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 : 1038892 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 : ['2618046'] with mtr_portfolio_ids : ['20860416'] and first list_photo_ids : [] new path : /proc/1038892/ 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 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.2986941337585449 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 Thu Feb 27 00:20:28 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 : 3177 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-27 00:20:31.090044: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-27 00:20:31.119344: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-27 00:20:31.121755: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f8ba8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-27 00:20:31.121814: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-27 00:20:31.126116: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-27 00:20:31.404881: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x15d05170 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-27 00:20:31.404944: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-27 00:20:31.405828: 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 2025-02-27 00:20:31.406293: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-27 00:20:31.410929: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-27 00:20:31.414318: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-27 00:20:31.414851: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-27 00:20:31.418171: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-27 00:20:31.419657: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-27 00:20:31.425740: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-27 00:20:31.426915: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-27 00:20:31.427008: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-27 00:20:31.427610: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-27 00:20:31.427630: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-27 00:20:31.427640: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-27 00:20:31.428627: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2725 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. 2025-02-27 00:20:31.714755: 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 2025-02-27 00:20:31.714869: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-27 00:20:31.714894: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-27 00:20:31.714933: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-27 00:20:31.714954: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-27 00:20:31.714974: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-27 00:20:31.714995: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-27 00:20:31.715016: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-27 00:20:31.716056: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-27 00:20:31.717312: 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 2025-02-27 00:20:31.717366: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-27 00:20:31.717386: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-27 00:20:31.717403: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-27 00:20:31.717420: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-27 00:20:31.717438: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-27 00:20:31.717455: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-27 00:20:31.717473: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-27 00:20:31.718496: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-27 00:20:31.718539: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-27 00:20:31.718551: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-27 00:20:31.718561: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-27 00:20:31.719703: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2725 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 : [] 2025-02-27 00:20:38.838632: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-27 00:20:39.034694: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-27 00:20:40.312887: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.312961: 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. 2025-02-27 00:20:40.313497: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.313513: 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. 2025-02-27 00:20:40.320601: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.320623: 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. 2025-02-27 00:20:40.321155: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.321169: 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. 2025-02-27 00:20:40.327764: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.327786: 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. 2025-02-27 00:20:40.328357: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.328372: 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. 2025-02-27 00:20:40.359092: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.359118: 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. 2025-02-27 00:20:40.359708: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.359724: 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. 2025-02-27 00:20:40.365502: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.365520: 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. 2025-02-27 00:20:40.366048: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.366063: 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. 2025-02-27 00:20:40.399879: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.400463: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.402136: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.402669: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.440640: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.441194: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.443196: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.443733: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.469991: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.470538: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.472111: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.472646: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.478346: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.478942: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.480683: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.481272: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.487180: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.487762: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.489327: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.489905: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.517594: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.518146: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.518679: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.519257: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.522870: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.523415: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.539454: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.539991: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.540517: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.541043: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.554109: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.554647: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.555197: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.555759: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.560167: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.560744: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.565395: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.565930: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.578562: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.579151: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.583503: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.584071: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.584597: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.585123: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.585795: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.586328: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.597600: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.598141: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.598689: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.599230: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.599765: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.600346: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.615127: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.615672: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.662489: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.662532: 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. 2025-02-27 00:20:40.663151: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.663739: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.671043: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.671628: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.679637: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.680254: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.695115: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.695735: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.696317: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.696869: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.700834: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.701411: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.701985: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.702556: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.703612: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.713579: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.714114: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.722992: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.723532: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.724071: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.724599: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.725136: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-27 00:20:40.725664: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2322464768 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 : 2 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: 217.00000 molded_images shape: (1, 640, 640, 3) min: -118.30938 max: 99.94375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.0003044605255126953 length of segment : 19 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.00019860267639160156 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.98516 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 : 0.00010538101196289062 nb_pixel_total : 568 time to create 1 rle with old method : 0.0011527538299560547 length of segment : 120 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0009708404541015625 length of segment : 40 time for calcul the mask position with numpy : 0.00013637542724609375 nb_pixel_total : 2900 time to create 1 rle with old method : 0.004601716995239258 length of segment : 67 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0010356903076171875 length of segment : 34 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003783702850341797 length of segment : 55 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0007026195526123047 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.68828 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 : 4.0531158447265625e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.00023412704467773438 length of segment : 15 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.00021529197692871094 length of segment : 18 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 488 time to create 1 rle with old method : 0.0007066726684570312 length of segment : 39 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0006337165832519531 length of segment : 18 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0006992816925048828 length of segment : 22 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0007448196411132812 length of segment : 25 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0006275177001953125 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: -122.90703 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 : 7.605552673339844e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0008137226104736328 length of segment : 23 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 2599 time to create 1 rle with old method : 0.005093574523925781 length of segment : 41 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0008816719055175781 length of segment : 16 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 1482 time to create 1 rle with old method : 0.0028617382049560547 length of segment : 46 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 352 time to create 1 rle with old method : 0.001399993896484375 length of segment : 24 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.00025010108947753906 length of segment : 20 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003826618194580078 length of segment : 18 time for calcul the mask position with numpy : 0.0002148151397705078 nb_pixel_total : 8286 time to create 1 rle with old method : 0.010352849960327148 length of segment : 187 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00020551681518554688 length of segment : 25 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 413 time to create 1 rle with old method : 0.0006225109100341797 length of segment : 24 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005981922149658203 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.05547 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 : 7.152557373046875e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0006394386291503906 length of segment : 22 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 782 time to create 1 rle with old method : 0.0014984607696533203 length of segment : 36 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.001074075698852539 length of segment : 34 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0007183551788330078 length of segment : 19 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0007407665252685547 length of segment : 17 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 652 time to create 1 rle with old method : 0.0013170242309570312 length of segment : 23 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1053 time to create 1 rle with old method : 0.0019097328186035156 length of segment : 58 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0010097026824951172 length of segment : 32 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0007011890411376953 length of segment : 25 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.0004086494445800781 length of segment : 12 time for calcul the mask position with numpy : 0.0001266002655029297 nb_pixel_total : 3388 time to create 1 rle with old method : 0.006026744842529297 length of segment : 96 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.0009808540344238281 length of segment : 36 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0004074573516845703 length of segment : 24 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00022482872009277344 length of segment : 17 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0004940032958984375 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.64531 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 : 8.940696716308594e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0013260841369628906 length of segment : 42 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0005662441253662109 length of segment : 28 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0011682510375976562 length of segment : 41 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007927417755126953 length of segment : 45 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0006594657897949219 length of segment : 36 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.0012006759643554688 length of segment : 31 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 676 time to create 1 rle with old method : 0.001321554183959961 length of segment : 43 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0006961822509765625 length of segment : 18 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 813 time to create 1 rle with old method : 0.0012044906616210938 length of segment : 30 time for calcul the mask position with numpy : 0.0003066062927246094 nb_pixel_total : 13125 time to create 1 rle with old method : 0.016294240951538086 length of segment : 164 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005509853363037109 length of segment : 19 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 250.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 142.39687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 822 time to create 1 rle with old method : 0.0010838508605957031 length of segment : 45 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006196498870849609 length of segment : 36 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003707408905029297 length of segment : 25 time for calcul the mask position with numpy : 0.00043392181396484375 nb_pixel_total : 11296 time to create 1 rle with old method : 0.014056682586669922 length of segment : 406 time for calcul the mask position with numpy : 0.00011229515075683594 nb_pixel_total : 1413 time to create 1 rle with old method : 0.003180265426635742 length of segment : 80 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.52813 max: 150.52187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 3949 time to create 1 rle with old method : 0.004914522171020508 length of segment : 100 time for calcul the mask position with numpy : 0.00011706352233886719 nb_pixel_total : 4158 time to create 1 rle with old method : 0.005344867706298828 length of segment : 128 Processing 1 images image shape: (400, 400, 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 : 17 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.0004277229309082031 length of segment : 11 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.0003905296325683594 length of segment : 12 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0005698204040527344 length of segment : 37 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 675 time to create 1 rle with old method : 0.0013346672058105469 length of segment : 24 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.0002827644348144531 length of segment : 23 time for calcul the mask position with numpy : 0.00011324882507324219 nb_pixel_total : 3324 time to create 1 rle with old method : 0.005910634994506836 length of segment : 100 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1128 time to create 1 rle with old method : 0.0020623207092285156 length of segment : 44 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002834796905517578 length of segment : 12 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 1492 time to create 1 rle with old method : 0.0028815269470214844 length of segment : 56 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 678 time to create 1 rle with old method : 0.0009856224060058594 length of segment : 40 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.0003256797790527344 length of segment : 13 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 636 time to create 1 rle with old method : 0.0009291172027587891 length of segment : 32 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.00046062469482421875 length of segment : 46 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.00028634071350097656 length of segment : 13 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 1037 time to create 1 rle with old method : 0.0013484954833984375 length of segment : 37 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002911090850830078 length of segment : 13 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 649 time to create 1 rle with old method : 0.0009016990661621094 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.39531 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 : 549 time to create 1 rle with old method : 0.0007116794586181641 length of segment : 54 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003886222839355469 length of segment : 24 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 252 time to create 1 rle with old method : 0.0003612041473388672 length of segment : 32 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002701282501220703 length of segment : 20 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 3333 time to create 1 rle with old method : 0.0041351318359375 length of segment : 124 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0004792213439941406 length of segment : 22 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0003311634063720703 length of segment : 8 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001819133758544922 length of segment : 14 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1220 time to create 1 rle with old method : 0.0016698837280273438 length of segment : 29 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.000400543212890625 length of segment : 27 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.0006289482116699219 length of segment : 31 time for calcul the mask position with numpy : 0.0001316070556640625 nb_pixel_total : 6111 time to create 1 rle with old method : 0.00771641731262207 length of segment : 100 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.00032520294189453125 length of segment : 14 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003497600555419922 length of segment : 24 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0014793872833251953 length of segment : 37 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 1901 time to create 1 rle with old method : 0.0025093555450439453 length of segment : 61 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 932 time to create 1 rle with old method : 0.0012826919555664062 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.28594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 1047 time to create 1 rle with old method : 0.0015006065368652344 length of segment : 35 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.0008845329284667969 length of segment : 28 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0014107227325439453 length of segment : 61 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0008182525634765625 length of segment : 36 time for calcul the mask position with numpy : 0.0001475811004638672 nb_pixel_total : 1965 time to create 1 rle with old method : 0.002984762191772461 length of segment : 163 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006241798400878906 length of segment : 28 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002856254577636719 length of segment : 23 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1848 time to create 1 rle with old method : 0.0023229122161865234 length of segment : 71 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.0008058547973632812 length of segment : 43 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.0001823902130126953 length of segment : 11 time for calcul the mask position with numpy : 0.00011229515075683594 nb_pixel_total : 5296 time to create 1 rle with old method : 0.006444215774536133 length of segment : 82 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004677772521972656 length of segment : 27 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0005390644073486328 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.86016 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 454 time to create 1 rle with old method : 0.0006387233734130859 length of segment : 35 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1547 time to create 1 rle with old method : 0.002087116241455078 length of segment : 37 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 2273 time to create 1 rle with old method : 0.002902507781982422 length of segment : 58 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.001096963882446289 length of segment : 27 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1907 time to create 1 rle with old method : 0.0028879642486572266 length of segment : 45 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 2219 time to create 1 rle with old method : 0.0027887821197509766 length of segment : 85 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005319118499755859 length of segment : 36 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.0001811981201171875 length of segment : 11 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1125 time to create 1 rle with old method : 0.0015785694122314453 length of segment : 57 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.24297 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 : 8.988380432128906e-05 nb_pixel_total : 786 time to create 1 rle with old method : 0.001562356948852539 length of segment : 25 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0006160736083984375 length of segment : 33 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1910 time to create 1 rle with old method : 0.002515077590942383 length of segment : 56 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1428 time to create 1 rle with old method : 0.0018472671508789062 length of segment : 45 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.00035381317138671875 length of segment : 28 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.000301361083984375 length of segment : 23 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.000881195068359375 length of segment : 25 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0004322528839111328 length of segment : 28 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0006496906280517578 length of segment : 19 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.0001895427703857422 length of segment : 14 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1307 time to create 1 rle with old method : 0.001814126968383789 length of segment : 67 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.00044417381286621094 length of segment : 31 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0007190704345703125 length of segment : 29 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.00036525726318359375 length of segment : 26 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1238 time to create 1 rle with old method : 0.0016393661499023438 length of segment : 51 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 248.