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 : 332370 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 we have a portfolio with more photos than limit : 6>5 please execute split_portfolio.py -i 20479196 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2579689'] with mtr_portfolio_ids : ['20479196'] and first list_photo_ids : [] new path : /proc/332370/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 0.7934246063232422 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 Wed Feb 12 18:20:31 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 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 : 3137 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-12 18:20:35.231613: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-12 18:20:35.263228: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-12 18:20:35.265481: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f8538000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-12 18:20:35.265550: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-12 18:20:35.269772: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-12 18:20:35.622835: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x22246060 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-12 18:20:35.622918: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-12 18:20:35.624278: 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 2025-02-12 18:20:35.624840: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 18:20:35.627614: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 18:20:35.647987: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 18:20:35.648785: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 18:20:35.688087: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 18:20:35.693991: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 18:20:35.762767: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 18:20:35.764973: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 18:20:35.765435: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 18:20:35.766715: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-12 18:20:35.766735: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-12 18:20:35.766746: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-12 18:20:35.769580: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2534 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. 2025-02-12 18:20:36.121717: 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 2025-02-12 18:20:36.121811: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 18:20:36.121834: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 18:20:36.121854: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 18:20:36.121873: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 18:20:36.121890: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 18:20:36.121909: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 18:20:36.121927: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 18:20:36.123705: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 18:20:36.125315: 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 2025-02-12 18:20:36.125390: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 18:20:36.125411: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 18:20:36.125429: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 18:20:36.125447: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 18:20:36.125465: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 18:20:36.125483: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 18:20:36.125501: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 18:20:36.126509: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 18:20:36.126546: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-12 18:20:36.126558: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-12 18:20:36.126568: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-12 18:20:36.127696: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2534 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 : [] 2025-02-12 18:20:45.691231: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 18:20:45.903141: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 18:20:47.923063: 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. 2025-02-12 18:20:47.923153: 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. 2025-02-12 18:20:47.929857: 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. 2025-02-12 18:20:47.929899: 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. 2025-02-12 18:20:47.979710: 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. 2025-02-12 18:20:47.979761: 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. 2025-02-12 18:20:48.022361: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB 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. 2025-02-12 18:20:48.022410: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB 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. 2025-02-12 18:20:48.074341: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB 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. 2025-02-12 18:20:48.074394: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB 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. 2025-02-12 18:20:48.076793: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.48G (1585315840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.077325: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.33G (1426784256 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.077817: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.20G (1284105984 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.077832: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-02-12 18:20:48.092077: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.092841: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.119049: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.119663: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.121230: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.121807: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.128691: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.129294: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.131081: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.131673: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.137406: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.138007: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.139579: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.140158: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.168013: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.168620: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.169194: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.169763: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.174022: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.174617: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.191820: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.192418: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.192989: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.193556: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.206652: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.207315: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.207889: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.208456: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.212898: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.213509: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.218245: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.218836: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.231166: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.231768: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.235953: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.236538: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.237107: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.237673: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.238476: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.239075: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.249534: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.250394: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.251358: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.252272: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.253180: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.254087: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.269983: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.270944: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.321587: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.322539: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.331231: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.332294: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.364828: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.366249: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.367634: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.368947: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.374248: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.375561: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.376823: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.378072: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.380391: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.380459: 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. 2025-02-12 18:20:48.391706: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.393118: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.406190: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.407310: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.408419: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.409500: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.410629: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 18:20:48.411722: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.98G (2122186752 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 5 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.07109 max: 148.62344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 865 time to create 1 rle with old method : 0.001676797866821289 length of segment : 33 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 55 time to create 1 rle with old method : 0.00013589859008789062 length of segment : 25 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.0002834796905517578 length of segment : 31 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 48 time to create 1 rle with old method : 0.00017380714416503906 length of segment : 15 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 776 time to create 1 rle with old method : 0.0014798641204833984 length of segment : 28 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 2 time to create 1 rle with old method : 2.9802322387695312e-05 length of segment : 1 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 8 time to create 1 rle with old method : 0.00010371208190917969 length of segment : 3 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.61016 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1015 time to create 1 rle with old method : 0.001271963119506836 length of segment : 32 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1059 time to create 1 rle with old method : 0.001348257064819336 length of segment : 30 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1968 time to create 1 rle with old method : 0.0024385452270507812 length of segment : 41 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 845 time to create 1 rle with old method : 0.0010874271392822266 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.12578 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 : 6.198883056640625e-05 nb_pixel_total : 1455 time to create 1 rle with old method : 0.001967191696166992 length of segment : 21 time for calcul the mask position with numpy : 0.00014472007751464844 nb_pixel_total : 5089 time to create 1 rle with old method : 0.006681203842163086 length of segment : 137 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 722 time to create 1 rle with old method : 0.0010194778442382812 length of segment : 25 time for calcul the mask position with numpy : 0.00014519691467285156 nb_pixel_total : 6289 time to create 1 rle with old method : 0.0074040889739990234 length of segment : 100 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 521 time to create 1 rle with old method : 0.0006918907165527344 length of segment : 24 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 4267 time to create 1 rle with old method : 0.005394697189331055 length of segment : 69 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.73516 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 1369 time to create 1 rle with old method : 0.002306222915649414 length of segment : 73 time for calcul the mask position with numpy : 0.00022077560424804688 nb_pixel_total : 8304 time to create 1 rle with old method : 0.01546168327331543 length of segment : 133 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0007555484771728516 length of segment : 26 time for calcul the mask position with numpy : 0.000148773193359375 nb_pixel_total : 8152 time to create 1 rle with old method : 0.009777069091796875 length of segment : 112 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.00084686279296875 length of segment : 27 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 125.43984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0008838176727294922 length of segment : 20 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1087 time to create 1 rle with old method : 0.0012562274932861328 length of segment : 116 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 218.00000 molded_images shape: (1, 640, 640, 3) min: -86.53594 max: 92.05156 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: -118.72734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1302 time to create 1 rle with old method : 0.0015764236450195312 length of segment : 29 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00040030479431152344 length of segment : 18 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 2439 time to create 1 rle with old method : 0.002882719039916992 length of segment : 48 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.0003304481506347656 length of segment : 20 time for calcul the mask position with numpy : 0.0002193450927734375 nb_pixel_total : 9591 time to create 1 rle with old method : 0.012451648712158203 length of segment : 128 time for calcul the mask position with numpy : 0.0002689361572265625 nb_pixel_total : 9729 time to create 1 rle with old method : 0.012189149856567383 length of segment : 154 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.0010461807250976562 length of segment : 32 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.0010323524475097656 length of segment : 39 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0005409717559814453 length of segment : 19 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.0009751319885253906 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.32500 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 : 9.512901306152344e-05 nb_pixel_total : 2638 time to create 1 rle with old method : 0.004056692123413086 length of segment : 35 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 739 time to create 1 rle with old method : 0.0012221336364746094 length of segment : 17 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 655 time to create 1 rle with old method : 0.001031637191772461 length of segment : 36 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0008847713470458984 length of segment : 51 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.001230478286743164 length of segment : 26 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 836 time to create 1 rle with old method : 0.0013222694396972656 length of segment : 36 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 700 time to create 1 rle with old method : 0.0009591579437255859 length of segment : 29 time for calcul the mask position with numpy : 9.751319885253906e-05 nb_pixel_total : 728 time to create 1 rle with old method : 0.001180887222290039 length of segment : 37 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 881 time to create 1 rle with old method : 0.0013523101806640625 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.96953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00046443939208984375 nb_pixel_total : 19597 time to create 1 rle with old method : 0.027191162109375 length of segment : 293 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0018532276153564453 length of segment : 41 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 804 time to create 1 rle with old method : 0.0011739730834960938 length of segment : 37 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 811 time to create 1 rle with old method : 0.0012040138244628906 length of segment : 37 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 1436 time to create 1 rle with old method : 0.002054929733276367 length of segment : 46 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 251.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 126.11562 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0006172657012939453 length of segment : 34 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.0011036396026611328 length of segment : 35 time for calcul the mask position with numpy : 0.0003447532653808594 nb_pixel_total : 4253 time to create 1 rle with old method : 0.007993936538696289 length of segment : 219 time for calcul the mask position with numpy : 0.00028777122497558594 nb_pixel_total : 3331 time to create 1 rle with old method : 0.008040904998779297 length of segment : 194 time for calcul the mask position with numpy : 0.0003256797790527344 nb_pixel_total : 3308 time to create 1 rle with old method : 0.005572080612182617 length of segment : 180 Processing 1 images image shape: (280, 400, 3) min: 5.00000 max: 193.