : 9 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002892017364501953 length of segment : 15 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 419 time to create 1 rle with old method : 0.0006232261657714844 length of segment : 28 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006678104400634766 length of segment : 27 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.00080108642578125 length of segment : 58 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.00026488304138183594 length of segment : 17 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.87344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0003046989440917969 length of segment : 16 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 487 time to create 1 rle with old method : 0.0006780624389648438 length of segment : 29 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.0002875328063964844 length of segment : 15 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0018584728240966797 length of segment : 70 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 661 time to create 1 rle with old method : 0.0009026527404785156 length of segment : 37 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.00021910667419433594 length of segment : 17 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1406 time to create 1 rle with old method : 0.0025377273559570312 length of segment : 69 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 1723 time to create 1 rle with old method : 0.002591848373413086 length of segment : 94 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.0005390644073486328 nb_pixel_total : 29473 time to create 1 rle with old method : 0.038436174392700195 length of segment : 204 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.00031280517578125 length of segment : 65 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.96563 max: 145.11953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.00026297569274902344 length of segment : 31 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 39 time to create 1 rle with old method : 8.797645568847656e-05 length of segment : 13 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 661 time to create 1 rle with old method : 0.00091552734375 length of segment : 48 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 608 time to create 1 rle with old method : 0.0009140968322753906 length of segment : 47 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001590251922607422 length of segment : 21 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 18 time to create 1 rle with old method : 0.00010633468627929688 length of segment : 12 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1869 time to create 1 rle with old method : 0.0025336742401123047 length of segment : 50 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.11406 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1388 time to create 1 rle with old method : 0.0018498897552490234 length of segment : 27 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 738 time to create 1 rle with old method : 0.0009717941284179688 length of segment : 34 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 2153 time to create 1 rle with old method : 0.002674102783203125 length of segment : 83 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1134 time to create 1 rle with old method : 0.0014591217041015625 length of segment : 29 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 750 time to create 1 rle with old method : 0.0010912418365478516 length of segment : 33 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1124 time to create 1 rle with old method : 0.0017435550689697266 length of segment : 26 time for calcul the mask position with numpy : 0.00019788742065429688 nb_pixel_total : 6791 time to create 1 rle with old method : 0.00861215591430664 length of segment : 106 time for calcul the mask position with numpy : 0.00012826919555664062 nb_pixel_total : 843 time to create 1 rle with old method : 0.0016400814056396484 length of segment : 56 Processing 1 images image shape: (400, 400, 3) min: 36.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -82.41484 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 2355 time to create 1 rle with old method : 0.003561735153198242 length of segment : 51 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0006535053253173828 length of segment : 25 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 2108 time to create 1 rle with old method : 0.0036017894744873047 length of segment : 45 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 2119 time to create 1 rle with old method : 0.0029087066650390625 length of segment : 44 time for calcul the mask position with numpy : 9.894371032714844e-05 nb_pixel_total : 2649 time to create 1 rle with old method : 0.003584146499633789 length of segment : 53 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 939 time to create 1 rle with old method : 0.0015323162078857422 length of segment : 23 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1127 time to create 1 rle with old method : 0.0017783641815185547 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 18.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -105.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.0001163482666015625 nb_pixel_total : 4734 time to create 1 rle with old method : 0.006148815155029297 length of segment : 105 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 4981 time to create 1 rle with old method : 0.00737452507019043 length of segment : 128 Processing 1 images image shape: (400, 320, 3) min: 0.00000 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: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.0011005401611328125 length of segment : 17 time for calcul the mask position with numpy : 0.0006747245788574219 nb_pixel_total : 53378 time to create 1 rle with old method : 0.06233954429626465 length of segment : 305 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0007808208465576172 length of segment : 19 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 67 time to create 1 rle with old method : 0.00013375282287597656 length of segment : 9 time for calcul the mask position with numpy : 0.0007309913635253906 nb_pixel_total : 67549 time to create 1 rle with old method : 0.0802009105682373 length of segment : 352 time for calcul the mask position with numpy : 0.0006468296051025391 nb_pixel_total : 38714 time to create 1 rle with old method : 0.0483245849609375 length of segment : 346 Processing 1 images image shape: (400, 400, 3) min: 18.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -94.32891 max: 73.76406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.29375 max: 133.66641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.00034165382385253906 length of segment : 20 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 3086 time to create 1 rle with old method : 0.0038933753967285156 length of segment : 65 time for calcul the mask position with numpy : 0.0002446174621582031 nb_pixel_total : 12125 time to create 1 rle with old method : 0.015462875366210938 length of segment : 219 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003733634948730469 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.26250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1695 time to create 1 rle with old method : 0.002246379852294922 length of segment : 42 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.00025725364685058594 length of segment : 11 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002942085266113281 length of segment : 16 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.00027179718017578125 length of segment : 15 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0008556842803955078 length of segment : 19 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.00038170814514160156 length of segment : 21 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0005719661712646484 length of segment : 16 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.000804901123046875 length of segment : 27 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003516674041748047 length of segment : 20 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 39 time to create 1 rle with old method : 7.987022399902344e-05 length of segment : 8 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.59063 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.00029754638671875 length of segment : 15 time for calcul the mask position with numpy : 0.00020122528076171875 nb_pixel_total : 14283 time to create 1 rle with old method : 0.016887903213500977 length of segment : 130 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1625 time to create 1 rle with old method : 0.002201080322265625 length of segment : 28 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1230 time to create 1 rle with old method : 0.0015065670013427734 length of segment : 41 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0006330013275146484 length of segment : 44 time for calcul the mask position with numpy : 0.00042319297790527344 nb_pixel_total : 20824 time to create 1 rle with old method : 0.025414228439331055 length of segment : 327 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00019216537475585938 length of segment : 9 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 923 time to create 1 rle with old method : 0.001252889633178711 length of segment : 39 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1607 time to create 1 rle with old method : 0.0020585060119628906 length of segment : 103 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0004601478576660156 length of segment : 30 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00016832351684570312 length of segment : 19 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1436 time to create 1 rle with old method : 0.0018401145935058594 length of segment : 44 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1631 time to create 1 rle with old method : 0.0022814273834228516 length of segment : 29 time for calcul the mask position with numpy : 0.0002391338348388672 nb_pixel_total : 7449 time to create 1 rle with old method : 0.009106159210205078 length of segment : 163 time for calcul the mask position with numpy : 0.00021576881408691406 nb_pixel_total : 6636 time to create 1 rle with old method : 0.0077664852142333984 length of segment : 148 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 130.09219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1394 time to create 1 rle with old method : 0.0017061233520507812 length of segment : 74 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1757 time to create 1 rle with old method : 0.002281665802001953 length of segment : 103 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 2235 time to create 1 rle with old method : 0.0027980804443359375 length of segment : 150 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 766 time to create 1 rle with old method : 0.0009572505950927734 length of segment : 50 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.00016617774963378906 length of segment : 16 time for calcul the mask position with numpy : 0.00021409988403320312 nb_pixel_total : 2500 time to create 1 rle with old method : 0.0031752586364746094 length of segment : 173 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.0010602474212646484 length of segment : 44 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0007953643798828125 length of segment : 39 time for calcul the mask position with numpy : 0.0001323223114013672 nb_pixel_total : 2540 time to create 1 rle with old method : 0.0031180381774902344 length of segment : 171 time for calcul the mask position with numpy : 0.00014400482177734375 nb_pixel_total : 2748 time to create 1 rle with old method : 0.0033991336822509766 length of segment : 163 Processing 1 images image shape: (280, 400, 3) min: 17.00000 max: 194.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 75.08437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008974075317382812 nb_pixel_total : 104882 time to create 1 rle with old method : 0.12882184982299805 length of segment : 281 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 128.16641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00017142295837402344 nb_pixel_total : 10396 time to create 1 rle with old method : 0.013598918914794922 length of segment : 146 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004608631134033203 length of segment : 23 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.00044798851013183594 length of segment : 23 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 1224 time to create 1 rle with old method : 0.0015707015991210938 length of segment : 37 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1327 time to create 1 rle with old method : 0.0017161369323730469 length of segment : 40 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.18203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 20 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007061958312988281 length of segment : 29 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.0002269744873046875 length of segment : 14 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.00020313262939453125 length of segment : 12 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 988 time to create 1 rle with old method : 0.001262664794921875 length of segment : 41 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.00030350685119628906 length of segment : 17 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0003483295440673828 length of segment : 16 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.00032591819763183594 length of segment : 29 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0006268024444580078 length of segment : 26 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001697540283203125 length of segment : 9 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.03359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004534721374511719 length of segment : 31 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1514 time to create 1 rle with old method : 0.0019702911376953125 length of segment : 73 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.00027108192443847656 length of segment : 15 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00016164779663085938 length of segment : 16 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0007915496826171875 length of segment : 36 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 762 time to create 1 rle with old method : 0.0010266304016113281 length of segment : 43 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00031685829162597656 length of segment : 16 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.53750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0007803440093994141 length of segment : 100 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003848075866699219 length of segment : 32 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.25859 max: 145.36953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002741813659667969 length of segment : 31 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 40 time to create 1 rle with old method : 9.560585021972656e-05 length of segment : 11 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 670 time to create 1 rle with old method : 0.0009415149688720703 length of segment : 52 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00013256072998046875 length of segment : 19 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 603 time to create 1 rle with old method : 0.0009024143218994141 length of segment : 42 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001785755157470703 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.86016 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1241 time to create 1 rle with old method : 0.0017681121826171875 length of segment : 26 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 951 time to create 1 rle with old method : 0.0011677742004394531 length of segment : 38 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 865 time to create 1 rle with old method : 0.0011432170867919922 length of segment : 36 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 964 time to create 1 rle with old method : 0.0012431144714355469 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 27.