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.93594 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 : 584 time to create 1 rle with old method : 0.00081634521484375 length of segment : 33 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1445 time to create 1 rle with old method : 0.0018978118896484375 length of segment : 44 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0003247261047363281 length of segment : 41 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005593299865722656 length of segment : 58 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.00022983551025390625 length of segment : 26 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003991127014160156 length of segment : 23 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0006792545318603516 length of segment : 54 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.27422 max: 147.35781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 67 time to create 1 rle with old method : 0.00021576881408691406 length of segment : 11 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1286 time to create 1 rle with old method : 0.0016849040985107422 length of segment : 41 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00020956993103027344 length of segment : 20 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00020813941955566406 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: -121.60625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002894401550292969 length of segment : 18 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0007448196411132812 length of segment : 57 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 4566 time to create 1 rle with old method : 0.005629777908325195 length of segment : 62 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.0001838207244873047 length of segment : 24 time for calcul the mask position with numpy : 0.00023293495178222656 nb_pixel_total : 6000 time to create 1 rle with old method : 0.012761592864990234 length of segment : 82 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1332 time to create 1 rle with old method : 0.0018146038055419922 length of segment : 36 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1384 time to create 1 rle with old method : 0.001847982406616211 length of segment : 38 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 5474 time to create 1 rle with old method : 0.006597757339477539 length of segment : 87 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 3913 time to create 1 rle with old method : 0.004842996597290039 length of segment : 87 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.38359 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 : 4.792213439941406e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009462833404541016 length of segment : 24 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1821 time to create 1 rle with old method : 0.0021445751190185547 length of segment : 46 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 633 time to create 1 rle with old method : 0.0008833408355712891 length of segment : 44 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0015077590942382812 length of segment : 55 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1481 time to create 1 rle with old method : 0.0021080970764160156 length of segment : 31 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0008690357208251953 length of segment : 34 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0006763935089111328 length of segment : 34 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004489421844482422 length of segment : 25 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005710124969482422 length of segment : 22 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.00016689300537109375 length of segment : 11 time for calcul the mask position with numpy : 0.00021958351135253906 nb_pixel_total : 4857 time to create 1 rle with old method : 0.0060923099517822266 length of segment : 331 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.05938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0006566047668457031 length of segment : 24 time for calcul the mask position with numpy : 0.0002875328063964844 nb_pixel_total : 11274 time to create 1 rle with old method : 0.016026735305786133 length of segment : 163 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 786 time to create 1 rle with old method : 0.001005411148071289 length of segment : 50 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.0004456043243408203 length of segment : 17 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 2391 time to create 1 rle with old method : 0.0029082298278808594 length of segment : 79 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0013003349304199219 length of segment : 28 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0012042522430419922 length of segment : 32 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1317 time to create 1 rle with old method : 0.001546621322631836 length of segment : 56 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 5573 time to create 1 rle with old method : 0.007030487060546875 length of segment : 80 time for calcul the mask position with numpy : 0.0001316070556640625 nb_pixel_total : 7323 time to create 1 rle with old method : 0.008713960647583008 length of segment : 103 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.0003254413604736328 length of segment : 28 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1080 time to create 1 rle with old method : 0.0015118122100830078 length of segment : 66 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0013988018035888672 length of segment : 30 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0005002021789550781 length of segment : 47 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 3261 time to create 1 rle with old method : 0.0039577484130859375 length of segment : 60 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003070831298828125 length of segment : 15 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 932 time to create 1 rle with old method : 0.0013599395751953125 length of segment : 73 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 3885 time to create 1 rle with old method : 0.004643440246582031 length of segment : 126 time for calcul the mask position with numpy : 0.0001227855682373047 nb_pixel_total : 2518 time to create 1 rle with old method : 0.003014802932739258 length of segment : 78 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 2474 time to create 1 rle with old method : 0.0028994083404541016 length of segment : 46 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 2639 time to create 1 rle with old method : 0.003169536590576172 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.88750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.0009970664978027344 length of segment : 23 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002799034118652344 length of segment : 16 time for calcul the mask position with numpy : 0.00026869773864746094 nb_pixel_total : 13916 time to create 1 rle with old method : 0.016757965087890625 length of segment : 266 time for calcul the mask position with numpy : 0.0001277923583984375 nb_pixel_total : 7451 time to create 1 rle with old method : 0.008751869201660156 length of segment : 115 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 2027 time to create 1 rle with old method : 0.0025916099548339844 length of segment : 55 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1488 time to create 1 rle with old method : 0.001886606216430664 length of segment : 88 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 569 time to create 1 rle with old method : 0.0007700920104980469 length of segment : 29 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 3864 time to create 1 rle with old method : 0.004617452621459961 length of segment : 86 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 1036 time to create 1 rle with old method : 0.0013041496276855469 length of segment : 50 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0006432533264160156 length of segment : 27 time for calcul the mask position with numpy : 0.00015401840209960938 nb_pixel_total : 10047 time to create 1 rle with old method : 0.011190414428710938 length of segment : 143 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 2218 time to create 1 rle with old method : 0.0026090145111083984 length of segment : 76 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 778 time to create 1 rle with old method : 0.0010752677917480469 length of segment : 25 time for calcul the mask position with numpy : 0.0001697540283203125 nb_pixel_total : 10750 time to create 1 rle with old method : 0.011908531188964844 length of segment : 115 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 911 time to create 1 rle with old method : 0.0012502670288085938 length of segment : 57 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.0008332729339599609 length of segment : 22 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 2160 time to create 1 rle with old method : 0.0025436878204345703 length of segment : 67 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1516 time to create 1 rle with old method : 0.0018284320831298828 length of segment : 46 time for calcul the mask position with numpy : 0.00015306472778320312 nb_pixel_total : 7564 time to create 1 rle with old method : 0.009039640426635742 length of segment : 153 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.04375 max: 147.31875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0007503032684326172 length of segment : 41 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003485679626464844 length of segment : 25 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0004696846008300781 length of segment : 36 Processing 1 images image shape: (400, 160, 3) min: 4.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 139.35000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.69375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 4427 time to create 1 rle with old method : 0.004931449890136719 length of segment : 106 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003085136413574219 length of segment : 22 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.000732421875 length of segment : 27 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0005242824554443359 length of segment : 33 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0009272098541259766 length of segment : 37 Processing 1 images image shape: (240, 400, 3) min: 8.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.86562 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0007634162902832031 length of segment : 53 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1649 time to create 1 rle with old method : 0.002025604248046875 length of segment : 86 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 729 time to create 1 rle with old method : 0.0009284019470214844 length of segment : 39 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 882 time to create 1 rle with old method : 0.0011553764343261719 length of segment : 68 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 1469 time to create 1 rle with old method : 0.002107858657836914 length of segment : 108 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 3232 time to create 1 rle with old method : 0.004162311553955078 length of segment : 105 Processing 1 images image shape: (240, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.99453 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 : 524 time to create 1 rle with old method : 0.0006508827209472656 length of segment : 38 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0008897781372070312 length of segment : 37 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1544 time to create 1 rle with old method : 0.002211332321166992 length of segment : 47 time for calcul the mask position with numpy : 0.0005910396575927734 nb_pixel_total : 48333 time to create 1 rle with old method : 0.05733323097229004 length of segment : 265 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 2541 time to create 1 rle with old method : 0.0033495426177978516 length of segment : 45 Processing 1 images image shape: (240, 400, 3) min: 3.00000 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 : 16 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1714 time to create 1 rle with old method : 0.0022313594818115234 length of segment : 59 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2952 time to create 1 rle with old method : 0.0038857460021972656 length of segment : 58 time for calcul the mask position with numpy : 0.00018262863159179688 nb_pixel_total : 1171 time to create 1 rle with old method : 0.0016393661499023438 length of segment : 94 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2633 time to create 1 rle with old method : 0.003717660903930664 length of segment : 47 time for calcul the mask position with numpy : 0.00018835067749023438 nb_pixel_total : 8278 time to create 1 rle with old method : 0.010174274444580078 length of segment : 111 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 780 time to create 1 rle with old method : 0.0010704994201660156 length of segment : 57 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 2482 time to create 1 rle with old method : 0.0029773712158203125 length of segment : 179 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 732 time to create 1 rle with old method : 0.0009586811065673828 length of segment : 39 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0004582405090332031 length of segment : 15 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 818 time to create 1 rle with old method : 0.00113677978515625 length of segment : 57 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006451606750488281 length of segment : 33 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1573 time to create 1 rle with old method : 0.001878499984741211 length of segment : 59 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 3292 time to create 1 rle with old method : 0.0041196346282958984 length of segment : 82 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1113 time to create 1 rle with old method : 0.001657247543334961 length of segment : 46 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 926 time to create 1 rle with old method : 0.0013172626495361328 length of segment : 35 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 778 time to create 1 rle with old method : 0.0010178089141845703 length of segment : 45 Processing 1 images image shape: (240, 400, 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 : 16 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1222 time to create 1 rle with old method : 0.0018165111541748047 length of segment : 80 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1408 time to create 1 rle with old method : 0.001962900161743164 length of segment : 22 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 2888 time to create 1 rle with old method : 0.003796100616455078 length of segment : 105 time for calcul the mask position with numpy : 0.00015616416931152344 nb_pixel_total : 7421 time to create 1 rle with old method : 0.00933837890625 length of segment : 234 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 2416 time to create 1 rle with old method : 0.0030465126037597656 length of segment : 128 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1441 time to create 1 rle with old method : 0.0020084381103515625 length of segment : 53 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 689 time to create 1 rle with old method : 0.0009353160858154297 length of segment : 36 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 521 time to create 1 rle with old method : 0.0007266998291015625 length of segment : 32 time for calcul the mask position with numpy : 0.00038123130798339844 nb_pixel_total : 24668 time to create 1 rle with old method : 0.029707908630371094 length of segment : 180 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.00029206275939941406 length of segment : 13 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 821 time to create 1 rle with old method : 0.0011053085327148438 length of segment : 22 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.00024628639221191406 length of segment : 20 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1791 time to create 1 rle with old method : 0.0021698474884033203 length of segment : 61 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1814 time to create 1 rle with old method : 0.002201557159423828 length of segment : 62 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0013854503631591797 length of segment : 30 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005311965942382812 length of segment : 17 Processing 1 images image shape: (240, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.28203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 1466 time to create 1 rle with old method : 0.0032405853271484375 length of segment : 60 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 698 time to create 1 rle with old method : 0.0011522769927978516 length of segment : 60 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0008285045623779297 length of segment : 27 Processing 1 images image shape: (240, 160, 3) min: 36.00000 max: 182.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 75.57307 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.00021791458129882812 length of segment : 13 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 36 time to create 1 rle with old method : 8.487701416015625e-05 length of segment : 11 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 8.00000 max: 216.00000 molded_images shape: (1, 640, 640, 3) min: -109.45000 max: 102.67031 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: -122.13750 max: 150.95937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 2496 time to create 1 rle with old method : 0.003347635269165039 length of segment : 60 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0007023811340332031 length of segment : 39 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0007917881011962891 length of segment : 86 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00033545494079589844 length of segment : 24 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.00040984153747558594 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: -121.47734 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 : 4.029273986816406e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.00029397010803222656 length of segment : 16 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.000514984130859375 length of segment : 21 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00015282630920410156 length of segment : 11 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004582405090332031 length of segment : 24 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00022411346435546875 length of segment : 8 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1147 time to create 1 rle with old method : 0.0014491081237792969 length of segment : 48 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004363059997558594 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.46953 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 : 4.100799560546875e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004432201385498047 length of segment : 23 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 2485 time to create 1 rle with old method : 0.0032677650451660156 length of segment : 41 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.00022673606872558594 length of segment : 19 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.0006237030029296875 length of segment : 22 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.000263214111328125 length of segment : 19 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0005309581756591797 length of segment : 23 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00023293495178222656 length of segment : 14 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003609657287597656 length of segment : 16 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1463 time to create 1 rle with old method : 0.0018770694732666016 length of segment : 47 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.0002315044403076172 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: -121.06328 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 : 4.3392181396484375e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0004630088806152344 length of segment : 15 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 748 time to create 1 rle with old method : 0.0010187625885009766 length of segment : 34 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0004856586456298828 length of segment : 24 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0004436969757080078 length of segment : 12 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0007257461547851562 length of segment : 34 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.0001614093780517578 length of segment : 12 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0004901885986328125 length of segment : 34 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0009894371032714844 length of segment : 22 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002624988555908203 length of segment : 11 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 2353 time to create 1 rle with old method : 0.0030374526977539062 length of segment : 60 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 138 time to create 1 rle with old method : 0.00023794174194335938 length of segment : 18 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 965 time to create 1 rle with old method : 0.0012743473052978516 length of segment : 60 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005745887756347656 length of segment : 25 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.000934600830078125 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: -123.54766 max: 150.68984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 599 time to create 1 rle with old method : 0.0007772445678710938 length of segment : 41 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0005068778991699219 length of segment : 21 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005273818969726562 length of segment : 37 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.00043654441833496094 length of segment : 17 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 419 time to create 1 rle with old method : 0.0006196498870849609 length of segment : 30 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0007269382476806641 length of segment : 40 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006480216979980469 length of segment : 23 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003688335418701172 length of segment : 28 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 1769 time to create 1 rle with old method : 0.002443552017211914 length of segment : 133 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0008368492126464844 length of segment : 37 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.0016813278198242188 length of segment : 32 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.000499725341796875 length of segment : 19 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.0008425712585449219 length of segment : 56 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0011603832244873047 length of segment : 29 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 237.