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 60.05547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0015215873718261719 nb_pixel_total : 106305 time to create 1 rle with old method : 0.15003633499145508 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 761 time to create 1 rle with old method : 0.0010075569152832031 length of segment : 30 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 3567 time to create 1 rle with old method : 0.004245758056640625 length of segment : 63 time for calcul the mask position with numpy : 0.00015497207641601562 nb_pixel_total : 2363 time to create 1 rle with old method : 0.0031502246856689453 length of segment : 65 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.0011768341064453125 length of segment : 30 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00030684471130371094 length of segment : 12 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.00041031837463378906 length of segment : 23 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005905628204345703 length of segment : 26 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.0010807514190673828 length of segment : 45 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0007405281066894531 length of segment : 44 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0006344318389892578 length of segment : 25 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 681 time to create 1 rle with old method : 0.0009074211120605469 length of segment : 31 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0007679462432861328 length of segment : 47 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0007462501525878906 length of segment : 41 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00019693374633789062 length of segment : 12 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 901 time to create 1 rle with old method : 0.001255035400390625 length of segment : 35 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.0003838539123535156 length of segment : 13 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0010404586791992188 length of segment : 31 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 723 time to create 1 rle with old method : 0.0009739398956298828 length of segment : 33 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.34609 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 : 322 time to create 1 rle with old method : 0.0004298686981201172 length of segment : 28 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0006089210510253906 length of segment : 18 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005443096160888672 length of segment : 25 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.0003209114074707031 length of segment : 26 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0005342960357666016 length of segment : 26 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.0001976490020751953 length of segment : 12 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002853870391845703 length of segment : 11 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0009090900421142578 length of segment : 22 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0005495548248291016 length of segment : 22 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 63 time to create 1 rle with old method : 0.00013327598571777344 length of segment : 6 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002727508544921875 length of segment : 17 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.69375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0005409717559814453 length of segment : 23 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0006728172302246094 length of segment : 20 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0007894039154052734 length of segment : 29 length of segment : 0 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 433 time to create 1 rle with old method : 0.0008068084716796875 length of segment : 22 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0009014606475830078 length of segment : 37 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0012652873992919922 length of segment : 31 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.00028204917907714844 length of segment : 21 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 42 time to create 1 rle with old method : 0.0001246929168701172 length of segment : 7 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.28750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.00014019012451171875 length of segment : 23 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.20000 max: 148.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 855 time to create 1 rle with old method : 0.0011112689971923828 length of segment : 31 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 49 time to create 1 rle with old method : 7.748603820800781e-05 length of segment : 27 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001990795135498047 length of segment : 22 time for calcul the mask position with numpy : 0.00023651123046875 nb_pixel_total : 803 time to create 1 rle with old method : 0.0015444755554199219 length of segment : 36 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00034308433532714844 length of segment : 25 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00023484230041503906 length of segment : 33 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 1 time to create 1 rle with old method : 2.9087066650390625e-05 length of segment : 1 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.61406 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 : 5.125999450683594e-05 nb_pixel_total : 875 time to create 1 rle with old method : 0.0015418529510498047 length of segment : 43 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 731 time to create 1 rle with old method : 0.0009593963623046875 length of segment : 39 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 2495 time to create 1 rle with old method : 0.003149747848510742 length of segment : 34 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 2584 time to create 1 rle with old method : 0.003145933151245117 length of segment : 55 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 824 time to create 1 rle with old method : 0.001081705093383789 length of segment : 36 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.00021600723266601562 length of segment : 35 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 2261 time to create 1 rle with old method : 0.0028295516967773438 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.48906 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1277 time to create 1 rle with old method : 0.001779794692993164 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: -122.05547 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00015401840209960938 nb_pixel_total : 7936 time to create 1 rle with old method : 0.009183406829833984 length of segment : 132 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00035452842712402344 length of segment : 24 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0007646083831787109 length of segment : 26 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004649162292480469 length of segment : 32 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003612041473388672 length of segment : 15 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 128.28750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0006906986236572266 length of segment : 20 time for calcul the mask position with numpy : 0.000629425048828125 nb_pixel_total : 53963 time to create 1 rle with old method : 0.0598602294921875 length of segment : 256 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 217.00000 molded_images shape: (1, 640, 640, 3) min: -87.18828 max: 86.86406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.00020551681518554688 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: -118.25469 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 : 7.128715515136719e-05 nb_pixel_total : 1284 time to create 1 rle with old method : 0.0016245841979980469 length of segment : 32 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.00043654441833496094 length of segment : 19 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 2421 time to create 1 rle with old method : 0.0030736923217773438 length of segment : 50 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 19 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0005025863647460938 length of segment : 19 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0009553432464599609 length of segment : 26 time for calcul the mask position with numpy : 0.00023746490478515625 nb_pixel_total : 9665 time to create 1 rle with old method : 0.011554479598999023 length of segment : 151 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 345 time to create 1 rle with old method : 0.0005042552947998047 length of segment : 25 time for calcul the mask position with numpy : 0.00013065338134765625 nb_pixel_total : 1693 time to create 1 rle with old method : 0.0022013187408447266 length of segment : 50 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0004341602325439453 length of segment : 18 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005490779876708984 length of segment : 18 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0003409385681152344 length of segment : 12 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002911090850830078 length of segment : 9 time for calcul the mask position with numpy : 0.00016951560974121094 nb_pixel_total : 5987 time to create 1 rle with old method : 0.007713794708251953 length of segment : 92 time for calcul the mask position with numpy : 0.00010824203491210938 nb_pixel_total : 801 time to create 1 rle with old method : 0.0014693737030029297 length of segment : 35 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.73125 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 918 time to create 1 rle with old method : 0.0011446475982666016 length of segment : 64 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 844 time to create 1 rle with old method : 0.0012583732604980469 length of segment : 38 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.0009477138519287109 length of segment : 15 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.0001461505889892578 length of segment : 20 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 788 time to create 1 rle with old method : 0.0011336803436279297 length of segment : 35 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 704 time to create 1 rle with old method : 0.0009937286376953125 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: -122.28594 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 : 0.00033855438232421875 nb_pixel_total : 18883 time to create 1 rle with old method : 0.022105693817138672 length of segment : 281 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00035452842712402344 length of segment : 40 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 1022 time to create 1 rle with old method : 0.0021889209747314453 length of segment : 40 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1339 time to create 1 rle with old method : 0.002156972885131836 length of segment : 41 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 818 time to create 1 rle with old method : 0.001035451889038086 length of segment : 39 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1347 time to create 1 rle with old method : 0.0016977787017822266 length of segment : 41 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 253.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 123.11562 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0004963874816894531 length of segment : 35 time for calcul the mask position with numpy : 0.0002613067626953125 nb_pixel_total : 4584 time to create 1 rle with old method : 0.006459474563598633 length of segment : 223 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 1457 time to create 1 rle with old method : 0.0018799304962158203 length of segment : 74 time for calcul the mask position with numpy : 0.00020051002502441406 nb_pixel_total : 3449 time to create 1 rle with old method : 0.0055084228515625 length of segment : 187 Processing 1 images image shape: (280, 400, 3) min: 8.00000 max: 198.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 59.92656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009098052978515625 nb_pixel_total : 106330 time to create 1 rle with old method : 0.12244772911071777 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.11953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 3560 time to create 1 rle with old method : 0.004193305969238281 length of segment : 61 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0006537437438964844 length of segment : 29 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0006117820739746094 length of segment : 27 time for calcul the mask position with numpy : 0.00012946128845214844 nb_pixel_total : 2920 time to create 1 rle with old method : 0.0037195682525634766 length of segment : 86 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 718 time to create 1 rle with old method : 0.0009634494781494141 length of segment : 74 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00019288063049316406 length of segment : 11 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 748 time to create 1 rle with old method : 0.0009717941284179688 length of segment : 31 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 673 time to create 1 rle with old method : 0.0009648799896240234 length of segment : 30 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 2550 time to create 1 rle with old method : 0.003213167190551758 length of segment : 50 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0006949901580810547 length of segment : 36 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0004942417144775391 length of segment : 30 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007047653198242188 length of segment : 30 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0007259845733642578 length of segment : 41 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0009706020355224609 length of segment : 33 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00016641616821289062 length of segment : 12 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0003936290740966797 length of segment : 26 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 617 time to create 1 rle with old method : 0.0007848739624023438 length of segment : 42 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.00038743019104003906 length of segment : 14 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.33047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004413127899169922 length of segment : 25 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0006487369537353516 length of segment : 23 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005156993865966797 length of segment : 27 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003581047058105469 length of segment : 17 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004703998565673828 length of segment : 18 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0005724430084228516 length of segment : 27 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.000347137451171875 length of segment : 26 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0009381771087646484 length of segment : 55 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003178119659423828 length of segment : 22 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0006685256958007812 length of segment : 19 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 717 time to create 1 rle with old method : 0.0009729862213134766 length of segment : 44 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 75 time to create 1 rle with old method : 0.0001366138458251953 length of segment : 11 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.00011920928955078125 length of segment : 5 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0004951953887939453 length of segment : 26 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00017881393432617188 length of segment : 15 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 59 time to create 1 rle with old method : 9.846687316894531e-05 length of segment : 11 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0005121231079101562 length of segment : 35 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.04922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.00034427642822265625 length of segment : 24 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0004425048828125 length of segment : 27 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.000164031982421875 length of segment : 23 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 2 time to create 1 rle with old method : 1.9073486328125e-05 length of segment : 2 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.53750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.39531 max: 149.92031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00012493133544921875 nb_pixel_total : 788 time to create 1 rle with old method : 0.0015726089477539062 length of segment : 35 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 60 time to create 1 rle with old method : 0.00014734268188476562 length of segment : 27 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 48 time to create 1 rle with old method : 0.00020694732666015625 length of segment : 18 time for calcul the mask position with numpy : 0.00061798095703125 nb_pixel_total : 4803 time to create 1 rle with old method : 0.008851289749145508 length of segment : 140 time for calcul the mask position with numpy : 0.00012564659118652344 nb_pixel_total : 144 time to create 1 rle with old method : 0.0003018379211425781 length of segment : 32 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 2 time to create 1 rle with old method : 5.269050598144531e-05 length of segment : 1 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0012624263763427734 length of segment : 31 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 6 time to create 1 rle with old method : 5.14984130859375e-05 length of segment : 6 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.61406 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 : 7.343292236328125e-05 nb_pixel_total : 658 time to create 1 rle with old method : 0.0009236335754394531 length of segment : 35 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 810 time to create 1 rle with old method : 0.0011568069458007812 length of segment : 37 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 2173 time to create 1 rle with old method : 0.0028045177459716797 length of segment : 30 time for calcul the mask position with numpy : 0.00016951560974121094 nb_pixel_total : 2038 time to create 1 rle with old method : 0.002610921859741211 length of segment : 53 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 2413 time to create 1 rle with old method : 