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -87.89922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 2918 time to create 1 rle with old method : 0.0038650035858154297 length of segment : 53 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 2346 time to create 1 rle with old method : 0.002894878387451172 length of segment : 48 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 2413 time to create 1 rle with old method : 0.003155231475830078 length of segment : 51 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 2438 time to create 1 rle with old method : 0.0034532546997070312 length of segment : 47 Processing 1 images image shape: (400, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.18828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00014162063598632812 nb_pixel_total : 5772 time to create 1 rle with old method : 0.006691694259643555 length of segment : 127 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1336 time to create 1 rle with old method : 0.0016069412231445312 length of segment : 55 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 5775 time to create 1 rle with old method : 0.0073108673095703125 length of segment : 123 Processing 1 images image shape: (400, 320, 3) min: 0.00000 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: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 549 time to create 1 rle with old method : 0.0011706352233886719 length of segment : 16 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.000301361083984375 length of segment : 13 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 673 time to create 1 rle with old method : 0.0013132095336914062 length of segment : 109 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0011849403381347656 length of segment : 16 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0013496875762939453 length of segment : 17 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.0005209445953369141 length of segment : 52 time for calcul the mask position with numpy : 0.001172780990600586 nb_pixel_total : 69993 time to create 1 rle with old method : 0.09351921081542969 length of segment : 427 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 193.00000 molded_images shape: (1, 640, 640, 3) min: -92.02422 max: 70.82266 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 249.00000 molded_images shape: (1, 640, 640, 3) min: -114.85625 max: 136.49062 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00032830238342285156 length of segment : 21 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 3077 time to create 1 rle with old method : 0.00386810302734375 length of segment : 63 time for calcul the mask position with numpy : 0.00017142295837402344 nb_pixel_total : 6852 time to create 1 rle with old method : 0.008586645126342773 length of segment : 219 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003139972686767578 length of segment : 25 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.00022411346435546875 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.83672 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.0003612041473388672 length of segment : 16 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0002732276916503906 length of segment : 9 time for calcul the mask position with numpy : 0.00040912628173828125 nb_pixel_total : 20785 time to create 1 rle with old method : 0.03147387504577637 length of segment : 196 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 1738 time to create 1 rle with old method : 0.002299785614013672 length of segment : 45 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 652 time to create 1 rle with old method : 0.0012416839599609375 length of segment : 31 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1676 time to create 1 rle with old method : 0.0025882720947265625 length of segment : 35 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00014448165893554688 length of segment : 14 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1735 time to create 1 rle with old method : 0.0022068023681640625 length of segment : 101 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003237724304199219 length of segment : 23 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 1483 time to create 1 rle with old method : 0.0019881725311279297 length of segment : 112 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 522 time to create 1 rle with old method : 0.0007338523864746094 length of segment : 17 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003859996795654297 length of segment : 20 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.00021409988403320312 length of segment : 35 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0007140636444091797 length of segment : 25 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0014061927795410156 length of segment : 39 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 1585 time to create 1 rle with old method : 0.003784656524658203 length of segment : 55 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.93047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00031948089599609375 length of segment : 16 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.000179290771484375 length of segment : 9 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 1468 time to create 1 rle with old method : 0.0020542144775390625 length of segment : 25 time for calcul the mask position with numpy : 0.0002682209014892578 nb_pixel_total : 14857 time to create 1 rle with old method : 0.01824665069580078 length of segment : 137 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0005671977996826172 length of segment : 31 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1335 time to create 1 rle with old method : 0.0016698837280273438 length of segment : 40 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 1567 time to create 1 rle with old method : 0.0020160675048828125 length of segment : 109 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1447 time to create 1 rle with old method : 0.0017931461334228516 length of segment : 43 time for calcul the mask position with numpy : 0.0005748271942138672 nb_pixel_total : 19647 time to create 1 rle with old method : 0.024205446243286133 length of segment : 308 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001628398895263672 length of segment : 19 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0006191730499267578 length of segment : 44 time for calcul the mask position with numpy : 0.00049591064453125 nb_pixel_total : 25570 time to create 1 rle with old method : 0.030346155166625977 length of segment : 395 time for calcul the mask position with numpy : 0.00021505355834960938 nb_pixel_total : 12434 time to create 1 rle with old method : 0.014648675918579102 length of segment : 180 time for calcul the mask position with numpy : 0.0002353191375732422 nb_pixel_total : 7726 time to create 1 rle with old method : 0.009163856506347656 length of segment : 150 time for calcul the mask position with numpy : 0.0001990795135498047 nb_pixel_total : 6713 time to create 1 rle with old method : 0.008192300796508789 length of segment : 158 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.00047898292541503906 length of segment : 30 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1613 time to create 1 rle with old method : 0.0021514892578125 length of segment : 27 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 134.73672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 1548 time to create 1 rle with old method : 0.002050161361694336 length of segment : 132 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.00015735626220703125 length of segment : 16 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1535 time to create 1 rle with old method : 0.0020134449005126953 length of segment : 75 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1691 time to create 1 rle with old method : 0.002271890640258789 length of segment : 120 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0007567405700683594 length of segment : 47 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 863 time to create 1 rle with old method : 0.0011026859283447266 length of segment : 49 time for calcul the mask position with numpy : 0.0002281665802001953 nb_pixel_total : 3440 time to create 1 rle with old method : 0.004437923431396484 length of segment : 201 time for calcul the mask position with numpy : 0.00019121170043945312 nb_pixel_total : 3055 time to create 1 rle with old method : 0.003703594207763672 length of segment : 172 time for calcul the mask position with numpy : 0.0001995563507080078 nb_pixel_total : 3170 time to create 1 rle with old method : 0.0038580894470214844 length of segment : 201 Processing 1 images image shape: (280, 400, 3) min: 9.00000 max: 194.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 75.48672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009152889251708984 nb_pixel_total : 105296 time to create 1 rle with old method : 0.12551021575927734 length of segment : 281 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 134.21328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 0.000209808349609375 nb_pixel_total : 326 time to create 1 rle with old method : 0.001476287841796875 length of segment : 24 time for calcul the mask position with numpy : 0.00017189979553222656 nb_pixel_total : 492 time to create 1 rle with old method : 0.0018224716186523438 length of segment : 25 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 478 time to create 1 rle with old method : 0.0013854503631591797 length of segment : 50 time for calcul the mask position with numpy : 0.00014090538024902344 nb_pixel_total : 1620 time to create 1 rle with old method : 0.004051923751831055 length of segment : 97 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 1181 time to create 1 rle with old method : 0.0034592151641845703 length of segment : 36 time for calcul the mask position with numpy : 0.0001404285430908203 nb_pixel_total : 871 time to create 1 rle with old method : 0.005547761917114258 length of segment : 27 time for calcul the mask position with numpy : 0.000217437744140625 nb_pixel_total : 1322 time to create 1 rle with old method : 0.003477334976196289 length of segment : 40 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.45781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0006783008575439453 length of segment : 22 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0009131431579589844 length of segment : 25 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 833 time to create 1 rle with old method : 0.0015461444854736328 length of segment : 35 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00032973289489746094 length of segment : 14 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0002777576446533203 length of segment : 11 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0009219646453857422 length of segment : 29 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00032830238342285156 length of segment : 15 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.0002307891845703125 length of segment : 17 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.00037670135498046875 length of segment : 16 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0003829002380371094 length of segment : 15 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.000993967056274414 length of segment : 27 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 27 time to create 1 rle with old method : 0.00011301040649414062 length of segment : 5 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.00022220611572265625 length of segment : 9 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.06875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0007660388946533203 length of segment : 31 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.00038623809814453125 length of segment : 14 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 1522 time to create 1 rle with old method : 0.002657651901245117 length of segment : 66 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00034880638122558594 length of segment : 14 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0006921291351318359 length of segment : 15 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00033926963806152344 length of segment : 17 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 590 time to create 1 rle with old method : 0.0010364055633544922 length of segment : 38 time for calcul the mask position with numpy : 0.0001125335693359375 nb_pixel_total : 1274 time to create 1 rle with old method : 0.0022382736206054688 length of segment : 65 time for calcul the mask position with numpy : 0.00013017654418945312 nb_pixel_total : 1963 time to create 1 rle with old method : 0.0036454200744628906 length of segment : 90 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 568 time to create 1 rle with old method : 0.001461029052734375 length of segment : 102 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.59063 max: 145.41641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0003345012664794922 length of segment : 30 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 34 time to create 1 rle with old method : 0.0001010894775390625 length of segment : 9 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0011019706726074219 length of segment : 48 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00015616416931152344 length of segment : 20 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0009837150573730469 length of segment : 47 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.00011682510375976562 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.57109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 875 time to create 1 rle with old method : 0.0014314651489257812 length of segment : 37 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 1064 time to create 1 rle with old method : 0.0015301704406738281 length of segment : 26 time for calcul the mask position with numpy : 0.00021910667419433594 nb_pixel_total : 8856 time to create 1 rle with old method : 0.011345386505126953 length of segment : 74 Processing 1 images image shape: (400, 400, 3) min: 21.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -91.93438 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1133 time to create 1 rle with old method : 0.0017778873443603516 length of segment : 25 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 2294 time to create 1 rle with old method : 0.0031685829162597656 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.14922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00012350082397460938 nb_pixel_total : 5343 time to create 1 rle with old method : 0.006236076354980469 length of segment : 110 Processing 1 images image shape: (400, 320, 3) min: 0.00000 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: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.000751495361328125 length of segment : 17 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1046 time to create 1 rle with old method : 0.0013370513916015625 length of segment : 47 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003483295440673828 length of segment : 54 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.0001995563507080078 length of segment : 15 time for calcul the mask position with numpy : 0.0007693767547607422 nb_pixel_total : 70868 time to create 1 rle with old method : 0.08218264579772949 length of segment : 458 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1161 time to create 1 rle with old method : 0.0015201568603515625 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 24.00000 max: 189.00000 molded_images shape: (1, 640, 640, 3) min: -89.77813 max: 74.01406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.61797 max: 139.76406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003752708435058594 length of segment : 21 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0004813671112060547 length of segment : 30 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 3129 time to create 1 rle with old method : 0.003802776336669922 length of segment : 63 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.40703 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002827644348144531 length of segment : 16 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1715 time to create 1 rle with old method : 0.002069711685180664 length of segment : 44 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.000217437744140625 length of segment : 18 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00022172927856445312 length of segment : 13 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.0001926422119140625 length of segment : 8 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00016999244689941406 length of segment : 32 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1563 time to create 1 rle with old method : 0.00218963623046875 length of segment : 35 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005948543548583984 length of segment : 17 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0005252361297607422 length of segment : 35 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 372 time to create 1 rle with old method : 0.0005221366882324219 length of segment : 17 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00025177001953125 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.51641 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 9.775161743164062e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.00033354759216308594 length of segment : 15 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001938343048095703 length of segment : 9 time for calcul the mask position with numpy : 0.00011968612670898438 nb_pixel_total : 391 time to create 1 rle with old method : 0.000762939453125 length of segment : 24 time for calcul the mask position with numpy : 0.00027298927307128906 nb_pixel_total : 14033 time to create 1 rle with old method : 0.017862796783447266 length of segment : 128 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007901191711425781 length of segment : 58 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 1652 time to create 1 rle with old method : 0.002254962921142578 length of segment : 29 time for calcul the mask position with numpy : 0.0003299713134765625 nb_pixel_total : 1605 time to create 1 rle with old method : 0.001979827880859375 length of segment : 101 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1260 time to create 1 rle with old method : 0.001600503921508789 length of segment : 40 time for calcul the mask position with numpy : 0.0002694129943847656 nb_pixel_total : 12274 time to create 1 rle with old method : 0.014301538467407227 length of segment : 167 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0004734992980957031 length of segment : 30 time for calcul the mask position with numpy : 0.0003504753112792969 nb_pixel_total : 5821 time to create 1 rle with old method : 0.0072405338287353516 length of segment : 133 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 454 time to create 1 rle with old method : 0.0005960464477539062 length of segment : 33 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00017595291137695312 length of segment : 19 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1423 time to create 1 rle with old method : 0.0018658638000488281 length of segment : 45 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1860 time to create 1 rle with old method : 0.0024857521057128906 length of segment : 27 time for calcul the mask position with numpy : 0.0008497238159179688 nb_pixel_total : 25723 time to create 1 rle with old method : 0.031085968017578125 length of segment : 322 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.81875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 2039 time to create 1 rle with old method : 0.0027534961700439453 length of segment : 137 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 1469 time to create 1 rle with old method : 0.0019245147705078125 length of segment : 76 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.0009531974792480469 length of segment : 53 time for calcul the mask position with numpy : 0.0002868175506591797 nb_pixel_total : 2789 time to create 1 rle with old method : 0.0035974979400634766 length of segment : 212 time for calcul the mask position with numpy : 0.0001251697540283203 nb_pixel_total : 2453 time to create 1 rle with old method : 0.004468202590942383 length of segment : 145 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0005552768707275391 length of segment : 33 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0010199546813964844 length of segment : 50 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.0005245208740234375 length of segment : 12 time for calcul the mask position with numpy : 0.0002658367156982422 nb_pixel_total : 3211 time to create 1 rle with old method : 0.0058858394622802734 length of segment : 214 time for calcul the mask position with numpy : 0.0002429485321044922 nb_pixel_total : 3282 time to create 1 rle with old method : 0.003927707672119141 length of segment : 173 Processing 1 images image shape: (280, 400, 3) min: 12.00000 max: 187.