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 116.08281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 893 time to create 1 rle with old method : 0.0014185905456542969 length of segment : 44 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.00039267539978027344 length of segment : 31 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003268718719482422 length of segment : 39 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.86797 max: 146.92812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00011086463928222656 nb_pixel_total : 4048 time to create 1 rle with old method : 0.005155801773071289 length of segment : 110 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004143714904785156 length of segment : 30 time for calcul the mask position with numpy : 0.00010037422180175781 nb_pixel_total : 3557 time to create 1 rle with old method : 0.004554033279418945 length of segment : 107 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.65703 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 : 7.510185241699219e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0009562969207763672 length of segment : 25 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00023031234741210938 length of segment : 32 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0007069110870361328 length of segment : 19 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00028252601623535156 length of segment : 12 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1086 time to create 1 rle with old method : 0.002024412155151367 length of segment : 42 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.0012781620025634766 length of segment : 35 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0004742145538330078 length of segment : 13 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.001466512680053711 length of segment : 26 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.0005464553833007812 length of segment : 17 time for calcul the mask position with numpy : 0.00013899803161621094 nb_pixel_total : 2048 time to create 1 rle with old method : 0.003921985626220703 length of segment : 125 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.000438690185546875 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: -114.17266 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 : 5.078315734863281e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00019311904907226562 length of segment : 13 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.000659942626953125 length of segment : 34 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0004634857177734375 length of segment : 25 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.00035452842712402344 length of segment : 24 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0004215240478515625 length of segment : 24 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0008435249328613281 length of segment : 40 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0009999275207519531 length of segment : 23 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002796649932861328 length of segment : 22 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1374 time to create 1 rle with old method : 0.0017881393432617188 length of segment : 76 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0005192756652832031 length of segment : 22 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0009262561798095703 length of segment : 28 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 590 time to create 1 rle with old method : 0.0008075237274169922 length of segment : 36 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.0011410713195800781 length of segment : 38 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004470348358154297 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: -117.98906 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1059 time to create 1 rle with old method : 0.0018057823181152344 length of segment : 38 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0007605552673339844 length of segment : 39 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 687 time to create 1 rle with old method : 0.0009181499481201172 length of segment : 37 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0006747245788574219 length of segment : 39 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0007660388946533203 length of segment : 60 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.001024007797241211 length of segment : 30 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005559921264648438 length of segment : 28 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 682 time to create 1 rle with old method : 0.0009267330169677734 length of segment : 40 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0008428096771240234 length of segment : 38 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1157 time to create 1 rle with old method : 0.0016252994537353516 length of segment : 35 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.00030040740966796875 length of segment : 17 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003848075866699219 length of segment : 23 time for calcul the mask position with numpy : 0.00010776519775390625 nb_pixel_total : 5146 time to create 1 rle with old method : 0.006312370300292969 length of segment : 88 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0008060932159423828 length of segment : 26 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0008203983306884766 length of segment : 27 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00038313865661621094 length of segment : 21 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 4459 time to create 1 rle with old method : 0.005402326583862305 length of segment : 103 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.0008003711700439453 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.39922 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 : 4.9591064453125e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007143020629882812 length of segment : 38 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 2407 time to create 1 rle with old method : 0.0031414031982421875 length of segment : 61 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0005891323089599609 length of segment : 32 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.00028967857360839844 length of segment : 17 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1469 time to create 1 rle with old method : 0.0019097328186035156 length of segment : 59 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1152 time to create 1 rle with old method : 0.001486063003540039 length of segment : 37 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1863 time to create 1 rle with old method : 0.0024094581604003906 length of segment : 46 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1208 time to create 1 rle with old method : 0.0016300678253173828 length of segment : 41 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 919 time to create 1 rle with old method : 0.0013356208801269531 length of segment : 18 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0007638931274414062 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.43047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 709 time to create 1 rle with old method : 0.0010166168212890625 length of segment : 31 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1440 time to create 1 rle with old method : 0.0019450187683105469 length of segment : 56 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.00027489662170410156 length of segment : 22 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.00032019615173339844 length of segment : 17 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0010471343994140625 length of segment : 23 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.0004475116729736328 length of segment : 31 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1254 time to create 1 rle with old method : 0.0017042160034179688 length of segment : 69 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.00020194053649902344 length of segment : 14 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 2255 time to create 1 rle with old method : 0.0028460025787353516 length of segment : 66 time for calcul the mask position with numpy : 0.00037550926208496094 nb_pixel_total : 15796 time to create 1 rle with old method : 0.020322322845458984 length of segment : 330 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 27 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002880096435546875 length of segment : 51 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 694 time to create 1 rle with old method : 0.0009598731994628906 length of segment : 35 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 28 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0006031990051269531 length of segment : 20 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0008275508880615234 length of segment : 37 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1207 time to create 1 rle with old method : 0.0015289783477783203 length of segment : 48 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1724 time to create 1 rle with old method : 0.002252340316772461 length of segment : 63 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.11172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1443 time to create 1 rle with old method : 0.001941680908203125 length of segment : 53 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 633 time to create 1 rle with old method : 0.0008747577667236328 length of segment : 32 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.00021028518676757812 length of segment : 35 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00028967857360839844 length of segment : 18 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1144 time to create 1 rle with old method : 0.0014946460723876953 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: -121.07109 max: 145.70156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.0002465248107910156 length of segment : 21 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 4051 time to create 1 rle with old method : 0.005049467086791992 length of segment : 110 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.76250 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 : 3.910064697265625e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002989768981933594 length of segment : 19 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0005083084106445312 length of segment : 56 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1790 time to create 1 rle with old method : 0.002351522445678711 length of segment : 64 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.0002765655517578125 length of segment : 31 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005662441253662109 length of segment : 27 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 4002 time to create 1 rle with old method : 0.005070924758911133 length of segment : 55 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1667 time to create 1 rle with old method : 0.00222015380859375 length of segment : 77 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 885 time to create 1 rle with old method : 0.0015075206756591797 length of segment : 40 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 3704 time to create 1 rle with old method : 0.0047109127044677734 length of segment : 55 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 3737 time to create 1 rle with old method : 0.004684925079345703 length of segment : 61 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.43438 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 714 time to create 1 rle with old method : 0.0010137557983398438 length of segment : 25 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1931 time to create 1 rle with old method : 0.0025339126586914062 length of segment : 47 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 659 time to create 1 rle with old method : 0.0009360313415527344 length of segment : 33 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 757 time to create 1 rle with old method : 0.0010859966278076172 length of segment : 50 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0005030632019042969 length of segment : 26 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1260 time to create 1 rle with old method : 0.0017976760864257812 length of segment : 57 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1703 time to create 1 rle with old method : 0.0023193359375 length of segment : 32 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1201 time to create 1 rle with old method : 0.0017046928405761719 length of segment : 81 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.000362396240234375 length of segment : 44 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 4628 time to create 1 rle with old method : 0.005957126617431641 length of segment : 120 time for calcul the mask position with numpy : 0.0002186298370361328 nb_pixel_total : 5487 time to create 1 rle with old method : 0.006846189498901367 length of segment : 269 time for calcul the mask position with numpy : 0.0002942085266113281 nb_pixel_total : 19598 time to create 1 rle with old method : 0.023163318634033203 length of segment : 382 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.72734 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 : 7.414817810058594e-05 nb_pixel_total : 836 time to create 1 rle with old method : 0.0014865398406982422 length of segment : 48 time for calcul the mask position with numpy : 0.0001537799835205078 nb_pixel_total : 5275 time to create 1 rle with old method : 0.008774042129516602 length of segment : 103 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003993511199951172 length of segment : 15 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 482 time to create 1 rle with old method : 0.0006988048553466797 length of segment : 22 time for calcul the mask position with numpy : 0.0001747608184814453 nb_pixel_total : 12011 time to create 1 rle with old method : 0.014060735702514648 length of segment : 177 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 3174 time to create 1 rle with old method : 0.003920078277587891 length of segment : 54 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.001112222671508789 length of segment : 55 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.00074005126953125 length of segment : 45 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0003750324249267578 length of segment : 19 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 2213 time to create 1 rle with old method : 0.002888917922973633 length of segment : 44 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1234 time to create 1 rle with old method : 0.0015211105346679688 length of segment : 48 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1261 time to create 1 rle with old method : 0.0017383098602294922 length of segment : 35 time for calcul the mask position with numpy : 0.00016617774963378906 nb_pixel_total : 11880 time to create 1 rle with old method : 0.013701915740966797 length of segment : 178 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 882 time to create 1 rle with old method : 0.0012047290802001953 length of segment : 30 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 686 time to create 1 rle with old method : 0.0010044574737548828 length of segment : 42 time for calcul the mask position with numpy : 0.00011610984802246094 nb_pixel_total : 5568 time to create 1 rle with old method : 0.0072307586669921875 length of segment : 80 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 2055 time to create 1 rle with old method : 0.0027742385864257812 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.60234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 0.0001423358917236328 nb_pixel_total : 6725 time to create 1 rle with old method : 0.00838327407836914 length of segment : 148 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 901 time to create 1 rle with old method : 0.0012426376342773438 length of segment : 33 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 2092 time to create 1 rle with old method : 0.0027561187744140625 length of segment : 60 time for calcul the mask position with numpy : 0.00018596649169921875 nb_pixel_total : 9510 time to create 1 rle with old method : 0.011661767959594727 length of segment : 132 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 3011 time to create 1 rle with old method : 0.0038471221923828125 length of segment : 78 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006971359252929688 length of segment : 27 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 576 time to create 1 rle with old method : 0.0007669925689697266 length of segment : 21 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003299713134765625 length of segment : 16 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006794929504394531 length of segment : 21 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0008389949798583984 length of segment : 34 time for calcul the mask position with numpy : 0.0001499652862548828 nb_pixel_total : 6182 time to create 1 rle with old method : 0.007560014724731445 length of segment : 163 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009121894836425781 length of segment : 33 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0010454654693603516 length of segment : 40 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005116462707519531 length of segment : 23 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006954669952392578 length of segment : 37 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1229 time to create 1 rle with old method : 0.0016527175903320312 length of segment : 43 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1543 time to create 1 rle with old method : 0.002141714096069336 length of segment : 43 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 5090 time to create 1 rle with old method : 0.006010532379150391 length of segment : 112 time for calcul the mask position with numpy : 0.0001773834228515625 nb_pixel_total : 10883 time to create 1 rle with old method : 0.01281285285949707 length of segment : 145 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1707 time to create 1 rle with old method : 0.002363443374633789 length of segment : 67 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1274 time to create 1 rle with old method : 0.001710653305053711 length of segment : 55 time for calcul the mask position with numpy : 0.00015473365783691406 nb_pixel_total : 8706 time to create 1 rle with old method : 0.011160135269165039 length of segment : 150 time for calcul the mask position with numpy : 0.000209808349609375 nb_pixel_total : 14051 time to create 1 rle with old method : 0.016435861587524414 length of segment : 136 time for calcul the mask position with numpy : 0.00011324882507324219 nb_pixel_total : 6729 time to create 1 rle with old method : 0.00761103630065918 length of segment : 175 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.91094 max: 147.88516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004677772521972656 length of segment : 28 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003597736358642578 length of segment : 23 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0005674362182617188 length of segment : 18 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0008912086486816406 length of segment : 30 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.0001590251922607422 length of segment : 23 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003304481506347656 length of segment : 17 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1524 time to create 1 rle with old method : 0.001989603042602539 length of segment : 45 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1491 time to create 1 rle with old method : 0.0020105838775634766 length of segment : 50 Processing 1 images image shape: (400, 160, 3) min: 5.00000 max: 235.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 116.57656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.00035381317138671875 length of segment : 20 Processing 1 images image shape: (240, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.41641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 4582 time to create 1 rle with old method : 0.0055255889892578125 length of segment : 112 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0007138252258300781 length of segment : 36 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.00012087821960449219 length of segment : 23 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.0002684593200683594 length of segment : 21 Processing 1 images image shape: (240, 400, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.05703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 2311 time to create 1 rle with old method : 0.0029213428497314453 length of segment : 66 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0009725093841552734 length of segment : 67 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 804 time to create 1 rle with old method : 0.0010764598846435547 length of segment : 44 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0004980564117431641 length of segment : 38 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1401 time to create 1 rle with old method : 0.0017435550689697266 length of segment : 89 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1022 time to create 1 rle with old method : 0.0013422966003417969 length of segment : 92 Processing 1 images image shape: (240, 400, 3) min: 12.