0.0032453536987304688 length of segment : 35 time for calcul the mask position with numpy : 0.00013065338134765625 nb_pixel_total : 2717 time to create 1 rle with old method : 0.0033779144287109375 length of segment : 52 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 2338 time to create 1 rle with old method : 0.002907276153564453 length of segment : 51 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.98125 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.0001266002655029297 nb_pixel_total : 4829 time to create 1 rle with old method : 0.007409811019897461 length of segment : 133 time for calcul the mask position with numpy : 0.00012302398681640625 nb_pixel_total : 1058 time to create 1 rle with old method : 0.0014104843139648438 length of segment : 25 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 953 time to create 1 rle with old method : 0.0015323162078857422 length of segment : 28 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1318 time to create 1 rle with old method : 0.0017673969268798828 length of segment : 37 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1055 time to create 1 rle with old method : 0.0014493465423583984 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.34453 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00019884109497070312 nb_pixel_total : 7856 time to create 1 rle with old method : 0.009486198425292969 length of segment : 134 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 1303 time to create 1 rle with old method : 0.0016036033630371094 length of segment : 70 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0007674694061279297 length of segment : 26 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0008633136749267578 length of segment : 28 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00030350685119628906 length of segment : 17 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 125.35000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 8.940696716308594e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0007119178771972656 length of segment : 20 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 1113 time to create 1 rle with old method : 0.0015187263488769531 length of segment : 83 time for calcul the mask position with numpy : 0.00010895729064941406 nb_pixel_total : 1003 time to create 1 rle with old method : 0.0012564659118652344 length of segment : 99 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0003590583801269531 length of segment : 17 time for calcul the mask position with numpy : 0.00012612342834472656 nb_pixel_total : 2349 time to create 1 rle with old method : 0.003313779830932617 length of segment : 53 time for calcul the mask position with numpy : 0.0007181167602539062 nb_pixel_total : 51164 time to create 1 rle with old method : 0.05852985382080078 length of segment : 268 Processing 1 images image shape: (400, 400, 3) min: 14.00000 max: 217.00000 molded_images shape: (1, 640, 640, 3) min: -80.73906 max: 88.21563 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: -118.70000 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 : 0.00010275840759277344 nb_pixel_total : 1392 time to create 1 rle with old method : 0.0025968551635742188 length of segment : 32 time for calcul the mask position with numpy : 0.00016689300537109375 nb_pixel_total : 2347 time to create 1 rle with old method : 0.003598928451538086 length of segment : 47 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0004222393035888672 length of segment : 18 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0005247592926025391 length of segment : 21 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 772 time to create 1 rle with old method : 0.0010335445404052734 length of segment : 33 time for calcul the mask position with numpy : 0.0002579689025878906 nb_pixel_total : 7747 time to create 1 rle with old method : 0.009577512741088867 length of segment : 132 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0005271434783935547 length of segment : 17 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0003485679626464844 length of segment : 13 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.0010809898376464844 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.09453 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 : 6.508827209472656e-05 nb_pixel_total : 792 time to create 1 rle with old method : 0.0016181468963623047 length of segment : 16 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 868 time to create 1 rle with old method : 0.0011930465698242188 length of segment : 41 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0007758140563964844 length of segment : 54 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0009047985076904297 length of segment : 35 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 800 time to create 1 rle with old method : 0.0011167526245117188 length of segment : 38 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 662 time to create 1 rle with old method : 0.0008609294891357422 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.15313 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.0003495216369628906 nb_pixel_total : 19258 time to create 1 rle with old method : 0.02306199073791504 length of segment : 273 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0010066032409667969 length of segment : 37 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1323 time to create 1 rle with old method : 0.0016970634460449219 length of segment : 40 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.00038313865661621094 length of segment : 19 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 123.43984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.00045299530029296875 length of segment : 35 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.00047469139099121094 length of segment : 76 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1397 time to create 1 rle with old method : 0.001817941665649414 length of segment : 77 time for calcul the mask position with numpy : 0.0001888275146484375 nb_pixel_total : 4533 time to create 1 rle with old method : 0.005387783050537109 length of segment : 222 time for calcul the mask position with numpy : 0.0001437664031982422 nb_pixel_total : 3293 time to create 1 rle with old method : 0.0038805007934570312 length of segment : 205 Processing 1 images image shape: (280, 400, 3) min: 7.00000 max: 201.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 65.73516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009150505065917969 nb_pixel_total : 106309 time to create 1 rle with old method : 0.11993980407714844 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.51797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 3504 time to create 1 rle with old method : 0.0041539669036865234 length of segment : 60 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 779 time to create 1 rle with old method : 0.0010342597961425781 length of segment : 33 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 2440 time to create 1 rle with old method : 0.003151416778564453 length of segment : 68 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005931854248046875 length of segment : 25 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001819133758544922 length of segment : 11 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006361007690429688 length of segment : 32 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.0011146068572998047 length of segment : 32 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.0009036064147949219 length of segment : 52 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0006666183471679688 length of segment : 30 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006511211395263672 length of segment : 37 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.0004398822784423828 length of segment : 30 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.0002582073211669922 length of segment : 24 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.63906 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0004673004150390625 length of segment : 25 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0007154941558837891 length of segment : 24 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0006163120269775391 length of segment : 27 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0005559921264648438 length of segment : 17 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003185272216796875 length of segment : 18 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003254413604736328 length of segment : 24 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0005099773406982422 length of segment : 25 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.00015974044799804688 length of segment : 9 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0003006458282470703 length of segment : 14 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.00016808509826660156 length of segment : 6 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1360 time to create 1 rle with old method : 0.0018222332000732422 length of segment : 73 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 54 time to create 1 rle with old method : 0.00010800361633300781 length of segment : 11 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1119 time to create 1 rle with old method : 0.0015599727630615234 length of segment : 42 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005905628204345703 length of segment : 23 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0009050369262695312 length of segment : 32 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 638 time to create 1 rle with old method : 0.0008172988891601562 length of segment : 33 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.37344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0005559921264648438 length of segment : 40 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00033473968505859375 length of segment : 21 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.00015163421630859375 length of segment : 24 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.00031948089599609375 length of segment : 22 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005373954772949219 length of segment : 29 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 21 time to create 1 rle with old method : 0.00011992454528808594 length of segment : 9 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0001995563507080078 length of segment : 20 time for calcul the mask position with numpy : 2.765655517578125e-05 nb_pixel_total : 53 time to create 1 rle with old method : 0.00010251998901367188 length of segment : 7 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 134.22500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.55547 max: 149.36562 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0010776519775390625 length of segment : 47 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 75 time to create 1 rle with old method : 0.00013017654418945312 length of segment : 31 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.00022935867309570312 length of segment : 32 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.0011050701141357422 length of segment : 38 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 2 time to create 1 rle with old method : 3.170967102050781e-05 length of segment : 2 time for calcul the mask position with numpy : 0.00022983551025390625 nb_pixel_total : 3118 time to create 1 rle with old method : 0.0042514801025390625 length of segment : 89 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 50 time to create 1 rle with old method : 0.00010418891906738281 length of segment : 12 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 7 time to create 1 rle with old method : 8.416175842285156e-05 length of segment : 4 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.83672 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.001079559326171875 length of segment : 32 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 2646 time to create 1 rle with old method : 0.003302335739135742 length of segment : 53 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 892 time to create 1 rle with old method : 0.0011610984802246094 length of segment : 47 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.98125 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0005991458892822266 length of segment : 26 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 807 time to create 1 rle with old method : 0.0011243820190429688 length of segment : 36 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.0012352466583251953 length of segment : 28 time for calcul the mask position with numpy : 9.846687316894531e-05 nb_pixel_total : 4768 time to create 1 rle with old method : 0.005447864532470703 length of segment : 139 time for calcul the mask position with numpy : 0.00012636184692382812 nb_pixel_total : 2464 time to create 1 rle with old method : 0.0030777454376220703 length of segment : 124 time for calcul the mask position with numpy : 0.00017309188842773438 nb_pixel_total : 6518 time to create 1 rle with old method : 0.007551908493041992 length of segment : 112 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.96172 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.0007367134094238281 length of segment : 26 time for calcul the mask position with numpy : 0.00015282630920410156 nb_pixel_total : 8550 time to create 1 rle with old method : 0.010579586029052734 length of segment : 132 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0006275177001953125 length of segment : 47 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0009641647338867188 length of segment : 26 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.29141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.0007047653198242188 length of segment : 21 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1079 time to create 1 rle with old method : 0.0013277530670166016 length of segment : 104 time for calcul the mask position with numpy : 0.0006186962127685547 nb_pixel_total : 53673 time to create 1 rle with old method : 0.06059575080871582 length of segment : 353 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 228.00000 molded_images shape: (1, 640, 640, 3) min: -81.09453 max: 90.11406 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: -118.45391 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 : 9.965896606445312e-05 nb_pixel_total : 1223 time to create 1 rle with old method : 0.0016148090362548828 length of segment : 28 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.00044918060302734375 length of segment : 20 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0010368824005126953 length of segment : 38 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 2434 time to create 1 rle with old method : 0.003369569778442383 length of segment : 50 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004978179931640625 length of segment : 19 time for calcul the mask position with numpy : 0.0004017353057861328 nb_pixel_total : 11513 time to create 1 rle with old method : 0.01449275016784668 length of segment : 144 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 785 time to create 1 rle with old method : 0.0010170936584472656 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.39531 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1033 time to create 1 rle with old method : 0.001453399658203125 length of segment : 18 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 840 time to create 1 rle with old method : 0.0011229515075683594 length of segment : 67 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 734 time to create 1 rle with old method : 0.0011088848114013672 length of segment : 35 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 746 time to create 1 rle with old method : 0.0010447502136230469 length of segment : 35 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 931 time to create 1 rle with old method : 0.0013446807861328125 length of segment : 43 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002543926239013672 length of segment : 17 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 857 time to create 1 rle with old method : 0.0012309551239013672 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: -121.90703 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 : 0.00039315223693847656 nb_pixel_total : 19360 time to create 1 rle with old method : 0.02292943000793457 length of segment : 328 time for calcul the mask position with numpy : 0.00016307830810546875 nb_pixel_total : 195 time to create 1 rle with old method : 0.0003192424774169922 length of segment : 43 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0017271041870117188 length of segment : 40 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 900 time to create 1 rle with old method : 0.0011470317840576172 length of segment : 39 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1339 time to create 1 rle with old method : 0.0016412734985351562 length of segment : 42 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 840 time to create 1 rle with old method : 0.0011548995971679688 length of segment : 37 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 118.93594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.00041365623474121094 length of segment : 33 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003514289855957031 length of segment : 63 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1179 time to create 1 rle with old method : 0.0015382766723632812 length of segment : 62 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0008859634399414062 length of segment : 42 time for calcul the mask position with numpy : 0.0003409385681152344 nb_pixel_total : 4667 time to create 1 rle with old method : 0.0054569244384765625 length of segment : 228 time for calcul the mask position with numpy : 0.0002512931823730469 nb_pixel_total : 3022 time to create 1 rle with old method : 0.003629922866821289 length of segment : 194 time for calcul the mask position with numpy : 0.00012302398681640625 nb_pixel_total : 1369 time to create 1 rle with old method : 0.001739501953125 length of segment : 75 Processing 1 images image shape: (280, 400, 3) min: 10.00000 max: 192.