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 70.73672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009965896606445312 nb_pixel_total : 105120 time to create 1 rle with old method : 0.11832737922668457 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.95937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0005946159362792969 length of segment : 23 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0008218288421630859 length of segment : 27 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1257 time to create 1 rle with old method : 0.00223541259765625 length of segment : 36 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 925 time to create 1 rle with old method : 0.0019061565399169922 length of segment : 29 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 1322 time to create 1 rle with old method : 0.0025947093963623047 length of segment : 39 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.27812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.0007455348968505859 length of segment : 30 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0005407333374023438 length of segment : 19 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00021958351135253906 length of segment : 13 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 725 time to create 1 rle with old method : 0.0010025501251220703 length of segment : 34 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.0002601146697998047 length of segment : 18 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001964569091796875 length of segment : 13 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002841949462890625 length of segment : 16 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.000518798828125 length of segment : 39 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.00015807151794433594 length of segment : 9 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0007369518280029297 length of segment : 27 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.0003006458282470703 length of segment : 16 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.70156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.00034499168395996094 length of segment : 15 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.00043964385986328125 length of segment : 27 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 1637 time to create 1 rle with old method : 0.0022232532501220703 length of segment : 71 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 873 time to create 1 rle with old method : 0.00119781494140625 length of segment : 56 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.00041866302490234375 length of segment : 16 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 1232 time to create 1 rle with old method : 0.0017976760864257812 length of segment : 85 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 1598 time to create 1 rle with old method : 0.0020895004272460938 length of segment : 74 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 709 time to create 1 rle with old method : 0.0009229183197021484 length of segment : 38 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 129.85000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.00030231475830078125 length of segment : 44 time for calcul the mask position with numpy : 0.0003695487976074219 nb_pixel_total : 25295 time to create 1 rle with old method : 0.03257298469543457 length of segment : 235 Detection mask done ! Trying to reset tf kernel 597761 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1967 tf kernel not reseted sub process len(results) : 448 len(list_Values) 448 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 448 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 : 3160 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Catched exception ! Connect or reconnect ! Number saved : None batch 1 Loaded 448 chid ids of type : 4228 Number RLEs to save : 28882 save missing photos in datou_result : time spend for datou_step_exec : 37.09312629699707 time spend to save output : 44.03516912460327 total time spend for step 1 : 81.12829542160034 step2:brightness Tue Mar 11 12:21:51 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 complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1741692029_597117_1342952167_c8cdc5968d0b42d631ab15c51f73269f.jpg treat image : temp/1741692029_597117_1342952161_d6ee0da3b65c068a808f15cef7978024.jpg treat image : temp/1741692029_597117_1342951909_6709664159402b96677229a1a36ba14e.jpg treat image : temp/1741692029_597117_1342951827_2dd0bcdbea2befd2d5acfaa90dac66b4.jpg treat image : temp/1741692029_597117_1342951775_a3c3da66fe9308b8f969a2e390ede03f.jpg 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 : 5 time used for this insertion : 0.015715837478637695 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.016194820404052734 save missing photos in datou_result : time spend for datou_step_exec : 1.3274319171905518 time spend to save output : 0.05832648277282715 total time spend for step 2 : 1.385758399963379 step3:blur_detection Tue Mar 11 12:21:53 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1741692029_597117_1342952167_c8cdc5968d0b42d631ab15c51f73269f.jpg resize: (1080, 1920) 1342952167 -7.437412602335962 treat image : temp/1741692029_597117_1342952161_d6ee0da3b65c068a808f15cef7978024.jpg resize: (1080, 1920) 1342952161 -7.440184933550058 treat image : temp/1741692029_597117_1342951909_6709664159402b96677229a1a36ba14e.jpg resize: (1080, 1920) 1342951909 -7.422659876675957 treat image : temp/1741692029_597117_1342951827_2dd0bcdbea2befd2d5acfaa90dac66b4.jpg resize: (1080, 1920) 1342951827 -7.419615535539704 treat image : temp/1741692029_597117_1342951775_a3c3da66fe9308b8f969a2e390ede03f.jpg resize: (1080, 1920) 1342951775 -7.4077677828466815 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 : 5 time used for this insertion : 0.012428998947143555 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.012812614440917969 save missing photos in datou_result : time spend for datou_step_exec : 4.675614595413208 time spend to save output : 0.02968430519104004 total time spend for step 3 : 4.705298900604248 step4:rle_unique_nms_with_priority Tue Mar 11 12:21:57 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 448 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 83 nb_hashtags : 7 time to prepare the origin masks : 1.1627495288848877 time for calcul the mask position with numpy : 0.12358951568603516 nb_pixel_total : 1760570 time to create 1 rle with new method : 0.09815454483032227 time for calcul the mask position with numpy : 0.009583234786987305 nb_pixel_total : 63257 time to create 1 rle with old method : 0.08282971382141113 time for calcul the mask position with numpy : 0.01129007339477539 nb_pixel_total : 8901 time to create 1 rle with old method : 0.010483741760253906 time for calcul the mask position with numpy : 0.008561849594116211 nb_pixel_total : 167 time to create 1 rle with old method : 0.00021147727966308594 time for calcul the mask position with numpy : 0.008523941040039062 nb_pixel_total : 1286 time to create 1 rle with old method : 0.0014340877532958984 time for calcul the mask position with numpy : 0.008583545684814453 nb_pixel_total : 764 time to create 1 rle with old method : 0.0009076595306396484 time for calcul the mask position with numpy : 0.008702278137207031 nb_pixel_total : 34 time to create 1 rle with old method : 5.841255187988281e-05 time for calcul the mask position with numpy : 0.008492708206176758 nb_pixel_total : 1779 time to create 1 rle with old method : 0.0020325183868408203 time for calcul the mask position with numpy : 0.008438348770141602 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005083084106445312 time for calcul the mask position with numpy : 0.008416891098022461 nb_pixel_total : 830 time to create 1 rle with old method : 0.0009419918060302734 time for calcul the mask position with numpy : 0.008405447006225586 nb_pixel_total : 67 time to create 1 rle with old method : 0.0001685619354248047 time for calcul the mask position with numpy : 0.008094310760498047 nb_pixel_total : 2712 time to create 1 rle with old method : 0.0030879974365234375 time for calcul the mask position with numpy : 0.008201122283935547 nb_pixel_total : 888 time to create 1 rle with old method : 0.0010521411895751953 time for calcul the mask position with numpy : 0.008385658264160156 nb_pixel_total : 1441 time to create 1 rle with old method : 0.0016112327575683594 time for calcul the mask position with numpy : 0.008252143859863281 nb_pixel_total : 2406 time to create 1 rle with old method : 0.002624988555908203 time for calcul the mask position with numpy : 0.008159399032592773 nb_pixel_total : 5395 time to create 1 rle with old method : 0.00592494010925293 time for calcul the mask position with numpy : 0.00824284553527832 nb_pixel_total : 490 time to create 1 rle with old method : 0.0006878376007080078 time for calcul the mask position with numpy : 0.00832366943359375 nb_pixel_total : 180 time to create 1 rle with old method : 0.00021600723266601562 time for calcul the mask position with numpy : 0.00841975212097168 nb_pixel_total : 83 time to create 1 rle with old method : 0.00010251998901367188 time for calcul the mask position with numpy : 0.008344888687133789 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006394386291503906 time for calcul the mask position with numpy : 0.008293390274047852 nb_pixel_total : 1247 time to create 1 rle with old method : 0.001337289810180664 time for calcul the mask position with numpy : 0.008223533630371094 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001323223114013672 time for calcul the mask position with numpy : 0.00814962387084961 nb_pixel_total : 14485 time to create 1 rle with old method : 0.01657271385192871 time for calcul the mask position with numpy : 0.008382320404052734 nb_pixel_total : 6560 time to create 1 rle with old method : 0.007694244384765625 time for calcul the mask position with numpy : 0.008558273315429688 nb_pixel_total : 124 time to create 1 rle with old method : 0.00016617774963378906 time for calcul the mask position with numpy : 0.008647918701171875 nb_pixel_total : 23025 time to create 1 rle with old method : 0.0257871150970459 time for calcul the mask position with numpy : 0.008848905563354492 nb_pixel_total : 275 time to create 1 rle with old method : 0.00031828880310058594 time for calcul the mask position with numpy : 0.008592844009399414 nb_pixel_total : 240 time to create 1 rle with old method : 0.0002856254577636719 time for calcul the mask position with numpy : 0.008449077606201172 nb_pixel_total : 172 time to create 1 rle with old method : 0.0002002716064453125 time for calcul the mask position with numpy : 0.008367300033569336 nb_pixel_total : 1304 time to create 1 rle with old method : 0.0015156269073486328 time for calcul the mask position with numpy : 0.008793115615844727 nb_pixel_total : 479 time to create 1 rle with old method : 0.0005948543548583984 time for calcul the mask position with numpy : 0.008993148803710938 nb_pixel_total : 646 time to create 1 rle with old method : 0.0007171630859375 time for calcul the mask position with numpy : 0.008369207382202148 nb_pixel_total : 28 time to create 1 rle with old method : 5.245208740234375e-05 time for calcul the mask position with numpy : 0.008778095245361328 nb_pixel_total : 1831 time to create 1 rle with old method : 0.002053976058959961 time for calcul the mask position with numpy : 0.008403301239013672 nb_pixel_total : 303 time to create 1 rle with old method : 0.0003685951232910156 time for calcul the mask position with numpy : 0.008285284042358398 nb_pixel_total : 7313 time to create 1 rle with old method : 0.008208990097045898 time for calcul the mask position with numpy : 0.008379697799682617 nb_pixel_total : 36 time to create 1 rle with old method : 8.034706115722656e-05 time for calcul the mask position with numpy : 0.008327722549438477 nb_pixel_total : 162 time to create 1 rle with old method : 0.00019550323486328125 time for calcul the mask position with numpy : 0.008420467376708984 nb_pixel_total : 583 time to create 1 rle with old method : 0.0006453990936279297 time for calcul the mask position with numpy : 0.008568763732910156 nb_pixel_total : 2200 time to create 1 rle with old method : 0.0025606155395507812 time for calcul the mask position with numpy : 0.008350610733032227 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003173351287841797 time for calcul the mask position with numpy : 0.008545637130737305 nb_pixel_total : 525 time to create 1 rle with old method : 0.0006258487701416016 time for calcul the mask position with numpy : 0.008356809616088867 nb_pixel_total : 850 time to create 1 rle with old method : 0.0011396408081054688 time for calcul the mask position with numpy : 0.008113384246826172 nb_pixel_total : 3353 time to create 1 rle with old method : 0.003766298294067383 time for calcul the mask position with numpy : 0.00849604606628418 nb_pixel_total : 11 time to create 1 rle with old method : 3.4809112548828125e-05 time for calcul the mask position with numpy : 0.008277177810668945 nb_pixel_total : 713 time to create 1 rle with old method : 0.0008194446563720703 time for calcul the mask position with numpy : 0.008314371109008789 nb_pixel_total : 371 time to create 1 rle with old method : 0.0004401206970214844 time for calcul the mask position with numpy : 0.00835418701171875 nb_pixel_total : 107 time to create 1 rle with old method : 0.00022792816162109375 time for calcul the mask position with numpy : 0.008266925811767578 nb_pixel_total : 98 time to create 1 rle with old method : 0.00011539459228515625 time for calcul the mask position with numpy : 0.008449792861938477 nb_pixel_total : 1807 time to create 1 rle with old method : 0.0021026134490966797 time for calcul the mask position with numpy : 0.008292436599731445 nb_pixel_total : 1576 time to create 1 rle with old method : 0.0018770694732666016 time for calcul the mask position with numpy : 0.008167505264282227 nb_pixel_total : 1372 time to create 1 rle with old method : 0.0015971660614013672 time for calcul the mask position with numpy : 0.008327007293701172 nb_pixel_total : 1578 time to create 1 rle with old method : 0.0017087459564208984 time for calcul the mask position with numpy : 0.008397102355957031 nb_pixel_total : 188 time to create 1 rle with old method : 0.0002200603485107422 time for calcul the mask position with numpy : 0.008367538452148438 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002396106719970703 time for calcul the mask position with numpy : 0.008812665939331055 nb_pixel_total : 104209 time to create 1 rle with old method : 0.11528587341308594 time for calcul the mask position with numpy : 0.008480072021484375 nb_pixel_total : 868 time to create 1 rle with old method : 0.001003265380859375 time for calcul the mask position with numpy : 0.008460521697998047 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002593994140625 time for calcul the mask position with numpy : 0.008392333984375 nb_pixel_total : 369 time to create 1 rle with old method : 0.0004315376281738281 time for calcul the mask position with numpy : 0.008488655090332031 nb_pixel_total : 918 time to create 1 rle with old method : 0.0010387897491455078 time for calcul the mask position with numpy : 0.008349418640136719 nb_pixel_total : 6995 time to create 1 rle with old method : 0.007992982864379883 time for calcul the mask position with numpy : 0.008278369903564453 nb_pixel_total : 333 time to create 1 rle with old method : 0.00037980079650878906 time for calcul the mask position with numpy : 0.008348464965820312 nb_pixel_total : 24354 time to create 1 rle with old method : 0.026980161666870117 time for calcul the mask position with numpy : 0.008585929870605469 nb_pixel_total : 99 time to create 1 rle with old method : 0.0001316070556640625 time for calcul the mask position with numpy : 0.00863504409790039 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005047321319580078 time for calcul the mask position with numpy : 0.008539438247680664 nb_pixel_total : 115 time to create 1 rle with old method : 0.00015425682067871094 time for calcul the mask position with numpy : 0.008434772491455078 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0011534690856933594 time for calcul the mask position with numpy : 0.008461952209472656 nb_pixel_total : 361 time to create 1 rle with old method : 0.0004246234893798828 time for calcul the mask position with numpy : 0.00842142105102539 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003409385681152344 time for calcul the mask position with numpy : 0.008512496948242188 nb_pixel_total : 1320 time to create 1 rle with old method : 0.0015439987182617188 time for calcul the mask position with numpy : 0.00839376449584961 nb_pixel_total : 124 time to create 1 rle with old method : 0.0001480579376220703 time for calcul the mask position with numpy : 0.008411169052124023 nb_pixel_total : 136 time to create 1 rle with old method : 0.00016617774963378906 time for calcul the mask position with numpy : 0.008444786071777344 nb_pixel_total : 784 time to create 1 rle with old method : 0.0008983612060546875 time for calcul the mask position with numpy : 0.008355140686035156 nb_pixel_total : 1 time to create 1 rle with old method : 9.059906005859375e-06 time for calcul the mask position with numpy : 0.008379697799682617 nb_pixel_total : 336 time to create 1 rle with old method : 0.000392913818359375 time for calcul the mask position with numpy : 0.00820469856262207 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003192424774169922 