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.94766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007357597351074219 length of segment : 37 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 4798 time to create 1 rle with old method : 0.006563425064086914 length of segment : 74 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 590 time to create 1 rle with old method : 0.001077413558959961 length of segment : 57 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.000438690185546875 length of segment : 25 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1043 time to create 1 rle with old method : 0.0015935897827148438 length of segment : 67 time for calcul the mask position with numpy : 0.0005681514739990234 nb_pixel_total : 48138 time to create 1 rle with old method : 0.05846428871154785 length of segment : 274 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 998 time to create 1 rle with old method : 0.0015163421630859375 length of segment : 75 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 996 time to create 1 rle with old method : 0.0015087127685546875 length of segment : 76 Processing 1 images image shape: (240, 400, 3) min: 7.00000 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 : 19 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005915164947509766 length of segment : 35 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 2645 time to create 1 rle with old method : 0.0035049915313720703 length of segment : 46 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0008585453033447266 length of segment : 36 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1687 time to create 1 rle with old method : 0.0022149085998535156 length of segment : 60 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.0013399124145507812 length of segment : 52 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 734 time to create 1 rle with old method : 0.0010235309600830078 length of segment : 58 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.00042247772216796875 length of segment : 22 time for calcul the mask position with numpy : 0.0001990795135498047 nb_pixel_total : 8593 time to create 1 rle with old method : 0.010584115982055664 length of segment : 110 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 2452 time to create 1 rle with old method : 0.0032567977905273438 length of segment : 41 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 2435 time to create 1 rle with old method : 0.0029854774475097656 length of segment : 98 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.00039887428283691406 length of segment : 12 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 935 time to create 1 rle with old method : 0.0012679100036621094 length of segment : 22 time for calcul the mask position with numpy : 0.0001735687255859375 nb_pixel_total : 1319 time to create 1 rle with old method : 0.0018126964569091797 length of segment : 60 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1483 time to create 1 rle with old method : 0.001956939697265625 length of segment : 60 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 2256 time to create 1 rle with old method : 0.003016233444213867 length of segment : 64 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 3700 time to create 1 rle with old method : 0.004723787307739258 length of segment : 69 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0006246566772460938 length of segment : 18 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1987 time to create 1 rle with old method : 0.0023734569549560547 length of segment : 178 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 2239 time to create 1 rle with old method : 0.0026171207427978516 length of segment : 164 Processing 1 images image shape: (240, 400, 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 : 21 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 5819 time to create 1 rle with old method : 0.006953716278076172 length of segment : 115 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 592 time to create 1 rle with old method : 0.0008618831634521484 length of segment : 61 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 800 time to create 1 rle with old method : 0.0010991096496582031 length of segment : 40 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 1624 time to create 1 rle with old method : 0.0022954940795898438 length of segment : 51 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1657 time to create 1 rle with old method : 0.002511262893676758 length of segment : 24 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 1951 time to create 1 rle with old method : 0.0038552284240722656 length of segment : 99 time for calcul the mask position with numpy : 0.00031948089599609375 nb_pixel_total : 9952 time to create 1 rle with old method : 0.014696836471557617 length of segment : 185 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 539 time to create 1 rle with old method : 0.0007674694061279297 length of segment : 33 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 1856 time to create 1 rle with old method : 0.002472400665283203 length of segment : 80 time for calcul the mask position with numpy : 0.00033092498779296875 nb_pixel_total : 18986 time to create 1 rle with old method : 0.022756338119506836 length of segment : 151 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 2365 time to create 1 rle with old method : 0.0029299259185791016 length of segment : 118 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 3900 time to create 1 rle with old method : 0.005007266998291016 length of segment : 73 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1835 time to create 1 rle with old method : 0.0021338462829589844 length of segment : 64 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.00026702880859375 length of segment : 10 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0003609657287597656 length of segment : 26 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.0002579689025878906 length of segment : 19 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.00048661231994628906 length of segment : 23 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 965 time to create 1 rle with old method : 0.0012500286102294922 length of segment : 30 time for calcul the mask position with numpy : 0.0001232624053955078 nb_pixel_total : 645 time to create 1 rle with old method : 0.0009958744049072266 length of segment : 57 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 822 time to create 1 rle with old method : 0.0011398792266845703 length of segment : 22 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 2941 time to create 1 rle with old method : 0.003534078598022461 length of segment : 132 Processing 1 images image shape: (240, 400, 3) min: 11.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.33672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1433 time to create 1 rle with old method : 0.002271413803100586 length of segment : 62 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1058 time to create 1 rle with old method : 0.0017240047454833984 length of segment : 29 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 935 time to create 1 rle with old method : 0.0011112689971923828 length of segment : 57 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006885528564453125 length of segment : 34 Processing 1 images image shape: (240, 160, 3) min: 49.00000 max: 184.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 77.39625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.00026416778564453125 length of segment : 22 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.0002002716064453125 length of segment : 14 Detection mask done ! Trying to reset tf kernel 1039349 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1984 tf kernel not reseted sub process len(results) : 527 len(list_Values) 527 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 527 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 : 3177 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 527 chid ids of type : 4228 Number RLEs to save : 27193 save missing photos in datou_result : time spend for datou_step_exec : 27.839409351348877 time spend to save output : 2.5714895725250244 total time spend for step 1 : 30.4108989238739 step2:brightness Thu Feb 27 00:20:58 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/1740612027_1038892_1339808855_d2801421f1bfb00184bd55b02f9e5229.jpg treat image : temp/1740612027_1038892_1339806785_6d6d5a7ee7efa6779d2f7124ac14f019.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 : 2 time used for this insertion : 0.014229774475097656 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.013664484024047852 save missing photos in datou_result : time spend for datou_step_exec : 0.9896094799041748 time spend to save output : 0.03254961967468262 total time spend for step 2 : 1.0221590995788574 step3:blur_detection Thu Feb 27 00:20:59 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 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/1740612027_1038892_1339808855_d2801421f1bfb00184bd55b02f9e5229.jpg resize: (1440, 2560) 1339808855 -7.911842347683338 treat image : temp/1740612027_1038892_1339806785_6d6d5a7ee7efa6779d2f7124ac14f019.jpg resize: (1440, 2560) 1339806785 -7.8344871232538695 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 : 2 time used for this insertion : 0.013755083084106445 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.012006998062133789 save missing photos in datou_result : time spend for datou_step_exec : 3.298981189727783 time spend to save output : 0.030431270599365234 total time spend for step 3 : 3.3294124603271484 step4:rle_unique_nms_with_priority Thu Feb 27 00:21:02 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 Begin step rle-unique-nms batch 1 Loaded 527 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 256 nb_hashtags : 5 time to prepare the origin masks : 1.998955249786377 time for calcul the mask position with numpy : 0.12749385833740234 nb_pixel_total : 3275409 time to create 1 rle with new method : 0.21026897430419922 time for calcul the mask position with numpy : 0.019046545028686523 nb_pixel_total : 120 time to create 1 rle with old method : 0.00016999244689941406 time for calcul the mask position with numpy : 0.014897823333740234 nb_pixel_total : 333 time to create 1 rle with old method : 0.0004620552062988281 time for calcul the mask position with numpy : 0.016567468643188477 nb_pixel_total : 86 time to create 1 rle with old method : 0.0001277923583984375 time for calcul the mask position with numpy : 0.01670098304748535 nb_pixel_total : 158 time to create 1 rle with old method : 0.0002319812774658203 time for calcul the mask position with numpy : 0.017217159271240234 nb_pixel_total : 782 time to create 1 rle with old method : 0.0010035037994384766 time for calcul the mask position with numpy : 0.016040325164794922 nb_pixel_total : 142 time to create 1 rle with old method : 0.00020384788513183594 time for calcul the mask position with numpy : 0.01684427261352539 nb_pixel_total : 290 time to create 1 rle with old method : 0.0004143714904785156 time for calcul the mask position with numpy : 0.015352249145507812 nb_pixel_total : 13006 time to create 1 rle with old method : 0.015030622482299805 time for calcul the mask position with numpy : 0.01462554931640625 nb_pixel_total : 3388 time to create 1 rle with old method : 0.0038623809814453125 time for calcul the mask position with numpy : 0.014885663986206055 nb_pixel_total : 385 time to create 1 rle with old method : 0.0004475116729736328 time for calcul the mask position with numpy : 0.014796733856201172 nb_pixel_total : 307 time to create 1 rle with old method : 0.0003726482391357422 time for calcul the mask position with numpy : 0.014918804168701172 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002162456512451172 time for calcul the mask position with numpy : 0.014661073684692383 nb_pixel_total : 231 time to create 1 rle with old method : 0.00028824806213378906 time for calcul the mask position with numpy : 0.015561580657958984 nb_pixel_total : 500 time to create 1 rle with old method : 0.0005981922149658203 time for calcul the mask position with numpy : 0.015286922454833984 nb_pixel_total : 632 time to create 1 rle with old method : 0.0007543563842773438 time for calcul the mask position with numpy : 0.01578211784362793 nb_pixel_total : 652 time to create 1 rle with old method : 0.0008482933044433594 time for calcul the mask position with numpy : 0.014989614486694336 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007073879241943359 time for calcul the mask position with numpy : 0.014820098876953125 nb_pixel_total : 2599 time to create 1 rle with old method : 0.0033347606658935547 time for calcul the mask position with numpy : 0.015999317169189453 nb_pixel_total : 7926 time to create 1 rle with old method : 0.009364128112792969 time for calcul the mask position with numpy : 0.015238046646118164 nb_pixel_total : 333 time to create 1 rle with old method : 0.0003936290740966797 time for calcul the mask position with numpy : 0.014908790588378906 nb_pixel_total : 568 time to create 1 rle with old method : 0.0006783008575439453 time for calcul the mask position with numpy : 0.014896869659423828 nb_pixel_total : 486 time to create 1 rle with old method : 0.0005984306335449219 time for calcul the mask position with numpy : 0.014859914779663086 nb_pixel_total : 362 time to create 1 rle with old method : 0.00043487548828125 time for calcul the mask position with numpy : 0.014901161193847656 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003266334533691406 time for calcul the mask position with numpy : 0.01485443115234375 nb_pixel_total : 540 time to create 1 rle with old method : 0.0006461143493652344 time for calcul the mask position with numpy : 0.014916181564331055 nb_pixel_total : 358 time to create 1 rle with old method : 0.00042438507080078125 time for calcul the mask position with numpy : 0.01493692398071289 nb_pixel_total : 813 time to create 1 rle with old method : 0.000993967056274414 time for calcul the mask position with numpy : 0.014944791793823242 nb_pixel_total : 502 time to create 1 rle with old method : 0.0006015300750732422 time for calcul the mask position with numpy : 0.015012979507446289 nb_pixel_total : 11004 time to create 1 rle with old method : 0.01304316520690918 time for calcul the mask position with numpy : 0.015129566192626953 nb_pixel_total : 307 time to create 1 rle with old method : 0.0003914833068847656 time for calcul the mask position with numpy : 0.015119314193725586 nb_pixel_total : 558 time to create 1 rle with old method : 0.0006866455078125 time for calcul the mask position with numpy : 0.014991998672485352 nb_pixel_total : 1482 time to create 1 rle with old method : 0.0017457008361816406 time for calcul the mask position with numpy : 0.014967918395996094 nb_pixel_total : 6 time to create 1 rle with old method : 3.147125244140625e-05 time for calcul the mask position with numpy : 0.014440059661865234 nb_pixel_total : 413 time to create 1 rle with old method : 0.00046443939208984375 time for calcul the mask position with numpy : 0.014830827713012695 nb_pixel_total : 346 time to create 1 rle with old method : 0.00043582916259765625 time for calcul the mask position with numpy : 0.014915227890014648 nb_pixel_total : 289 time to create 1 rle with old method : 0.00036454200744628906 time for calcul the mask position with numpy : 0.014914989471435547 nb_pixel_total : 2900 time to create 1 rle with old method : 0.0033860206604003906 time for calcul the mask position with numpy : 0.016015052795410156 nb_pixel_total : 1053 time to create 1 rle with old method : 0.001748800277709961 time for calcul the mask position with numpy : 0.0172121524810791 nb_pixel_total : 146 time to create 1 rle with old method : 0.00025725364685058594 time for calcul the mask position with numpy : 0.017435073852539062 nb_pixel_total : 352 time to create 1 rle with old method : 0.0006031990051269531 time for calcul the mask position with numpy : 0.017216205596923828 nb_pixel_total : 532 time to create 1 rle with old method : 0.0010502338409423828 time for calcul the mask position with numpy : 0.0171358585357666 nb_pixel_total : 262 time to create 1 rle with old method : 0.00034332275390625 time for calcul the mask position with numpy : 0.015006303787231445 nb_pixel_total : 240 time to create 1 rle with old method : 0.00030159950256347656 time for calcul the mask position with numpy : 0.014880657196044922 nb_pixel_total : 925 time to create 1 rle with old method : 0.0011374950408935547 time for calcul the mask position with numpy : 0.014808893203735352 nb_pixel_total : 492 time to create 1 rle with old method : 0.0005860328674316406 time for calcul the mask position with numpy : 0.014763116836547852 nb_pixel_total : 676 time to create 1 rle with old method : 0.0008270740509033203 time for calcul the mask position with numpy : 0.014891386032104492 nb_pixel_total : 125 time to create 1 rle with old method : 0.0001678466796875 time for calcul the mask position with numpy : 0.01486063003540039 nb_pixel_total : 99 time to create 1 rle with old method : 0.00012302398681640625 time for calcul the mask position with numpy : 0.014682531356811523 nb_pixel_total : 656 time to create 1 rle with old method : 0.0007722377777099609 time for calcul the mask position with numpy : 0.014843463897705078 nb_pixel_total : 488 time to create 1 rle with old method : 0.0005960464477539062 time for calcul the mask position with numpy : 0.014816045761108398 nb_pixel_total : 352 time to create 1 rle with old method : 0.00042557716369628906 time for calcul the mask position with numpy : 0.01462411880493164 nb_pixel_total : 822 time to create 1 rle with old method : 0.0009675025939941406 time for calcul the mask position with numpy : 0.014826774597167969 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005288124084472656 time for calcul the mask position with numpy : 0.014854907989501953 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003390312194824219 time for calcul the mask position with numpy : 0.014966487884521484 nb_pixel_total : 307 time to create 1 rle with old method : 0.0003757476806640625 time for calcul the mask position with numpy : 0.014854907989501953 nb_pixel_total : 330 time to create 1 rle with old method : 0.00039267539978027344 time for calcul the mask position with numpy : 0.014864683151245117 nb_pixel_total : 317 time to create 1 rle with old method : 0.0003972053527832031 time for calcul the mask position with numpy : 0.014901399612426758 nb_pixel_total : 151 time to create 1 rle with old method : 0.00020265579223632812 time for calcul the mask position with numpy : 0.01494288444519043 nb_pixel_total : 168 time to create 1 rle with old method : 0.00022673606872558594 time for calcul the mask position with numpy : 0.014869928359985352 nb_pixel_total : 632 time to create 1 rle with old method : 0.0007390975952148438 time for calcul the mask position with numpy : 0.01484990119934082 nb_pixel_total : 204 time to create 1 rle with old method : 0.00024771690368652344 time for calcul the mask position with numpy : 0.014583110809326172 nb_pixel_total : 378 time to create 1 rle with old method : 0.0004527568817138672 time for calcul the mask position with numpy : 0.01485896110534668 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006289482116699219 time for calcul the mask position with numpy : 0.014796733856201172 nb_pixel_total : 1848 time to create 1 rle with old method : 0.0022020339965820312 time for calcul the mask position with numpy : 0.014659404754638672 nb_pixel_total : 2273 time to create 1 rle with old method : 0.002641916275024414 time for calcul the mask position with numpy : 0.014859914779663086 nb_pixel_total : 180 time to create 1 rle with old method : 0.00023746490478515625 time for calcul the mask position with numpy : 0.014889240264892578 nb_pixel_total : 206 time to create 1 rle with old method : 0.000255584716796875 time for calcul the mask position with numpy : 0.014848709106445312 nb_pixel_total : 1 time to create 1 rle with old method : 8.821487426757812e-06 time for calcul the mask position with numpy : 0.014749765396118164 nb_pixel_total : 295 time to create 1 rle with old method : 0.0003573894500732422 time for calcul the mask position with numpy : 0.014882087707519531 nb_pixel_total : 123 time to create 1 rle with old method : 0.00016999244689941406 time for calcul the mask position with numpy : 0.014898538589477539 nb_pixel_total : 3324 time to create 1 rle with old method : 0.003911018371582031 time for calcul the mask position with numpy : 0.014566659927368164 nb_pixel_total : 1125 time to create 1 rle with old method : 0.001386404037475586 time for calcul the mask position with numpy : 0.01485443115234375 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004100799560546875 time for calcul the mask position with numpy : 0.014989852905273438 nb_pixel_total : 932 time to create 1 rle with old method : 0.0010411739349365234 time for calcul the mask position with numpy : 0.01454615592956543 nb_pixel_total : 3333 time to create 1 rle with old method : 0.0038633346557617188 time for calcul the mask position with numpy : 0.014827251434326172 nb_pixel_total : 251 time to create 1 rle with old method : 0.00030922889709472656 time for calcul the mask position with numpy : 0.014849424362182617 nb_pixel_total : 582 time to create 1 rle with old method : 0.0007150173187255859 time for calcul the mask position with numpy : 0.01475381851196289 nb_pixel_total : 1037 time to create 1 rle with old method : 0.0012254714965820312 time for calcul the mask position with numpy : 0.014572620391845703 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004074573516845703 time for calcul the mask position with numpy : 0.014798164367675781 nb_pixel_total : 410 time to create 1 rle with old method : 0.0004878044128417969 time for calcul the mask position with numpy : 0.014842033386230469 nb_pixel_total : 1128 time to create 1 rle with old method : 0.0013203620910644531 time for calcul the mask position with numpy : 0.014870405197143555 nb_pixel_total : 265 time to create 1 rle with old method : 0.0003132820129394531 time for calcul the mask position with numpy : 0.014761686325073242 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003407001495361328 time for calcul the mask position with numpy : 0.016620159149169922 nb_pixel_total : 1428 time to create 1 rle with old method : 0.001752614974975586 time for calcul the mask position with numpy : 0.014913558959960938 nb_pixel_total : 19 time to create 1 rle with old method : 3.790855407714844e-05 time for calcul the mask position with numpy : 0.014874935150146484 nb_pixel_total : 584 time to create 1 rle with old method : 0.0006990432739257812 time for calcul the mask position with numpy : 0.014892101287841797 nb_pixel_total : 328 time to create 1 rle with old method : 0.0003845691680908203 time for calcul the mask position with numpy : 0.014832019805908203 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001285076141357422 time for calcul the mask position with numpy : 0.014689445495605469 nb_pixel_total : 1965 time to create 1 rle with old method : 0.0023767948150634766 time for calcul the mask position with numpy : 0.014888763427734375 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003216266632080078 time for calcul the mask position with numpy : 0.014778614044189453 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002067089080810547 time for calcul the mask position with numpy : 0.014614343643188477 nb_pixel_total : 1492 time to create 1 rle with old method : 0.001779794692993164 time for calcul the mask position with numpy : 0.014394044876098633 nb_pixel_total : 454 time to create 1 rle with old method : 0.0005464553833007812 time for calcul the mask position with numpy : 0.014875650405883789 nb_pixel_total : 155 time to create 1 rle with old method : 0.0001895427703857422 time for calcul the mask position with numpy : 0.014862775802612305 nb_pixel_total : 1307 time to create 1 rle with old method : 0.0015552043914794922 time for calcul the mask position with numpy : 0.014499187469482422 nb_pixel_total : 786 time to create 1 rle with old method : 0.0009121894836425781 time for calcul the mask position with numpy : 0.014781951904296875 nb_pixel_total : 229 time to create 1 rle with old method : 0.0002732276916503906 time for calcul the mask position with numpy : 0.014632225036621094 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007176399230957031 time for calcul the mask position with numpy : 0.014838933944702148 nb_pixel_total : 3949 time to create 1 rle with old method : 0.00464940071105957 time for calcul the mask position with numpy : 0.014217615127563477 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0011501312255859375 time for calcul the mask position with numpy : 0.014198780059814453 nb_pixel_total : 132 time to create 1 rle with old method : 0.00016498565673828125 time for calcul the mask position with numpy : 0.01458597183227539 nb_pixel_total : 1238 time to create 1 rle with old method : 0.0013360977172851562 time for calcul the mask position with numpy : 0.014748334884643555 nb_pixel_total : 1445 time to create 1 rle with old method : 0.0017042160034179688 time for calcul the mask position with numpy : 0.014857053756713867 nb_pixel_total : 2219 time to create 1 rle with old method : 0.0025911331176757812 time for calcul the mask position with numpy : 0.014548063278198242 nb_pixel_total : 104 time to create 1 rle with old method : 0.00013637542724609375 time for calcul the mask position with numpy : 0.01454019546508789 nb_pixel_total : 252 time to create 1 rle with old method : 0.0003018379211425781 time for calcul the mask position with numpy : 0.01488637924194336 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0011913776397705078 time for calcul the mask position with numpy : 0.014832496643066406 nb_pixel_total : 549 time to create 1 rle with old method : 0.0006773471832275391 time for calcul the mask position with numpy : 0.014609575271606445 nb_pixel_total : 5296 time to create 1 rle with old method : 0.006089687347412109 time for calcul the mask position with numpy : 0.014759063720703125 nb_pixel_total : 573 time to create 1 rle with old method : 0.0006906986236572266 time for calcul the mask position with numpy : 0.01511240005493164 nb_pixel_total : 478 time to create 1 rle with old method : 0.0005915164947509766 time for calcul the mask position with numpy : 0.015097856521606445 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003256797790527344 time for calcul the mask position with numpy : 0.015001535415649414 nb_pixel_total : 130 time to create 1 rle with old method : 0.0001728534698486328 time for calcul the mask position with numpy : 0.018899917602539062 