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 59.75078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0011548995971679688 nb_pixel_total : 106272 time to create 1 rle with old method : 0.11726641654968262 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.32656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 3585 time to create 1 rle with old method : 0.004281044006347656 length of segment : 63 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0006434917449951172 length of segment : 28 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1112 time to create 1 rle with old method : 0.001435995101928711 length of segment : 61 time for calcul the mask position with numpy : 0.00014448165893554688 nb_pixel_total : 2358 time to create 1 rle with old method : 0.003045320510864258 length of segment : 69 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0008120536804199219 length of segment : 60 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0006177425384521484 length of segment : 24 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001990795135498047 length of segment : 12 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0006279945373535156 length of segment : 25 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1764 time to create 1 rle with old method : 0.002227306365966797 length of segment : 67 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005066394805908203 length of segment : 21 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00036835670471191406 length of segment : 22 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 707 time to create 1 rle with old method : 0.0009641647338867188 length of segment : 32 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 677 time to create 1 rle with old method : 0.0009288787841796875 length of segment : 30 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 649 time to create 1 rle with old method : 0.0009291172027587891 length of segment : 28 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 596 time to create 1 rle with old method : 0.0007920265197753906 length of segment : 29 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.00015020370483398438 length of segment : 11 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005333423614501953 length of segment : 26 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.00048828125 length of segment : 18 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.0006234645843505859 length of segment : 23 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005743503570556641 length of segment : 26 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005705356597900391 length of segment : 27 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.0002014636993408203 length of segment : 12 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.00014925003051757812 length of segment : 7 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 664 time to create 1 rle with old method : 0.0008978843688964844 length of segment : 33 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00031375885009765625 length of segment : 24 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.00037407875061035156 length of segment : 12 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.00047707557678222656 length of segment : 25 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0006020069122314453 length of segment : 23 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.00019240379333496094 length of segment : 12 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004138946533203125 length of segment : 22 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.00022339820861816406 length of segment : 16 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0004057884216308594 length of segment : 27 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.00015282630920410156 length of segment : 10 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0004787445068359375 length of segment : 25 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.70156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0007536411285400391 length of segment : 29 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.0002148151397705078 length of segment : 8 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0004780292510986328 length of segment : 24 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 23 time to create 1 rle with old method : 7.510185241699219e-05 length of segment : 11 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 10 time to create 1 rle with old method : 0.00011014938354492188 length of segment : 5 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.0002434253692626953 length of segment : 19 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.0003829002380371094 length of segment : 21 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0007731914520263672 length of segment : 19 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 56 time to create 1 rle with old method : 0.00011301040649414062 length of segment : 23 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.57891 max: 150.22500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0010516643524169922 length of segment : 33 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.00013446807861328125 length of segment : 36 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 4 time to create 1 rle with old method : 3.62396240234375e-05 length of segment : 1 time for calcul the mask position with numpy : 0.00016808509826660156 nb_pixel_total : 4295 time to create 1 rle with old method : 0.005251646041870117 length of segment : 150 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 779 time to create 1 rle with old method : 0.0010328292846679688 length of segment : 32 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00028443336486816406 length of segment : 34 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.00020837783813476562 length of segment : 32 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 53 time to create 1 rle with old method : 0.00013303756713867188 length of segment : 16 time for calcul the mask position with numpy : 0.00016188621520996094 nb_pixel_total : 8026 time to create 1 rle with old method : 0.009947538375854492 length of segment : 123 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.00018405914306640625 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: -118.12188 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 : 9.059906005859375e-05 nb_pixel_total : 2134 time to create 1 rle with old method : 0.003267049789428711 length of segment : 32 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 682 time to create 1 rle with old method : 0.0008845329284667969 length of segment : 33 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 2740 time to create 1 rle with old method : 0.0033881664276123047 length of segment : 54 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.001194000244140625 length of segment : 40 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 2400 time to create 1 rle with old method : 0.0030007362365722656 length of segment : 37 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 2349 time to create 1 rle with old method : 0.0028638839721679688 length of segment : 53 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 670 time to create 1 rle with old method : 0.0009028911590576172 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.45000 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 : 0.00011587142944335938 nb_pixel_total : 7323 time to create 1 rle with old method : 0.008485794067382812 length of segment : 103 time for calcul the mask position with numpy : 0.00012612342834472656 nb_pixel_total : 4562 time to create 1 rle with old method : 0.0052394866943359375 length of segment : 124 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.0012166500091552734 length of segment : 19 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.000675201416015625 length of segment : 25 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.00098419189453125 length of segment : 31 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 988 time to create 1 rle with old method : 0.0012824535369873047 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.49297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.0002200603485107422 nb_pixel_total : 486 time to create 1 rle with old method : 0.0012371540069580078 length of segment : 27 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004189014434814453 length of segment : 39 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005304813385009766 length of segment : 32 time for calcul the mask position with numpy : 0.00016927719116210938 nb_pixel_total : 7651 time to create 1 rle with old method : 0.009090423583984375 length of segment : 129 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.00030612945556640625 length of segment : 17 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 130.28750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0013561248779296875 length of segment : 38 time for calcul the mask position with numpy : 0.000934600830078125 nb_pixel_total : 52937 time to create 1 rle with old method : 0.07775068283081055 length of segment : 313 time for calcul the mask position with numpy : 0.0007505416870117188 nb_pixel_total : 62238 time to create 1 rle with old method : 0.07345151901245117 length of segment : 362 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 218.00000 molded_images shape: (1, 640, 640, 3) min: -90.10703 max: 92.05156 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: -118.44219 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 : 0.00012063980102539062 nb_pixel_total : 1393 time to create 1 rle with old method : 0.0018780231475830078 length of segment : 31 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004379749298095703 length of segment : 19 time for calcul the mask position with numpy : 0.0001442432403564453 nb_pixel_total : 2459 time to create 1 rle with old method : 0.0032029151916503906 length of segment : 50 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004703998565673828 length of segment : 19 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0010867118835449219 length of segment : 32 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.00038933753967285156 length of segment : 16 time for calcul the mask position with numpy : 0.0002837181091308594 nb_pixel_total : 6816 time to create 1 rle with old method : 0.008515596389770508 length of segment : 106 time for calcul the mask position with numpy : 0.00011134147644042969 nb_pixel_total : 794 time to create 1 rle with old method : 0.0010919570922851562 length of segment : 30 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 737 time to create 1 rle with old method : 0.0010793209075927734 length of segment : 35 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.0010197162628173828 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.50859 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 : 0.00012946128845214844 nb_pixel_total : 757 time to create 1 rle with old method : 0.0013937950134277344 length of segment : 59 time for calcul the mask position with numpy : 0.00012731552124023438 nb_pixel_total : 1141 time to create 1 rle with old method : 0.0022423267364501953 length of segment : 21 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 41 time to create 1 rle with old method : 0.0001475811004638672 length of segment : 12 time for calcul the mask position with numpy : 0.00010919570922851562 nb_pixel_total : 835 time to create 1 rle with old method : 0.0016756057739257812 length of segment : 38 time for calcul the mask position with numpy : 0.00019812583923339844 nb_pixel_total : 2750 time to create 1 rle with old method : 0.0051844120025634766 length of segment : 43 time for calcul the mask position with numpy : 0.00010037422180175781 nb_pixel_total : 168 time to create 1 rle with old method : 0.0005567073822021484 length of segment : 11 time for calcul the mask position with numpy : 0.00013709068298339844 nb_pixel_total : 877 time to create 1 rle with old method : 0.0022835731506347656 length of segment : 46 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 33 time to create 1 rle with old method : 9.846687316894531e-05 length of segment : 6 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0008342266082763672 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.23125 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00011777877807617188 nb_pixel_total : 147 time to create 1 rle with old method : 0.00029349327087402344 length of segment : 37 time for calcul the mask position with numpy : 0.0005066394805908203 nb_pixel_total : 16960 time to create 1 rle with old method : 0.020212411880493164 length of segment : 310 time for calcul the mask position with numpy : 0.00011730194091796875 nb_pixel_total : 784 time to create 1 rle with old method : 0.0010349750518798828 length of segment : 36 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1336 time to create 1 rle with old method : 0.0016760826110839844 length of segment : 43 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 1277 time to create 1 rle with old method : 0.0016663074493408203 length of segment : 40 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 254.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 121.72500 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 : 386 time to create 1 rle with old method : 0.0005240440368652344 length of segment : 34 time for calcul the mask position with numpy : 0.00013184547424316406 nb_pixel_total : 771 time to create 1 rle with old method : 0.0010082721710205078 length of segment : 36 time for calcul the mask position with numpy : 0.0001704692840576172 nb_pixel_total : 903 time to create 1 rle with old method : 0.0013012886047363281 length of segment : 104 time for calcul the mask position with numpy : 0.00038242340087890625 nb_pixel_total : 4693 time to create 1 rle with old method : 0.005925416946411133 length of segment : 222 time for calcul the mask position with numpy : 0.00020074844360351562 nb_pixel_total : 1248 time to create 1 rle with old method : 0.001909017562866211 length of segment : 66 Processing 1 images image shape: (280, 400, 3) min: 4.00000 max: 194.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 60.61016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012409687042236328 nb_pixel_total : 106264 time to create 1 rle with old method : 0.13045239448547363 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.93984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 3616 time to create 1 rle with old method : 0.004501819610595703 length of segment : 61 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0006742477416992188 length of segment : 57 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006608963012695312 length of segment : 30 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 780 time to create 1 rle with old method : 0.0010423660278320312 length of segment : 32 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.00020742416381835938 length of segment : 12 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 596 time to create 1 rle with old method : 0.0008330345153808594 length of segment : 45 time for calcul the mask position with numpy : 0.000148773193359375 nb_pixel_total : 2637 time to create 1 rle with old method : 0.003505706787109375 length of segment : 63 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004417896270751953 length of segment : 31 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005941390991210938 length of segment : 26 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007729530334472656 length of segment : 39 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 684 time to create 1 rle with old method : 0.0009338855743408203 length of segment : 31 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 2954 time to create 1 rle with old method : 0.003866910934448242 length of segment : 59 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 977 time to create 1 rle with old method : 0.001272439956665039 length of segment : 34 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0006012916564941406 length of segment : 25 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0009732246398925781 length of segment : 33 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.17812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 469 time to create 1 rle with old method : 0.0006458759307861328 length of segment : 22 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005791187286376953 length of segment : 27 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 667 time to create 1 rle with old method : 0.0008947849273681641 length of segment : 33 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.00038051605224609375 length of segment : 12 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.00045037269592285156 length of segment : 26 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.00046443939208984375 length of segment : 18 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.00030994415283203125 length of segment : 26 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.00016999244689941406 length of segment : 7 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005772113800048828 length of segment : 27 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0006210803985595703 length of segment : 39 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0004994869232177734 length of segment : 26 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.00031948089599609375 length of segment : 27 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005884170532226562 length of segment : 23 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.0002353191375732422 length of segment : 18 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0004885196685791016 length of segment : 26 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.0002589225769042969 length of segment : 13 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 708 time to create 1 rle with old method : 0.0008978843688964844 length of segment : 38 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.00625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.00045013427734375 length of segment : 33 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0005245208740234375 length of segment : 33 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 58 time to create 1 rle with old method : 0.00011801719665527344 length of segment : 25 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003781318664550781 length of segment : 25 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005471706390380859 length of segment : 43 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.000316619873046875 nb_pixel_total : 21211 time to create 1 rle with old method : 0.02415943145751953 length of segment : 584 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 20 time to create 1 rle with old method : 6.461143493652344e-05 length of segment : 5 Detection mask done ! Trying to reset tf kernel 332983 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 336 tf kernel not reseted sub process len(results) : 474 len(list_Values) 474 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 474 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 : 1281 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 474 chid ids of type : 4228 Number RLEs to save : 23499 save missing photos in datou_result : time spend for datou_step_exec : 36.31065368652344 time spend to save output : 1.5568833351135254 total time spend for step 1 : 37.86753702163696 step2:brightness Wed Feb 12 18:21:08 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1739380830_332370_1337118339_eba264b4f37d876e7ce4626dbad9e5c6.jpg treat image : temp/1739380830_332370_1337118336_b2377572427db033df6552158dcc458a.jpg treat image : temp/1739380830_332370_1337118333_86a6548477a7b377b5d7ae5737354ee9.jpg treat image : temp/1739380830_332370_1337118331_4d678fb330a4d89d799d29c580ee69f1.jpg treat image : temp/1739380830_332370_1337118329_91c9bdc8ec718db9209b385ca38b61f9.