time for calcul the mask position with numpy : 0.008369922637939453 nb_pixel_total : 556 time to create 1 rle with old method : 0.0006330013275146484 time for calcul the mask position with numpy : 0.008236408233642578 nb_pixel_total : 328 time to create 1 rle with old method : 0.00037384033203125 time for calcul the mask position with numpy : 0.00820612907409668 nb_pixel_total : 1605 time to create 1 rle with old method : 0.0018115043640136719 time for calcul the mask position with numpy : 0.008369207382202148 nb_pixel_total : 371 time to create 1 rle with old method : 0.00044226646423339844 time for calcul the mask position with numpy : 0.008244752883911133 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002605915069580078 time for calcul the mask position with numpy : 0.008443832397460938 nb_pixel_total : 30 time to create 1 rle with old method : 6.67572021484375e-05 time for calcul the mask position with numpy : 0.008310317993164062 nb_pixel_total : 588 time to create 1 rle with old method : 0.0006866455078125 time for calcul the mask position with numpy : 0.008355855941772461 nb_pixel_total : 112 time to create 1 rle with old method : 0.00014972686767578125 create new chi : 1.3417787551879883 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.006860971450805664 batch 1 Loaded 84 chid ids of type : 4230 Number RLEs to save : 10577 TO DO : save crop sub photo not yet done ! save time : 14.745992660522461 nb_obj : 82 nb_hashtags : 8 time to prepare the origin masks : 2.4896090030670166 time for calcul the mask position with numpy : 0.12170672416687012 nb_pixel_total : 1607727 time to create 1 rle with new method : 0.22750258445739746 time for calcul the mask position with numpy : 0.007353782653808594 nb_pixel_total : 17899 time to create 1 rle with old method : 0.021162033081054688 time for calcul the mask position with numpy : 0.007719755172729492 nb_pixel_total : 58770 time to create 1 rle with old method : 0.06757116317749023 time for calcul the mask position with numpy : 0.00685429573059082 nb_pixel_total : 34 time to create 1 rle with old method : 7.033348083496094e-05 time for calcul the mask position with numpy : 0.007309913635253906 nb_pixel_total : 112 time to create 1 rle with old method : 0.00021266937255859375 time for calcul the mask position with numpy : 0.00667572021484375 nb_pixel_total : 128 time to create 1 rle with old method : 0.0001804828643798828 time for calcul the mask position with numpy : 0.00664210319519043 nb_pixel_total : 824 time to create 1 rle with old method : 0.0012331008911132812 time for calcul the mask position with numpy : 0.007201671600341797 nb_pixel_total : 796 time to create 1 rle with old method : 0.0010387897491455078 time for calcul the mask position with numpy : 0.007021903991699219 nb_pixel_total : 49 time to create 1 rle with old method : 0.00011348724365234375 time for calcul the mask position with numpy : 0.006678104400634766 nb_pixel_total : 1998 time to create 1 rle with old method : 0.013627290725708008 time for calcul the mask position with numpy : 0.008100509643554688 nb_pixel_total : 1019 time to create 1 rle with old method : 0.001573324203491211 time for calcul the mask position with numpy : 0.006962299346923828 nb_pixel_total : 916 time to create 1 rle with old method : 0.0011332035064697266 time for calcul the mask position with numpy : 0.006865024566650391 nb_pixel_total : 2884 time to create 1 rle with old method : 0.0049173831939697266 time for calcul the mask position with numpy : 0.009229898452758789 nb_pixel_total : 6076 time to create 1 rle with old method : 0.007620573043823242 time for calcul the mask position with numpy : 0.0075724124908447266 nb_pixel_total : 276 time to create 1 rle with old method : 0.0004162788391113281 time for calcul the mask position with numpy : 0.007087230682373047 nb_pixel_total : 79 time to create 1 rle with old method : 0.00011992454528808594 time for calcul the mask position with numpy : 0.009788036346435547 nb_pixel_total : 18 time to create 1 rle with old method : 9.34600830078125e-05 time for calcul the mask position with numpy : 0.011458635330200195 nb_pixel_total : 541 time to create 1 rle with old method : 0.0006411075592041016 time for calcul the mask position with numpy : 0.011722326278686523 nb_pixel_total : 154231 time to create 1 rle with new method : 0.11208939552307129 time for calcul the mask position with numpy : 0.011442422866821289 nb_pixel_total : 1574 time to create 1 rle with old method : 0.0018463134765625 time for calcul the mask position with numpy : 0.011733531951904297 nb_pixel_total : 106 time to create 1 rle with old method : 0.0001685619354248047 time for calcul the mask position with numpy : 0.013541221618652344 nb_pixel_total : 14165 time to create 1 rle with old method : 0.01972651481628418 time for calcul the mask position with numpy : 0.011081218719482422 nb_pixel_total : 520 time to create 1 rle with old method : 0.0006165504455566406 time for calcul the mask position with numpy : 0.010960817337036133 nb_pixel_total : 5461 time to create 1 rle with old method : 0.00746917724609375 time for calcul the mask position with numpy : 0.014463186264038086 nb_pixel_total : 1413 time to create 1 rle with old method : 0.0023233890533447266 time for calcul the mask position with numpy : 0.011619806289672852 nb_pixel_total : 276 time to create 1 rle with old method : 0.00038051605224609375 time for calcul the mask position with numpy : 0.014858245849609375 nb_pixel_total : 129 time to create 1 rle with old method : 0.00022482872009277344 time for calcul the mask position with numpy : 0.012428760528564453 nb_pixel_total : 516 time to create 1 rle with old method : 0.0009057521820068359 time for calcul the mask position with numpy : 0.015724897384643555 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0022301673889160156 time for calcul the mask position with numpy : 0.01415562629699707 nb_pixel_total : 23 time to create 1 rle with old method : 0.00010061264038085938 time for calcul the mask position with numpy : 0.015110254287719727 nb_pixel_total : 269 time to create 1 rle with old method : 0.00034809112548828125 time for calcul the mask position with numpy : 0.011212348937988281 nb_pixel_total : 820 time to create 1 rle with old method : 0.0009860992431640625 time for calcul the mask position with numpy : 0.0072536468505859375 nb_pixel_total : 15 time to create 1 rle with old method : 5.7697296142578125e-05 time for calcul the mask position with numpy : 0.00721430778503418 nb_pixel_total : 32 time to create 1 rle with old method : 7.009506225585938e-05 time for calcul the mask position with numpy : 0.007393836975097656 nb_pixel_total : 1858 time to create 1 rle with old method : 0.0023338794708251953 time for calcul the mask position with numpy : 0.007555961608886719 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002942085266113281 time for calcul the mask position with numpy : 0.008648157119750977 nb_pixel_total : 525 time to create 1 rle with old method : 0.0007305145263671875 time for calcul the mask position with numpy : 0.007652759552001953 nb_pixel_total : 17 time to create 1 rle with old method : 0.00011610984802246094 time for calcul the mask position with numpy : 0.008045434951782227 nb_pixel_total : 462 time to create 1 rle with old method : 0.0009033679962158203 time for calcul the mask position with numpy : 0.006796836853027344 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004191398620605469 time for calcul the mask position with numpy : 0.006673336029052734 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002987384796142578 time for calcul the mask position with numpy : 0.006691455841064453 nb_pixel_total : 2569 time to create 1 rle with old method : 0.0031418800354003906 time for calcul the mask position with numpy : 0.0073909759521484375 nb_pixel_total : 3512 time to create 1 rle with old method : 0.004714488983154297 time for calcul the mask position with numpy : 0.007315397262573242 nb_pixel_total : 30323 time to create 1 rle with old method : 0.04332733154296875 time for calcul the mask position with numpy : 0.008289337158203125 nb_pixel_total : 148 time to create 1 rle with old method : 0.00033783912658691406 time for calcul the mask position with numpy : 0.007528066635131836 nb_pixel_total : 109 time to create 1 rle with old method : 0.00019693374633789062 time for calcul the mask position with numpy : 0.007841110229492188 nb_pixel_total : 59 time to create 1 rle with old method : 0.000186920166015625 time for calcul the mask position with numpy : 0.007549762725830078 nb_pixel_total : 1812 time to create 1 rle with old method : 0.002784252166748047 time for calcul the mask position with numpy : 0.008394718170166016 nb_pixel_total : 10 time to create 1 rle with old method : 8.821487426757812e-05 time for calcul the mask position with numpy : 0.009399652481079102 nb_pixel_total : 114 time to create 1 rle with old method : 0.00023031234741210938 time for calcul the mask position with numpy : 0.007953643798828125 nb_pixel_total : 1639 time to create 1 rle with old method : 0.0027799606323242188 time for calcul the mask position with numpy : 0.008034706115722656 nb_pixel_total : 1574 time to create 1 rle with old method : 0.0028007030487060547 time for calcul the mask position with numpy : 0.008031129837036133 nb_pixel_total : 174 time to create 1 rle with old method : 0.0003604888916015625 time for calcul the mask position with numpy : 0.009241580963134766 nb_pixel_total : 203 time to create 1 rle with old method : 0.0004112720489501953 time for calcul the mask position with numpy : 0.009256839752197266 nb_pixel_total : 104849 time to create 1 rle with old method : 0.132171630859375 time for calcul the mask position with numpy : 0.006865262985229492 nb_pixel_total : 807 time to create 1 rle with old method : 0.0010058879852294922 time for calcul the mask position with numpy : 0.0069427490234375 nb_pixel_total : 161 time to create 1 rle with old method : 0.00023055076599121094 time for calcul the mask position with numpy : 0.007002115249633789 nb_pixel_total : 193 time to create 1 rle with old method : 0.00025391578674316406 time for calcul the mask position with numpy : 0.007143497467041016 nb_pixel_total : 21 time to create 1 rle with old method : 6.771087646484375e-05 time for calcul the mask position with numpy : 0.006644725799560547 nb_pixel_total : 329 time to create 1 rle with old method : 0.00043511390686035156 time for calcul the mask position with numpy : 0.006918430328369141 nb_pixel_total : 82 time to create 1 rle with old method : 0.00015401840209960938 time for calcul the mask position with numpy : 0.007756233215332031 nb_pixel_total : 29473 time to create 1 rle with old method : 0.045336246490478516 time for calcul the mask position with numpy : 0.00878286361694336 nb_pixel_total : 110 time to create 1 rle with old method : 0.00020742416381835938 time for calcul the mask position with numpy : 0.00831151008605957 nb_pixel_total : 1515 time to create 1 rle with old method : 0.0031197071075439453 time for calcul the mask position with numpy : 0.008454322814941406 nb_pixel_total : 287 time to create 1 rle with old method : 0.0006229877471923828 time for calcul the mask position with numpy : 0.008404970169067383 nb_pixel_total : 1285 time to create 1 rle with old method : 0.0021636486053466797 time for calcul the mask position with numpy : 0.0073697566986083984 nb_pixel_total : 139 time to create 1 rle with old method : 0.00029087066650390625 time for calcul the mask position with numpy : 0.00927877426147461 nb_pixel_total : 460 time to create 1 rle with old method : 0.0008480548858642578 time for calcul the mask position with numpy : 0.0077059268951416016 nb_pixel_total : 348 time to create 1 rle with old method : 0.0006041526794433594 time for calcul the mask position with numpy : 0.0072994232177734375 nb_pixel_total : 419 time to create 1 rle with old method : 0.0007421970367431641 time for calcul the mask position with numpy : 0.006995439529418945 nb_pixel_total : 487 time to create 1 rle with old method : 0.0005786418914794922 time for calcul the mask position with numpy : 0.006742238998413086 nb_pixel_total : 323 time to create 1 rle with old method : 0.000453948974609375 time for calcul the mask position with numpy : 0.007643461227416992 nb_pixel_total : 575 time to create 1 rle with old method : 0.0007448196411132812 time for calcul the mask position with numpy : 0.0072956085205078125 nb_pixel_total : 105 time to create 1 rle with old method : 0.000152587890625 time for calcul the mask position with numpy : 0.007288932800292969 nb_pixel_total : 1402 time to create 1 rle with old method : 0.0017049312591552734 time for calcul the mask position with numpy : 0.007476329803466797 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003509521484375 time for calcul the mask position with numpy : 0.007464170455932617 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0016100406646728516 time for calcul the mask position with numpy : 0.00686955451965332 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005154609680175781 time for calcul the mask position with numpy : 0.007076263427734375 nb_pixel_total : 146 time to create 1 rle with old method : 0.00021409988403320312 time for calcul the mask position with numpy : 0.007021665573120117 nb_pixel_total : 187 time to create 1 rle with old method : 0.00025177001953125 time for calcul the mask position with numpy : 0.007226467132568359 nb_pixel_total : 661 time to create 1 rle with old method : 0.0008170604705810547 time for calcul the mask position with numpy : 0.00768733024597168 nb_pixel_total : 224 time to create 1 rle with old method : 0.00033164024353027344 time for calcul the mask position with numpy : 0.007538795471191406 nb_pixel_total : 132 time to create 1 rle with old method : 0.00020623207092285156 create new chi : 1.5985229015350342 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.001688241958618164 batch 1 Loaded 83 chid ids of type : 4230 Number RLEs to save : 10301 TO DO : save crop sub photo not yet done ! save time : 7.419865846633911 nb_obj : 93 nb_hashtags : 8 time to prepare the origin masks : 1.429297924041748 time for calcul the mask position with numpy : 0.4568479061126709 nb_pixel_total : 1775302 time to create 1 rle with new method : 0.23918843269348145 time for calcul the mask position with numpy : 0.007362842559814453 nb_pixel_total : 6579 time to create 1 rle with old method : 0.008852005004882812 time for calcul the mask position with numpy : 0.007683992385864258 nb_pixel_total : 282 time to create 1 rle with old method : 0.0005409717559814453 time for calcul the mask position with numpy : 0.007303476333618164 nb_pixel_total : 2355 time to create 1 rle with old method : 0.0027010440826416016 time for calcul the mask position with numpy : 0.0071413516998291016 nb_pixel_total : 174 time to create 1 rle with old method : 0.00036787986755371094 time for calcul the mask position with numpy : 0.00714421272277832 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.0072515010833740234 nb_pixel_total : 15897 time to create 1 rle with old method : 0.018026351928710938 time for calcul the mask position with numpy : 0.00748443603515625 nb_pixel_total : 180 time to create 1 rle with old method : 0.0002391338348388672 time for calcul the mask position with numpy : 0.007083892822265625 nb_pixel_total : 39 time to create 1 rle with old method : 8.368492126464844e-05 time for calcul the mask position with numpy : 0.007132291793823242 nb_pixel_total : 661 time to create 1 rle with old method : 0.0007965564727783203 time for calcul the mask position with numpy : 0.006944179534912109 nb_pixel_total : 1869 time to create 1 rle with old method : 0.00215911865234375 time for calcul the mask position with numpy : 0.007149696350097656 nb_pixel_total : 738 time to create 1 rle with old method : 0.0008559226989746094 time for calcul the mask position with numpy : 0.0069386959075927734 nb_pixel_total : 1134 time to create 1 rle with old method : 0.0012891292572021484 time for calcul the mask position with numpy : 0.006914377212524414 nb_pixel_total : 61 time to create 1 rle with old method : 0.00013518333435058594 time for calcul the mask position with numpy : 0.006492137908935547 nb_pixel_total : 103 time to create 1 rle with old method : 0.0002617835998535156 time for calcul the mask position with numpy : 0.007050037384033203 nb_pixel_total : 53378 time to create 1 rle with old method : 0.0690305233001709 time for calcul the mask position with numpy : 0.00653839111328125 nb_pixel_total : 11 time to create 1 rle with old method : 4.6253204345703125e-05 time for calcul the mask position with numpy : 0.006717205047607422 nb_pixel_total : 1388 time to create 1 rle with old method : 0.0023479461669921875 time for calcul the mask position with numpy : 0.00658106803894043 nb_pixel_total : 2153 time to create 1 rle with old method : 0.0025086402893066406 time for calcul the mask position with numpy : 0.006924629211425781 nb_pixel_total : 192 time to create 1 rle with old method : 0.0004143714904785156 time for calcul the mask position with numpy : 0.011613130569458008 nb_pixel_total : 939 time to create 1 rle with old method : 0.0011954307556152344 time for calcul the mask position with numpy : 0.0062906742095947266 nb_pixel_total : 2108 time to create 1 rle with old method : 0.002469778060913086 time for calcul the mask position with numpy : 0.006535053253173828 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003879070281982422 time for calcul the mask position with numpy : 0.006840705871582031 nb_pixel_total : 305 time to create 1 rle with old method : 0.0003814697265625 time for calcul the mask position with numpy : 0.006702899932861328 nb_pixel_total : 409 time to create 1 rle with old method : 0.0006482601165771484 time for calcul the mask position with numpy : 0.006603717803955078 nb_pixel_total : 629 time to create 1 rle with old method : 0.0008618831634521484 time for calcul the mask position with numpy : 0.0068700313568115234 nb_pixel_total : 4734 time to create 1 rle with old method : 0.0064847469329833984 time for calcul the mask position with numpy : 0.007437944412231445 nb_pixel_total : 67 time to create 1 rle with old method : 0.00010180473327636719 time for calcul the mask position with numpy : 0.006880760192871094 nb_pixel_total : 95 time to create 1 rle with old method : 0.00019502639770507812 time for calcul the mask position with numpy : 0.006913900375366211 nb_pixel_total : 37 time to create 1 rle with old method : 0.00010013580322265625 time for calcul the mask position with numpy : 0.008045196533203125 nb_pixel_total : 546 time to create 1 rle with old method : 0.0006473064422607422 time for calcul the mask position with numpy : 0.0069463253021240234 nb_pixel_total : 300 time to create 1 rle with old method : 0.0003883838653564453 time for calcul the mask position with numpy : 0.012832880020141602 nb_pixel_total : 59 time to create 1 rle with old method : 0.00023698806762695312 time for calcul the mask position with numpy : 0.008191823959350586 nb_pixel_total : 1378 time to create 1 rle with old method : 0.0042498111724853516 time for calcul the mask position with numpy : 0.00935506820678711 nb_pixel_total : 14283 time to create 1 rle with old method : 0.031613826751708984 time for calcul the mask position with numpy : 0.009239673614501953 nb_pixel_total : 15 time to create 1 rle with old method : 4.696846008300781e-05 time for calcul the mask position with numpy : 0.007136821746826172 nb_pixel_total : 474 time to create 1 rle with old method : 0.0008275508880615234 time for calcul the mask position with numpy : 0.0073699951171875 nb_pixel_total : 7449 time to create 1 rle with old method : 0.012014150619506836 time for calcul the mask position with numpy : 0.0069141387939453125 nb_pixel_total : 208 time to create 1 rle with old method : 0.00037598609924316406 time for calcul the mask position with numpy : 0.006825923919677734 nb_pixel_total : 251 time to create 1 rle with old method : 0.0004382133483886719 time for calcul the mask position with numpy : 0.006687641143798828 nb_pixel_total : 39 time to create 1 rle with old method : 6.508827209472656e-05 time for calcul the mask position with numpy : 0.0072138309478759766 nb_pixel_total : 1230 time to create 1 rle with old method : 0.0018377304077148438 time for calcul the mask position with numpy : 0.00625920295715332 nb_pixel_total : 244 time to create 1 rle with old method : 0.00031638145446777344 time for calcul the mask position with numpy : 0.006394147872924805 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006697177886962891 time for calcul the mask position with numpy : 0.006518363952636719 nb_pixel_total : 766 time to create 1 rle with old method : 0.0012755393981933594 time for calcul the mask position with numpy : 0.0073070526123046875 nb_pixel_total : 12033 time to create 1 rle with old method : 0.013605117797851562 time for calcul the mask position with numpy : 0.006669282913208008 nb_pixel_total : 74 time to create 1 rle with old method : 0.00013327598571777344 time for calcul the mask position with numpy : 0.006368398666381836 nb_pixel_total : 77 time to create 1 rle with old method : 0.00011491775512695312 time for calcul the mask position with numpy : 0.011116743087768555 nb_pixel_total : 230 time to create 1 rle with old method : 0.0020837783813476562 time for calcul the mask position with numpy : 0.010419845581054688 nb_pixel_total : 232 time to create 1 rle with old method : 0.0002779960632324219 time for calcul the mask position with numpy : 0.010318756103515625 nb_pixel_total : 241 time to create 1 rle with old method : 0.0002925395965576172 time for calcul the mask position with numpy : 0.010352134704589844 nb_pixel_total : 588 time to create 1 rle with old method : 0.0006906986236572266 time for calcul the mask position with numpy : 0.010769367218017578 nb_pixel_total : 20824 time to create 1 rle with old method : 0.026502132415771484 time for calcul the mask position with numpy : 0.010929346084594727 nb_pixel_total : 245 time to create 1 rle with old method : 0.00030303001403808594 time for calcul the mask position with numpy : 0.01081538200378418 nb_pixel_total : 701 time to create 1 rle with old method : 0.0009484291076660156 time for calcul the mask position with numpy : 0.010776519775390625 nb_pixel_total : 1757 time to create 1 rle with old method : 0.0020532608032226562 time for calcul the mask position with numpy : 0.010765790939331055 nb_pixel_total : 604 time to create 1 rle with old method : 0.0007023811340332031 time for calcul the mask position with numpy : 0.010984420776367188 nb_pixel_total : 447 time to create 1 rle with old method : 0.0008566379547119141 time for calcul the mask position with numpy : 0.011593103408813477 nb_pixel_total : 2500 time to create 1 rle with old method : 0.002890348434448242 time for calcul the mask position with numpy : 0.011247396469116211 nb_pixel_total : 153 time to create 1 rle with old method : 0.00020933151245117188 time for calcul the mask position with numpy : 0.010378360748291016 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001354217529296875 time for calcul the mask position with numpy : 0.010432958602905273 nb_pixel_total : 1695 time to create 1 rle with old method : 0.001956939697265625 time for calcul the mask position with numpy : 0.010793447494506836 nb_pixel_total : 144 time to create 1 rle with old method : 0.0002532005310058594 time for calcul the mask position with numpy : 0.010697603225708008 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002281665802001953 time for calcul the mask position with numpy : 0.011180639266967773 nb_pixel_total : 1607 time to create 1 rle with old method : 0.001911163330078125 time for calcul the mask position with numpy : 0.010789632797241211 nb_pixel_total : 113 time to create 1 rle with old method : 0.00022459030151367188 time for calcul the mask position with numpy : 0.011795759201049805 nb_pixel_total : 3086 time to create 1 rle with old method : 0.005074501037597656 time for calcul the mask position with numpy : 0.011864423751831055 nb_pixel_total : 1394 time to create 1 rle with old method : 0.002354860305786133 time for calcul the mask position with numpy : 0.012213468551635742 nb_pixel_total : 191 time to create 1 rle with old method : 0.00035190582275390625 time for calcul the mask position with numpy : 0.012173891067504883 nb_pixel_total : 185 time to create 1 rle with old method : 0.00033593177795410156 time for calcul the mask position with numpy : 0.012647151947021484 nb_pixel_total : 104882 time to create 1 rle with old method : 0.11885547637939453 time for calcul the mask position with numpy : 0.010354280471801758 nb_pixel_total : 988 time to create 1 rle with old method : 0.0011661052703857422 time for calcul the mask position with numpy : 0.010433673858642578 nb_pixel_total : 189 time to create 1 rle with old method : 0.00022792816162109375 time for calcul the mask position with numpy : 0.010372400283813477 nb_pixel_total : 556 time to create 1 rle with old method : 0.0006673336029052734 time for calcul the mask position with numpy : 0.010492086410522461 nb_pixel_total : 10396 time to create 1 rle with old method : 0.011610269546508789 time for calcul the mask position with numpy : 0.010552644729614258 nb_pixel_total : 90 time to create 1 rle with old method : 0.00012946128845214844 time for calcul the mask position with numpy : 0.01058053970336914 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011372566223144531 time for calcul the mask position with numpy : 0.010566473007202148 nb_pixel_total : 117 time to create 1 rle with old method : 0.00016880035400390625 time for calcul the mask position with numpy : 0.010760784149169922 nb_pixel_total : 295 time to create 1 rle with old method : 0.00035190582275390625 time for calcul the mask position with numpy : 0.010726213455200195 nb_pixel_total : 104 time to create 1 rle with old method : 0.0001723766326904297 time for calcul the mask position with numpy : 0.010759115219116211 nb_pixel_total : 1224 time to create 1 rle with old method : 0.0013675689697265625 time for calcul the mask position with numpy : 0.010561704635620117 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001544952392578125 time for calcul the mask position with numpy : 0.008639335632324219 nb_pixel_total : 129 time to create 1 rle with old method : 0.00018310546875 time for calcul the mask position with numpy : 0.008697986602783203 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005941390991210938 time for calcul the mask position with numpy : 0.008765935897827148 nb_pixel_total : 321 time to create 1 rle with old method : 0.00039315223693847656 time for calcul the mask position with numpy : 0.00871133804321289 nb_pixel_total : 530 time to create 1 rle with old method : 0.000637054443359375 time for calcul the mask position with numpy : 0.013764619827270508 nb_pixel_total : 100 time to create 1 rle with old method : 0.00025773048400878906 time for calcul the mask position with numpy : 0.009252309799194336 nb_pixel_total : 234 time to create 1 rle with old method : 0.0002994537353515625 time for calcul the mask position with numpy : 0.010363340377807617 nb_pixel_total : 762 time to create 1 rle with old method : 0.0009005069732666016 time for calcul the mask position with numpy : 0.008795976638793945 nb_pixel_total : 1514 time to create 1 rle with old method : 0.0017642974853515625 time for calcul the mask position with numpy : 0.008661746978759766 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003581047058105469 time for calcul the mask position with numpy : 0.008993864059448242 nb_pixel_total : 161 time to create 1 rle with old method : 0.00021409988403320312 time for calcul the mask position with numpy : 0.00930023193359375 nb_pixel_total : 591 time to create 1 rle with old method : 0.0007119178771972656 time for calcul the mask position with numpy : 0.008702516555786133 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002186298370361328 create new chi : 1.9529244899749756 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.0033173561096191406 batch 1 Loaded 94 chid ids of type : 4230 Number RLEs to save : 10555 TO DO : save crop sub photo not yet done ! save time : 13.373579978942871 nb_obj : 102 nb_hashtags : 8 time to prepare the origin masks : 1.796766996383667 time for calcul the mask position with numpy : 0.10222649574279785 nb_pixel_total : 1742218 time to create 1 rle with new method : 0.5525403022766113 time for calcul the mask position with numpy : 0.0068471431732177734 nb_pixel_total : 69993 time to create 1 rle with old method : 0.07879304885864258 time for calcul the mask position with numpy : 0.006160736083984375 nb_pixel_total : 2346 time to create 1 rle with old method : 0.0026564598083496094 time for calcul the mask position with numpy : 0.010193109512329102 nb_pixel_total : 99 time to create 1 rle with old method : 0.00019812583923339844 time for calcul the mask position with numpy : 0.0075643062591552734 nb_pixel_total : 189 time to create 1 rle with old method : 0.00024199485778808594 time for calcul the mask position with numpy : 0.006011247634887695 nb_pixel_total : 670 time to create 1 rle with old method : 0.0008134841918945312 time for calcul the mask position with numpy : 0.006056070327758789 nb_pixel_total : 865 time to create 1 rle with old method : 0.0010228157043457031 time for calcul the mask position with numpy : 0.0060231685638427734 nb_pixel_total : 40 time to create 1 rle with old method : 7.43865966796875e-05 time for calcul the mask position with numpy : 0.006057262420654297 nb_pixel_total : 964 time to create 1 rle with old method : 0.0011239051818847656 time for calcul the mask position with numpy : 0.006192445755004883 nb_pixel_total : 81 time to create 1 rle with old method : 0.00014901161193847656 time for calcul the mask position with numpy : 0.00611114501953125 nb_pixel_total : 263 time to create 1 rle with old method : 0.0003216266632080078 time for calcul the mask position with numpy : 0.006092548370361328 nb_pixel_total : 1241 time to create 1 rle with old method : 0.0014731884002685547 time for calcul the mask position with numpy : 0.006031513214111328 nb_pixel_total : 109 time to create 1 rle with old method : 0.000148773193359375 time for calcul the mask position with numpy : 0.006056070327758789 nb_pixel_total : 1336 time to create 1 rle with old method : 0.0015439987182617188 time for calcul the mask position with numpy : 0.006011009216308594 nb_pixel_total : 673 time to create 1 rle with old method : 0.0008609294891357422 time for calcul the mask position with numpy : 0.006044149398803711 nb_pixel_total : 951 time to create 1 rle with old method : 0.0011179447174072266 time for calcul the mask position with numpy : 0.006188392639160156 nb_pixel_total : 2918 time to create 1 rle with old method : 0.0034301280975341797 time for calcul the mask position with numpy : 0.006295204162597656 nb_pixel_total : 22 time to create 1 rle with old method : 4.982948303222656e-05 time for calcul the mask position with numpy : 0.006180524826049805 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005846023559570312 time for calcul the mask position with numpy : 0.0060498714447021484 nb_pixel_total : 5772 time to create 1 rle with old method : 0.006532192230224609 time for calcul the mask position with numpy : 0.0060558319091796875 nb_pixel_total : 80 time to create 1 rle with old method : 0.0001289844512939453 time for calcul the mask position with numpy : 0.005993366241455078 nb_pixel_total : 77 time to create 1 rle with old method : 9.894371032714844e-05 time for calcul the mask position with numpy : 0.005990505218505859 nb_pixel_total : 549 time to create 1 rle with old method : 0.0006463527679443359 time for calcul the mask position with numpy : 0.006012678146362305 nb_pixel_total : 40 time to create 1 rle with old method : 0.00010514259338378906 time for calcul the mask position with numpy : 0.006230592727661133 nb_pixel_total : 9 time to create 1 rle with old method : 6.890296936035156e-05 time for calcul the mask position with numpy : 0.006094932556152344 nb_pixel_total : 100 time to create 1 rle with old method : 0.00018787384033203125 time for calcul the mask position with numpy : 0.006064891815185547 nb_pixel_total : 1450 time to create 1 rle with old method : 0.0016720294952392578 time for calcul the mask position with numpy : 0.00605463981628418 nb_pixel_total : 405 time to create 1 rle with old method : 0.0005030632019042969 time for calcul the mask position with numpy : 0.006263017654418945 nb_pixel_total : 14454 time to create 1 rle with old method : 0.01638936996459961 time for calcul the mask position with numpy : 0.010807991027832031 nb_pixel_total : 101 time to create 1 rle with old method : 0.0001404285430908203 time for calcul the mask position with numpy : 0.01028752326965332 nb_pixel_total : 1735 time to create 1 rle with old method : 0.0020134449005126953 time for calcul the mask position with numpy : 0.009943962097167969 nb_pixel_total : 222 time to create 1 rle with old method : 0.0002770423889160156 time for calcul the mask position with numpy : 0.010182380676269531 nb_pixel_total : 451 time to create 1 rle with old method : 0.000530242919921875 time for calcul the mask position with numpy : 0.010177850723266602 nb_pixel_total : 7726 time to create 1 rle with old method : 0.00877070426940918 time for calcul the mask position with numpy : 0.010274648666381836 nb_pixel_total : 24992 time to create 1 rle with old method : 0.027950525283813477 time for calcul the mask position with numpy : 0.010015010833740234 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006988048553466797 time for calcul the mask position with numpy : 0.010309696197509766 nb_pixel_total : 1676 time to create 1 rle with old method : 0.001934051513671875 time for calcul the mask position with numpy : 0.010369300842285156 nb_pixel_total : 243 time to create 1 rle with old method : 0.00028967857360839844 time for calcul the mask position with numpy : 0.010232686996459961 nb_pixel_total : 1335 time to create 1 rle with old method : 0.0015146732330322266 time for calcul the mask position with numpy : 0.010078668594360352 nb_pixel_total : 128 time to create 1 rle with old method : 0.0001800060272216797 time for calcul the mask position with numpy : 0.010311603546142578 nb_pixel_total : 6852 time to create 1 rle with old method : 0.007749795913696289 time for calcul the mask position with numpy : 0.01026463508605957 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005638599395751953 time for calcul the mask position with numpy : 0.010228872299194336 nb_pixel_total : 863 time to create 1 rle with old method : 0.0009412765502929688 time for calcul the mask position with numpy : 0.010311365127563477 nb_pixel_total : 113 time to create 1 rle with old method : 0.00022554397583007812 time for calcul the mask position with numpy : 0.010454654693603516 nb_pixel_total : 24 time to create 1 rle with old method : 6.628036499023438e-05 time for calcul the mask position with numpy : 0.010358572006225586 nb_pixel_total : 222 time to create 1 rle with old method : 0.0002701282501220703 time for calcul the mask position with numpy : 0.010480642318725586 nb_pixel_total : 107 time to create 1 rle with old method : 0.00014448165893554688 time for calcul the mask position with numpy : 0.010226011276245117 nb_pixel_total : 589 time to create 1 rle with old method : 0.0006854534149169922 time for calcul the mask position with numpy : 0.010230064392089844 nb_pixel_total : 260 time to create 1 rle with old method : 0.00037479400634765625 time for calcul the mask position with numpy : 0.010638236999511719 nb_pixel_total : 19647 time to create 1 rle with old method : 0.021461963653564453 time for calcul the mask position with numpy : 0.010542869567871094 nb_pixel_total : 1548 time to create 1 rle with old method : 0.0017955303192138672 time for calcul the mask position with numpy : 0.010399103164672852 nb_pixel_total : 522 time to create 1 rle with old method : 0.0006084442138671875 time for calcul the mask position with numpy : 0.010417938232421875 nb_pixel_total : 61 time to create 1 rle with old method : 9.751319885253906e-05 time for calcul the mask position with numpy : 0.01016998291015625 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004818439483642578 time for calcul the mask position with numpy : 0.010263919830322266 nb_pixel_total : 223 time to create 1 rle with old method : 0.00033926963806152344 time for calcul the mask position with numpy : 0.006194353103637695 nb_pixel_total : 3440 time to create 1 rle with old method : 0.0039408206939697266 time for calcul the mask position with numpy : 0.006413698196411133 nb_pixel_total : 303 time to create 1 rle with old method : 0.0004096031188964844 time for calcul the mask position with numpy : 0.0063860416412353516 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0011601448059082031 time for calcul the mask position with numpy : 0.006521940231323242 nb_pixel_total : 230 time to create 1 rle with old method : 0.00033545494079589844 time for calcul the mask position with numpy : 0.007226705551147461 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002346038818359375 time for calcul the mask position with numpy : 0.007490396499633789 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001838207244873047 time for calcul the mask position with numpy : 0.007502079010009766 nb_pixel_total : 20733 time to create 1 rle with old method : 0.02349686622619629 time for calcul the mask position with numpy : 0.0069925785064697266 nb_pixel_total : 102 time to create 1 rle with old method : 0.0001571178436279297 time for calcul the mask position with numpy : 0.006055593490600586 nb_pixel_total : 1738 time to create 1 rle with old method : 0.001950979232788086 time for calcul the mask position with numpy : 0.005982160568237305 nb_pixel_total : 633 time to create 1 rle with old method : 0.0007488727569580078 time for calcul the mask position with numpy : 0.0059070587158203125 nb_pixel_total : 1567 time to create 1 rle with old method : 0.0017223358154296875 time for calcul the mask position with numpy : 0.006083011627197266 nb_pixel_total : 110 time to create 1 rle with old method : 0.0001513957977294922 time for calcul the mask position with numpy : 0.006028890609741211 nb_pixel_total : 87 time to create 1 rle with old method : 0.00011610984802246094 time for calcul the mask position with numpy : 0.006212949752807617 nb_pixel_total : 3077 time to create 1 rle with old method : 0.0035321712493896484 time for calcul the mask position with numpy : 0.005881071090698242 nb_pixel_total : 1535 time to create 1 rle with old method : 0.0016868114471435547 time for calcul the mask position with numpy : 0.005915164947509766 nb_pixel_total : 168 time to create 1 rle with old method : 0.0002269744873046875 time for calcul the mask position with numpy : 0.006032705307006836 nb_pixel_total : 198 time to create 1 rle with old method : 0.00025200843811035156 time for calcul the mask position with numpy : 0.00644683837890625 nb_pixel_total : 105296 time to create 1 rle with old method : 0.11784768104553223 time for calcul the mask position with numpy : 0.006167888641357422 nb_pixel_total : 321 time to create 1 rle with old method : 0.0003731250762939453 time for calcul the mask position with numpy : 0.005987644195556641 nb_pixel_total : 833 time to create 1 rle with old method : 0.00096893310546875 time for calcul the mask position with numpy : 0.006030082702636719 nb_pixel_total : 568 time to create 1 rle with old method : 0.0006940364837646484 time for calcul the mask position with numpy : 0.005919933319091797 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002338886260986328 time for calcul the mask position with numpy : 0.0060808658599853516 nb_pixel_total : 16 time to create 1 rle with old method : 5.1021575927734375e-05 time for calcul the mask position with numpy : 0.005893707275390625 nb_pixel_total : 871 time to create 1 rle with old method : 0.0010030269622802734 time for calcul the mask position with numpy : 0.006017923355102539 nb_pixel_total : 27 time to create 1 rle with old method : 5.245208740234375e-05 time for calcul the mask position with numpy : 0.00589752197265625 nb_pixel_total : 326 time to create 1 rle with old method : 0.00039577484130859375 time for calcul the mask position with numpy : 0.005978107452392578 nb_pixel_total : 87 time to create 1 rle with old method : 0.00012636184692382812 time for calcul the mask position with numpy : 0.006018400192260742 nb_pixel_total : 114 time to create 1 rle with old method : 0.00015807151794433594 time for calcul the mask position with numpy : 0.006067037582397461 nb_pixel_total : 492 time to create 1 rle with old method : 0.0005965232849121094 time for calcul the mask position with numpy : 0.0060842037200927734 nb_pixel_total : 478 time to create 1 rle with old method : 0.0005757808685302734 time for calcul the mask position with numpy : 0.010105609893798828 nb_pixel_total : 1173 time to create 1 rle with old method : 0.001374959945678711 time for calcul the mask position with numpy : 0.010135889053344727 nb_pixel_total : 338 time to create 1 rle with old method : 0.00041365623474121094 time for calcul the mask position with numpy : 0.005887269973754883 nb_pixel_total : 145 time to create 1 rle with old method : 0.00022602081298828125 time for calcul the mask position with numpy : 0.005964994430541992 nb_pixel_total : 1181 time to create 1 rle with old method : 0.0013668537139892578 time for calcul the mask position with numpy : 0.006074666976928711 nb_pixel_total : 106 time to create 1 rle with old method : 0.00015044212341308594 time for calcul the mask position with numpy : 0.005999565124511719 nb_pixel_total : 135 time to create 1 rle with old method : 0.00022363662719726562 time for calcul the mask position with numpy : 0.005860805511474609 nb_pixel_total : 472 time to create 1 rle with old method : 0.0005371570587158203 time for calcul the mask position with numpy : 0.005770206451416016 nb_pixel_total : 428 time to create 1 rle with old method : 0.0005059242248535156 time for calcul the mask position with numpy : 0.00599360466003418 nb_pixel_total : 617 time to create 1 rle with old method : 0.0008034706115722656 time for calcul the mask position with numpy : 0.008153438568115234 nb_pixel_total : 472 time to create 1 rle with old method : 0.0005633831024169922 time for calcul the mask position with numpy : 0.00838470458984375 nb_pixel_total : 109 time to create 1 rle with old method : 0.00013566017150878906 time for calcul the mask position with numpy : 0.008438348770141602 nb_pixel_total : 1274 time to create 1 rle with old method : 0.0014414787292480469 time for calcul the mask position with numpy : 0.008424520492553711 nb_pixel_total : 1522 time to create 1 rle with old method : 0.001664876937866211 time for calcul the mask position with numpy : 0.008111953735351562 nb_pixel_total : 156 time to create 1 rle with old method : 0.0001800060272216797 time for calcul the mask position with numpy : 0.008395671844482422 nb_pixel_total : 169 time to create 1 rle with old method : 0.00020599365234375 time for calcul the mask position with numpy : 0.008256673812866211 nb_pixel_total : 590 time to create 1 rle with old method : 0.0006842613220214844 time for calcul the mask position with numpy : 0.008424520492553711 nb_pixel_total : 524 time to create 1 rle with old method : 0.0006101131439208984 time for calcul the mask position with numpy : 0.008396148681640625 nb_pixel_total : 108 time to create 1 rle with old method : 0.00015211105346679688 create new chi : 1.8138978481292725 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.002991199493408203 batch 1 Loaded 103 chid ids of type : 4230 Number RLEs to save : 12070 TO DO : save crop sub photo not yet done ! save time : 14.900657653808594 nb_obj : 85 nb_hashtags : 7 time to prepare the origin masks : 1.5992753505706787 time for calcul the mask position with numpy : 0.02319812774658203 nb_pixel_total : 1771052 time to create 1 rle with new method : 0.03671002388000488 time for calcul the mask position with numpy : 0.006747722625732422 nb_pixel_total : 70455 time to create 1 rle with old method : 0.07849526405334473 time for calcul the mask position with numpy : 0.009530067443847656 nb_pixel_total : 665 time to create 1 rle with old method : 0.0007848739624023438 time for calcul the mask position with numpy : 0.010154247283935547 nb_pixel_total : 181 time to create 1 rle with old method : 0.00022482872009277344 time for calcul the mask position with numpy : 0.0060710906982421875 nb_pixel_total : 875 time to create 1 rle with old method : 0.0010390281677246094 time for calcul the mask position with numpy : 0.006041288375854492 nb_pixel_total : 34 time to create 1 rle with old method : 6.341934204101562e-05 time for calcul the mask position with numpy : 0.0061435699462890625 nb_pixel_total : 1064 time to create 1 rle with old method : 0.0011920928955078125 time for calcul the mask position with numpy : 0.006056785583496094 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002865791320800781 time for calcul the mask position with numpy : 0.006083250045776367 nb_pixel_total : 276 time to create 1 rle with old method : 0.00032520294189453125 time for calcul the mask position with numpy : 0.0061528682708740234 nb_pixel_total : 8856 time to create 1 rle with old method : 0.010014533996582031 time for calcul the mask position with numpy : 0.006232023239135742 nb_pixel_total : 64 time to create 1 rle with old method : 9.5367431640625e-05 time for calcul the mask position with numpy : 0.0059967041015625 nb_pixel_total : 1133 time to create 1 rle with old method : 0.0014417171478271484 time for calcul the mask position with numpy : 0.006233692169189453 nb_pixel_total : 2294 time to create 1 rle with old method : 0.002739429473876953 time for calcul the mask position with numpy : 0.006104230880737305 nb_pixel_total : 121 time to create 1 rle with old method : 0.00016546249389648438 time for calcul the mask position with numpy : 0.0059814453125 nb_pixel_total : 5343 time to create 1 rle with old method : 0.005913972854614258 time for calcul the mask position with numpy : 0.005927085876464844 nb_pixel_total : 1046 time to create 1 rle with old method : 0.0011973381042480469 time for calcul the mask position with numpy : 0.005849599838256836 nb_pixel_total : 77 time to create 1 rle with old method : 0.00014472007751464844 time for calcul the mask position with numpy : 0.005736112594604492 nb_pixel_total : 85 time to create 1 rle with old method : 0.00011110305786132812 time for calcul the mask position with numpy : 0.005769968032836914 nb_pixel_total : 505 time to create 1 rle with old method : 0.0005645751953125 time for calcul the mask position with numpy : 0.009665489196777344 nb_pixel_total : 1581 time to create 1 rle with old method : 0.0018014907836914062 time for calcul the mask position with numpy : 0.010162591934204102 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002219676971435547 time for calcul the mask position with numpy : 0.00605010986328125 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001461505889892578 time for calcul the mask position with numpy : 0.005891323089599609 nb_pixel_total : 13755 time to create 1 rle with old method : 0.014437675476074219 time for calcul the mask position with numpy : 0.00583648681640625 nb_pixel_total : 324 time to create 1 rle with old method : 0.0004305839538574219 time for calcul the mask position with numpy : 0.005998134613037109 nb_pixel_total : 390 time to create 1 rle with old method : 0.00047278404235839844 time for calcul the mask position with numpy : 0.006049156188964844 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007023811340332031 time for calcul the mask position with numpy : 0.006168842315673828 nb_pixel_total : 10 time to create 1 rle with old method : 5.316734313964844e-05 time for calcul the mask position with numpy : 0.006176948547363281 nb_pixel_total : 5821 time to create 1 rle with old method : 0.006593465805053711 time for calcul the mask position with numpy : 0.006111860275268555 nb_pixel_total : 22 time to create 1 rle with old method : 6.437301635742188e-05 time for calcul the mask position with numpy : 0.0061109066009521484 nb_pixel_total : 111 time to create 1 rle with old method : 0.00015997886657714844 time for calcul the mask position with numpy : 0.006041526794433594 nb_pixel_total : 139 time to create 1 rle with old method : 0.0001785755157470703 time for calcul the mask position with numpy : 0.006136417388916016 nb_pixel_total : 277 time to create 1 rle with old method : 0.000331878662109375 time for calcul the mask position with numpy : 0.0060651302337646484 nb_pixel_total : 391 time to create 1 rle with old method : 0.0004754066467285156 time for calcul the mask position with numpy : 0.007158041000366211 nb_pixel_total : 182 time to create 1 rle with old method : 0.00029468536376953125 time for calcul the mask position with numpy : 0.006367921829223633 nb_pixel_total : 1260 time to create 1 rle with old method : 0.0014445781707763672 time for calcul the mask position with numpy : 0.00609898567199707 nb_pixel_total : 705 time to create 1 rle with old method : 0.0008296966552734375 time for calcul the mask position with numpy : 0.0061719417572021484 nb_pixel_total : 364 time to create 1 rle with old method : 0.00043582916259765625 time for calcul the mask position with numpy : 0.006196498870849609 nb_pixel_total : 73 time to create 1 rle with old method : 0.00010919570922851562 time for calcul the mask position with numpy : 0.006169557571411133 nb_pixel_total : 201 time to create 1 rle with old method : 0.00027441978454589844 time for calcul the mask position with numpy : 0.006244182586669922 nb_pixel_total : 75 time to create 1 rle with old method : 0.0001442432403564453 time for calcul the mask position with numpy : 0.006111621856689453 nb_pixel_total : 25022 time to create 1 rle with old method : 0.028013229370117188 time for calcul the mask position with numpy : 0.01077890396118164 nb_pixel_total : 496 time to create 1 rle with old method : 0.0005972385406494141 time for calcul the mask position with numpy : 0.006196737289428711 nb_pixel_total : 2039 time to create 1 rle with old method : 0.0024335384368896484 time for calcul the mask position with numpy : 0.006270408630371094 nb_pixel_total : 902 time to create 1 rle with old method : 0.0011441707611083984 time for calcul the mask position with numpy : 0.0063326358795166016 nb_pixel_total : 615 time to create 1 rle with old method : 0.000843048095703125 time for calcul the mask position with numpy : 0.006318330764770508 nb_pixel_total : 2575 time to create 1 rle with old method : 0.0056231021881103516 time for calcul the mask position with numpy : 0.007437467575073242 nb_pixel_total : 206 time to create 1 rle with old method : 0.0003235340118408203 time for calcul the mask position with numpy : 0.006725311279296875 nb_pixel_total : 332 time to create 1 rle with old method : 0.000446319580078125 time for calcul the mask position with numpy : 0.006227731704711914 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003123283386230469 time for calcul the mask position with numpy : 0.006292819976806641 nb_pixel_total : 103 time to create 1 rle with old method : 0.00014066696166992188 time for calcul the mask position with numpy : 0.006244182586669922 nb_pixel_total : 131 time to create 1 rle with old method : 0.00023555755615234375 time for calcul the mask position with numpy : 0.006525516510009766 nb_pixel_total : 1715 time to create 1 rle with old method : 0.0019905567169189453 time for calcul the mask position with numpy : 0.00623631477355957 nb_pixel_total : 28 time to create 1 rle with old method : 9.608268737792969e-05 time for calcul the mask position with numpy : 0.0062139034271240234 nb_pixel_total : 110 time to create 1 rle with old method : 0.00014925003051757812 time for calcul the mask position with numpy : 0.006171226501464844 nb_pixel_total : 1605 time to create 1 rle with old method : 0.0018644332885742188 time for calcul the mask position with numpy : 0.00620579719543457 nb_pixel_total : 3129 time to create 1 rle with old method : 0.0036308765411376953 time for calcul the mask position with numpy : 0.006262063980102539 nb_pixel_total : 1469 time to create 1 rle with old method : 0.0016739368438720703 time for calcul the mask position with numpy : 0.006200075149536133 nb_pixel_total : 194 time to create 1 rle with old method : 0.000244140625 time for calcul the mask position with numpy : 0.006339311599731445 nb_pixel_total : 193 time to create 1 rle with old method : 0.00024580955505371094 time for calcul the mask position with numpy : 0.006814479827880859 nb_pixel_total : 105120 time to create 1 rle with old method : 0.11832547187805176 time for calcul the mask position with numpy : 0.00620579719543457 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003275871276855469 time for calcul the mask position with numpy : 0.006206989288330078 nb_pixel_total : 725 time to create 1 rle with old method : 0.0008444786071777344 time for calcul the mask position with numpy : 0.006235599517822266 nb_pixel_total : 41 time to create 1 rle with old method : 7.939338684082031e-05 time for calcul the mask position with numpy : 0.006325483322143555 nb_pixel_total : 178 time to create 1 rle with old method : 0.00021910667419433594 time for calcul the mask position with numpy : 0.010562896728515625 nb_pixel_total : 170 time to create 1 rle with old method : 0.00022268295288085938 time for calcul the mask position with numpy : 0.010507583618164062 nb_pixel_total : 925 time to create 1 rle with old method : 0.0010869503021240234 time for calcul the mask position with numpy : 0.010241508483886719 nb_pixel_total : 341 time to create 1 rle with old method : 0.00040531158447265625 time for calcul the mask position with numpy : 0.010304689407348633 nb_pixel_total : 25295 time to create 1 rle with old method : 0.028183460235595703 time for calcul the mask position with numpy : 0.010385751724243164 nb_pixel_total : 89 time to create 1 rle with old method : 0.00012421607971191406 time for calcul the mask position with numpy : 0.01041269302368164 nb_pixel_total : 113 time to create 1 rle with old method : 0.00015735626220703125 time for calcul the mask position with numpy : 0.010471820831298828 nb_pixel_total : 515 time to create 1 rle with old method : 0.0006165504455566406 time for calcul the mask position with numpy : 0.010289907455444336 nb_pixel_total : 291 time to create 1 rle with old method : 0.00035858154296875 time for calcul the mask position with numpy : 0.010352849960327148 nb_pixel_total : 83 time to create 1 rle with old method : 0.00014591217041015625 time for calcul the mask position with numpy : 0.01045989990234375 nb_pixel_total : 1257 time to create 1 rle with old method : 0.0014503002166748047 time for calcul the mask position with numpy : 0.010347604751586914 nb_pixel_total : 124 time to create 1 rle with old method : 0.00017642974853515625 time for calcul the mask position with numpy : 0.006293535232543945 nb_pixel_total : 474 time to create 1 rle with old method : 0.0005657672882080078 time for calcul the mask position with numpy : 0.00619196891784668 nb_pixel_total : 285 time to create 1 rle with old method : 0.00034117698669433594 time for calcul the mask position with numpy : 0.006242513656616211 nb_pixel_total : 740 time to create 1 rle with old method : 0.0009064674377441406 time for calcul the mask position with numpy : 0.007025718688964844 nb_pixel_total : 528 time to create 1 rle with old method : 0.0006246566772460938 time for calcul the mask position with numpy : 0.010454416275024414 nb_pixel_total : 320 time to create 1 rle with old method : 0.0003762245178222656 time for calcul the mask position with numpy : 0.010422468185424805 nb_pixel_total : 873 time to create 1 rle with old method : 0.0010128021240234375 time for calcul the mask position with numpy : 0.010481834411621094 nb_pixel_total : 1637 time to create 1 rle with old method : 0.0018417835235595703 time for calcul the mask position with numpy : 0.010303258895874023 nb_pixel_total : 179 time to create 1 rle with old method : 0.00022077560424804688 time for calcul the mask position with numpy : 0.010371208190917969 nb_pixel_total : 207 time to create 1 rle with old method : 0.000263214111328125 time for calcul the mask position with numpy : 0.01045536994934082 nb_pixel_total : 209 time to create 1 rle with old method : 0.0002884864807128906 time for calcul the mask position with numpy : 0.010592222213745117 nb_pixel_total : 709 time to create 1 rle with old method : 0.0008094310760498047 create new chi : 1.031137228012085 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.0017628669738769531 batch 1 Loaded 86 chid ids of type : 4230 Number RLEs to save : 9641 TO DO : save crop sub photo not yet done ! save time : 10.460327863693237 map_output_result : {1342952167: (0.0, 'Should be the crop_list due to order', 0.0), 1342952161: (0.0, 'Should be the crop_list due to order', 0.0), 1342951909: (0.0, 'Should be the crop_list due to order', 0.0), 1342951827: (0.0, 'Should be the crop_list due to order', 0.0), 1342951775: (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 [1342952167, 1342952161, 1342951909, 1342951827, 1342951775] Looping around the photos to save general results len do output : 5 /1342952167.Didn't retrieve data . /1342952161.Didn't retrieve data . /1342951909.Didn't retrieve data . /1342951827.Didn't retrieve data . /1342951775.