nb_pixel_total : 470 time to create 1 rle with old method : 0.0005972385406494141 time for calcul the mask position with numpy : 0.01572108268737793 nb_pixel_total : 713 time to create 1 rle with old method : 0.0008809566497802734 time for calcul the mask position with numpy : 0.014952898025512695 nb_pixel_total : 1901 time to create 1 rle with old method : 0.002306222915649414 time for calcul the mask position with numpy : 0.014926910400390625 nb_pixel_total : 248 time to create 1 rle with old method : 0.0003018379211425781 time for calcul the mask position with numpy : 0.015062332153320312 nb_pixel_total : 163 time to create 1 rle with old method : 0.00023484230041503906 time for calcul the mask position with numpy : 0.014921426773071289 nb_pixel_total : 1907 time to create 1 rle with old method : 0.0022482872009277344 time for calcul the mask position with numpy : 0.015700578689575195 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005106925964355469 time for calcul the mask position with numpy : 0.01505422592163086 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003647804260253906 time for calcul the mask position with numpy : 0.015091896057128906 nb_pixel_total : 678 time to create 1 rle with old method : 0.0008442401885986328 time for calcul the mask position with numpy : 0.015152931213378906 nb_pixel_total : 6111 time to create 1 rle with old method : 0.0074880123138427734 time for calcul the mask position with numpy : 0.015137910842895508 nb_pixel_total : 117 time to create 1 rle with old method : 0.00016164779663085938 time for calcul the mask position with numpy : 0.014816761016845703 nb_pixel_total : 384 time to create 1 rle with old method : 0.00048661231994628906 time for calcul the mask position with numpy : 0.014910459518432617 nb_pixel_total : 675 time to create 1 rle with old method : 0.0008244514465332031 time for calcul the mask position with numpy : 0.014829874038696289 nb_pixel_total : 445 time to create 1 rle with old method : 0.0005114078521728516 time for calcul the mask position with numpy : 0.014808177947998047 nb_pixel_total : 30 time to create 1 rle with old method : 8.606910705566406e-05 time for calcul the mask position with numpy : 0.01489567756652832 nb_pixel_total : 636 time to create 1 rle with old method : 0.0007960796356201172 time for calcul the mask position with numpy : 0.014858484268188477 nb_pixel_total : 295 time to create 1 rle with old method : 0.0003719329833984375 time for calcul the mask position with numpy : 0.014883756637573242 nb_pixel_total : 239 time to create 1 rle with old method : 0.0002918243408203125 time for calcul the mask position with numpy : 0.014898300170898438 nb_pixel_total : 1910 time to create 1 rle with old method : 0.0022656917572021484 time for calcul the mask position with numpy : 0.014973640441894531 nb_pixel_total : 1047 time to create 1 rle with old method : 0.0012369155883789062 time for calcul the mask position with numpy : 0.01475214958190918 nb_pixel_total : 1547 time to create 1 rle with old method : 0.001888275146484375 time for calcul the mask position with numpy : 0.014969825744628906 nb_pixel_total : 1220 time to create 1 rle with old method : 0.0014872550964355469 time for calcul the mask position with numpy : 0.014864683151245117 nb_pixel_total : 646 time to create 1 rle with old method : 0.0007836818695068359 time for calcul the mask position with numpy : 0.01485896110534668 nb_pixel_total : 177 time to create 1 rle with old method : 0.00022268295288085938 time for calcul the mask position with numpy : 0.014909744262695312 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002422332763671875 time for calcul the mask position with numpy : 0.014919519424438477 nb_pixel_total : 666 time to create 1 rle with old method : 0.0008246898651123047 time for calcul the mask position with numpy : 0.014900684356689453 nb_pixel_total : 647 time to create 1 rle with old method : 0.0007958412170410156 time for calcul the mask position with numpy : 0.014882087707519531 nb_pixel_total : 83 time to create 1 rle with old method : 0.00010538101196289062 time for calcul the mask position with numpy : 0.014607667922973633 nb_pixel_total : 781 time to create 1 rle with old method : 0.0010066032409667969 time for calcul the mask position with numpy : 0.014497995376586914 nb_pixel_total : 214 time to create 1 rle with old method : 0.000278472900390625 time for calcul the mask position with numpy : 0.01479792594909668 nb_pixel_total : 1516 time to create 1 rle with old method : 0.0019249916076660156 time for calcul the mask position with numpy : 0.014633655548095703 nb_pixel_total : 504 time to create 1 rle with old method : 0.0005779266357421875 time for calcul the mask position with numpy : 0.014708757400512695 nb_pixel_total : 478 time to create 1 rle with old method : 0.0006101131439208984 time for calcul the mask position with numpy : 0.015212774276733398 nb_pixel_total : 13916 time to create 1 rle with old method : 0.016156435012817383 time for calcul the mask position with numpy : 0.014849185943603516 nb_pixel_total : 582 time to create 1 rle with old method : 0.0006670951843261719 time for calcul the mask position with numpy : 0.014606475830078125 nb_pixel_total : 67 time to create 1 rle with old method : 0.0001068115234375 time for calcul the mask position with numpy : 0.01472020149230957 nb_pixel_total : 374 time to create 1 rle with old method : 0.0005240440368652344 time for calcul the mask position with numpy : 0.01460576057434082 nb_pixel_total : 347 time to create 1 rle with old method : 0.00043654441833496094 time for calcul the mask position with numpy : 0.014578104019165039 nb_pixel_total : 7323 time to create 1 rle with old method : 0.010075092315673828 time for calcul the mask position with numpy : 0.01704549789428711 nb_pixel_total : 136 time to create 1 rle with old method : 0.00025463104248046875 time for calcul the mask position with numpy : 0.01711273193359375 nb_pixel_total : 1031 time to create 1 rle with old method : 0.0017576217651367188 time for calcul the mask position with numpy : 0.01714777946472168 nb_pixel_total : 1821 time to create 1 rle with old method : 0.003121614456176758 time for calcul the mask position with numpy : 0.017075538635253906 nb_pixel_total : 473 time to create 1 rle with old method : 0.0008492469787597656 time for calcul the mask position with numpy : 0.015882015228271484 nb_pixel_total : 70 time to create 1 rle with old method : 9.632110595703125e-05 time for calcul the mask position with numpy : 0.014799833297729492 nb_pixel_total : 61 time to create 1 rle with old method : 0.0001399517059326172 time for calcul the mask position with numpy : 0.014711856842041016 nb_pixel_total : 1332 time to create 1 rle with old method : 0.0016388893127441406 time for calcul the mask position with numpy : 0.014297008514404297 nb_pixel_total : 39 time to create 1 rle with old method : 0.00012826919555664062 time for calcul the mask position with numpy : 0.014664888381958008 nb_pixel_total : 4566 time to create 1 rle with old method : 0.0053174495697021484 time for calcul the mask position with numpy : 0.014520406723022461 nb_pixel_total : 176 time to create 1 rle with old method : 0.00020599365234375 time for calcul the mask position with numpy : 0.014091730117797852 nb_pixel_total : 4857 time to create 1 rle with old method : 0.005787372589111328 time for calcul the mask position with numpy : 0.014702320098876953 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0015516281127929688 time for calcul the mask position with numpy : 0.014409065246582031 nb_pixel_total : 633 time to create 1 rle with old method : 0.0007412433624267578 time for calcul the mask position with numpy : 0.014413595199584961 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005049705505371094 time for calcul the mask position with numpy : 0.015004634857177734 nb_pixel_total : 7445 time to create 1 rle with old method : 0.012448787689208984 time for calcul the mask position with numpy : 0.017040491104125977 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002410411834716797 time for calcul the mask position with numpy : 0.017061471939086914 nb_pixel_total : 332 time to create 1 rle with old method : 0.0005600452423095703 time for calcul the mask position with numpy : 0.01710677146911621 nb_pixel_total : 3261 time to create 1 rle with old method : 0.005480527877807617 time for calcul the mask position with numpy : 0.015892505645751953 nb_pixel_total : 285 time to create 1 rle with old method : 0.0003559589385986328 time for calcul the mask position with numpy : 0.014609813690185547 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003752708435058594 time for calcul the mask position with numpy : 0.014649629592895508 nb_pixel_total : 2391 time to create 1 rle with old method : 0.002805948257446289 time for calcul the mask position with numpy : 0.015069723129272461 nb_pixel_total : 455 time to create 1 rle with old method : 0.0005691051483154297 time for calcul the mask position with numpy : 0.015095949172973633 nb_pixel_total : 2027 time to create 1 rle with old method : 0.002414226531982422 time for calcul the mask position with numpy : 0.016681671142578125 nb_pixel_total : 1286 time to create 1 rle with old method : 0.001535654067993164 time for calcul the mask position with numpy : 0.015138387680053711 nb_pixel_total : 11274 time to create 1 rle with old method : 0.01351022720336914 time for calcul the mask position with numpy : 0.01499176025390625 nb_pixel_total : 888 time to create 1 rle with old method : 0.001054525375366211 time for calcul the mask position with numpy : 0.014893054962158203 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002675056457519531 time for calcul the mask position with numpy : 0.014742851257324219 nb_pixel_total : 2474 time to create 1 rle with old method : 0.002867460250854492 time for calcul the mask position with numpy : 0.014859199523925781 nb_pixel_total : 7451 time to create 1 rle with old method : 0.008599996566772461 time for calcul the mask position with numpy : 0.01442265510559082 nb_pixel_total : 2218 time to create 1 rle with old method : 0.0025374889373779297 time for calcul the mask position with numpy : 0.014581918716430664 nb_pixel_total : 64 time to create 1 rle with old method : 0.00013065338134765625 time for calcul the mask position with numpy : 0.014729499816894531 nb_pixel_total : 257 time to create 1 rle with old method : 0.0002834796905517578 time for calcul the mask position with numpy : 0.01460409164428711 nb_pixel_total : 10750 time to create 1 rle with old method : 0.012158393859863281 time for calcul the mask position with numpy : 0.014723539352416992 nb_pixel_total : 950 time to create 1 rle with old method : 0.0011227130889892578 time for calcul the mask position with numpy : 0.014812469482421875 nb_pixel_total : 786 time to create 1 rle with old method : 0.0009930133819580078 time for calcul the mask position with numpy : 0.01468348503112793 nb_pixel_total : 10047 time to create 1 rle with old method : 0.01140737533569336 time for calcul the mask position with numpy : 0.015009641647338867 nb_pixel_total : 373 time to create 1 rle with old method : 0.0004658699035644531 time for calcul the mask position with numpy : 0.014935016632080078 nb_pixel_total : 950 time to create 1 rle with old method : 0.001107931137084961 time for calcul the mask position with numpy : 0.014874458312988281 nb_pixel_total : 5474 time to create 1 rle with old method : 0.006356239318847656 time for calcul the mask position with numpy : 0.014956235885620117 nb_pixel_total : 3864 time to create 1 rle with old method : 0.004383087158203125 time for calcul the mask position with numpy : 0.014850139617919922 nb_pixel_total : 120 time to create 1 rle with old method : 0.00021648406982421875 time for calcul the mask position with numpy : 0.015027999877929688 nb_pixel_total : 6000 time to create 1 rle with old method : 0.006928920745849609 time for calcul the mask position with numpy : 0.014893770217895508 nb_pixel_total : 1080 time to create 1 rle with old method : 0.0013186931610107422 time for calcul the mask position with numpy : 0.014799833297729492 nb_pixel_total : 228 time to create 1 rle with old method : 0.0004124641418457031 time for calcul the mask position with numpy : 0.014923810958862305 nb_pixel_total : 5573 time to create 1 rle with old method : 0.006511688232421875 time for calcul the mask position with numpy : 0.014878511428833008 nb_pixel_total : 1488 time to create 1 rle with old method : 0.0017671585083007812 time for calcul the mask position with numpy : 0.014610052108764648 nb_pixel_total : 565 time to create 1 rle with old method : 0.0006628036499023438 time for calcul the mask position with numpy : 0.01475834846496582 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0012314319610595703 time for calcul the mask position with numpy : 0.014862060546875 nb_pixel_total : 705 time to create 1 rle with old method : 0.0008599758148193359 time for calcul the mask position with numpy : 0.01489400863647461 nb_pixel_total : 1481 time to create 1 rle with old method : 0.0017242431640625 time for calcul the mask position with numpy : 0.01486659049987793 nb_pixel_total : 778 time to create 1 rle with old method : 0.0009124279022216797 time for calcul the mask position with numpy : 0.014928579330444336 nb_pixel_total : 225 time to create 1 rle with old method : 0.0002715587615966797 time for calcul the mask position with numpy : 0.014597892761230469 nb_pixel_total : 2952 time to create 1 rle with old method : 0.0034503936767578125 time for calcul the mask position with numpy : 0.014737367630004883 nb_pixel_total : 192 time to create 1 rle with old method : 0.00023317337036132812 time for calcul the mask position with numpy : 0.015402793884277344 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004298686981201172 time for calcul the mask position with numpy : 0.014302492141723633 nb_pixel_total : 1544 time to create 1 rle with old method : 0.0018570423126220703 time for calcul the mask position with numpy : 0.014803409576416016 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006115436553955078 time for calcul the mask position with numpy : 0.014824867248535156 nb_pixel_total : 821 time to create 1 rle with old method : 0.0009543895721435547 time for calcul the mask position with numpy : 0.014766216278076172 nb_pixel_total : 2541 time to create 1 rle with old method : 0.003024578094482422 time for calcul the mask position with numpy : 0.014974594116210938 nb_pixel_total : 39 time to create 1 rle with old method : 0.0001468658447265625 time for calcul the mask position with numpy : 0.014935493469238281 nb_pixel_total : 54 time to create 1 rle with old method : 0.0001308917999267578 time for calcul the mask position with numpy : 0.014878988265991211 nb_pixel_total : 1113 time to create 1 rle with old method : 0.0013759136199951172 time for calcul the mask position with numpy : 0.014835596084594727 nb_pixel_total : 1714 time to create 1 rle with old method : 0.0020363330841064453 time for calcul the mask position with numpy : 0.01492619514465332 nb_pixel_total : 521 time to create 1 rle with old method : 0.0006251335144042969 time for calcul the mask position with numpy : 0.01501321792602539 nb_pixel_total : 6112 time to create 1 rle with old method : 0.0072019100189208984 time for calcul the mask position with numpy : 0.014496326446533203 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0012171268463134766 time for calcul the mask position with numpy : 0.014734506607055664 nb_pixel_total : 2888 time to create 1 rle with old method : 0.00342559814453125 time for calcul the mask position with numpy : 0.015281915664672852 nb_pixel_total : 47966 time to create 1 rle with old method : 0.054221391677856445 time for calcul the mask position with numpy : 0.014909505844116211 nb_pixel_total : 882 time to create 1 rle with old method : 0.0010488033294677734 time for calcul the mask position with numpy : 0.014879226684570312 nb_pixel_total : 732 time to create 1 rle with old method : 0.0008718967437744141 time for calcul the mask position with numpy : 0.014943122863769531 nb_pixel_total : 729 time to create 1 rle with old method : 0.0009188652038574219 time for calcul the mask position with numpy : 0.014899969100952148 nb_pixel_total : 1439 time to create 1 rle with old method : 0.001753091812133789 time for calcul the mask position with numpy : 0.014873266220092773 nb_pixel_total : 809 time to create 1 rle with old method : 0.0009920597076416016 time for calcul the mask position with numpy : 0.01491999626159668 nb_pixel_total : 1222 time to create 1 rle with old method : 0.0015101432800292969 time for calcul the mask position with numpy : 0.014709711074829102 nb_pixel_total : 1171 time to create 1 rle with old method : 0.0013723373413085938 time for calcul the mask position with numpy : 0.014696121215820312 nb_pixel_total : 491 time to create 1 rle with old method : 0.0006248950958251953 time for calcul the mask position with numpy : 0.01467752456665039 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002570152282714844 time for calcul the mask position with numpy : 0.014494895935058594 nb_pixel_total : 780 time to create 1 rle with old method : 0.0009562969207763672 time for calcul the mask position with numpy : 0.01425933837890625 nb_pixel_total : 1466 time to create 1 rle with old method : 0.0016543865203857422 time for calcul the mask position with numpy : 0.014670133590698242 nb_pixel_total : 1569 time to create 1 rle with old method : 0.0018460750579833984 time for calcul the mask position with numpy : 0.014452695846557617 nb_pixel_total : 66 time to create 1 rle with old method : 0.0001323223114013672 time for calcul the mask position with numpy : 0.014847993850708008 nb_pixel_total : 371 time to create 1 rle with old method : 0.0004429817199707031 time for calcul the mask position with numpy : 0.014436721801757812 nb_pixel_total : 1192 time to create 1 rle with old method : 0.0013761520385742188 time for calcul the mask position with numpy : 0.014263153076171875 nb_pixel_total : 1953 time to create 1 rle with old method : 0.0023851394653320312 time for calcul the mask position with numpy : 0.01433110237121582 nb_pixel_total : 4427 time to create 1 rle with old method : 0.0050847530364990234 time for calcul the mask position with numpy : 0.014150619506835938 nb_pixel_total : 2401 time to create 1 rle with old method : 0.0029516220092773438 time for calcul the mask position with numpy : 0.014314651489257812 nb_pixel_total : 1408 time to create 1 rle with old method : 0.0016090869903564453 time for calcul the mask position with numpy : 0.01465606689453125 nb_pixel_total : 48 time to create 1 rle with old method : 9.298324584960938e-05 time for calcul the mask position with numpy : 0.01442408561706543 nb_pixel_total : 1725 time to create 1 rle with old method : 0.002057313919067383 time for calcul the mask position with numpy : 0.014709711074829102 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006551742553710938 time for calcul the mask position with numpy : 0.015049457550048828 nb_pixel_total : 22737 time to create 1 rle with old method : 0.02711176872253418 time for calcul the mask position with numpy : 0.016764402389526367 nb_pixel_total : 8278 time to create 1 rle with old method : 0.010235071182250977 time for calcul the mask position with numpy : 0.015170097351074219 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005452632904052734 time for calcul the mask position with numpy : 0.014693260192871094 nb_pixel_total : 1649 time to create 1 rle with old method : 0.00196075439453125 time for calcul the mask position with numpy : 0.014382123947143555 nb_pixel_total : 2416 time to create 1 rle with old method : 0.0030493736267089844 time for calcul the mask position with numpy : 0.014878034591674805 nb_pixel_total : 5 time to create 1 rle with old method : 1.9073486328125e-05 time for calcul the mask position with numpy : 0.014821052551269531 nb_pixel_total : 118 time to create 1 rle with old method : 0.00016641616821289062 time for calcul the mask position with numpy : 0.014550209045410156 nb_pixel_total : 698 time to create 1 rle with old method : 0.0008451938629150391 time for calcul the mask position with numpy : 0.014674663543701172 nb_pixel_total : 524 time to create 1 rle with old method : 0.0006432533264160156 time for calcul the mask position with numpy : 0.014542818069458008 nb_pixel_total : 3292 time to create 1 rle with old method : 0.003893613815307617 time for calcul the mask position with numpy : 0.014496088027954102 nb_pixel_total : 475 time to create 1 rle with old method : 0.0006384849548339844 time for calcul the mask position with numpy : 0.014809846878051758 nb_pixel_total : 175 time to create 1 rle with old method : 0.00023984909057617188 time for calcul the mask position with numpy : 0.014729976654052734 nb_pixel_total : 550 time to create 1 rle with old method : 0.0006792545318603516 time for calcul the mask position with numpy : 0.014670848846435547 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003027915954589844 create new chi : 4.702836036682129 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 : 0.014734268188476562 batch 1 Loaded 257 chid ids of type : 4230 Number RLEs to save : 26123 TO DO : save crop sub photo not yet done ! save time : 1.639547348022461 nb_obj : 268 nb_hashtags : 7 time to prepare the origin masks : 8.769361972808838 time for calcul the mask position with numpy : 0.27562999725341797 nb_pixel_total : 3287253 time to create 1 rle with new method : 0.48306965827941895 time for calcul the mask position with numpy : 0.017401933670043945 nb_pixel_total : 167 time to create 1 rle with old method : 0.00022530555725097656 time for calcul the mask position with numpy : 0.013520240783691406 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003037452697753906 time for calcul the mask position with numpy : 0.01432490348815918 nb_pixel_total : 110 time to create 1 rle with old method : 0.00016808509826660156 time for calcul the mask position with numpy : 0.018787622451782227 nb_pixel_total : 147 time to create 1 rle with old method : 0.000179290771484375 time for calcul the mask position with numpy : 0.010523080825805664 nb_pixel_total : 16 time to create 1 rle with old method : 4.363059997558594e-05 time for calcul the mask position with numpy : 0.010668754577636719 nb_pixel_total : 748 time to create 1 rle with old method : 0.0009307861328125 time for calcul the mask position with numpy : 0.01349949836730957 nb_pixel_total : 135 time to create 1 rle with old method : 0.00019025802612304688 time for calcul the mask position with numpy : 0.01593184471130371 nb_pixel_total : 500 time to create 1 rle with old method : 0.0006518363952636719 time for calcul the mask position with numpy : 0.017435550689697266 nb_pixel_total : 395 time to create 1 rle with old method : 0.00048661231994628906 time for calcul the mask position with numpy : 0.015459775924682617 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003037452697753906 time for calcul the mask position with numpy : 0.017130374908447266 nb_pixel_total : 159 time to create 1 rle with old method : 0.00020956993103027344 time for calcul the mask position with numpy : 0.023674488067626953 nb_pixel_total : 82 time to create 1 rle with old method : 0.0002028942108154297 time for calcul the mask position with numpy : 0.0180208683013916 nb_pixel_total : 232 time to create 1 rle with old method : 0.0002968311309814453 time for calcul the mask position with numpy : 0.017961978912353516 nb_pixel_total : 10 time to create 1 rle with old method : 5.936622619628906e-05 time for calcul the mask position with numpy : 0.017981767654418945 nb_pixel_total : 695 time to create 1 rle with old method : 0.000820159912109375 time for calcul the mask position with numpy : 0.01879096031188965 nb_pixel_total : 330 time to create 1 rle with old method : 0.0003974437713623047 time for calcul the mask position with numpy : 0.017980337142944336 nb_pixel_total : 2485 time to create 1 rle with old method : 0.0029718875885009766 time for calcul the mask position with numpy : 0.01768183708190918 nb_pixel_total : 1769 time to create 1 rle with old method : 0.0021657943725585938 time for calcul the mask position with numpy : 0.017885684967041016 nb_pixel_total : 289 time to create 1 rle with old method : 0.00036525726318359375 time for calcul the mask position with numpy : 0.01792597770690918 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003490447998046875 time for calcul the mask position with numpy : 0.018012046813964844 nb_pixel_total : 620 time to create 1 rle with old method : 0.0007433891296386719 time for calcul the mask position with numpy : 