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 5 time used for this insertion : 0.014390945434570312 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.012090921401977539 save missing photos in datou_result : time spend for datou_step_exec : 1.3735671043395996 time spend to save output : 0.0326685905456543 total time spend for step 2 : 1.406235694885254 step3:blur_detection Wed Feb 12 18:21:10 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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/1739380830_332370_1337118339_eba264b4f37d876e7ce4626dbad9e5c6.jpg resize: (1080, 1920) 1337118339 -7.804511933549772 treat image : temp/1739380830_332370_1337118336_b2377572427db033df6552158dcc458a.jpg resize: (1080, 1920) 1337118336 -7.782289418624392 treat image : temp/1739380830_332370_1337118333_86a6548477a7b377b5d7ae5737354ee9.jpg resize: (1080, 1920) 1337118333 -7.789489584782072 treat image : temp/1739380830_332370_1337118331_4d678fb330a4d89d799d29c580ee69f1.jpg resize: (1080, 1920) 1337118331 -7.791605882568465 treat image : temp/1739380830_332370_1337118329_91c9bdc8ec718db9209b385ca38b61f9.jpg resize: (1080, 1920) 1337118329 -7.773127011043167 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 5 time used for this insertion : 0.012788057327270508 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.012685060501098633 save missing photos in datou_result : time spend for datou_step_exec : 4.589339971542358 time spend to save output : 0.030440568923950195 total time spend for step 3 : 4.619780540466309 step4:rle_unique_nms_with_priority Wed Feb 12 18:21:14 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 474 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 90 nb_hashtags : 7 time to prepare the origin masks : 1.0282318592071533 time for calcul the mask position with numpy : 0.07132959365844727 nb_pixel_total : 1858820 time to create 1 rle with new method : 0.1808936595916748 time for calcul the mask position with numpy : 0.008529901504516602 nb_pixel_total : 865 time to create 1 rle with old method : 0.0010104179382324219 time for calcul the mask position with numpy : 0.008504390716552734 nb_pixel_total : 151 time to create 1 rle with old method : 0.00018739700317382812 time for calcul the mask position with numpy : 0.009117841720581055 nb_pixel_total : 1015 time to create 1 rle with old method : 0.0011720657348632812 time for calcul the mask position with numpy : 0.00887298583984375 nb_pixel_total : 96 time to create 1 rle with old method : 0.00015401840209960938 time for calcul the mask position with numpy : 0.008849620819091797 nb_pixel_total : 55 time to create 1 rle with old method : 8.821487426757812e-05 time for calcul the mask position with numpy : 0.008763790130615234 nb_pixel_total : 48 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.008886337280273438 nb_pixel_total : 27 time to create 1 rle with old method : 7.414817810058594e-05 time for calcul the mask position with numpy : 0.00857853889465332 nb_pixel_total : 7 time to create 1 rle with old method : 3.933906555175781e-05 time for calcul the mask position with numpy : 0.008543014526367188 nb_pixel_total : 2 time to create 1 rle with old method : 2.2411346435546875e-05 time for calcul the mask position with numpy : 0.008586645126342773 nb_pixel_total : 1968 time to create 1 rle with old method : 0.002250194549560547 time for calcul the mask position with numpy : 0.00860285758972168 nb_pixel_total : 1369 time to create 1 rle with old method : 0.0015301704406738281 time for calcul the mask position with numpy : 0.008548259735107422 nb_pixel_total : 4267 time to create 1 rle with old method : 0.004886150360107422 time for calcul the mask position with numpy : 0.008525371551513672 nb_pixel_total : 1087 time to create 1 rle with old method : 0.0015320777893066406 time for calcul the mask position with numpy : 0.008594989776611328 nb_pixel_total : 845 time to create 1 rle with old method : 0.0010247230529785156 time for calcul the mask position with numpy : 0.008529901504516602 nb_pixel_total : 31 time to create 1 rle with old method : 6.198883056640625e-05 time for calcul the mask position with numpy : 0.008431434631347656 nb_pixel_total : 722 time to create 1 rle with old method : 0.000850677490234375 time for calcul the mask position with numpy : 0.008486270904541016 nb_pixel_total : 76 time to create 1 rle with old method : 0.0001366138458251953 time for calcul the mask position with numpy : 0.008858203887939453 nb_pixel_total : 494 time to create 1 rle with old method : 0.0009582042694091797 time for calcul the mask position with numpy : 0.010149717330932617 nb_pixel_total : 1455 time to create 1 rle with old method : 0.0017826557159423828 time for calcul the mask position with numpy : 0.008449316024780273 nb_pixel_total : 5089 time to create 1 rle with old method : 0.005917549133300781 time for calcul the mask position with numpy : 0.008424758911132812 nb_pixel_total : 6289 time to create 1 rle with old method : 0.007119655609130859 time for calcul the mask position with numpy : 0.008568048477172852 nb_pixel_total : 8304 time to create 1 rle with old method : 0.009660720825195312 time for calcul the mask position with numpy : 0.00854945182800293 nb_pixel_total : 822 time to create 1 rle with old method : 0.001032114028930664 time for calcul the mask position with numpy : 0.008449792861938477 nb_pixel_total : 493 time to create 1 rle with old method : 0.0006046295166015625 time for calcul the mask position with numpy : 0.008445262908935547 nb_pixel_total : 700 time to create 1 rle with old method : 0.0008976459503173828 time for calcul the mask position with numpy : 0.008651018142700195 nb_pixel_total : 19597 time to create 1 rle with old method : 0.021970748901367188 time for calcul the mask position with numpy : 0.008522272109985352 nb_pixel_total : 27 time to create 1 rle with old method : 5.745887756347656e-05 time for calcul the mask position with numpy : 0.008480548858642578 nb_pixel_total : 804 time to create 1 rle with old method : 0.0009479522705078125 time for calcul the mask position with numpy : 0.008475542068481445 nb_pixel_total : 94 time to create 1 rle with old method : 0.00015997886657714844 time for calcul the mask position with numpy : 0.00860142707824707 nb_pixel_total : 806 time to create 1 rle with old method : 0.0009958744049072266 time for calcul the mask position with numpy : 0.008500099182128906 nb_pixel_total : 2638 time to create 1 rle with old method : 0.0029833316802978516 time for calcul the mask position with numpy : 0.008485078811645508 nb_pixel_total : 221 time to create 1 rle with old method : 0.0002739429473876953 time for calcul the mask position with numpy : 0.008437395095825195 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001544952392578125 time for calcul the mask position with numpy : 0.009134054183959961 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0017223358154296875 time for calcul the mask position with numpy : 0.008688211441040039 nb_pixel_total : 9591 time to create 1 rle with old method : 0.010906457901000977 time for calcul the mask position with numpy : 0.008650541305541992 nb_pixel_total : 59 time to create 1 rle with old method : 0.00019049644470214844 time for calcul the mask position with numpy : 0.008527517318725586 nb_pixel_total : 713 time to create 1 rle with old method : 0.000904083251953125 time for calcul the mask position with numpy : 0.00854039192199707 nb_pixel_total : 836 time to create 1 rle with old method : 0.0010311603546142578 time for calcul the mask position with numpy : 0.008611679077148438 nb_pixel_total : 4253 time to create 1 rle with old method : 0.004944324493408203 time for calcul the mask position with numpy : 0.008682012557983398 nb_pixel_total : 68 time to create 1 rle with old method : 0.00013399124145507812 time for calcul the mask position with numpy : 0.008551836013793945 nb_pixel_total : 61 time to create 1 rle with old method : 0.0001499652862548828 time for calcul the mask position with numpy : 0.008721351623535156 nb_pixel_total : 602 time to create 1 rle with old method : 0.0008375644683837891 time for calcul the mask position with numpy : 0.009244918823242188 nb_pixel_total : 192 time to create 1 rle with old method : 0.0004088878631591797 time for calcul the mask position with numpy : 0.01005244255065918 nb_pixel_total : 655 time to create 1 rle with old method : 0.0008311271667480469 time for calcul the mask position with numpy : 0.009068012237548828 nb_pixel_total : 108 time to create 1 rle with old method : 0.000194549560546875 time for calcul the mask position with numpy : 0.008761882781982422 nb_pixel_total : 6 time to create 1 rle with old method : 7.176399230957031e-05 time for calcul the mask position with numpy : 0.008871316909790039 nb_pixel_total : 2439 time to create 1 rle with old method : 0.0029001235961914062 time for calcul the mask position with numpy : 0.01687335968017578 nb_pixel_total : 8091 time to create 1 rle with old method : 0.0157773494720459 time for calcul the mask position with numpy : 0.012172222137451172 nb_pixel_total : 371 time to create 1 rle with old method : 0.0005695819854736328 time for calcul the mask position with numpy : 0.009398937225341797 nb_pixel_total : 290 time to create 1 rle with old method : 0.0003666877746582031 time for calcul the mask position with numpy : 0.00864410400390625 nb_pixel_total : 1302 time to create 1 rle with old method : 0.001592874526977539 time for calcul the mask position with numpy : 0.00948333740234375 nb_pixel_total : 106305 time to create 1 rle with old method : 0.11535453796386719 time for calcul the mask position with numpy : 0.009228706359863281 nb_pixel_total : 832 time to create 1 rle with old method : 0.0010519027709960938 time for calcul the mask position with numpy : 0.008896112442016602 nb_pixel_total : 3567 time to create 1 rle with old method : 0.004434823989868164 time for calcul the mask position with numpy : 0.008855342864990234 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001316070556640625 time for calcul the mask position with numpy : 0.008826494216918945 nb_pixel_total : 116 time to create 1 rle with old method : 0.00018024444580078125 time for calcul the mask position with numpy : 0.008909940719604492 nb_pixel_total : 234 time to create 1 rle with old method : 0.000316619873046875 time for calcul the mask position with numpy : 0.00893092155456543 nb_pixel_total : 5 time to create 1 rle with old method : 6.031990051269531e-05 time for calcul the mask position with numpy : 0.008853912353515625 nb_pixel_total : 335 time to create 1 rle with old method : 0.0004355907440185547 time for calcul the mask position with numpy : 0.008758306503295898 nb_pixel_total : 234 time to create 1 rle with old method : 0.00032258033752441406 time for calcul the mask position with numpy : 0.008803606033325195 nb_pixel_total : 548 time to create 1 rle with old method : 0.0006856918334960938 time for calcul the mask position with numpy : 0.008772134780883789 nb_pixel_total : 761 time to create 1 rle with old method : 0.0009176731109619141 time for calcul the mask position with numpy : 0.008788824081420898 nb_pixel_total : 294 time to create 1 rle with old method : 0.00038051605224609375 time for calcul the mask position with numpy : 0.008781671524047852 nb_pixel_total : 363 time to create 1 rle with old method : 0.0004639625549316406 time for calcul the mask position with numpy : 0.00879526138305664 nb_pixel_total : 2363 time to create 1 rle with old method : 0.0027840137481689453 time for calcul the mask position with numpy : 0.008753299713134766 nb_pixel_total : 110 time to create 1 rle with old method : 0.0001633167266845703 time for calcul the mask position with numpy : 0.009118080139160156 nb_pixel_total : 901 time to create 1 rle with old method : 0.0011150836944580078 time for calcul the mask position with numpy : 0.008777141571044922 nb_pixel_total : 200 time to create 1 rle with old method : 0.000293731689453125 time for calcul the mask position with numpy : 0.008795499801635742 nb_pixel_total : 21 time to create 1 rle with old method : 8.988380432128906e-05 time for calcul the mask position with numpy : 0.008752107620239258 nb_pixel_total : 433 time to create 1 rle with old method : 0.0005338191986083984 time for calcul the mask position with numpy : 0.008707761764526367 nb_pixel_total : 35 time to create 1 rle with old method : 0.00011301040649414062 time for calcul the mask position with numpy : 0.008779287338256836 nb_pixel_total : 681 time to create 1 rle with old method : 0.0008258819580078125 time for calcul the mask position with numpy : 0.008825063705444336 nb_pixel_total : 322 time to create 1 rle with old method : 0.0004062652587890625 time for calcul the mask position with numpy : 0.008538961410522461 nb_pixel_total : 257 time to create 1 rle with old method : 0.00032782554626464844 time for calcul the mask position with numpy : 0.00866246223449707 nb_pixel_total : 63 time to create 1 rle with old method : 0.00010848045349121094 time for calcul the mask position with numpy : 0.008557558059692383 nb_pixel_total : 60 time to create 1 rle with old method : 0.00011086463928222656 time for calcul the mask position with numpy : 0.008683204650878906 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005867481231689453 time for calcul the mask position with numpy : 0.008537530899047852 nb_pixel_total : 571 time to create 1 rle with old method : 0.0006887912750244141 time for calcul the mask position with numpy : 0.008474588394165039 nb_pixel_total : 9 time to create 1 rle with old method : 0.00010752677917480469 time for calcul the mask position with numpy : 0.008435964584350586 nb_pixel_total : 272 time to create 1 rle with old method : 0.00030493736267089844 time for calcul the mask position with numpy : 0.008388757705688477 nb_pixel_total : 376 time to create 1 rle with old method : 0.0004239082336425781 time for calcul the mask position with numpy : 0.008486032485961914 nb_pixel_total : 460 time to create 1 rle with old method : 0.0005438327789306641 time for calcul the mask position with numpy : 0.008472919464111328 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005156993865966797 time for calcul the mask position with numpy : 0.00845646858215332 nb_pixel_total : 19 time to create 1 rle with old method : 5.078315734863281e-05 time for calcul the mask position with numpy : 0.009721517562866211 nb_pixel_total : 595 time to create 1 rle with old method : 0.0010216236114501953 time for calcul the mask position with numpy : 0.010212421417236328 nb_pixel_total : 274 time to create 1 rle with old method : 0.00036907196044921875 time for calcul the mask position with numpy : 0.008476734161376953 nb_pixel_total : 257 time to create 1 rle with old method : 0.00035834312438964844 time for calcul the mask position with numpy : 0.008487462997436523 nb_pixel_total : 42 time to create 1 rle with old method : 6.175041198730469e-05 time for calcul the mask position with numpy : 0.008467912673950195 nb_pixel_total : 146 time to create 1 rle with old method : 0.0001747608184814453 time for calcul the mask position with numpy : 0.008499383926391602 nb_pixel_total : 190 time to create 1 rle with old method : 0.00022935867309570312 create new chi : 1.3162858486175537 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 : 0.010565042495727539 batch 1 Loaded 91 chid ids of type : 4230 Number RLEs to save : 8289 TO DO : save crop sub photo not yet done ! save time : 0.49544692039489746 nb_obj : 94 nb_hashtags : 7 time to prepare the origin masks : 1.979466199874878 time for calcul the mask position with numpy : 0.07197451591491699 nb_pixel_total : 1819902 time to create 1 rle with new method : 0.11457276344299316 time for calcul the mask position with numpy : 0.007946014404296875 nb_pixel_total : 143 time to create 1 rle with old method : 0.00020933151245117188 time for calcul the mask position with numpy : 0.0077512264251708984 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002989768981933594 time for calcul the mask position with numpy : 0.007330894470214844 nb_pixel_total : 13 time to create 1 rle with old method : 5.269050598144531e-05 time for calcul the mask position with numpy : 0.007674694061279297 nb_pixel_total : 875 time to create 1 rle with old method : 0.0010128021240234375 time for calcul the mask position with numpy : 0.007309436798095703 nb_pixel_total : 855 time to create 1 rle with old method : 0.0010833740234375 time for calcul the mask position with numpy : 0.007759571075439453 nb_pixel_total : 49 time to create 1 rle with old method : 8.487701416015625e-05 time for calcul the mask position with numpy : 0.007446765899658203 nb_pixel_total : 95 time to create 1 rle with old method : 0.00023746490478515625 time for calcul the mask position with numpy : 0.007863998413085938 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002465248107910156 time for calcul the mask position with numpy : 0.007584810256958008 nb_pixel_total : 2584 time to create 1 rle with old method : 0.0028676986694335938 time for calcul the mask position with numpy : 0.007774829864501953 nb_pixel_total : 1 time to create 1 rle with old method : 3.2901763916015625e-05 time for calcul