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 ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952167', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952161', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951909', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951827', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951775', None, None, None, None, None, '2657890') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.02310323715209961 save_final save missing photos in datou_result : time spend for datou_step_exec : 81.58663868904114 time spend to save output : 0.03421926498413086 total time spend for step 4 : 81.62085795402527 step5:crop_condition Tue Mar 11 12:23:19 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 5 ! batch 1 Loaded 450 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 138 About to insert : list_path_to_insert length 138 new photo from crops ! About to upload 138 photos upload in portfolio : 4869462 init cache_photo without model_param we have 138 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741692204_597117 we have uploaded 138 photos in the portfolio 4869462 time of upload the photos Elapsed time : 47.033198833465576 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 41 About to insert : list_path_to_insert length 41 new photo from crops ! About to upload 41 photos upload in portfolio : 4869462 init cache_photo without model_param we have 41 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741692252_597117 we have uploaded 41 photos in the portfolio 4869462 time of upload the photos Elapsed time : 14.067896842956543 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 20 About to insert : list_path_to_insert length 20 new photo from crops ! About to upload 20 photos upload in portfolio : 4869462 init cache_photo without model_param we have 20 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741692266_597117 we have uploaded 20 photos in the portfolio 4869462 time of upload the photos Elapsed time : 5.557459354400635 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 67 About to insert : list_path_to_insert length 67 new photo from crops ! About to upload 67 photos upload in portfolio : 4869462 init cache_photo without model_param we have 67 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741692273_597117 we have uploaded 67 photos in the portfolio 4869462 time of upload the photos Elapsed time : 21.63152551651001 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1342952167, 1342952161, 1342951909, 1342951827, 1342951775] Looping around the photos to save general results len do output : 266 /1342986523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342986921Didn'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 ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952167', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952161', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951909', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951827', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951775', None, None, None, None, None, '2657890') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 803 time used for this insertion : 0.05364823341369629 save_final save missing photos in datou_result : time spend for datou_step_exec : 102.65118622779846 time spend to save output : 0.08589673042297363 total time spend for step 5 : 102.73708295822144 step6:thcl Tue Mar 11 12:25:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step Thcl ! we are using the classfication for only one thcl 3237 time to import caffe and check if the image exist : 0.017813920974731445 time to convert the images to numpy array : 0.0684058666229248 time to import caffe and check if the image exist : 0.02123570442199707 time to convert the images to numpy array : 0.09162235260009766 time to import caffe and check if the image exist : 0.026463031768798828 time to convert the images to numpy array : 0.09368276596069336 time to import caffe and check if the image exist : 0.03164029121398926 time to convert the images to numpy array : 0.09262228012084961 time to import caffe and check if the image exist : 0.02575397491455078 time to convert the images to numpy array : 0.09955716133117676 time to import caffe and check if the image exist : 0.029458045959472656 time to convert the images to numpy array : 0.0967099666595459 time to import caffe and check if the image exist : 0.035292625427246094 time to convert the images to numpy array : 0.0934901237487793 time to import caffe and check if the image exist : 0.023464202880859375 time to convert the images to numpy array : 0.10742068290710449 time to import caffe and check if the image exist : 0.026583194732666016 time to convert the images to numpy array : 0.10680603981018066 time to import caffe and check if the image exist : 0.036026954650878906 time to convert the images to numpy array : 0.09792661666870117 total time to convert the images to numpy array : 0.6534113883972168 list photo_ids error: [] list photo_ids correct : [1342986899, 1342986900, 1342986901, 1342986902, 1342986903, 1342986904, 1342986905, 1342986906, 1342986907, 1342986908, 1342986909, 1342986910, 1342986911, 1342986912, 1342986913, 1342986914, 1342986915, 1342986916, 1342986917, 1342986918, 1342986919, 1342986920, 1342986921, 1342986816, 1342986817, 1342986818, 1342986819, 1342986820, 1342986821, 1342986823, 1342986824, 1342986825, 1342986826, 1342986848, 1342986849, 1342986850, 1342986851, 1342986852, 1342986854, 1342986855, 1342986856, 1342986857, 1342986858, 1342986859, 1342986860, 1342986861, 1342986863, 1342986864, 1342986865, 1342986866, 1342986780, 1342986781, 1342986782, 1342986783, 1342986784, 1342986785, 1342986786, 1342986787, 1342986788, 1342986789, 1342986790, 1342986791, 1342986792, 1342986793, 1342986794, 1342986795, 1342986796, 1342986805, 1342986806, 1342986807, 1342986808, 1342986809, 1342986810, 1342986812, 1342986813, 1342986814, 1342986815, 1342986685, 1342986686, 1342986687, 1342986689, 1342986690, 1342986691, 1342986693, 1342986695, 1342986696, 1342986697, 1342986699, 1342986700, 1342986701, 1342986703, 1342986704, 1342986705, 1342986707, 1342986708, 1342986709, 1342986711, 1342986712, 1342986713, 1342986715, 1342986716, 1342986717, 1342986719, 1342986720, 1342986606, 1342986607, 1342986608, 1342986609, 1342986610, 1342986611, 1342986612, 1342986613, 1342986614, 1342986615, 1342986617, 1342986619, 1342986622, 1342986623, 1342986624, 1342986626, 1342986627, 1342986628, 1342986630, 1342986631, 1342986632, 1342986634, 1342986636, 1342986637, 1342986639, 1342986641, 1342986643, 1342986523, 1342986525, 1342986526, 1342986527, 1342986529, 1342986530, 1342986531, 1342986533, 1342986534, 1342986535, 1342986537, 1342986538, 1342986539, 1342986541, 1342986542, 1342986543, 1342986545, 1342986546, 1342986547, 1342986549, 1342986550, 1342986551, 1342986553, 1342986554, 1342986557, 1342986559, 1342986560, 1342986721, 1342986723, 1342986724, 1342986753, 1342986754, 1342986758, 1342986759, 1342986760, 1342986761, 1342986762, 1342986763, 1342986764, 1342986765, 1342986766, 1342986767, 1342986768, 1342986769, 1342986770, 1342986771, 1342986772, 1342986773, 1342986774, 1342986775, 1342986776, 1342986777, 1342986778, 1342986779, 1342986644, 1342986645, 1342986647, 1342986648, 1342986649, 1342986651, 1342986653, 1342986655, 1342986657, 1342986658, 1342986659, 1342986662, 1342986663, 1342986664, 1342986666, 1342986667, 1342986668, 1342986670, 1342986671, 1342986673, 1342986674, 1342986675, 1342986677, 1342986678, 1342986680, 1342986682, 1342986683, 1342986867, 1342986868, 1342986870, 1342986871, 1342986872, 1342986873, 1342986875, 1342986877, 1342986879, 1342986880, 1342986881, 1342986882, 1342986883, 1342986885, 1342986886, 1342986887, 1342986888, 1342986889, 1342986890, 1342986891, 1342986892, 1342986893, 1342986894, 1342986895, 1342986896, 1342986897, 1342986898, 1342986561, 1342986563, 1342986564, 1342986565, 1342986568, 1342986572, 1342986577, 1342986579, 1342986581, 1342986582, 1342986583, 1342986585, 1342986586, 1342986587, 1342986589, 1342986590, 1342986591, 1342986593, 1342986594, 1342986595, 1342986597, 1342986598, 1342986600, 1342986602, 1342986603, 1342986604, 1342986605] number of photos to traite : 266 try to delete the photos incorrect in DB tagging for thcl : 3237 To do loadFromThcl(), then load ParamDescType : thcl3237 thcls : [{'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'}] thcl {'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'} Update svm_hashtag_type_desc : 5561 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) To loadFromThcl() : net_5561 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3381 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_rubbia_refus_2500 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_rubbia_refus_2500 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_rubbia_refus_2500 /data/models_weight/learn_rubbia_refus_2500/caffemodel size_local : 94358479 size in s3 : 94358479 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:16 caffemodel already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt size_local : 32544 size in s3 : 32544 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:15 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:09:52 mean.npy already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/synset_words.txt size_local : 334 size in s3 : 334 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:10:06 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /home/admin/workarea/install/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/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt caffemodel_filename : /data/models_weight/learn_rubbia_refus_2500/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3162 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 1.438020944595337 time used to do the prediction : 1.0584681034088135 save descriptor for thcl : 3237 time to traite the descriptors : 1.7377195358276367 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1342986899 To insert : 1342986900 To insert : 1342986901 To insert : 1342986902 To insert : 1342986903 To insert : 1342986904 To insert : 1342986905 To insert : 1342986906 To insert : 1342986907 To insert : 1342986908 To insert : 1342986909 To insert : 1342986910 To insert : 1342986911 To insert : 1342986912 To insert : 1342986913 To insert : 1342986914 To insert : 1342986915 To insert : 1342986916 To insert : 1342986917 To insert : 1342986918 To insert : 1342986919 To insert : 1342986920 To insert : 1342986921 To insert : 1342986816 To insert : 1342986817 To insert : 1342986818 To insert : 1342986819 To insert : 1342986820 To insert : 1342986821 To insert : 1342986823 To insert : 1342986824 To insert : 1342986825 To insert : 1342986826 To insert : 1342986848 To insert : 1342986849 To insert : 1342986850 To insert : 1342986851 To insert : 1342986852 To insert : 1342986854 To insert : 1342986855 To insert : 1342986856 To insert : 1342986857 To insert : 1342986858 To insert : 1342986859 To insert : 1342986860 To insert : 1342986861 To insert : 1342986863 To insert : 1342986864 To insert : 1342986865 To insert : 1342986866 To insert : 1342986780 To insert : 1342986781 To insert : 1342986782 To insert : 1342986783 To insert : 1342986784 To insert : 1342986785 To insert : 1342986786 To insert : 1342986787 To insert : 1342986788 To insert : 1342986789 To insert : 1342986790 To insert : 1342986791 To insert : 1342986792 To insert : 1342986793 To insert : 1342986794 To insert : 1342986795 To insert : 1342986796 To insert : 1342986805 To insert : 1342986806 To insert : 1342986807 To insert : 1342986808 To insert : 1342986809 To insert : 1342986810 To insert : 1342986812 To insert : 1342986813 To insert : 1342986814 To insert : 1342986815 To insert : 1342986685 To insert : 1342986686 To insert : 1342986687 To insert : 1342986689 To insert : 1342986690 To insert : 1342986691 To insert : 1342986693 To insert : 1342986695 To insert : 1342986696 To insert : 1342986697 To insert : 1342986699 To insert : 1342986700 To insert : 1342986701 To insert : 1342986703 To insert : 1342986704 To insert : 1342986705 To insert : 1342986707 To insert : 1342986708 To insert : 1342986709 To insert : 1342986711 To insert : 1342986712 To insert : 1342986713 To insert : 1342986715 To insert : 1342986716 To insert : 1342986717 To insert : 1342986719 To insert : 1342986720 To insert : 1342986606 To insert : 1342986607 To insert : 1342986608 To insert : 1342986609 To insert : 1342986610 To insert : 1342986611 To insert : 1342986612 To insert : 1342986613 To insert : 1342986614 To insert : 1342986615 To insert : 1342986617 To insert : 1342986619 To insert : 1342986622 To insert : 1342986623 To insert : 1342986624 To insert : 1342986626 To insert : 1342986627 To insert : 1342986628 To insert : 1342986630 To insert : 1342986631 To insert : 1342986632 To insert : 1342986634 To insert : 1342986636 To insert : 1342986637 To insert : 1342986639 To insert : 1342986641 To insert : 1342986643 To insert : 1342986523 To insert : 1342986525 To insert : 1342986526 To insert : 1342986527 To insert : 1342986529 To insert : 1342986530 To insert : 1342986531 To insert : 1342986533 To insert : 1342986534 To insert : 1342986535 To insert : 1342986537 To insert : 1342986538 To insert : 1342986539 To insert : 1342986541 To insert : 1342986542 To insert : 1342986543 To insert : 1342986545 To insert : 1342986546 To insert : 1342986547 To insert : 1342986549 To insert : 1342986550 To insert : 1342986551 To insert : 1342986553 To insert : 1342986554 To insert : 1342986557 To insert : 1342986559 To insert : 1342986560 To insert : 1342986721 To insert : 1342986723 To insert : 1342986724 To insert : 1342986753 To insert : 1342986754 To insert : 1342986758 To insert : 1342986759 To insert : 1342986760 To insert : 1342986761 To insert : 1342986762 To insert : 1342986763 To insert : 1342986764 To insert : 1342986765 To insert : 1342986766 To insert : 1342986767 To insert : 1342986768 To insert : 1342986769 To insert : 1342986770 To insert : 1342986771 To insert : 1342986772 To insert : 1342986773 To insert : 1342986774 To insert : 1342986775 To insert : 1342986776 To insert : 1342986777 To insert : 1342986778 To insert : 1342986779 To insert : 1342986644 To insert : 1342986645 To insert : 1342986647 To insert : 1342986648 To insert : 1342986649 To insert : 1342986651 To insert : 1342986653 To insert : 1342986655 To insert : 1342986657 To insert : 1342986658 To insert : 1342986659 To insert : 1342986662 To insert : 1342986663 To insert : 1342986664 To insert : 1342986666 To insert : 1342986667 To insert : 1342986668 To insert : 1342986670 To insert : 1342986671 To insert : 1342986673 To insert : 1342986674 To insert : 1342986675 To insert : 1342986677 To insert : 1342986678 To insert : 1342986680 To insert : 1342986682 To insert : 1342986683 To insert : 1342986867 To insert : 1342986868 To insert : 1342986870 To insert : 1342986871 To insert : 1342986872 To insert : 1342986873 To insert : 1342986875 To insert : 1342986877 To insert : 1342986879 To insert : 1342986880 To insert : 1342986881 To insert : 1342986882 To insert : 1342986883 To insert : 1342986885 To insert : 1342986886 To insert : 1342986887 To insert : 1342986888 To insert : 1342986889 To insert : 1342986890 To insert : 1342986891 To insert : 1342986892 To insert : 1342986893 To insert : 1342986894 To insert : 1342986895 To insert : 1342986896 To insert : 1342986897 To insert : 1342986898 To insert : 1342986561 To insert : 1342986563 To insert : 1342986564 To insert : 1342986565 To insert : 1342986568 To insert : 1342986572 To insert : 1342986577 To insert : 1342986579 To insert : 1342986581 To insert : 1342986582 To insert : 1342986583 To insert : 1342986585 To insert : 1342986586 To insert : 1342986587 To insert : 1342986589 To insert : 1342986590 To insert : 1342986591 To insert : 1342986593 To insert : 1342986594 To insert : 1342986595 To insert : 1342986597 To insert : 1342986598 To insert : 1342986600 To insert : 1342986602 To insert : 1342986603 To insert : 1342986604 To insert : 1342986605 time to insert the descriptors : 75.41825151443481 Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos SAVE THCL : begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 440 time used for this insertion : 0.03907966613769531 save missing photos in datou_result : time spend for datou_step_exec : 85.1956992149353 time spend to save output : 0.11728572845458984 total time spend for step 6 : 85.31298494338989 step7:ventilate_hashtags_in_portfolio Tue Mar 11 12:26:27 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 21280472 get user id for portfolio 21280472 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`=21280472 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PEHD','Papier','papier','carton','pehd','mal_croppe','autre','flou','Film_plastique','refus','PET_clair','metal','PET_fonce','Carton','environnement','pet_clair','Tetrapak','pet_fonce')) AND mptpi.