0.01826953887939453 nb_pixel_total : 450 time to create 1 rle with old method : 0.0005781650543212891 time for calcul the mask position with numpy : 0.018221378326416016 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007481575012207031 time for calcul the mask position with numpy : 0.012038230895996094 nb_pixel_total : 527 time to create 1 rle with old method : 0.0007107257843017578 time for calcul the mask position with numpy : 0.011202573776245117 nb_pixel_total : 294 time to create 1 rle with old method : 0.0003752708435058594 time for calcul the mask position with numpy : 0.011039495468139648 nb_pixel_total : 493 time to create 1 rle with old method : 0.0006172657012939453 time for calcul the mask position with numpy : 0.010758399963378906 nb_pixel_total : 171 time to create 1 rle with old method : 0.00026988983154296875 time for calcul the mask position with numpy : 0.010741233825683594 nb_pixel_total : 632 time to create 1 rle with old method : 0.0008084774017333984 time for calcul the mask position with numpy : 0.010773420333862305 nb_pixel_total : 327 time to create 1 rle with old method : 0.0004184246063232422 time for calcul the mask position with numpy : 0.010645866394042969 nb_pixel_total : 85 time to create 1 rle with old method : 0.00012302398681640625 time for calcul the mask position with numpy : 0.010664939880371094 nb_pixel_total : 300 time to create 1 rle with old method : 0.0003788471221923828 time for calcul the mask position with numpy : 0.011005878448486328 nb_pixel_total : 1463 time to create 1 rle with old method : 0.0017621517181396484 time for calcul the mask position with numpy : 0.010840892791748047 nb_pixel_total : 419 time to create 1 rle with old method : 0.0005328655242919922 time for calcul the mask position with numpy : 0.010775089263916016 nb_pixel_total : 425 time to create 1 rle with old method : 0.0005402565002441406 time for calcul the mask position with numpy : 0.010850906372070312 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003714561462402344 time for calcul the mask position with numpy : 0.010967254638671875 nb_pixel_total : 274 time to create 1 rle with old method : 0.00034689903259277344 time for calcul the mask position with numpy : 0.010918617248535156 nb_pixel_total : 2496 time to create 1 rle with old method : 0.003097057342529297 time for calcul the mask position with numpy : 0.010864734649658203 nb_pixel_total : 944 time to create 1 rle with old method : 0.0011529922485351562 time for calcul the mask position with numpy : 0.01125192642211914 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003116130828857422 time for calcul the mask position with numpy : 0.011075496673583984 nb_pixel_total : 181 time to create 1 rle with old method : 0.00023698806762695312 time for calcul the mask position with numpy : 0.011690139770507812 nb_pixel_total : 359 time to create 1 rle with old method : 0.00047516822814941406 time for calcul the mask position with numpy : 0.012333154678344727 nb_pixel_total : 1147 time to create 1 rle with old method : 0.0015265941619873047 time for calcul the mask position with numpy : 0.01118016242980957 nb_pixel_total : 632 time to create 1 rle with old method : 0.0009937286376953125 time for calcul the mask position with numpy : 0.011241912841796875 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004930496215820312 time for calcul the mask position with numpy : 0.010802030563354492 nb_pixel_total : 138 time to create 1 rle with old method : 0.0001766681671142578 time for calcul the mask position with numpy : 0.010563135147094727 nb_pixel_total : 2353 time to create 1 rle with old method : 0.0027549266815185547 time for calcul the mask position with numpy : 0.010585308074951172 nb_pixel_total : 246 time to create 1 rle with old method : 0.0002994537353515625 time for calcul the mask position with numpy : 0.010699272155761719 nb_pixel_total : 599 time to create 1 rle with old method : 0.0006985664367675781 time for calcul the mask position with numpy : 0.01070094108581543 nb_pixel_total : 378 time to create 1 rle with old method : 0.0004487037658691406 time for calcul the mask position with numpy : 0.010514020919799805 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004513263702392578 time for calcul the mask position with numpy : 0.010262250900268555 nb_pixel_total : 893 time to create 1 rle with old method : 0.0010728836059570312 time for calcul the mask position with numpy : 0.01060938835144043 nb_pixel_total : 300 time to create 1 rle with old method : 0.00036525726318359375 time for calcul the mask position with numpy : 0.01104116439819336 nb_pixel_total : 339 time to create 1 rle with old method : 0.0958244800567627 time for calcul the mask position with numpy : 0.014083623886108398 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003490447998046875 time for calcul the mask position with numpy : 0.013200044631958008 nb_pixel_total : 709 time to create 1 rle with old method : 0.0009026527404785156 time for calcul the mask position with numpy : 0.013722658157348633 nb_pixel_total : 182 time to create 1 rle with old method : 0.00037741661071777344 time for calcul the mask position with numpy : 0.012784004211425781 nb_pixel_total : 104 time to create 1 rle with old method : 0.00015687942504882812 time for calcul the mask position with numpy : 0.012610673904418945 nb_pixel_total : 351 time to create 1 rle with old method : 0.0005376338958740234 time for calcul the mask position with numpy : 0.014422178268432617 nb_pixel_total : 289 time to create 1 rle with old method : 0.0004904270172119141 time for calcul the mask position with numpy : 0.013783931732177734 nb_pixel_total : 566 time to create 1 rle with old method : 0.0008244514465332031 time for calcul the mask position with numpy : 0.013566255569458008 nb_pixel_total : 2407 time to create 1 rle with old method : 0.003401517868041992 time for calcul the mask position with numpy : 0.013533592224121094 nb_pixel_total : 12 time to create 1 rle with old method : 6.604194641113281e-05 time for calcul the mask position with numpy : 0.013309240341186523 nb_pixel_total : 183 time to create 1 rle with old method : 0.0003211498260498047 time for calcul the mask position with numpy : 0.013475656509399414 nb_pixel_total : 171 time to create 1 rle with old method : 0.0003101825714111328 time for calcul the mask position with numpy : 0.013423919677734375 nb_pixel_total : 255 time to create 1 rle with old method : 0.0004336833953857422 time for calcul the mask position with numpy : 0.013670921325683594 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004627704620361328 time for calcul the mask position with numpy : 0.01500558853149414 nb_pixel_total : 58 time to create 1 rle with old method : 0.0002002716064453125 time for calcul the mask position with numpy : 0.014444351196289062 nb_pixel_total : 402 time to create 1 rle with old method : 0.0008637905120849609 time for calcul the mask position with numpy : 0.014315605163574219 nb_pixel_total : 2048 time to create 1 rle with old method : 0.003150463104248047 time for calcul the mask position with numpy : 0.013951301574707031 nb_pixel_total : 502 time to create 1 rle with old method : 0.0008132457733154297 time for calcul the mask position with numpy : 0.010885477066040039 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003185272216796875 time for calcul the mask position with numpy : 0.010672569274902344 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002658367156982422 time for calcul the mask position with numpy : 0.010599374771118164 nb_pixel_total : 543 time to create 1 rle with old method : 0.0006277561187744141 time for calcul the mask position with numpy : 0.010844230651855469 nb_pixel_total : 382 time to create 1 rle with old method : 0.0004584789276123047 time for calcul the mask position with numpy : 0.010324716567993164 nb_pixel_total : 1086 time to create 1 rle with old method : 0.0013458728790283203 time for calcul the mask position with numpy : 0.011302947998046875 nb_pixel_total : 694 time to create 1 rle with old method : 0.0008139610290527344 time for calcul the mask position with numpy : 0.010975360870361328 nb_pixel_total : 1254 time to create 1 rle with old method : 0.0015442371368408203 time for calcul the mask position with numpy : 0.010812759399414062 nb_pixel_total : 633 time to create 1 rle with old method : 0.0007660388946533203 time for calcul the mask position with numpy : 0.012987613677978516 nb_pixel_total : 100 time to create 1 rle with old method : 0.0002155303955078125 time for calcul the mask position with numpy : 0.010741233825683594 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002593994140625 time for calcul the mask position with numpy : 0.010795116424560547 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003445148468017578 time for calcul the mask position with numpy : 0.010561227798461914 nb_pixel_total : 1724 time to create 1 rle with old method : 0.001975536346435547 time for calcul the mask position with numpy : 0.010514020919799805 nb_pixel_total : 290 time to create 1 rle with old method : 0.0003631114959716797 time for calcul the mask position with numpy : 0.010896444320678711 nb_pixel_total : 530 time to create 1 rle with old method : 0.0006787776947021484 time for calcul the mask position with numpy : 0.010563850402832031 nb_pixel_total : 4048 time to create 1 rle with old method : 0.00471806526184082 time for calcul the mask position with numpy : 0.01052999496459961 nb_pixel_total : 379 time to create 1 rle with old method : 0.0004515647888183594 time for calcul the mask position with numpy : 0.01071619987487793 nb_pixel_total : 740 time to create 1 rle with old method : 0.0008919239044189453 time for calcul the mask position with numpy : 0.01081228256225586 nb_pixel_total : 152 time to create 1 rle with old method : 0.0001976490020751953 time for calcul the mask position with numpy : 0.010944366455078125 nb_pixel_total : 1144 time to create 1 rle with old method : 0.0012764930725097656 time for calcul the mask position with numpy : 0.010654449462890625 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003383159637451172 time for calcul the mask position with numpy : 0.01115560531616211 nb_pixel_total : 919 time to create 1 rle with old method : 0.0015473365783691406 time for calcul the mask position with numpy : 0.011422872543334961 nb_pixel_total : 1443 time to create 1 rle with old method : 0.002484560012817383 time for calcul the mask position with numpy : 0.0114593505859375 nb_pixel_total : 1440 time to create 1 rle with old method : 0.0024390220642089844 time for calcul the mask position with numpy : 0.011634349822998047 nb_pixel_total : 15796 time to create 1 rle with old method : 0.026388168334960938 time for calcul the mask position with numpy : 0.010961294174194336 nb_pixel_total : 663 time to create 1 rle with old method : 0.0007996559143066406 time for calcul the mask position with numpy : 0.010536909103393555 nb_pixel_total : 149 time to create 1 rle with old method : 0.0001876354217529297 time for calcul the mask position with numpy : 0.013737201690673828 nb_pixel_total : 187 time to create 1 rle with old method : 0.00035500526428222656 time for calcul the mask position with numpy : 0.010285377502441406 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002181529998779297 time for calcul the mask position with numpy : 0.010465145111083984 nb_pixel_total : 598 time to create 1 rle with old method : 0.0007231235504150391 time for calcul the mask position with numpy : 0.010367155075073242 nb_pixel_total : 1374 time to create 1 rle with old method : 0.001642465591430664 time for calcul the mask position with numpy : 0.01054072380065918 nb_pixel_total : 1469 time to create 1 rle with old method : 0.0016665458679199219 time for calcul the mask position with numpy : 0.010759115219116211 nb_pixel_total : 682 time to create 1 rle with old method : 0.0008444786071777344 time for calcul the mask position with numpy : 0.010646581649780273 nb_pixel_total : 101 time to create 1 rle with old method : 0.00020313262939453125 time for calcul the mask position with numpy : 0.010512590408325195 nb_pixel_total : 705 time to create 1 rle with old method : 0.0008745193481445312 time for calcul the mask position with numpy : 0.010474681854248047 nb_pixel_total : 5146 time to create 1 rle with old method : 0.0061168670654296875 time for calcul the mask position with numpy : 0.01046442985534668 nb_pixel_total : 319 time to create 1 rle with old method : 0.00040793418884277344 time for calcul the mask position with numpy : 0.01077580451965332 nb_pixel_total : 687 time to create 1 rle with old method : 0.0008852481842041016 time for calcul the mask position with numpy : 0.011398077011108398 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001494884490966797 time for calcul the mask position with numpy : 0.01114797592163086 nb_pixel_total : 1152 time to create 1 rle with old method : 0.0014100074768066406 time for calcul the mask position with numpy : 0.010929107666015625 nb_pixel_total : 108 time to create 1 rle with old method : 0.00015044212341308594 time for calcul the mask position with numpy : 0.011359453201293945 nb_pixel_total : 628 time to create 1 rle with old method : 0.0007622241973876953 time for calcul the mask position with numpy : 0.011020421981811523 nb_pixel_total : 285 time to create 1 rle with old method : 0.00033283233642578125 time for calcul the mask position with numpy : 0.01106119155883789 nb_pixel_total : 1863 time to create 1 rle with old method : 0.0021560192108154297 time for calcul the mask position with numpy : 0.011295557022094727 nb_pixel_total : 632 time to create 1 rle with old method : 0.0007841587066650391 time for calcul the mask position with numpy : 0.011020660400390625 nb_pixel_total : 85 time to create 1 rle with old method : 0.00013017654418945312 time for calcul the mask position with numpy : 0.011222362518310547 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006086826324462891 time for calcul the mask position with numpy : 0.011520147323608398 nb_pixel_total : 1207 time to create 1 rle with old method : 0.0013728141784667969 time for calcul the mask position with numpy : 0.010784387588500977 nb_pixel_total : 590 time to create 1 rle with old method : 0.0007357597351074219 time for calcul the mask position with numpy : 0.011490583419799805 nb_pixel_total : 772 time to create 1 rle with old method : 0.0009534358978271484 time for calcul the mask position with numpy : 0.011266231536865234 nb_pixel_total : 1157 time to create 1 rle with old method : 0.0014202594757080078 time for calcul the mask position with numpy : 0.010962486267089844 nb_pixel_total : 129 time to create 1 rle with old method : 0.000225067138671875 time for calcul the mask position with numpy : 0.011198043823242188 nb_pixel_total : 303 time to create 1 rle with old method : 0.0003864765167236328 time for calcul the mask position with numpy : 0.011196374893188477 nb_pixel_total : 713 time to create 1 rle with old method : 0.0008544921875 time for calcul the mask position with numpy : 0.011077165603637695 nb_pixel_total : 477 time to create 1 rle with old method : 0.0005810260772705078 time for calcul the mask position with numpy : 0.011600017547607422 nb_pixel_total : 641 time to create 1 rle with old method : 0.0007808208465576172 time for calcul the mask position with numpy : 0.010840892791748047 nb_pixel_total : 319 time to create 1 rle with old method : 0.00041794776916503906 time for calcul the mask position with numpy : 0.011133193969726562 nb_pixel_total : 2255 time to create 1 rle with old method : 0.0027031898498535156 time for calcul the mask position with numpy : 0.011044979095458984 nb_pixel_total : 1059 time to create 1 rle with old method : 0.0013103485107421875 time for calcul the mask position with numpy : 0.01076960563659668 nb_pixel_total : 244 time to create 1 rle with old method : 0.0003173351287841797 time for calcul the mask position with numpy : 0.010618925094604492 nb_pixel_total : 29 time to create 1 rle with old method : 7.581710815429688e-05 time for calcul the mask position with numpy : 0.010719060897827148 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007078647613525391 time for calcul the mask position with numpy : 0.010710477828979492 nb_pixel_total : 591 time to create 1 rle with old method : 0.0007529258728027344 time for calcul the mask position with numpy : 0.010625362396240234 nb_pixel_total : 194 time to create 1 rle with old method : 0.00025582313537597656 time for calcul the mask position with numpy : 0.010600566864013672 nb_pixel_total : 714 time to create 1 rle with old method : 0.0009088516235351562 time for calcul the mask position with numpy : 0.010768651962280273 nb_pixel_total : 836 time to create 1 rle with old method : 0.0010449886322021484 time for calcul the mask position with numpy : 0.010894060134887695 nb_pixel_total : 4051 time to create 1 rle with old method : 0.004954338073730469 time for calcul the mask position with numpy : 0.010706424713134766 nb_pixel_total : 1707 time to create 1 rle with old method : 0.002047300338745117 time for calcul the mask position with numpy : 0.01067209243774414 nb_pixel_total : 659 time to create 1 rle with old method : 0.0008022785186767578 time for calcul the mask position with numpy : 0.010829448699951172 nb_pixel_total : 1201 time to create 1 rle with old method : 0.0015156269073486328 time for calcul the mask position with numpy : 0.010803699493408203 nb_pixel_total : 482 time to create 1 rle with old method : 0.0005862712860107422 time for calcul the mask position with numpy : 0.010687589645385742 nb_pixel_total : 1329 time to create 1 rle with old method : 0.0016169548034667969 time for calcul the mask position with numpy : 0.01071929931640625 nb_pixel_total : 211 time to create 1 rle with old method : 0.00027489662170410156 time for calcul the mask position with numpy : 0.011819124221801758 nb_pixel_total : 180 time to create 1 rle with old method : 0.0002551078796386719 time for calcul the mask position with numpy : 0.010636568069458008 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006587505340576172 time for calcul the mask position with numpy : 0.010843038558959961 nb_pixel_total : 576 time to create 1 rle with old method : 0.0007078647613525391 time for calcul the mask position with numpy : 0.01150369644165039 nb_pixel_total : 344 time to create 1 rle with old method : 0.0006127357482910156 time for calcul the mask position with numpy : 0.011499166488647461 nb_pixel_total : 468 time to create 1 rle with old method : 0.0007801055908203125 time for calcul the mask position with numpy : 0.010980367660522461 nb_pixel_total : 4628 time to create 1 rle with old method : 0.005423545837402344 time for calcul the mask position with numpy : 0.01109933853149414 nb_pixel_total : 126 time to create 1 rle with old method : 0.0001914501190185547 time for calcul the mask position with numpy : 0.010873794555664062 nb_pixel_total : 9510 time to create 1 rle with old method : 0.011005163192749023 time for calcul the mask position with numpy : 0.010913372039794922 nb_pixel_total : 1931 time to create 1 rle with old method : 0.002285003662109375 time for calcul the mask position with numpy : 0.011070728302001953 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004017353057861328 time for calcul the mask position with numpy : 0.011018753051757812 nb_pixel_total : 787 time to create 1 rle with old method : 0.0009412765502929688 time for calcul the mask position with numpy : 0.010853052139282227 nb_pixel_total : 100 time to create 1 rle with old method : 0.00013518333435058594 time for calcul the mask position with numpy : 0.010943412780761719 nb_pixel_total : 885 time to create 1 rle with old method : 0.0011951923370361328 time for calcul the mask position with numpy : 0.010943412780761719 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002982616424560547 time for calcul the mask position with numpy : 0.0111236572265625 nb_pixel_total : 14795 time to create 1 rle with old method : 0.017598867416381836 time for calcul the mask position with numpy : 0.010992288589477539 nb_pixel_total : 5487 time to create 1 rle with old method : 0.006497383117675781 time for calcul the mask position with numpy : 0.010883808135986328 nb_pixel_total : 12 time to create 1 rle with old method : 7.987022399902344e-05 time for calcul the mask position with numpy : 0.010870933532714844 nb_pixel_total : 1790 time to create 1 rle with old method : 0.0021691322326660156 time for calcul the mask position with numpy : 0.010815858840942383 nb_pixel_total : 7 time to create 1 rle with old method : 7.581710815429688e-05 time for calcul the mask position with numpy : 0.01080322265625 nb_pixel_total : 4002 time to create 1 rle with old method : 0.004815101623535156 time for calcul the mask position with numpy : 0.01076054573059082 nb_pixel_total : 386 time to create 1 rle with old method : 0.0004813671112060547 time for calcul the mask position with numpy : 0.010729551315307617 nb_pixel_total : 757 time to create 1 rle with old method : 0.0009794235229492188 time for calcul the mask position with numpy : 0.010751724243164062 nb_pixel_total : 14051 time to create 1 rle with old method : 0.016684293746948242 time for calcul the mask position with numpy : 0.010942935943603516 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001533031463623047 time for calcul the mask position with numpy : 0.010714530944824219 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004394054412841797 time for calcul the mask position with numpy : 0.01072835922241211 nb_pixel_total : 3174 time to create 1 rle with old method : 0.0038535594940185547 time for calcul the mask position with numpy : 0.010831594467163086 nb_pixel_total : 222 time to create 1 rle with old method : 0.0002923011779785156 time for calcul the mask position with numpy : 0.01090860366821289 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003285408020019531 time for calcul the mask position with numpy : 0.011209726333618164 nb_pixel_total : 477 time to create 1 rle with old method : 0.0005993843078613281 time for calcul the mask position with numpy : 0.01194310188293457 nb_pixel_total : 273 time to create 1 rle with old method : 0.0004968643188476562 time for calcul the mask position with numpy : 0.012383460998535156 nb_pixel_total : 350 time to create 1 rle with old method : 0.0004553794860839844 time for calcul the mask position with numpy : 0.01151895523071289 nb_pixel_total : 1229 time to create 1 rle with old method : 0.0014660358428955078 time for calcul the mask position with numpy : 0.011354923248291016 nb_pixel_total : 2092 time to create 1 rle with old method : 0.003548145294189453 time for calcul the mask position with numpy : 0.01199650764465332 nb_pixel_total : 192 time to create 1 rle with old method : 0.0004668235778808594 time for calcul the mask position with numpy : 0.012118339538574219 nb_pixel_total : 12011 time to create 1 rle with old method : 0.019683837890625 time for calcul the mask position with numpy : 0.01189279556274414 nb_pixel_total : 666 time to create 1 rle with old method : 0.0011408329010009766 time for calcul the mask position with numpy : 0.011674642562866211 nb_pixel_total : 6725 time to create 1 rle with old method : 0.009868860244750977 time for calcul the mask position with numpy : 0.011398553848266602 nb_pixel_total : 882 time to create 1 rle with old method : 0.0013968944549560547 time for calcul the mask position with numpy : 0.012311220169067383 nb_pixel_total : 901 time to create 1 rle with old method : 0.0010788440704345703 time for calcul the mask position with numpy : 0.011353015899658203 nb_pixel_total : 2213 time to create 1 rle with old method : 0.0026466846466064453 time for calcul the mask position with numpy : 0.011279106140136719 nb_pixel_total : 480 time to create 1 rle with old method : 0.0006356239318847656 time for calcul the mask position with numpy : 0.011566162109375 nb_pixel_total : 6180 time to create 1 rle with old method : 0.0074350833892822266 time for calcul the mask position with numpy : 0.011424064636230469 nb_pixel_total : 232 time to create 1 rle with old method : 0.0004165172576904297 time for calcul the mask position with numpy : 0.011823177337646484 nb_pixel_total : 5090 time to create 1 rle with old method : 0.008478164672851562 time for calcul the mask position with numpy : 0.011843204498291016 nb_pixel_total : 1261 time to create 1 rle with old method : 0.0021431446075439453 time for calcul the mask position with numpy : 0.011620283126831055 nb_pixel_total : 3 time to create 1 rle with old method : 2.5510787963867188e-05 time for calcul the mask position with numpy : 0.011638641357421875 nb_pixel_total : 510 