the mask position with numpy : 0.00814199447631836 nb_pixel_total : 9 time to create 1 rle with old method : 8.606910705566406e-05 time for calcul the mask position with numpy : 0.007905721664428711 nb_pixel_total : 53963 time to create 1 rle with old method : 0.05727577209472656 time for calcul the mask position with numpy : 0.007482051849365234 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004172325134277344 time for calcul the mask position with numpy : 0.007498502731323242 nb_pixel_total : 803 time to create 1 rle with old method : 0.0010187625885009766 time for calcul the mask position with numpy : 0.00775456428527832 nb_pixel_total : 2495 time to create 1 rle with old method : 0.002813100814819336 time for calcul the mask position with numpy : 0.007414817810058594 nb_pixel_total : 242 time to create 1 rle with old method : 0.0002968311309814453 time for calcul the mask position with numpy : 0.007451057434082031 nb_pixel_total : 824 time to create 1 rle with old method : 0.0009212493896484375 time for calcul the mask position with numpy : 0.007509469985961914 nb_pixel_total : 496 time to create 1 rle with old method : 0.0006208419799804688 time for calcul the mask position with numpy : 0.0075740814208984375 nb_pixel_total : 1277 time to create 1 rle with old method : 0.0015730857849121094 time for calcul the mask position with numpy : 0.0081634521484375 nb_pixel_total : 7936 time to create 1 rle with old method : 0.010347366333007812 time for calcul the mask position with numpy : 0.007439136505126953 nb_pixel_total : 202 time to create 1 rle with old method : 0.0002727508544921875 time for calcul the mask position with numpy : 0.007386922836303711 nb_pixel_total : 498 time to create 1 rle with old method : 0.0005931854248046875 time for calcul the mask position with numpy : 0.007047414779663086 nb_pixel_total : 704 time to create 1 rle with old method : 0.0008075237274169922 time for calcul the mask position with numpy : 0.007436513900756836 nb_pixel_total : 18883 time to create 1 rle with old method : 0.02037191390991211 time for calcul the mask position with numpy : 0.007287502288818359 nb_pixel_total : 818 time to create 1 rle with old method : 0.0008935928344726562 time for calcul the mask position with numpy : 0.007136106491088867 nb_pixel_total : 641 time to create 1 rle with old method : 0.0007612705230712891 time for calcul the mask position with numpy : 0.007286548614501953 nb_pixel_total : 1339 time to create 1 rle with old method : 0.0013895034790039062 time for calcul the mask position with numpy : 0.007311582565307617 nb_pixel_total : 28 time to create 1 rle with old method : 9.822845458984375e-05 time for calcul the mask position with numpy : 0.007312297821044922 nb_pixel_total : 253 time to create 1 rle with old method : 0.00032973289489746094 time for calcul the mask position with numpy : 0.0074884891510009766 nb_pixel_total : 208 time to create 1 rle with old method : 0.00027060508728027344 time for calcul the mask position with numpy : 0.007480144500732422 nb_pixel_total : 117 time to create 1 rle with old method : 0.00016951560974121094 time for calcul the mask position with numpy : 0.0073888301849365234 nb_pixel_total : 5403 time to create 1 rle with old method : 0.006258726119995117 time for calcul the mask position with numpy : 0.0061492919921875 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003292560577392578 time for calcul the mask position with numpy : 0.006152153015136719 nb_pixel_total : 4584 time to create 1 rle with old method : 0.005178928375244141 time for calcul the mask position with numpy : 0.006129264831542969 nb_pixel_total : 788 time to create 1 rle with old method : 0.0008759498596191406 time for calcul the mask position with numpy : 0.006134986877441406 nb_pixel_total : 398 time to create 1 rle with old method : 0.000457763671875 time for calcul the mask position with numpy : 0.006025552749633789 nb_pixel_total : 42 time to create 1 rle with old method : 0.00011444091796875 time for calcul the mask position with numpy : 0.005769252777099609 nb_pixel_total : 918 time to create 1 rle with old method : 0.0010559558868408203 time for calcul the mask position with numpy : 0.0062639713287353516 nb_pixel_total : 358 time to create 1 rle with old method : 0.0004229545593261719 time for calcul the mask position with numpy : 0.006103038787841797 nb_pixel_total : 844 time to create 1 rle with old method : 0.001050710678100586 time for calcul the mask position with numpy : 0.006200075149536133 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002048015594482422 time for calcul the mask position with numpy : 0.006287574768066406 nb_pixel_total : 345 time to create 1 rle with old method : 0.0004458427429199219 time for calcul the mask position with numpy : 0.006359100341796875 nb_pixel_total : 69 time to create 1 rle with old method : 0.00013828277587890625 time for calcul the mask position with numpy : 0.006985187530517578 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002758502960205078 time for calcul the mask position with numpy : 0.00624537467956543 nb_pixel_total : 2421 time to create 1 rle with old method : 0.002894878387451172 time for calcul the mask position with numpy : 0.006812572479248047 nb_pixel_total : 7230 time to create 1 rle with old method : 0.008095026016235352 time for calcul the mask position with numpy : 0.006379604339599609 nb_pixel_total : 1022 time to create 1 rle with old method : 0.0012259483337402344 time for calcul the mask position with numpy : 0.007429361343383789 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005612373352050781 time for calcul the mask position with numpy : 0.006533622741699219 nb_pixel_total : 1457 time to create 1 rle with old method : 0.0015683174133300781 time for calcul the mask position with numpy : 0.006199836730957031 nb_pixel_total : 25 time to create 1 rle with old method : 6.246566772460938e-05 time for calcul the mask position with numpy : 0.006194114685058594 nb_pixel_total : 327 time to create 1 rle with old method : 0.00039505958557128906 time for calcul the mask position with numpy : 0.006230831146240234 nb_pixel_total : 312 time to create 1 rle with old method : 0.0003864765167236328 time for calcul the mask position with numpy : 0.007073879241943359 nb_pixel_total : 1284 time to create 1 rle with old method : 0.0015099048614501953 time for calcul the mask position with numpy : 0.0065364837646484375 nb_pixel_total : 645 time to create 1 rle with old method : 0.0007300376892089844 time for calcul the mask position with numpy : 0.0076141357421875 nb_pixel_total : 106330 time to create 1 rle with old method : 0.11458969116210938 time for calcul the mask position with numpy : 0.006063699722290039 nb_pixel_total : 3560 time to create 1 rle with old method : 0.003911733627319336 time for calcul the mask position with numpy : 0.006196498870849609 nb_pixel_total : 3 time to create 1 rle with old method : 2.9325485229492188e-05 time for calcul the mask position with numpy : 0.0059816837310791016 nb_pixel_total : 109 time to create 1 rle with old method : 0.00015044212341308594 time for calcul the mask position with numpy : 0.0062558650970458984 nb_pixel_total : 261 time to create 1 rle with old method : 0.00029087066650390625 time for calcul the mask position with numpy : 0.0060961246490478516 nb_pixel_total : 75 time to create 1 rle with old method : 0.00011134147644042969 time for calcul the mask position with numpy : 0.006073713302612305 nb_pixel_total : 117 time to create 1 rle with old method : 0.0001399517059326172 time for calcul the mask position with numpy : 0.00600743293762207 nb_pixel_total : 342 time to create 1 rle with old method : 0.00037550926208496094 time for calcul the mask position with numpy : 0.006106138229370117 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006005764007568359 time for calcul the mask position with numpy : 0.006598711013793945 nb_pixel_total : 2550 time to create 1 rle with old method : 0.003439188003540039 time for calcul the mask position with numpy : 0.0062406063079833984 nb_pixel_total : 492 time to create 1 rle with old method : 0.0005829334259033203 time for calcul the mask position with numpy : 0.00587153434753418 nb_pixel_total : 254 time to create 1 rle with old method : 0.00027680397033691406 time for calcul the mask position with numpy : 0.006051301956176758 nb_pixel_total : 59 time to create 1 rle with old method : 8.630752563476562e-05 time for calcul the mask position with numpy : 0.0061910152435302734 nb_pixel_total : 517 time to create 1 rle with old method : 0.0006444454193115234 time for calcul the mask position with numpy : 0.0062656402587890625 nb_pixel_total : 709 time to create 1 rle with old method : 0.00083160400390625 time for calcul the mask position with numpy : 0.006573915481567383 nb_pixel_total : 494 time to create 1 rle with old method : 0.0005846023559570312 time for calcul the mask position with numpy : 0.0064318180084228516 nb_pixel_total : 2920 time to create 1 rle with old method : 0.003254413604736328 time for calcul the mask position with numpy : 0.006559133529663086 nb_pixel_total : 284 time to create 1 rle with old method : 0.0003483295440673828 time for calcul the mask position with numpy : 0.006539106369018555 nb_pixel_total : 701 time to create 1 rle with old method : 0.0008029937744140625 time for calcul the mask position with numpy : 0.006494998931884766 nb_pixel_total : 364 time to create 1 rle with old method : 0.00041985511779785156 time for calcul the mask position with numpy : 0.006480216979980469 nb_pixel_total : 434 time to create 1 rle with old method : 0.0005159378051757812 time for calcul the mask position with numpy : 0.006704807281494141 nb_pixel_total : 97 time to create 1 rle with old method : 0.00013303756713867188 time for calcul the mask position with numpy : 0.006634950637817383 nb_pixel_total : 718 time to create 1 rle with old method : 0.0008709430694580078 time for calcul the mask position with numpy : 0.0065195560455322266 nb_pixel_total : 228 time to create 1 rle with old method : 0.0002791881561279297 time for calcul the mask position with numpy : 0.006804227828979492 nb_pixel_total : 170 time to create 1 rle with old method : 0.0002892017364501953 time for calcul the mask position with numpy : 0.006636619567871094 nb_pixel_total : 51 time to create 1 rle with old method : 0.000110626220703125 time for calcul the mask position with numpy : 0.006273984909057617 nb_pixel_total : 673 time to create 1 rle with old method : 0.0007996559143066406 time for calcul the mask position with numpy : 0.006214618682861328 nb_pixel_total : 323 time to create 1 rle with old method : 0.0003883838653564453 time for calcul the mask position with numpy : 0.006349325180053711 nb_pixel_total : 59 time to create 1 rle with old method : 8.940696716308594e-05 time for calcul the mask position with numpy : 0.006317853927612305 nb_pixel_total : 324 time to create 1 rle with old method : 0.0003864765167236328 time for calcul the mask position with numpy : 0.00635528564453125 nb_pixel_total : 224 time to create 1 rle with old method : 0.0002753734588623047 time for calcul the mask position with numpy : 0.006190776824951172 nb_pixel_total : 72 time to create 1 rle with old method : 0.0001125335693359375 time for calcul the mask position with numpy : 0.006370067596435547 nb_pixel_total : 551 time to create 1 rle with old method : 0.0006513595581054688 time for calcul the mask position with numpy : 0.006554365158081055 nb_pixel_total : 717 time to create 1 rle with old method : 0.0007765293121337891 time for calcul the mask position with numpy : 0.006224632263183594 nb_pixel_total : 258 time to create 1 rle with old method : 0.00031495094299316406 time for calcul the mask position with numpy : 0.006328582763671875 nb_pixel_total : 383 time to create 1 rle with old method : 0.00045752525329589844 time for calcul the mask position with numpy : 0.008492469787597656 nb_pixel_total : 493 time to create 1 rle with old method : 0.0005915164947509766 time for calcul the mask position with numpy : 0.00846552848815918 nb_pixel_total : 453 time to create 1 rle with old method : 0.0005180835723876953 time for calcul the mask position with numpy : 0.008535146713256836 nb_pixel_total : 2 time to create 1 rle with old method : 1.6927719116210938e-05 time for calcul the mask position with numpy : 0.00847625732421875 nb_pixel_total : 338 time to create 1 rle with old method : 0.0004036426544189453 create new chi : 1.126558780670166 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 : 0.0014548301696777344 batch 1 Loaded 95 chid ids of type : 4230 Number RLEs to save : 8567 TO DO : save crop sub photo not yet done ! save time : 0.5363519191741943 nb_obj : 92 nb_hashtags : 6 time to prepare the origin masks : 1.4306066036224365 time for calcul the mask position with numpy : 0.03276562690734863 nb_pixel_total : 1816823 time to create 1 rle with new method : 0.7900359630584717 time for calcul the mask position with numpy : 0.006725788116455078 nb_pixel_total : 51118 time to create 1 rle with old method : 0.05845022201538086 time for calcul the mask position with numpy : 0.007302045822143555 nb_pixel_total : 144 time to create 1 rle with old method : 0.00019693374633789062 time for calcul the mask position with numpy : 0.007150411605834961 nb_pixel_total : 788 time to create 1 rle with old method : 0.0009295940399169922 time for calcul the mask position with numpy : 0.006604194641113281 nb_pixel_total : 60 time to create 1 rle with old method : 9.083747863769531e-05 time for calcul the mask position with numpy : 0.006965160369873047 nb_pixel_total : 48 time to create 1 rle with old method : 8.869171142578125e-05 time for calcul the mask position with numpy : 0.006635427474975586 nb_pixel_total : 658 time to create 1 rle with old method : 0.0007889270782470703 time for calcul the mask position with numpy : 0.006522178649902344 nb_pixel_total : 29 time to create 1 rle with old method : 8.344650268554688e-05 time for calcul the mask position with numpy : 0.0063092708587646484 nb_pixel_total : 898 time to create 1 rle with old method : 0.0010902881622314453 time for calcul the mask position with numpy : 0.0066339969635009766 nb_pixel_total : 2 time to create 1 rle with old method : 2.5510787963867188e-05 time for calcul the mask position with numpy : 0.006625652313232422 nb_pixel_total : 6 time to create 1 rle with old method : 2.9325485229492188e-05 time for calcul the mask position with numpy : 0.006621837615966797 nb_pixel_total : 2038 time to create 1 rle with old method : 0.002463102340698242 time for calcul the mask position with numpy : 0.006667613983154297 nb_pixel_total : 1 time to create 1 rle with old method : 8.368492126464844e-05 time for calcul the mask position with numpy : 0.00931406021118164 nb_pixel_total : 4803 time to create 1 rle with old method : 0.0071680545806884766 time for calcul the mask position with numpy : 0.007059335708618164 nb_pixel_total : 1303 time to create 1 rle with old method : 0.001558542251586914 time for calcul the mask position with numpy : 0.0069468021392822266 nb_pixel_total : 269 time to create 1 rle with old method : 0.00037169456481933594 time for calcul the mask position with numpy : 0.007242679595947266 nb_pixel_total : 2173 time to create 1 rle with old method : 0.0024170875549316406 time for calcul the mask position with numpy : 0.007197856903076172 nb_pixel_total : 1003 time to create 1 rle with old method : 0.0011777877807617188 time for calcul the mask position with numpy : 0.007024526596069336 nb_pixel_total : 810 time to create 1 rle with old method : 0.0009586811065673828 time for calcul the mask position with numpy : 0.006941795349121094 nb_pixel_total : 1058 time to create 1 rle with old method : 0.0012621879577636719 time for calcul the mask position with numpy : 0.00734400749206543 nb_pixel_total : 75 time to create 1 rle with old method : 0.0001690387725830078 time for calcul the mask position with numpy : 0.007138252258300781 nb_pixel_total : 486 time to create 1 rle with old method : 0.0005993843078613281 time for calcul the mask position with numpy : 0.007062673568725586 nb_pixel_total : 953 time to create 1 rle with old method : 0.0011479854583740234 time for calcul the mask position with numpy : 0.006483316421508789 nb_pixel_total : 1113 time to create 1 rle with old method : 0.0013184547424316406 time for calcul the mask position with numpy : 0.006966352462768555 nb_pixel_total : 2335 time to create 1 rle with old method : 0.0027587413787841797 time for calcul the mask position with numpy : 0.006822347640991211 nb_pixel_total : 4829 time to create 1 rle with old method : 0.0055539608001708984 time for calcul the mask position with numpy : 0.006683826446533203 nb_pixel_total : 7856 time to create 1 rle with old method : 0.009115934371948242 time for calcul the mask position with numpy : 0.0064737796783447266 nb_pixel_total : 188 time to create 1 rle with old method : 0.00023436546325683594 time for calcul the mask position with numpy : 0.006458759307861328 nb_pixel_total : 1318 time to create 1 rle with old method : 0.0014812946319580078 time for calcul the mask position with numpy : 0.00642085075378418 nb_pixel_total : 233 time to create 1 rle with old method : 0.0002777576446533203 time for calcul the mask position with numpy : 0.006052255630493164 nb_pixel_total : 478 time to create 1 rle with old method : 0.0005843639373779297 time for calcul the mask position with numpy : 0.0069501399993896484 nb_pixel_total : 5 time to create 1 rle with old method : 2.8848648071289062e-05 time for calcul the mask position with numpy : 0.006922245025634766 nb_pixel_total : 662 time to create 1 rle with old method : 0.0007724761962890625 time for calcul the mask position with numpy : 0.0067212581634521484 nb_pixel_total : 19258 time to create 1 rle with old method : 0.02104806900024414 time for calcul the mask position with numpy : 0.0070269107818603516 nb_pixel_total : 834 time to create 1 rle with old method : 0.0016217231750488281 time for calcul the mask position with numpy : 0.007312297821044922 nb_pixel_total : 792 time to create 1 rle with old method : 0.0013992786407470703 time for calcul the mask position with numpy : 0.007330179214477539 nb_pixel_total : 337 time to create 1 rle with old method : 0.0005958080291748047 time for calcul the mask position with numpy : 0.007241249084472656 nb_pixel_total : 1323 time to create 1 rle with old method : 0.002150297164916992 time for calcul the mask position with numpy : 0.007537364959716797 