`min_score`=0.6 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`=21280472 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PEHD','Papier','papier','carton','pehd','mal_croppe','autre','flou','Film_plastique','refus','PET_clair','metal','PET_fonce','Carton','environnement','pet_clair','Tetrapak','pet_fonce')) AND mptpi.`min_score`=0.6 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") 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`=21280472 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PEHD','Papier','papier','carton','pehd','mal_croppe','autre','flou','Film_plastique','refus','PET_clair','metal','PET_fonce','Carton','environnement','pet_clair','Tetrapak','pet_fonce')) AND mptpi.`min_score`=0.6 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`=21280472 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PEHD','Papier','papier','carton','pehd','mal_croppe','autre','flou','Film_plastique','refus','PET_clair','metal','PET_fonce','Carton','environnement','pet_clair','Tetrapak','pet_fonce')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/21282121,21282119,21282130,21282122,21282123,21282124,21282125,21282126,21282132,21282128,21282134,21282131,21282133?tags=pehd,papier,carton,mal_croppe,autre,flou,film_plastique,refus,pet_clair,metal,pet_fonce,environnement,tetrapak&datou_id_consolidate=4235&port_consolidate=21280472 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1342952167, 1342952161, 1342951909, 1342951827, 1342951775] Looping around the photos to save general results len do output : 1 /21280472. 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 ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952167', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952161', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951909', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951827', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951775', None, None, None, None, None, '2657890') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.015112638473510742 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.8821253776550293 time spend to save output : 0.015456676483154297 total time spend for step 7 : 2.8975820541381836 step8:final Tue Mar 11 12:26:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : {1342952167: ('0.2509370351004086',), 1342952161: ('0.2509370351004086',), 1342951909: ('0.2509370351004086',), 1342951827: ('0.2509370351004086',), 1342951775: ('0.2509370351004086',)} new output for save of step final : {1342952167: ('0.2509370351004086',), 1342952161: ('0.2509370351004086',), 1342951909: ('0.2509370351004086',), 1342951827: ('0.2509370351004086',), 1342951775: ('0.2509370351004086',)} [1342952167, 1342952161, 1342951909, 1342951827, 1342951775] Looping around the photos to save general results len do output : 5 /1342952167.Didn't retrieve data . /1342952161.Didn't retrieve data . /1342951909.Didn't retrieve data . /1342951827.Didn't retrieve data . /1342951775.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 ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952167', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952161', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951909', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951827', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951775', None, None, None, None, None, '2657890') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.012877464294433594 save_final save missing photos in datou_result : time spend for datou_step_exec : 10.432880878448486 time spend to save output : 0.0132293701171875 total time spend for step 8 : 10.446110248565674 step9:velours_tree Tue Mar 11 12:26:40 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 list_portfolios : 21282121,21282119,21282130,21282122,21282123,21282124,21282125,21282126,21282132,21282128,21282134,21282131,21282133 photo desc type : 5561 - Retrieving photos to tag... query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282121 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282119 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282130 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282122 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282123 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282124 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282125 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282126 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282132 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282128 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282134 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282131 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21282133 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 266 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [5 3 2 4 5 2 2 5 0 0 0 0 0 4 0 5 2 1 0 0 1 0 0 0 2 4 0 4 5 5 3 2 5 2 2 0 4 0 0 0 4 5 4 5 2 5 1 0 1 0 0 0 0 0 4 0 4 5 3 2 5 5 0 0 0 0 4 0 5 0 2 2 1 0 1 0 5 2 1 5 0 0 0 4 4 5 5 3 5 1 5 2 5 1 2 0 0 0 0 4 0 5 2 0 1 0 1 0 0 0 4 0 4 4 5 5 3 5 0 0 0 0 4 0 2 2 2 5 1 0 1 0 2 0 0 0 4 4 3 0 5 5 1 2 2 0 5 5 2 1 2 3 5 5 2 2 2 2 3 0 5 5 5 1 4 2 3 0 5 0 5 0 5 5 0 1 4 4 2 2 1 2 5 2 1 2 1 1 2 2 5 2 1 1 2 2 2 2 2 2 5 0 3 2 4 2 5 0 0 2 2 3 2 2 3 5 5 0 2 0 0 2 2 3 2 2 2 5 5 5 5 2 0 0 0 2 2 3 5 2 2 2 5 5 2 2 2 0 0 2 2 3 2 2 0 5 5 2 0 0 2 2 3 0 2 2] Elapsed time: 0.05199456214904785 graph_id used : 82763 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/21282121,21282119,21282130,21282122,21282123,21282124,21282125,21282126,21282132,21282128,21282134,21282131,21282133?tags=pehd,papier,carton,mal_croppe,autre,flou,film_plastique,refus,pet_clair,metal,pet_fonce,environnement,tetrapak&datou_id_consolidate=4235&port_consolidate=21280472&tree_id=82763 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1342952167, 1342952161, 1342951909, 1342951827, 1342951775] Looping around the photos to save general results len do output : 1 /21280472Didn'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 ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952167', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952161', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951909', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951827', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951775', None, None, None, None, None, '2657890') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.015391111373901367 save_final save missing photos in datou_result : time spend for datou_step_exec : 18.414653778076172 time spend to save output : 0.015793323516845703 total time spend for step 9 : 18.430447101593018 step10:send_mail_cod Tue Mar 11 12:26:59 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 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 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_Qualipapia_P21280472_11-03-2025_12_26_59.pdf 21282085 imagette212820851741692419 21282083 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette212820831741692419 21282095 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette212820951741692420 21282086 imagette212820861741692421 21282087 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette212820871741692421 21282088 imagette212820881741692428 21282089 imagette212820891741692428 21282090 imagette212820901741692428 21282097 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette212820971741692428 21282092 imagette212820921741692429 21282100 imagette212821001741692429 21282098 imagette212820981741692429 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21280472 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21282121,21282119,21282130,21282122,21282123,21282124,21282125,21282126,21282132,21282128,21282134,21282131,21282133?tags=pehd,papier,carton,mal_croppe,autre,flou,film_plastique,refus,pet_clair,metal,pet_fonce,environnement,tetrapak&datou_id_consolidate=4235&port_consolidate=21280472&tree_id=82763 your option no_mail is active, we will not send the real mail to your client args[1342952167] : ((1342952167, -7.437412602335962, 492609224), (1342952167, -0.20976507188791824, 496442774), '0.2509370351004086') We are sending mail with results at cod@fotonower.com args[1342952161] : ((1342952161, -7.440184933550058, 492609224), (1342952161, -0.21172859775456268, 496442774), '0.2509370351004086') We are sending mail with results at cod@fotonower.com args[1342951909] : ((1342951909, -7.422659876675957, 492609224), (1342951909, -0.23270578073204273, 496442774), '0.2509370351004086') We are sending mail with results at cod@fotonower.com args[1342951827] : ((1342951827, -7.419615535539704, 492609224), (1342951827, -0.22625812114717336, 496442774), '0.2509370351004086') We are sending mail with results at cod@fotonower.com args[1342951775] : ((1342951775, -7.4077677828466815, 492609224), (1342951775, -0.18744879513142934, 496442774), '0.2509370351004086') We are sending mail with results at cod@fotonower.com refus_total : 0.2509370351004086 2022-04-13 10:29:59 0 SELECT ph.photo_id,ph.url,ph.username,ph.uploaded_at,ph.text FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21280472 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_Qualipapia_P21280472_11-03-2025_12_26_59.pdf results_Qualipapia_P21280472_11-03-2025_12_26_59.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280472_11-03-2025_12_26_59.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('4234','21280472','results_Qualipapia_P21280472_11-03-2025_12_26_59.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280472_11-03-2025_12_26_59.pdf','pdf','','0.18','0.2509370351004086') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1342952167, 1342952161, 1342951909, 1342951827, 1342951775] 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 ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952167', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952161', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951909', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951827', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951775', None, None, None, None, None, '2657890') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012743711471557617 save_final save missing photos in datou_result : time spend for datou_step_exec : 11.063141822814941 time spend to save output : 0.012999296188354492 total time spend for step 10 : 11.076141119003296 step11:split_time_score Tue Mar 11 12:27:10 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 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 begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 3442, 'mtr_user_id': 31, 'name': 'classifieur_2camions_valcor_021122_v1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'deux_camions,camion_droite,camion_gauche,pas_de_camion', 'svm_portfolios_learning': '7659379,7659034,7657685,7657114', 'photo_hashtag_type': 4458, 'photo_desc_type': 5723, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107760533,2107760534,2107760535,2107760536'}] 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'}] (('08', 5),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 11032025 21280472 Nombre de photos uploadées : 5 / 23040 (0%) 11032025 21280472 Nombre de photos taguées (types de déchets): 5 / 5 (100%) 11032025 21280472 Nombre de photos taguées (volume) : 0 / 5 (0%) elapsed_time : load_data_split_time_score 1.9073486328125e-06 elapsed_time : order_list_meta_photo_and_scores 5.9604644775390625e-06 ????? elapsed_time : fill_and_build_computed_from_old_data 0.0003037452697753906 elapsed_time : insert_dashboard_record_day_entry 0.023733854293823242 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 : 0.22714061189968543 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21277622_11-03-2025_11_42_13.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21277622 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21277622 AND mptpi.`type`=4230 To do Qualite : 0.24910878395863076 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21277623_11-03-2025_12_04_16.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21277623 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21277623 AND mptpi.`type`=4230 To do Qualite : 0.2356071487092859 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21277625_11-03-2025_11_40_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21277625 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21277625 AND mptpi.`type`=4230 To do Qualite : 0.23112404511114285 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21277626_11-03-2025_11_39_14.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21277626 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21277626 AND mptpi.`type`=4230 To do Qualite : 0.2118050916617007 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21277627_11-03-2025_11_49_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21277627 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21277627 AND mptpi.`type`=4230 To do Qualite : 0.197276231180961 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21277628_11-03-2025_11_41_44.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21277628 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21277628 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280459 order by id desc limit 1 Qualite : 0.2509370351004086 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280472_11-03-2025_12_26_59.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280472 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280472 AND mptpi.`type`=4230 To do Qualite : 0.19856955086683298 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280473_11-03-2025_12_25_08.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280473 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280473 AND mptpi.`type`=4230 To do Qualite : 0.2696024847711458 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280474_11-03-2025_12_23_19.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280474 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280474 AND mptpi.`type`=4230 To do Qualite : 0.2248136416311366 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280475 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280475 AND mptpi.`type`=4230 To do Qualite : 0.19797232639909476 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280487_11-03-2025_12_20_46.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280487 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280487 AND mptpi.`type`=4230 To do Qualite : 0.18525278575084841 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280489_11-03-2025_12_12_53.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280489 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280489 AND mptpi.`type`=4230 To do Qualite : 0.20786089970151592 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280490_11-03-2025_12_20_20.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280490 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280490 AND mptpi.`type`=4230 To do Qualite : 0.19957022730047014 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280491_11-03-2025_12_18_53.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280491 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280491 AND mptpi.`type`=4230 To do Qualite : 0.21642272114338673 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280492_11-03-2025_12_16_43.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280492 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280492 AND mptpi.`type`=4230 To do Qualite : 0.206299041647902 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280493_11-03-2025_12_15_15.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280493 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280493 AND mptpi.`type`=4230 To do Qualite : 0.21186549173528035 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21280494_11-03-2025_12_16_31.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21280494 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 ! 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 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 : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=21280494 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'11032025': {'nb_upload': 5, 'nb_taggue_class': 5, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1342952167, 1342952161, 1342951909, 1342951827, 1342951775] Looping around the photos to save general results len do output : 1 /21280472Didn'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 ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952167', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342952161', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951909', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951827', None, None, None, None, None, '2657890') ('4234', None, None, None, None, None, None, None, '2657890') ('4234', '21280472', '1342951775', None, None, None, None, None, '2657890') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.014318227767944336 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.8432929515838623 time spend to save output : 0.014496564865112305 total time spend for step 11 : 2.8577895164489746 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 5 set_done_treatment 62.43user 40.07system 6:48.15elapsed 25%CPU (0avgtext+0avgdata 2397844maxresident)k 1821616inputs+20216outputs (12186major+3274327minor)pagefaults 0swaps