time to create 1 rle with old method : 0.0009152889251708984 time for calcul the mask position with numpy : 0.011681556701660156 nb_pixel_total : 10883 time to create 1 rle with old method : 0.01598048210144043 time for calcul the mask position with numpy : 0.010825634002685547 nb_pixel_total : 19 time to create 1 rle with old method : 6.604194641113281e-05 time for calcul the mask position with numpy : 0.01103663444519043 nb_pixel_total : 686 time to create 1 rle with old method : 0.00083160400390625 time for calcul the mask position with numpy : 0.010838747024536133 nb_pixel_total : 110 time to create 1 rle with old method : 0.000171661376953125 time for calcul the mask position with numpy : 0.011180400848388672 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005400180816650391 time for calcul the mask position with numpy : 0.01092076301574707 nb_pixel_total : 96 time to create 1 rle with old method : 0.00015211105346679688 time for calcul the mask position with numpy : 0.01081085205078125 nb_pixel_total : 5275 time to create 1 rle with old method : 0.00625157356262207 time for calcul the mask position with numpy : 0.011076927185058594 nb_pixel_total : 1524 time to create 1 rle with old method : 0.0018417835235595703 time for calcul the mask position with numpy : 0.010875701904296875 nb_pixel_total : 943 time to create 1 rle with old method : 0.0011951923370361328 time for calcul the mask position with numpy : 0.011076688766479492 nb_pixel_total : 3011 time to create 1 rle with old method : 0.0035288333892822266 time for calcul the mask position with numpy : 0.01133108139038086 nb_pixel_total : 355 time to create 1 rle with old method : 0.0004508495330810547 time for calcul the mask position with numpy : 0.011849641799926758 nb_pixel_total : 1234 time to create 1 rle with old method : 0.0015227794647216797 time for calcul the mask position with numpy : 0.011883258819580078 nb_pixel_total : 211 time to create 1 rle with old method : 0.00026535987854003906 time for calcul the mask position with numpy : 0.011557340621948242 nb_pixel_total : 10 time to create 1 rle with old method : 4.100799560546875e-05 time for calcul the mask position with numpy : 0.011361360549926758 nb_pixel_total : 1260 time to create 1 rle with old method : 0.0015177726745605469 time for calcul the mask position with numpy : 0.010986328125 nb_pixel_total : 542 time to create 1 rle with old method : 0.0006954669952392578 time for calcul the mask position with numpy : 0.010988473892211914 nb_pixel_total : 1703 time to create 1 rle with old method : 0.002049684524536133 time for calcul the mask position with numpy : 0.01091146469116211 nb_pixel_total : 550 time to create 1 rle with old method : 0.0006911754608154297 time for calcul the mask position with numpy : 0.010891199111938477 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003604888916015625 time for calcul the mask position with numpy : 0.011090278625488281 nb_pixel_total : 292 time to create 1 rle with old method : 0.0003705024719238281 time for calcul the mask position with numpy : 0.011432170867919922 nb_pixel_total : 965 time to create 1 rle with old method : 0.0012004375457763672 time for calcul the mask position with numpy : 0.010964393615722656 nb_pixel_total : 2645 time to create 1 rle with old method : 0.003261566162109375 time for calcul the mask position with numpy : 0.011086702346801758 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001900196075439453 time for calcul the mask position with numpy : 0.011145591735839844 nb_pixel_total : 1687 time to create 1 rle with old method : 0.0020241737365722656 time for calcul the mask position with numpy : 0.010969877243041992 nb_pixel_total : 539 time to create 1 rle with old method : 0.0006511211395263672 time for calcul the mask position with numpy : 0.01146841049194336 nb_pixel_total : 8178 time to create 1 rle with old method : 0.009986162185668945 time for calcul the mask position with numpy : 0.012260913848876953 nb_pixel_total : 174 time to create 1 rle with old method : 0.00022649765014648438 time for calcul the mask position with numpy : 0.01095890998840332 nb_pixel_total : 5819 time to create 1 rle with old method : 0.006795644760131836 time for calcul the mask position with numpy : 0.011431455612182617 nb_pixel_total : 4798 time to create 1 rle with old method : 0.005587100982666016 time for calcul the mask position with numpy : 0.011341571807861328 nb_pixel_total : 82 time to create 1 rle with old method : 0.00015497207641601562 time for calcul the mask position with numpy : 0.010975360870361328 nb_pixel_total : 1951 time to create 1 rle with old method : 0.0023114681243896484 time for calcul the mask position with numpy : 0.010900020599365234 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005249977111816406 time for calcul the mask position with numpy : 0.011120080947875977 nb_pixel_total : 47661 time to create 1 rle with old method : 0.05670928955078125 time for calcul the mask position with numpy : 0.011084318161010742 nb_pixel_total : 478 time to create 1 rle with old method : 0.0006513595581054688 time for calcul the mask position with numpy : 0.011081457138061523 nb_pixel_total : 760 time to create 1 rle with old method : 0.0009272098541259766 time for calcul the mask position with numpy : 0.011211872100830078 nb_pixel_total : 346 time to create 1 rle with old method : 0.00044465065002441406 time for calcul the mask position with numpy : 0.011510133743286133 nb_pixel_total : 1624 time to create 1 rle with old method : 0.002035856246948242 time for calcul the mask position with numpy : 0.011156320571899414 nb_pixel_total : 69 time to create 1 rle with old method : 0.00010275840759277344 time for calcul the mask position with numpy : 0.011189699172973633 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005006790161132812 time for calcul the mask position with numpy : 0.011936187744140625 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006189346313476562 time for calcul the mask position with numpy : 0.012046337127685547 nb_pixel_total : 983 time to create 1 rle with old method : 0.0011811256408691406 time for calcul the mask position with numpy : 0.011959075927734375 nb_pixel_total : 1319 time to create 1 rle with old method : 0.0015845298767089844 time for calcul the mask position with numpy : 0.01207733154296875 nb_pixel_total : 2183 time to create 1 rle with old method : 0.0026743412017822266 time for calcul the mask position with numpy : 0.011253833770751953 nb_pixel_total : 1856 time to create 1 rle with old method : 0.0021927356719970703 time for calcul the mask position with numpy : 0.01116180419921875 nb_pixel_total : 800 time to create 1 rle with old method : 0.0009558200836181641 time for calcul the mask position with numpy : 0.011175870895385742 nb_pixel_total : 1058 time to create 1 rle with old method : 0.0013191699981689453 time for calcul the mask position with numpy : 0.011086225509643555 nb_pixel_total : 168 time to create 1 rle with old method : 0.0002276897430419922 time for calcul the mask position with numpy : 0.011400461196899414 nb_pixel_total : 1433 time to create 1 rle with old method : 0.001737356185913086 time for calcul the mask position with numpy : 0.011887073516845703 nb_pixel_total : 3889 time to create 1 rle with old method : 0.004616975784301758 time for calcul the mask position with numpy : 0.013679027557373047 nb_pixel_total : 734 time to create 1 rle with old method : 0.0011734962463378906 time for calcul the mask position with numpy : 0.011876821517944336 nb_pixel_total : 481 time to create 1 rle with old method : 0.0008413791656494141 time for calcul the mask position with numpy : 0.0332028865814209 nb_pixel_total : 1458 time to create 1 rle with old method : 0.0024034976959228516 time for calcul the mask position with numpy : 0.05373859405517578 nb_pixel_total : 2311 time to create 1 rle with old method : 0.0033423900604248047 time for calcul the mask position with numpy : 0.014569520950317383 nb_pixel_total : 4582 time to create 1 rle with old method : 0.008106470108032227 time for calcul the mask position with numpy : 0.013656854629516602 nb_pixel_total : 327 time to create 1 rle with old method : 0.0006108283996582031 time for calcul the mask position with numpy : 0.01350545883178711 nb_pixel_total : 1683 time to create 1 rle with old method : 0.003212451934814453 time for calcul the mask position with numpy : 0.013573646545410156 nb_pixel_total : 504 time to create 1 rle with old method : 0.0009148120880126953 time for calcul the mask position with numpy : 0.013629913330078125 nb_pixel_total : 1657 time to create 1 rle with old method : 0.0030634403228759766 time for calcul the mask position with numpy : 0.015608072280883789 nb_pixel_total : 1835 time to create 1 rle with old method : 0.002762317657470703 time for calcul the mask position with numpy : 0.011388778686523438 nb_pixel_total : 804 time to create 1 rle with old method : 0.0009775161743164062 time for calcul the mask position with numpy : 0.011662721633911133 nb_pixel_total : 8593 time to create 1 rle with old method : 0.010033369064331055 time for calcul the mask position with numpy : 0.012828588485717773 nb_pixel_total : 18986 time to create 1 rle with old method : 0.028215646743774414 time for calcul the mask position with numpy : 0.011715412139892578 nb_pixel_total : 2435 time to create 1 rle with old method : 0.002923727035522461 time for calcul the mask position with numpy : 0.01210927963256836 nb_pixel_total : 34 time to create 1 rle with old method : 8.535385131835938e-05 time for calcul the mask position with numpy : 0.011574506759643555 nb_pixel_total : 1401 time to create 1 rle with old method : 0.0017096996307373047 time for calcul the mask position with numpy : 0.015157461166381836 nb_pixel_total : 592 time to create 1 rle with old method : 0.0007343292236328125 time for calcul the mask position with numpy : 0.017168045043945312 nb_pixel_total : 301 time to create 1 rle with old method : 0.0005958080291748047 time for calcul the mask position with numpy : 0.017424583435058594 nb_pixel_total : 846 time to create 1 rle with old method : 0.0014927387237548828 time for calcul the mask position with numpy : 0.017329692840576172 nb_pixel_total : 127 time to create 1 rle with old method : 0.00018477439880371094 time for calcul the mask position with numpy : 0.016100168228149414 nb_pixel_total : 158 time to create 1 rle with old method : 0.00022101402282714844 time for calcul the mask position with numpy : 0.015471935272216797 nb_pixel_total : 935 time to create 1 rle with old method : 0.0015840530395507812 time for calcul the mask position with numpy : 0.017573833465576172 nb_pixel_total : 530 time to create 1 rle with old method : 0.0009028911590576172 time for calcul the mask position with numpy : 0.01712632179260254 nb_pixel_total : 3696 time to create 1 rle with old method : 0.006230831146240234 time for calcul the mask position with numpy : 0.01727008819580078 nb_pixel_total : 354 time to create 1 rle with old method : 0.0007145404815673828 time for calcul the mask position with numpy : 0.017377376556396484 nb_pixel_total : 590 time to create 1 rle with old method : 0.0010602474212646484 time for calcul the mask position with numpy : 0.020982980728149414 nb_pixel_total : 161 time to create 1 rle with old method : 0.0003566741943359375 time for calcul the mask position with numpy : 0.018379688262939453 nb_pixel_total : 1043 time to create 1 rle with old method : 0.0020012855529785156 time for calcul the mask position with numpy : 0.020121097564697266 nb_pixel_total : 63 time to create 1 rle with old method : 0.00024008750915527344 time for calcul the mask position with numpy : 0.019704341888427734 nb_pixel_total : 351 time to create 1 rle with old method : 0.0007300376892089844 create new chi : 4.7504472732543945 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 : 0.0067441463470458984 batch 1 Loaded 269 chid ids of type : 4230 Number RLEs to save : 25764 TO DO : save crop sub photo not yet done ! save time : 2.7291433811187744 map_output_result : {1339808855: (0.0, 'Should be the crop_list due to order', 0.0), 1339806785: (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 [1339808855, 1339806785] Looping around the photos to save general results len do output : 2 /1339808855.Didn't retrieve data . /1339806785.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, '2618046') ('4234', '20860416', '1339808855', None, None, None, None, None, '2618046') ('4234', None, None, None, None, None, None, None, '2618046') ('4234', '20860416', '1339806785', None, None, None, None, None, '2618046') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.0160980224609375 save_final save missing photos in datou_result : time spend for datou_step_exec : 26.397416591644287 time spend to save output : 0.016373872756958008 total time spend for step 4 : 26.413790464401245 step5:crop_condition Thu Feb 27 00:21:29 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure 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 : 2 ! batch 1 Loaded 526 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 ! 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 : 259 About to insert : list_path_to_insert length 259 new photo from crops ! About to upload 259 photos upload in portfolio : 4869462 init cache_photo without model_param we have 259 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740612096_1038892 we have uploaded 259 photos in the portfolio 4869462 time of upload the photos Elapsed time : 69.55742001533508 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 ! 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 : 57 About to insert : list_path_to_insert length 57 new photo from crops ! About to upload 57 photos upload in portfolio : 4869462 init cache_photo without model_param we have 57 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740612166_1038892 we have uploaded 57 photos in the portfolio 4869462 time of upload the photos Elapsed time : 20.185721158981323 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 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740612187_1038892 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.8697874546051025 we have finished the crop for the class : metal 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 27 About to insert : list_path_to_insert length 27 new photo from crops ! About to upload 27 photos upload in portfolio : 4869462 init cache_photo without model_param we have 27 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740612191_1038892 we have uploaded 27 photos in the portfolio 4869462 time of upload the photos Elapsed time : 6.508190631866455 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 ! map_result returned by crop_photo_return_map_crop : length : 18 About to insert : list_path_to_insert length 18 new photo from crops ! About to upload 18 photos upload in portfolio : 4869462 init cache_photo without model_param we have 18 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740612198_1038892 we have uploaded 18 photos in the portfolio 4869462 time of upload the photos Elapsed time : 5.391937494277954 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 [1339808855, 1339806785] Looping around the photos to save general results len do output : 363 /1339821380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821392Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821394Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821396Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821398Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821399Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821401Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821404Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821405Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821406Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821407Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821408Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821409Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821410Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821412Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821413Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821414Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821415Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821417Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821418Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821419Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821420Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821421Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821422Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821423Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821424Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821425Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821426Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821427Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821428Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821460Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821474Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821494Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821578Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339821767Didn'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, '2618046') ('4234', '20860416', '1339808855', None, None, None, None, None, '2618046') ('4234', None, None, None, None, None, None, None, '2618046') ('4234', '20860416', '1339806785', None, None, None, None, None, '2618046') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1091 time used for this insertion : 0.08895158767700195 save_final save missing photos in datou_result : time spend for datou_step_exec : 114.82976579666138 time spend to save output : 0.09942007064819336 total time spend for step 5 : 114.92918586730957 step6:thcl Thu Feb 27 00:23:24 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 : 0.02447223663330078 time to convert the images to numpy array : 0.11290502548217773 time to import caffe and check if the image exist : 0.030493497848510742 time to convert the images to numpy array : 0.11748147010803223 time to import caffe and check if the image exist : 0.026702404022216797 time to convert the images to numpy array : 0.12356877326965332 time to import caffe and check if the image exist : 0.023441314697265625 time to convert the images to numpy array : 0.13194656372070312 time to import caffe and check if the image exist : 0.031650543212890625 time to convert the images to numpy array : 0.12401366233825684 time to import caffe and check if the image exist : 0.024553298950195312 time to convert the images to numpy array : 0.1358494758605957 time to import caffe and check if the image exist : 0.03929471969604492 time to convert the images to numpy array : 0.1211085319519043 time to import caffe and check if the image exist : 0.030139684677124023 time to convert the images to numpy array : 0.13402986526489258 time to import caffe and check if the image exist : 0.025434255599975586 time to convert the images to numpy array : 0.1393585205078125 time to import caffe and check if the image exist : 0.028435707092285156 time to convert the images to numpy array : 0.13682150840759277 total time to convert the images to numpy array : 0.375077486038208 list photo_ids error: [] list photo_ids correct : [1339821735, 1339821736, 1339821737, 1339821738, 1339821739, 1339821740, 1339821741, 1339821742, 1339821743, 1339821744, 1339821745, 1339821746, 1339821749, 1339821750, 1339821751, 1339821752, 1339821753, 1339821754, 1339821755, 1339821756, 1339821757, 1339821758, 1339821759, 1339821760, 1339821762, 1339821763, 1339821764, 1339821765, 1339821766, 1339821767, 1339821420, 1339821421, 1339821422, 1339821423, 1339821424, 1339821425, 1339821426, 1339821427, 1339821428, 1339821429, 1339821430, 1339821431, 1339821432, 1339821433, 1339821434, 1339821435, 1339821436, 1339821437, 1339821438, 1339821439, 1339821440, 1339821441, 1339821442, 1339821443, 1339821444, 1339821445, 1339821446, 1339821447, 1339821448, 1339821449, 1339821450, 1339821451, 1339821452, 1339821453, 1339821454, 1339821455, 1339821456, 1339821611, 1339821612, 1339821614, 1339821615, 1339821616, 1339821617, 1339821618, 1339821619, 1339821620, 1339821621, 1339821622, 1339821623, 1339821624, 1339821625, 1339821626, 1339821627, 1339821628, 1339821629, 1339821630, 1339821631, 1339821632, 1339821633, 1339821634, 1339821635, 1339821636, 1339821637, 1339821638, 1339821639, 1339821640, 1339821641, 1339821642, 1339821643, 1339821644, 1339821646, 1339821647, 1339821648, 1339821649, 1339821457, 1339821458, 1339821459, 1339821460, 1339821461, 1339821462, 1339821463, 1339821464, 1339821465, 1339821466, 1339821467, 1339821468, 1339821470, 1339821471, 1339821472, 1339821473, 1339821474, 1339821475, 1339821476, 1339821477, 1339821479, 1339821480, 1339821481, 1339821482, 1339821483, 1339821484, 1339821485, 1339821486, 1339821487, 1339821488, 1339821489, 1339821490, 1339821491, 1339821492, 1339821493, 1339821494, 1339821495, 1339821659, 1339821660, 1339821661, 1339821662, 1339821663, 1339821664, 1339821665, 1339821666, 1339821667, 1339821668, 1339821669, 1339821670, 1339821671, 1339821672, 1339821673, 1339821674, 1339821675, 1339821676, 1339821677, 1339821678, 1339821679, 1339821680, 1339821681, 1339821682, 1339821683, 1339821684, 1339821685, 1339821686, 1339821687, 1339821688, 1339821689, 1339821690, 1339821691, 1339821692, 1339821693, 1339821694, 1339821695, 1339821496, 1339821497, 1339821498, 1339821499, 1339821500, 1339821501, 1339821502, 1339821503, 1339821504, 1339821505, 1339821506, 1339821507, 1339821508, 1339821509, 1339821510, 1339821511, 1339821512, 1339821513, 1339821514, 1339821515, 1339821516, 1339821517, 1339821518, 1339821519, 1339821520, 1339821521, 1339821522, 1339821523, 1339821524, 1339821525, 1339821526, 1339821527, 1339821528, 1339821529, 1339821530, 1339821531, 1339821532, 1339821696, 1339821697, 1339821698, 1339821699, 1339821700, 1339821701, 1339821702, 1339821703, 1339821704, 1339821705, 1339821706, 1339821707, 1339821708, 1339821709, 1339821710, 1339821711, 1339821712, 1339821713, 1339821714, 1339821715, 1339821716, 1339821717, 1339821720, 1339821721, 1339821722, 1339821723, 1339821724, 1339821725, 1339821726, 1339821727, 1339821728, 1339821729, 1339821730, 1339821731, 1339821732, 1339821733, 1339821734, 1339821380, 1339821382, 1339821383, 1339821384, 1339821385, 1339821386, 1339821387, 1339821389, 1339821390, 1339821391, 1339821392, 1339821393, 1339821394, 1339821395, 1339821396, 1339821397, 1339821398, 1339821399, 1339821400, 1339821401, 1339821402, 1339821403, 1339821404, 1339821405, 1339821406, 1339821407, 1339821408, 1339821409, 1339821410, 1339821411, 1339821412, 1339821413, 1339821414, 1339821415, 1339821417, 1339821418, 1339821419, 1339821533, 1339821534, 1339821536, 1339821537, 1339821538, 1339821539, 1339821541, 1339821542, 1339821543, 1339821544, 1339821545, 1339821546, 1339821547, 1339821548, 1339821549, 1339821550, 1339821551, 1339821552, 1339821553, 1339821554, 1339821555, 1339821556, 1339821558, 1339821559, 1339821560, 1339821561, 1339821562, 1339821563, 1339821564, 1339821565, 1339821566, 1339821567, 1339821568, 1339821569, 1339821570, 1339821571, 1339821572, 1339821573, 1339821574, 1339821575, 1339821576, 1339821577, 1339821578, 1339821579, 1339821580, 1339821581, 1339821582, 1339821584, 1339821585, 1339821586, 1339821587, 1339821588, 1339821589, 1339821590, 1339821591, 1339821592, 1339821593, 1339821594, 1339821595, 1339821596, 1339821597, 1339821598, 1339821599, 1339821600, 1339821601, 1339821602, 1339821603, 1339821604, 1339821605, 1339821606, 1339821607, 1339821608, 1339821609, 1339821610] number of photos to traite : 363 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 : 2956 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 : 2737 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 1.7761790752410889 time used to do the prediction : 1.277268648147583 save descriptor for thcl : 3237 time to traite the descriptors : 2.16694974899292 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1339821735 To insert : 1339821736 To insert : 1339821737 To insert : 1339821738 To insert : 1339821739 To insert : 1339821740 To insert : 1339821741 To insert : 1339821742 To insert : 1339821743 To insert : 1339821744 To insert : 1339821745 To insert : 1339821746 To insert : 1339821749 To insert : 1339821750 To insert : 1339821751 To insert : 1339821752 To insert : 1339821753 To insert : 1339821754 To insert : 1339821755 To insert : 1339821756 To insert : 1339821757 To insert : 1339821758 To insert : 1339821759 To insert : 1339821760 To insert : 1339821762 To insert : 1339821763 To insert : 