nb_pixel_total : 7065 time to create 1 rle with old method : 0.011462211608886719 time for calcul the mask position with numpy : 0.008146047592163086 nb_pixel_total : 164 time to create 1 rle with old method : 0.0004050731658935547 time for calcul the mask position with numpy : 0.011205673217773438 nb_pixel_total : 868 time to create 1 rle with old method : 0.001729726791381836 time for calcul the mask position with numpy : 0.007537126541137695 nb_pixel_total : 319 time to create 1 rle with old method : 0.0004227161407470703 time for calcul the mask position with numpy : 0.007613182067871094 nb_pixel_total : 4533 time to create 1 rle with old method : 0.005024909973144531 time for calcul the mask position with numpy : 0.007285594940185547 nb_pixel_total : 94 time to create 1 rle with old method : 0.00016951560974121094 time for calcul the mask position with numpy : 0.007025003433227539 nb_pixel_total : 772 time to create 1 rle with old method : 0.000986337661743164 time for calcul the mask position with numpy : 0.0072362422943115234 nb_pixel_total : 251 time to create 1 rle with old method : 0.00032019615173339844 time for calcul the mask position with numpy : 0.0073089599609375 nb_pixel_total : 597 time to create 1 rle with old method : 0.0007119178771972656 time for calcul the mask position with numpy : 0.006783485412597656 nb_pixel_total : 240 time to create 1 rle with old method : 0.00036072731018066406 time for calcul the mask position with numpy : 0.006633758544921875 nb_pixel_total : 573 time to create 1 rle with old method : 0.0006966590881347656 time for calcul the mask position with numpy : 0.007891416549682617 nb_pixel_total : 61 time to create 1 rle with old method : 9.703636169433594e-05 time for calcul the mask position with numpy : 0.007073879241943359 nb_pixel_total : 2347 time to create 1 rle with old method : 0.0026907920837402344 time for calcul the mask position with numpy : 0.0070192813873291016 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004303455352783203 time for calcul the mask position with numpy : 0.00685572624206543 nb_pixel_total : 1397 time to create 1 rle with old method : 0.0016541481018066406 time for calcul the mask position with numpy : 0.006789684295654297 nb_pixel_total : 200 time to create 1 rle with old method : 0.00025177001953125 time for calcul the mask position with numpy : 0.006567716598510742 nb_pixel_total : 289 time to create 1 rle with old method : 0.00033164024353027344 time for calcul the mask position with numpy : 0.006793975830078125 nb_pixel_total : 1392 time to create 1 rle with old method : 0.0016093254089355469 time for calcul the mask position with numpy : 0.007174015045166016 nb_pixel_total : 106309 time to create 1 rle with old method : 0.11509490013122559 time for calcul the mask position with numpy : 0.007053375244140625 nb_pixel_total : 87 time to create 1 rle with old method : 0.00012636184692382812 time for calcul the mask position with numpy : 0.006683349609375 nb_pixel_total : 3504 time to create 1 rle with old method : 0.003988981246948242 time for calcul the mask position with numpy : 0.006580829620361328 nb_pixel_total : 111 time to create 1 rle with old method : 0.00017189979553222656 time for calcul the mask position with numpy : 0.009788274765014648 nb_pixel_total : 370 time to create 1 rle with old method : 0.00045013427734375 time for calcul the mask position with numpy : 0.007693052291870117 nb_pixel_total : 246 time to create 1 rle with old method : 0.00030040740966796875 time for calcul the mask position with numpy : 0.007355213165283203 nb_pixel_total : 54 time to create 1 rle with old method : 9.1552734375e-05 time for calcul the mask position with numpy : 0.0076580047607421875 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006170272827148438 time for calcul the mask position with numpy : 0.008477449417114258 nb_pixel_total : 779 time to create 1 rle with old method : 0.0008952617645263672 time for calcul the mask position with numpy : 0.00766754150390625 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006287097930908203 time for calcul the mask position with numpy : 0.008662700653076172 nb_pixel_total : 637 time to create 1 rle with old method : 0.0009038448333740234 time for calcul the mask position with numpy : 0.008652687072753906 nb_pixel_total : 418 time to create 1 rle with old method : 0.0006742477416992188 time for calcul the mask position with numpy : 0.00859379768371582 nb_pixel_total : 8 time to create 1 rle with old method : 5.0067901611328125e-05 time for calcul the mask position with numpy : 0.006864786148071289 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004343986511230469 time for calcul the mask position with numpy : 0.007329702377319336 nb_pixel_total : 2440 time to create 1 rle with old method : 0.0028657913208007812 time for calcul the mask position with numpy : 0.007144927978515625 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005195140838623047 time for calcul the mask position with numpy : 0.007063150405883789 nb_pixel_total : 96 time to create 1 rle with old method : 0.00016498565673828125 time for calcul the mask position with numpy : 0.009467124938964844 nb_pixel_total : 105 time to create 1 rle with old method : 0.0001804828643798828 time for calcul the mask position with numpy : 0.0077092647552490234 nb_pixel_total : 1360 time to create 1 rle with old method : 0.0016129016876220703 time for calcul the mask position with numpy : 0.0077419281005859375 nb_pixel_total : 638 time to create 1 rle with old method : 0.0007784366607666016 time for calcul the mask position with numpy : 0.007575035095214844 nb_pixel_total : 320 time to create 1 rle with old method : 0.0004782676696777344 time for calcul the mask position with numpy : 0.00778651237487793 nb_pixel_total : 713 time to create 1 rle with old method : 0.0008580684661865234 time for calcul the mask position with numpy : 0.0075225830078125 nb_pixel_total : 335 time to create 1 rle with old method : 0.00041985511779785156 time for calcul the mask position with numpy : 0.007310152053833008 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005092620849609375 time for calcul the mask position with numpy : 0.007502079010009766 nb_pixel_total : 79 time to create 1 rle with old method : 0.00012302398681640625 time for calcul the mask position with numpy : 0.006967306137084961 nb_pixel_total : 426 time to create 1 rle with old method : 0.0005273818969726562 time for calcul the mask position with numpy : 0.0069735050201416016 nb_pixel_total : 621 time to create 1 rle with old method : 0.0007145404815673828 time for calcul the mask position with numpy : 0.007108926773071289 nb_pixel_total : 236 time to create 1 rle with old method : 0.00029730796813964844 time for calcul the mask position with numpy : 0.007578372955322266 nb_pixel_total : 21 time to create 1 rle with old method : 6.103515625e-05 time for calcul the mask position with numpy : 0.007188081741333008 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002646446228027344 time for calcul the mask position with numpy : 0.0064241886138916016 nb_pixel_total : 498 time to create 1 rle with old method : 0.0005757808685302734 time for calcul the mask position with numpy : 0.006405830383300781 nb_pixel_total : 417 time to create 1 rle with old method : 0.0004718303680419922 time for calcul the mask position with numpy : 0.006696462631225586 nb_pixel_total : 221 time to create 1 rle with old method : 0.00027680397033691406 time for calcul the mask position with numpy : 0.006505727767944336 nb_pixel_total : 1119 time to create 1 rle with old method : 0.0012981891632080078 time for calcul the mask position with numpy : 0.006593465805053711 nb_pixel_total : 135 time to create 1 rle with old method : 0.0001690387725830078 time for calcul the mask position with numpy : 0.006535530090332031 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002455711364746094 time for calcul the mask position with numpy : 0.006941795349121094 nb_pixel_total : 53 time to create 1 rle with old method : 7.891654968261719e-05 create new chi : 1.793973445892334 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 : 0.0014770030975341797 batch 1 Loaded 93 chid ids of type : 4230 Number RLEs to save : 9236 TO DO : save crop sub photo not yet done ! save time : 0.8933026790618896 nb_obj : 94 nb_hashtags : 7 time to prepare the origin masks : 1.7676105499267578 time for calcul the mask position with numpy : 0.08934950828552246 nb_pixel_total : 1812042 time to create 1 rle with new method : 0.29797792434692383 time for calcul the mask position with numpy : 0.014476299285888672 nb_pixel_total : 4061 time to create 1 rle with old method : 0.00645136833190918 time for calcul the mask position with numpy : 0.014904499053955078 nb_pixel_total : 2464 time to create 1 rle with old method : 0.003928184509277344 time for calcul the mask position with numpy : 0.015400886535644531 nb_pixel_total : 828 time to create 1 rle with old method : 0.0015535354614257812 time for calcul the mask position with numpy : 0.013557672500610352 nb_pixel_total : 806 time to create 1 rle with old method : 0.0010159015655517578 time for calcul the mask position with numpy : 0.013601064682006836 nb_pixel_total : 128 time to create 1 rle with old method : 0.00028634071350097656 time for calcul the mask position with numpy : 0.01345968246459961 nb_pixel_total : 10 time to create 1 rle with old method : 6.079673767089844e-05 time for calcul the mask position with numpy : 0.013268470764160156 nb_pixel_total : 28 time to create 1 rle with old method : 0.00023245811462402344 time for calcul the mask position with numpy : 0.012468814849853516 nb_pixel_total : 75 time to create 1 rle with old method : 0.00015687942504882812 time for calcul the mask position with numpy : 0.014127731323242188 nb_pixel_total : 2646 time to create 1 rle with old method : 0.003130197525024414 time for calcul the mask position with numpy : 0.014117956161499023 nb_pixel_total : 6 time to create 1 rle with old method : 8.678436279296875e-05 time for calcul the mask position with numpy : 0.013951301574707031 nb_pixel_total : 2 time to create 1 rle with old method : 5.507469177246094e-05 time for calcul the mask position with numpy : 0.014585018157958984 nb_pixel_total : 53521 time to create 1 rle with old method : 0.06741738319396973 time for calcul the mask position with numpy : 0.014205694198608398 nb_pixel_total : 892 time to create 1 rle with old method : 0.0011327266693115234 time for calcul the mask position with numpy : 0.013878822326660156 nb_pixel_total : 3118 time to create 1 rle with old method : 0.0037844181060791016 time for calcul the mask position with numpy : 0.020550966262817383 nb_pixel_total : 363 time to create 1 rle with old method : 0.0004978179931640625 time for calcul the mask position with numpy : 0.013800382614135742 nb_pixel_total : 1079 time to create 1 rle with old method : 0.0014841556549072266 time for calcul the mask position with numpy : 0.013903617858886719 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006101131439208984 time for calcul the mask position with numpy : 0.013855695724487305 nb_pixel_total : 413 time to create 1 rle with old method : 0.000598907470703125 time for calcul the mask position with numpy : 0.01359868049621582 nb_pixel_total : 485 time to create 1 rle with old method : 0.0010273456573486328 time for calcul the mask position with numpy : 0.013606071472167969 nb_pixel_total : 5 time to create 1 rle with old method : 8.368492126464844e-05 time for calcul the mask position with numpy : 0.01242828369140625 nb_pixel_total : 4768 time to create 1 rle with old method : 0.005800008773803711 time for calcul the mask position with numpy : 0.008117914199829102 nb_pixel_total : 8550 time to create 1 rle with old method : 0.010039091110229492 time for calcul the mask position with numpy : 0.008838891983032227 nb_pixel_total : 807 time to create 1 rle with old method : 0.0010106563568115234 time for calcul the mask position with numpy : 0.008452177047729492 nb_pixel_total : 485 time to create 1 rle with old method : 0.0009191036224365234 time for calcul the mask position with numpy : 0.010746955871582031 nb_pixel_total : 19360 time to create 1 rle with old method : 0.14616155624389648 time for calcul the mask position with numpy : 0.007960081100463867 nb_pixel_total : 900 time to create 1 rle with old method : 0.001104116439819336 time for calcul the mask position with numpy : 0.008583545684814453 nb_pixel_total : 12 time to create 1 rle with old method : 0.00010037422180175781 time for calcul the mask position with numpy : 0.010138750076293945 nb_pixel_total : 1033 time to create 1 rle with old method : 0.0020895004272460938 time for calcul the mask position with numpy : 0.010416269302368164 nb_pixel_total : 312 time to create 1 rle with old method : 0.0006639957427978516 time for calcul the mask position with numpy : 0.011493921279907227 nb_pixel_total : 66 time to create 1 rle with old method : 0.00020003318786621094 time for calcul the mask position with numpy : 0.010217666625976562 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0028319358825683594 time for calcul the mask position with numpy : 0.00975346565246582 nb_pixel_total : 785 time to create 1 rle with old method : 0.0014271736145019531 time for calcul the mask position with numpy : 0.009238958358764648 nb_pixel_total : 195 time to create 1 rle with old method : 0.0005426406860351562 time for calcul the mask position with numpy : 0.01855158805847168 nb_pixel_total : 251 time to create 1 rle with old method : 0.0006093978881835938 time for calcul the mask position with numpy : 0.01814103126525879 nb_pixel_total : 4667 time to create 1 rle with old method : 0.008816242218017578 time for calcul the mask position with numpy : 0.01961517333984375 nb_pixel_total : 746 time to create 1 rle with old method : 0.0016982555389404297 time for calcul the mask position with numpy : 0.018959999084472656 nb_pixel_total : 1179 time to create 1 rle with old method : 0.0027976036071777344 time for calcul the mask position with numpy : 0.019324779510498047 nb_pixel_total : 56 time to create 1 rle with old method : 0.0003504753112792969 time for calcul the mask position with numpy : 0.026617765426635742 nb_pixel_total : 811 time to create 1 rle with old method : 0.001688241958618164 time for calcul the mask position with numpy : 0.01760077476501465 nb_pixel_total : 702 time to create 1 rle with old method : 0.0013551712036132812 time for calcul the mask position with numpy : 0.01537179946899414 nb_pixel_total : 840 time to create 1 rle with old method : 0.0010612010955810547 time for calcul the mask position with numpy : 0.013764619827270508 nb_pixel_total : 43 time to create 1 rle with old method : 0.0001571178436279297 time for calcul the mask position with numpy : 0.014000415802001953 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003514289855957031 time for calcul the mask position with numpy : 0.013731241226196289 nb_pixel_total : 734 time to create 1 rle with old method : 0.0009379386901855469 time for calcul the mask position with numpy : 0.013355016708374023 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002262592315673828 time for calcul the mask position with numpy : 0.013203620910644531 nb_pixel_total : 2434 time to create 1 rle with old method : 0.002858400344848633 time for calcul the mask position with numpy : 0.013611316680908203 nb_pixel_total : 9470 time to create 1 rle with old method : 0.01041269302368164 time for calcul the mask position with numpy : 0.013545036315917969 nb_pixel_total : 323 time to create 1 rle with old method : 0.00040984153747558594 time for calcul the mask position with numpy : 0.01260828971862793 nb_pixel_total : 1369 time to create 1 rle with old method : 0.0016367435455322266 time for calcul the mask position with numpy : 0.0102386474609375 nb_pixel_total : 304 time to create 1 rle with old method : 0.0003800392150878906 time for calcul the mask position with numpy : 0.01016092300415039 nb_pixel_total : 1223 time to create 1 rle with old method : 0.0013926029205322266 time for calcul the mask position with numpy : 0.010826587677001953 nb_pixel_total : 106272 time to create 1 rle with old method : 0.11574053764343262 time for calcul the mask position with numpy : 0.011629819869995117 nb_pixel_total : 1764 time to create 1 rle with old method : 0.0021092891693115234 time for calcul the mask position with numpy : 0.011469841003417969 nb_pixel_total : 3585 time to create 1 rle with old method : 0.004150390625 time for calcul the mask position with numpy : 0.011421442031860352 nb_pixel_total : 56 time to create 1 rle with old method : 9.989738464355469e-05 time for calcul the mask position with numpy : 0.011113405227661133 nb_pixel_total : 115 time to create 1 rle with old method : 0.00016379356384277344 time for calcul the mask position with numpy : 0.015341997146606445 nb_pixel_total : 296 time to create 1 rle with old method : 0.0003688335418701172 time for calcul the mask position with numpy : 0.01139974594116211 nb_pixel_total : 84 time to create 1 rle with old method : 0.0001285076141357422 time for calcul the mask position with numpy : 0.011228799819946289 nb_pixel_total : 142 time to create 1 rle with old method : 0.0001938343048095703 time for calcul the mask position with numpy : 0.011142969131469727 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004353523254394531 time for calcul the mask position with numpy : 0.01230001449584961 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005528926849365234 time for calcul the mask position with numpy : 0.011731147766113281 nb_pixel_total : 27 time to create 1 rle with old method : 6.985664367675781e-05 time for calcul the mask position with numpy : 0.012234926223754883 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003147125244140625 time for calcul the mask position with numpy : 0.013267993927001953 nb_pixel_total : 596 time to create 1 rle with old method : 0.0008039474487304688 time for calcul the mask position with numpy : 0.013214826583862305 nb_pixel_total : 430 time to create 1 rle with old method : 0.0005886554718017578 time for calcul the mask position with numpy : 0.014351367950439453 nb_pixel_total : 483 time to create 1 rle with old method : 0.0007221698760986328 time for calcul the mask position with numpy : 0.016905784606933594 nb_pixel_total : 1112 time to create 1 rle with old method : 0.0018906593322753906 time for calcul the mask position with numpy : 0.015690326690673828 nb_pixel_total : 442 time