1339821764 To insert : 1339821765 To insert : 1339821766 To insert : 1339821767 To insert : 1339821420 To insert : 1339821421 To insert : 1339821422 To insert : 1339821423 To insert : 1339821424 To insert : 1339821425 To insert : 1339821426 To insert : 1339821427 To insert : 1339821428 To insert : 1339821429 To insert : 1339821430 To insert : 1339821431 To insert : 1339821432 To insert : 1339821433 To insert : 1339821434 To insert : 1339821435 To insert : 1339821436 To insert : 1339821437 To insert : 1339821438 To insert : 1339821439 To insert : 1339821440 To insert : 1339821441 To insert : 1339821442 To insert : 1339821443 To insert : 1339821444 To insert : 1339821445 To insert : 1339821446 To insert : 1339821447 To insert : 1339821448 To insert : 1339821449 To insert : 1339821450 To insert : 1339821451 To insert : 1339821452 To insert : 1339821453 To insert : 1339821454 To insert : 1339821455 To insert : 1339821456 To insert : 1339821611 To insert : 1339821612 To insert : 1339821614 To insert : 1339821615 To insert : 1339821616 To insert : 1339821617 To insert : 1339821618 To insert : 1339821619 To insert : 1339821620 To insert : 1339821621 To insert : 1339821622 To insert : 1339821623 To insert : 1339821624 To insert : 1339821625 To insert : 1339821626 To insert : 1339821627 To insert : 1339821628 To insert : 1339821629 To insert : 1339821630 To insert : 1339821631 To insert : 1339821632 To insert : 1339821633 To insert : 1339821634 To insert : 1339821635 To insert : 1339821636 To insert : 1339821637 To insert : 1339821638 To insert : 1339821639 To insert : 1339821640 To insert : 1339821641 To insert : 1339821642 To insert : 1339821643 To insert : 1339821644 To insert : 1339821646 To insert : 1339821647 To insert : 1339821648 To insert : 1339821649 To insert : 1339821457 To insert : 1339821458 To insert : 1339821459 To insert : 1339821460 To insert : 1339821461 To insert : 1339821462 To insert : 1339821463 To insert : 1339821464 To insert : 1339821465 To insert : 1339821466 To insert : 1339821467 To insert : 1339821468 To insert : 1339821470 To insert : 1339821471 To insert : 1339821472 To insert : 1339821473 To insert : 1339821474 To insert : 1339821475 To insert : 1339821476 To insert : 1339821477 To insert : 1339821479 To insert : 1339821480 To insert : 1339821481 To insert : 1339821482 To insert : 1339821483 To insert : 1339821484 To insert : 1339821485 To insert : 1339821486 To insert : 1339821487 To insert : 1339821488 To insert : 1339821489 To insert : 1339821490 To insert : 1339821491 To insert : 1339821492 To insert : 1339821493 To insert : 1339821494 To insert : 1339821495 To insert : 1339821659 To insert : 1339821660 To insert : 1339821661 To insert : 1339821662 To insert : 1339821663 To insert : 1339821664 To insert : 1339821665 To insert : 1339821666 To insert : 1339821667 To insert : 1339821668 To insert : 1339821669 To insert : 1339821670 To insert : 1339821671 To insert : 1339821672 To insert : 1339821673 To insert : 1339821674 To insert : 1339821675 To insert : 1339821676 To insert : 1339821677 To insert : 1339821678 To insert : 1339821679 To insert : 1339821680 To insert : 1339821681 To insert : 1339821682 To insert : 1339821683 To insert : 1339821684 To insert : 1339821685 To insert : 1339821686 To insert : 1339821687 To insert : 1339821688 To insert : 1339821689 To insert : 1339821690 To insert : 1339821691 To insert : 1339821692 To insert : 1339821693 To insert : 1339821694 To insert : 1339821695 To insert : 1339821496 To insert : 1339821497 To insert : 1339821498 To insert : 1339821499 To insert : 1339821500 To insert : 1339821501 To insert : 1339821502 To insert : 1339821503 To insert : 1339821504 To insert : 1339821505 To insert : 1339821506 To insert : 1339821507 To insert : 1339821508 To insert : 1339821509 To insert : 1339821510 To insert : 1339821511 To insert : 1339821512 To insert : 1339821513 To insert : 1339821514 To insert : 1339821515 To insert : 1339821516 To insert : 1339821517 To insert : 1339821518 To insert : 1339821519 To insert : 1339821520 To insert : 1339821521 To insert : 1339821522 To insert : 1339821523 To insert : 1339821524 To insert : 1339821525 To insert : 1339821526 To insert : 1339821527 To insert : 1339821528 To insert : 1339821529 To insert : 1339821530 To insert : 1339821531 To insert : 1339821532 To insert : 1339821696 To insert : 1339821697 To insert : 1339821698 To insert : 1339821699 To insert : 1339821700 To insert : 1339821701 To insert : 1339821702 To insert : 1339821703 To insert : 1339821704 To insert : 1339821705 To insert : 1339821706 To insert : 1339821707 To insert : 1339821708 To insert : 1339821709 To insert : 1339821710 To insert : 1339821711 To insert : 1339821712 To insert : 1339821713 To insert : 1339821714 To insert : 1339821715 To insert : 1339821716 To insert : 1339821717 To insert : 1339821720 To insert : 1339821721 To insert : 1339821722 To insert : 1339821723 To insert : 1339821724 To insert : 1339821725 To insert : 1339821726 To insert : 1339821727 To insert : 1339821728 To insert : 1339821729 To insert : 1339821730 To insert : 1339821731 To insert : 1339821732 To insert : 1339821733 To insert : 1339821734 To insert : 1339821380 To insert : 1339821382 To insert : 1339821383 To insert : 1339821384 To insert : 1339821385 To insert : 1339821386 To insert : 1339821387 To insert : 1339821389 To insert : 1339821390 To insert : 1339821391 To insert : 1339821392 To insert : 1339821393 To insert : 1339821394 To insert : 1339821395 To insert : 1339821396 To insert : 1339821397 To insert : 1339821398 To insert : 1339821399 To insert : 1339821400 To insert : 1339821401 To insert : 1339821402 To insert : 1339821403 To insert : 1339821404 To insert : 1339821405 To insert : 1339821406 To insert : 1339821407 To insert : 1339821408 To insert : 1339821409 To insert : 1339821410 To insert : 1339821411 To insert : 1339821412 To insert : 1339821413 To insert : 1339821414 To insert : 1339821415 To insert : 1339821417 To insert : 1339821418 To insert : 1339821419 To insert : 1339821533 To insert : 1339821534 To insert : 1339821536 To insert : 1339821537 To insert : 1339821538 To insert : 1339821539 To insert : 1339821541 To insert : 1339821542 To insert : 1339821543 To insert : 1339821544 To insert : 1339821545 To insert : 1339821546 To insert : 1339821547 To insert : 1339821548 To insert : 1339821549 To insert : 1339821550 To insert : 1339821551 To insert : 1339821552 To insert : 1339821553 To insert : 1339821554 To insert : 1339821555 To insert : 1339821556 To insert : 1339821558 To insert : 1339821559 To insert : 1339821560 To insert : 1339821561 To insert : 1339821562 To insert : 1339821563 To insert : 1339821564 To insert : 1339821565 To insert : 1339821566 To insert : 1339821567 To insert : 1339821568 To insert : 1339821569 To insert : 1339821570 To insert : 1339821571 To insert : 1339821572 To insert : 1339821573 To insert : 1339821574 To insert : 1339821575 To insert : 1339821576 To insert : 1339821577 To insert : 1339821578 To insert : 1339821579 To insert : 1339821580 To insert : 1339821581 To insert : 1339821582 To insert : 1339821584 To insert : 1339821585 To insert : 1339821586 To insert : 1339821587 To insert : 1339821588 To insert : 1339821589 To insert : 1339821590 To insert : 1339821591 To insert : 1339821592 To insert : 1339821593 To insert : 1339821594 To insert : 1339821595 To insert : 1339821596 To insert : 1339821597 To insert : 1339821598 To insert : 1339821599 To insert : 1339821600 To insert : 1339821601 To insert : 1339821602 To insert : 1339821603 To insert : 1339821604 To insert : 1339821605 To insert : 1339821606 To insert : 1339821607 To insert : 1339821608 To insert : 1339821609 To insert : 1339821610 time to insert the descriptors : 81.77484655380249 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 : 570 time used for this insertion : 0.05141186714172363 save missing photos in datou_result : time spend for datou_step_exec : 91.36145806312561 time spend to save output : 0.10572099685668945 total time spend for step 6 : 91.4671790599823 step7:ventilate_hashtags_in_portfolio Thu Feb 27 00:24:55 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 : 20860416 get user id for portfolio 20860416 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`=20860416 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PET_fonce','Film_plastique','metal','pet_clair','PET_clair','pehd','refus','pet_fonce','flou','PEHD','carton','autre','environnement','mal_croppe','Papier','Tetrapak','papier','Carton')) 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`=20860416 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PET_fonce','Film_plastique','metal','pet_clair','PET_clair','pehd','refus','pet_fonce','flou','PEHD','carton','autre','environnement','mal_croppe','Papier','Tetrapak','papier','Carton')) 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`=20860416 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PET_fonce','Film_plastique','metal','pet_clair','PET_clair','pehd','refus','pet_fonce','flou','PEHD','carton','autre','environnement','mal_croppe','Papier','Tetrapak','papier','Carton')) 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`=20860416 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PET_fonce','Film_plastique','metal','pet_clair','PET_clair','pehd','refus','pet_fonce','flou','PEHD','carton','autre','environnement','mal_croppe','Papier','Tetrapak','papier','Carton')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20861432,20861426,20861427,20861429,20861434,20861431,20861433,20861454,20861436,20861437,20861438,20861451,20861447?tags=pet_fonce,film_plastique,metal,pet_clair,pehd,refus,flou,carton,autre,environnement,mal_croppe,papier,tetrapak&datou_id_consolidate=4235&port_consolidate=20860416 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1339808855, 1339806785] Looping around the photos to save general results len do output : 1 /20860416. 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, '2618046') ('4234', '20860416', '1339808855', None, None, None, None, None, '2618046') ('4234', None, None, None, None, None, None, None, '2618046') ('4234', '20860416', '1339806785', None, None, None, None, None, '2618046') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.015120983123779297 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.4273784160614014 time spend to save output : 0.015368223190307617 total time spend for step 7 : 2.442746639251709 step8:final Thu Feb 27 00:24:58 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 : {1339808855: ('0.7498349546888065',), 1339806785: ('0.7498349546888065',)} new output for save of step final : {1339808855: ('0.7498349546888065',), 1339806785: ('0.7498349546888065',)} [1339808855, 1339806785] Looping around the photos to save general results len do output : 2 /1339808855.Didn't retrieve data . /1339806785.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, '2618046') ('4234', '20860416', '1339808855', None, None, None, None, None, '2618046') ('4234', None, None, None, None, None, None, None, '2618046') ('4234', '20860416', '1339806785', None, None, None, None, None, '2618046') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.01336979866027832 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11671185493469238 time spend to save output : 0.013598918914794922 total time spend for step 8 : 0.1303107738494873 step9:velours_tree Thu Feb 27 00:24:58 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 : 20861432,20861426,20861427,20861429,20861434,20861431,20861433,20861454,20861436,20861437,20861438,20861451,20861447 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=20861432 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=20861426 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=20861427 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=20861429 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=20861434 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=20861431 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=20861433 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=20861454 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=20861436 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=20861437 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=20861438 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=20861451 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=20861447 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 363 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [1 2 1 2 2 2 2 4 5 2 2 2 2 2 2 3 2 0 0 5 0 0 2 0 1 0 1 0 4 0 0 0 0 3 0 4 0 2 1 4 2 4 2 0 4 3 4 4 1 3 3 0 0 5 4 4 1 1 1 1 4 1 0 4 0 4 4 0 0 2 4 4 1 4 4 3 2 4 1 5 0 1 5 2 0 1 4 4 2 1 0 5 4 2 2 0 4 0 1 2 2 4 4 0 2 1 2 0 0 2 2 4 2 2 2 0 4 4 2 5 2 2 2 2 4 2 1 2 2 1 2 5 4 2 2 2 2 2 0 4 0 2 2 2 0 0 1 1 0 0 1 4 0 5 0 0 4 2 1 4 0 0 4 4 4 3 0 0 1 3 2 3 2 1 4 0 4 0 0 1 4 1 1 1 1 4 1 2 0 0 4 4 4 0 1 0 2 2 4 2 1 0 3 1 4 1 0 5 4 4 5 1 2 0 1 4 2 1 4 0 2 1 1 0 2 4 1 2 2 4 2 2 2 2 4 1 5 4 4 2 2 0 2 2 2 4 4 2 2 2 0 2 4 2 2 4 4 2 2 1 1 2 1 4 4 4 4 0 0 5 1 4 4 0 0 0 4 2 4 1 4 2 2 2 2 4 0 2 2 1 0 4 4 2 0 0 4 4 0 4 5 4 2 4 0 2 4 2 4 1 1 2 2 0 4 0 4 4 4 2 3 1 1 0 4 1 4 3 0 1 0 0 2 1 1 4 2 2 1 1 0 1 1 0 2 2 1 0 2 5 2 5 0 2 2 5 1 2 2 0 2 4 2] Elapsed time: 0.07062554359436035 graph_id used : 80411 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20861432,20861426,20861427,20861429,20861434,20861431,20861433,20861454,20861436,20861437,20861438,20861451,20861447?tags=pet_fonce,film_plastique,metal,pet_clair,pehd,refus,flou,carton,autre,environnement,mal_croppe,papier,tetrapak&datou_id_consolidate=4235&port_consolidate=20860416&tree_id=80411 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1339808855, 1339806785] Looping around the photos to save general results len do output : 1 /20860416Didn'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, '2618046') ('4234', '20860416', '1339808855', None, None, None, None, None, '2618046') ('4234', None, None, None, None, None, None, None, '2618046') ('4234', '20860416', '1339806785', None, None, None, None, None, '2618046') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.015257596969604492 save_final save missing photos in datou_result : time spend for datou_step_exec : 32.712409257888794 time spend to save output : 0.01563739776611328 total time spend for step 9 : 32.72804665565491 step10:send_mail_cod Thu Feb 27 00:25:31 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_P20860416_27-02-2025_00_25_31.pdf 20861414 imagette208614141740612331 20861408 imagette208614081740612331 20861409 change filename to text .change filename to text .imagette208614091740612331 20861411 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 .imagette208614111740612331 20861416 imagette208614161740612332 20861413 imagette208614131740612332 20861415 imagette208614151740612332 20861424 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 .imagette208614241740612332 20861418 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 .imagette208614181740612333 20861420 imagette208614201740612334 20861423 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 .imagette208614231740612334 20861422 imagette208614221740612334 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20860416 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20861432,20861426,20861427,20861429,20861434,20861431,20861433,20861454,20861436,20861437,20861438,20861451,20861447?tags=pet_fonce,film_plastique,metal,pet_clair,pehd,refus,flou,carton,autre,environnement,mal_croppe,papier,tetrapak&datou_id_consolidate=4235&port_consolidate=20860416&tree_id=80411 your option no_mail is active, we will not send the real mail to your client args[1339808855] : ((1339808855, -7.911842347683338, 492609224), (1339808855, 0.2020814606673192, 2107752395), '0.7498349546888065') We are sending mail with results at cod@fotonower.com args[1339806785] : ((1339806785, -7.8344871232538695, 492609224), (1339806785, 0.23834243031469368, 2107752395), '0.7498349546888065') We are sending mail with results at cod@fotonower.com refus_total : 0.7498349546888065 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=20860416 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_P20860416_27-02-2025_00_25_31.pdf results_Qualipapia_P20860416_27-02-2025_00_25_31.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20860416_27-02-2025_00_25_31.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','20860416','results_Qualipapia_P20860416_27-02-2025_00_25_31.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20860416_27-02-2025_00_25_31.pdf','pdf','','0.17','0.7498349546888065') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1339808855, 1339806785] 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, '2618046') ('4234', '20860416', '1339808855', None, None, None, None, None, '2618046') ('4234', None, None, None, None, None, None, None, '2618046') ('4234', '20860416', '1339806785', None, None, None, None, None, '2618046') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.012735128402709961 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.822307825088501 time spend to save output : 0.012970685958862305 total time spend for step 10 : 4.835278511047363 step11:split_time_score Thu Feb 27 00:25:35 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'}] (('20', 2),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 26022025 20860416 Nombre de photos uploadées : 2 / 23040 (0%) 26022025 20860416 Nombre de photos taguées (types de déchets): 0 / 2 (0%) 26022025 20860416 Nombre de photos taguées (volume) : 0 / 2 (0%) elapsed_time : load_data_split_time_score 2.384185791015625e-06 elapsed_time : order_list_meta_photo_and_scores 7.62939453125e-06 ?? elapsed_time : fill_and_build_computed_from_old_data 0.00022983551025390625 elapsed_time : insert_dashboard_record_day_entry 0.02361774444580078 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 : 0.6276294534906435 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20821360_26-02-2025_02_03_48.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20821360 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`=20821360 AND mptpi.`type`=4230 To do Qualite : 0.6441905892874558 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20821362_26-02-2025_02_40_50.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20821362 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`=20821362 AND mptpi.`type`=4230 To do Qualite : 0.6758532286835381 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20821883_26-02-2025_03_03_19.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20821883 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`=20821883 AND mptpi.`type`=4230 To do Qualite : 0.6491338101896319 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20822430_26-02-2025_05_39_26.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20822430 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`=20822430 AND mptpi.`type`=4230 To do Qualite : 0.6794979168726529 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20822795_26-02-2025_05_06_35.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20822795 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`=20822795 AND mptpi.`type`=4230 To do Qualite : 0.6942148724334576 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20824223_26-02-2025_06_24_01.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20824223 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`=20824223 AND mptpi.`type`=4230 To do Qualite : 0.6632362844551908 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20826355_26-02-2025_09_57_23.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20826355 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`=20826355 AND mptpi.`type`=4230 To do Qualite : 0.6819030661600797 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20828839_26-02-2025_08_06_36.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20828839 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`=20828839 AND mptpi.`type`=4230 To do Qualite : 0.6948971759675646 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20831250_26-02-2025_09_07_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20831250 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`=20831250 AND mptpi.`type`=4230 To do Qualite : 0.7447133706470982 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20832988_26-02-2025_10_37_59.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20832988 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`=20832988 AND mptpi.`type`=4230 To do Qualite : 0.7103947751315776 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20835339_26-02-2025_11_23_30.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20835339 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`=20835339 AND mptpi.`type`=4230 To do Qualite : 0.6639832598128153 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20838403_26-02-2025_12_12_15.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20838403 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`=20838403 AND mptpi.`type`=4230 To do Qualite : 0.6581242428996888 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20840006_26-02-2025_13_12_12.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20840006 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`=20840006 AND mptpi.`type`=4230 To do Qualite : 0.5844817734797334 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20841000_26-02-2025_23_46_44.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20841000 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`=20841000 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20842626 order by id desc limit 1 Qualite : 0.5599071890185797 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20845234_26-02-2025_16_16_41.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20845234 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`=20845234 AND mptpi.`type`=4230 To do Qualite : 0.6199288894847639 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20847671_26-02-2025_17_28_28.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20847671 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`=20847671 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20848578 order by id desc limit 1 Qualite : 0.6586493071788306 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20850338_26-02-2025_19_22_37.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20850338 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`=20850338 AND mptpi.`type`=4230 To do Qualite : 0.7228380286039671 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20852540_26-02-2025_20_18_45.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20852540 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`=20852540 AND mptpi.`type`=4230 To do Qualite : 0.7537762863186355 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20854867_26-02-2025_21_06_31.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20854867 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`=20854867 AND mptpi.`type`=4230 To do Qualite : 0.7435515463812097 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20856519_26-02-2025_22_05_11.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20856519 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`=20856519 AND mptpi.`type`=4230 To do Qualite : 0.7365647630694088 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20858471_26-02-2025_23_27_28.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20858471 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`=20858471 AND mptpi.`type`=4230 To do Qualite : 0.7498349546888065 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20860416_27-02-2025_00_25_31.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20860416 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`=20860416 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'26022025': {'nb_upload': 2, 'nb_taggue_class': 0, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1339808855, 1339806785] Looping around the photos to save general results len do output : 1 /20860416Didn'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, '2618046') ('4234', '20860416', '1339808855', None, None, None, None, None, '2618046') ('4234', None, None, None, None, None, None, None, '2618046') ('4234', '20860416', '1339806785', None, None, None, None, None, '2618046') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.014944076538085938 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.3269670009613037 time spend to save output : 0.015166044235229492 total time spend for step 11 : 3.342133045196533 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 2 set_done_treatment 59.19user 37.93system 5:13.62elapsed 30%CPU (0avgtext+0avgdata 8128552maxresident)k 15048inputs+25112outputs (44major+5464299minor)pagefaults 0swaps