to create 1 rle with old method : 0.0007536411285400391 time for calcul the mask position with numpy : 0.015184640884399414 nb_pixel_total : 263 time to create 1 rle with old method : 0.0006303787231445312 time for calcul the mask position with numpy : 0.016210079193115234 nb_pixel_total : 356 time to create 1 rle with old method : 0.0005097389221191406 time for calcul the mask position with numpy : 0.014174938201904297 nb_pixel_total : 13 time to create 1 rle with old method : 7.128715515136719e-05 time for calcul the mask position with numpy : 0.013143301010131836 nb_pixel_total : 2358 time to create 1 rle with old method : 0.0027756690979003906 time for calcul the mask position with numpy : 0.011977434158325195 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005438327789306641 time for calcul the mask position with numpy : 0.011858224868774414 nb_pixel_total : 23 time to create 1 rle with old method : 6.246566772460938e-05 time for calcul the mask position with numpy : 0.016552448272705078 nb_pixel_total : 86 time to create 1 rle with old method : 0.00017452239990234375 time for calcul the mask position with numpy : 0.013633251190185547 nb_pixel_total : 567 time to create 1 rle with old method : 0.0008628368377685547 time for calcul the mask position with numpy : 0.01322793960571289 nb_pixel_total : 123 time to create 1 rle with old method : 0.00018978118896484375 time for calcul the mask position with numpy : 0.012472152709960938 nb_pixel_total : 122 time to create 1 rle with old method : 0.00018453598022460938 time for calcul the mask position with numpy : 0.011645317077636719 nb_pixel_total : 707 time to create 1 rle with old method : 0.0008463859558105469 time for calcul the mask position with numpy : 0.01238107681274414 nb_pixel_total : 10 time to create 1 rle with old method : 0.00010728836059570312 time for calcul the mask position with numpy : 0.013423442840576172 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005304813385009766 time for calcul the mask position with numpy : 0.012834310531616211 nb_pixel_total : 649 time to create 1 rle with old method : 0.0009052753448486328 time for calcul the mask position with numpy : 0.01289987564086914 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005433559417724609 time for calcul the mask position with numpy : 0.012539148330688477 nb_pixel_total : 72 time to create 1 rle with old method : 0.0001347064971923828 time for calcul the mask position with numpy : 0.012366056442260742 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005125999450683594 time for calcul the mask position with numpy : 0.012297391891479492 nb_pixel_total : 664 time to create 1 rle with old method : 0.0008301734924316406 time for calcul the mask position with numpy : 0.012310504913330078 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003211498260498047 time for calcul the mask position with numpy : 0.013676643371582031 nb_pixel_total : 394 time to create 1 rle with old method : 0.0009407997131347656 time for calcul the mask position with numpy : 0.014009714126586914 nb_pixel_total : 108 time to create 1 rle with old method : 0.0002651214599609375 time for calcul the mask position with numpy : 0.014305353164672852 nb_pixel_total : 465 time to create 1 rle with old method : 0.0005559921264648438 time for calcul the mask position with numpy : 0.012629032135009766 nb_pixel_total : 455 time to create 1 rle with old method : 0.0005528926849365234 time for calcul the mask position with numpy : 0.009843587875366211 nb_pixel_total : 9 time to create 1 rle with old method : 4.410743713378906e-05 time for calcul the mask position with numpy : 0.009045839309692383 nb_pixel_total : 122 time to create 1 rle with old method : 0.00018072128295898438 time for calcul the mask position with numpy : 0.008714914321899414 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003020763397216797 create new chi : 2.0959157943725586 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 : 0.0019342899322509766 batch 1 Loaded 95 chid ids of type : 4230 Number RLEs to save : 9615 TO DO : save crop sub photo not yet done ! save time : 0.7080316543579102 nb_obj : 98 nb_hashtags : 6 time to prepare the origin masks : 1.5671696662902832 time for calcul the mask position with numpy : 0.17332196235656738 nb_pixel_total : 1768120 time to create 1 rle with new method : 0.0965123176574707 time for calcul the mask position with numpy : 0.011406660079956055 nb_pixel_total : 12482 time to create 1 rle with old method : 0.014046669006347656 time for calcul the mask position with numpy : 0.007079124450683594 nb_pixel_total : 52937 time to create 1 rle with old method : 0.05790305137634277 time for calcul the mask position with numpy : 0.006597757339477539 nb_pixel_total : 134 time to create 1 rle with old method : 0.00018334388732910156 time for calcul the mask position with numpy : 0.010449886322021484 nb_pixel_total : 797 time to create 1 rle with old method : 0.0009195804595947266 time for calcul the mask position with numpy : 0.010544776916503906 nb_pixel_total : 84 time to create 1 rle with old method : 0.00012636184692382812 time for calcul the mask position with numpy : 0.01046133041381836 nb_pixel_total : 167 time to create 1 rle with old method : 0.00023245811462402344 time for calcul the mask position with numpy : 0.010242938995361328 nb_pixel_total : 32 time to create 1 rle with old method : 9.083747863769531e-05 time for calcul the mask position with numpy : 0.009917497634887695 nb_pixel_total : 682 time to create 1 rle with old method : 0.000804901123046875 time for calcul the mask position with numpy : 0.010622024536132812 nb_pixel_total : 52 time to create 1 rle with old method : 0.00012445449829101562 time for calcul the mask position with numpy : 0.010938644409179688 nb_pixel_total : 2740 time to create 1 rle with old method : 0.003320932388305664 time for calcul the mask position with numpy : 0.010501384735107422 nb_pixel_total : 4 time to create 1 rle with old method : 2.9087066650390625e-05 time for calcul the mask position with numpy : 0.010265111923217773 nb_pixel_total : 12 time to create 1 rle with old method : 4.792213439941406e-05 time for calcul the mask position with numpy : 0.010359764099121094 nb_pixel_total : 4295 time to create 1 rle with old method : 0.004763364791870117 time for calcul the mask position with numpy : 0.010112762451171875 nb_pixel_total : 360 time to create 1 rle with old method : 0.00045037269592285156 time for calcul the mask position with numpy : 0.01007843017578125 nb_pixel_total : 8026 time to create 1 rle with old method : 0.008612871170043945 time for calcul the mask position with numpy : 0.010287284851074219 nb_pixel_total : 306 time to create 1 rle with old method : 0.000415802001953125 time for calcul the mask position with numpy : 0.01048588752746582 nb_pixel_total : 300 time to create 1 rle with old method : 0.0003800392150878906 time for calcul the mask position with numpy : 0.010138273239135742 nb_pixel_total : 2134 time to create 1 rle with old method : 0.0024704933166503906 time for calcul the mask position with numpy : 0.010157108306884766 nb_pixel_total : 879 time to create 1 rle with old method : 0.00104522705078125 time for calcul the mask position with numpy : 0.01029348373413086 nb_pixel_total : 528 time to create 1 rle with old method : 0.0005803108215332031 time for calcul the mask position with numpy : 0.010041952133178711 nb_pixel_total : 234 time to create 1 rle with old method : 0.0003044605255126953 time for calcul the mask position with numpy : 0.010123968124389648 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006036758422851562 time for calcul the mask position with numpy : 0.01022481918334961 nb_pixel_total : 765 time to create 1 rle with old method : 0.0009250640869140625 time for calcul the mask position with numpy : 0.010500907897949219 nb_pixel_total : 4562 time to create 1 rle with old method : 0.0053558349609375 time for calcul the mask position with numpy : 0.010190725326538086 nb_pixel_total : 7323 time to create 1 rle with old method : 0.007911920547485352 time for calcul the mask position with numpy : 0.010283470153808594 nb_pixel_total : 7651 time to create 1 rle with old method : 0.008408784866333008 time for calcul the mask position with numpy : 0.010359525680541992 nb_pixel_total : 185 time to create 1 rle with old method : 0.00023436546325683594 time for calcul the mask position with numpy : 0.01044774055480957 nb_pixel_total : 988 time to create 1 rle with old method : 0.0011341571807861328 time for calcul the mask position with numpy : 0.006423473358154297 nb_pixel_total : 610 time to create 1 rle with old method : 0.0007281303405761719 time for calcul the mask position with numpy : 0.006371498107910156 nb_pixel_total : 903 time to create 1 rle with old method : 0.0010683536529541016 time for calcul the mask position with numpy : 0.0062541961669921875 nb_pixel_total : 657 time to create 1 rle with old method : 0.0007610321044921875 time for calcul the mask position with numpy : 0.01057291030883789 nb_pixel_total : 168 time to create 1 rle with old method : 0.000225067138671875 time for calcul the mask position with numpy : 0.006514072418212891 nb_pixel_total : 16960 time to create 1 rle with old method : 0.025833845138549805 time for calcul the mask position with numpy : 0.006444692611694336 nb_pixel_total : 784 time to create 1 rle with old method : 0.0009102821350097656 time for calcul the mask position with numpy : 0.006451845169067383 nb_pixel_total : 1649 time to create 1 rle with old method : 0.0019292831420898438 time for calcul the mask position with numpy : 0.0064618587493896484 nb_pixel_total : 1141 time to create 1 rle with old method : 0.0013632774353027344 time for calcul the mask position with numpy : 0.00637054443359375 nb_pixel_total : 312 time to create 1 rle with old method : 0.00037169456481933594 time for calcul the mask position with numpy : 0.006429195404052734 nb_pixel_total : 1336 time to create 1 rle with old method : 0.0015480518341064453 time for calcul the mask position with numpy : 0.0064661502838134766 nb_pixel_total : 33 time to create 1 rle with old method : 0.00010418891906738281 time for calcul the mask position with numpy : 0.006376028060913086 nb_pixel_total : 147 time to create 1 rle with old method : 0.0001938343048095703 time for calcul the mask position with numpy : 0.006523847579956055 nb_pixel_total : 797 time to create 1 rle with old method : 0.0009529590606689453 time for calcul the mask position with numpy : 0.006476879119873047 nb_pixel_total : 6811 time to create 1 rle with old method : 0.007719993591308594 time for calcul the mask position with numpy : 0.0064792633056640625 nb_pixel_total : 771 time to create 1 rle with old method : 0.0008916854858398438 time for calcul the mask position with numpy : 0.00677943229675293 nb_pixel_total : 835 time to create 1 rle with old method : 0.0009748935699462891 time for calcul the mask position with numpy : 0.0067310333251953125 nb_pixel_total : 4693 time to create 1 rle with old method : 0.0052471160888671875 time for calcul the mask position with numpy : 0.006903648376464844 nb_pixel_total : 12 time to create 1 rle with old method : 6.29425048828125e-05 time for calcul the mask position with numpy : 0.0073163509368896484 nb_pixel_total : 184 time to create 1 rle with old method : 0.00037360191345214844 time for calcul the mask position with numpy : 0.007037639617919922 nb_pixel_total : 33 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.0069196224212646484 nb_pixel_total : 757 time to create 1 rle with old method : 0.001245260238647461 time for calcul the mask position with numpy : 0.006927967071533203 nb_pixel_total : 877 time to create 1 rle with old method : 0.0014545917510986328 time for calcul the mask position with numpy : 0.006869316101074219 nb_pixel_total : 41 time to create 1 rle with old method : 9.846687316894531e-05 time for calcul the mask position with numpy : 0.006947755813598633 nb_pixel_total : 2459 time to create 1 rle with old method : 0.003872394561767578 time for calcul the mask position with numpy : 0.010686874389648438 nb_pixel_total : 386 time to create 1 rle with old method : 0.0006358623504638672 time for calcul the mask position with numpy : 0.006619930267333984 nb_pixel_total : 1248 time to create 1 rle with old method : 0.0019822120666503906 time for calcul the mask position with numpy : 0.0066225528717041016 nb_pixel_total : 236 time to create 1 rle with old method : 0.0004220008850097656 time for calcul the mask position with numpy : 0.0068018436431884766 nb_pixel_total : 302 time to create 1 rle with old method : 0.0005199909210205078 time for calcul the mask position with numpy : 0.0064868927001953125 nb_pixel_total : 794 time to create 1 rle with old method : 0.0009329319000244141 time for calcul the mask position with numpy : 0.006343364715576172 nb_pixel_total : 1393 time to create 1 rle with old method : 0.0016376972198486328 time for calcul the mask position with numpy : 0.007125377655029297 nb_pixel_total : 106264 time to create 1 rle with old method : 0.14277267456054688 time for calcul the mask position with numpy : 0.006923675537109375 nb_pixel_total : 3616 time to create 1 rle with old method : 0.005733489990234375 time for calcul the mask position with numpy : 0.006888389587402344 nb_pixel_total : 123 time to create 1 rle with old method : 0.0002276897430419922 time for calcul the mask position with numpy : 0.006568193435668945 nb_pixel_total : 21211 time to create 1 rle with old method : 0.02315521240234375 time for calcul the mask position with numpy : 0.006440162658691406 nb_pixel_total : 158 time to create 1 rle with old method : 0.00020432472229003906 time for calcul the mask position with numpy : 0.006236553192138672 nb_pixel_total : 321 time to create 1 rle with old method : 0.00041961669921875 time for calcul the mask position with numpy : 0.006324291229248047 nb_pixel_total : 2954 time to create 1 rle with old method : 0.003411531448364258 time for calcul the mask position with numpy : 0.006417512893676758 nb_pixel_total : 236 time to create 1 rle with old method : 0.00028443336486816406 time for calcul the mask position with numpy : 0.010407447814941406 nb_pixel_total : 28 time to create 1 rle with old method : 6.29425048828125e-05 time for calcul the mask position with numpy : 0.01032257080078125 nb_pixel_total : 526 time to create 1 rle with old method : 0.0006303787231445312 time for calcul the mask position with numpy : 0.01080322265625 nb_pixel_total : 780 time to create 1 rle with old method : 0.0009179115295410156 time for calcul the mask position with numpy : 0.010643243789672852 nb_pixel_total : 506 time to create 1 rle with old method : 0.0005781650543212891 time for calcul the mask position with numpy : 0.012209177017211914 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005776882171630859 time for calcul the mask position with numpy : 0.010827779769897461 nb_pixel_total : 495 time to create 1 rle with old method : 0.0005929470062255859 time for calcul the mask position with numpy : 0.010288238525390625 nb_pixel_total : 361 time to create 1 rle with old method : 0.000431060791015625 time for calcul the mask position with numpy : 0.01064300537109375 nb_pixel_total : 5 time to create 1 rle with old method : 3.123283386230469e-05 time for calcul the mask position with numpy : 0.011045217514038086 nb_pixel_total : 2637 time to create 1 rle with old method : 0.0029675960540771484 time for calcul the mask position with numpy : 0.01105046272277832 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005285739898681641 time for calcul the mask position with numpy : 0.011002302169799805 nb_pixel_total : 58 time to create 1 rle with old method : 9.679794311523438e-05 time for calcul the mask position with numpy : 0.011684894561767578 nb_pixel_total : 131 time to create 1 rle with old method : 0.0001761913299560547 time for calcul the mask position with numpy : 0.010827302932739258 nb_pixel_total : 976 time to create 1 rle with old method : 0.0011298656463623047 time for calcul the mask position with numpy : 0.017154216766357422 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004036426544189453 time for calcul the mask position with numpy : 0.010586977005004883 nb_pixel_total : 24 time to create 1 rle with old method : 7.891654968261719e-05 time for calcul the mask position with numpy : 0.011340856552124023 nb_pixel_total : 684 time to create 1 rle with old method : 0.0008246898651123047 time for calcul the mask position with numpy : 0.010449409484863281 nb_pixel_total : 335 time to create 1 rle with old method : 0.0003914833068847656 time for calcul the mask position with numpy : 0.010969400405883789 nb_pixel_total : 84 time to create 1 rle with old method : 0.00012183189392089844 time for calcul the mask position with numpy : 0.010499715805053711 nb_pixel_total : 318 time to create 1 rle with old method : 0.00038814544677734375 time for calcul the mask position with numpy : 0.01058650016784668 nb_pixel_total : 596 time to create 1 rle with old method : 0.0007178783416748047 time for calcul the mask position with numpy : 0.010804891586303711 nb_pixel_total : 20 time to create 1 rle with old method : 5.5789947509765625e-05 time for calcul the mask position with numpy : 0.01210474967956543 nb_pixel_total : 667 time to create 1 rle with old method : 0.0010027885437011719 time for calcul the mask position with numpy : 0.011368513107299805 nb_pixel_total : 282 time to create 1 rle with old method : 0.0004291534423828125 time for calcul the mask position with numpy : 0.011068344116210938 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005502700805664062 time for calcul the mask position with numpy : 0.01073002815246582 nb_pixel_total : 308 time to create 1 rle with old method : 0.0004057884216308594 time for calcul the mask position with numpy : 0.010486841201782227 nb_pixel_total : 463 time to create 1 rle with old method : 0.0005660057067871094 time for calcul the mask position with numpy : 0.010400772094726562 nb_pixel_total : 469 time to create 1 rle with old method : 0.0005428791046142578 time for calcul the mask position with numpy : 0.010432243347167969 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005109310150146484 time for calcul the mask position with numpy : 0.010371923446655273 nb_pixel_total : 22 time to create 1 rle with old method : 7.009506225585938e-05 time for calcul the mask position with numpy : 0.008455753326416016 nb_pixel_total : 708 time to create 1 rle with old method : 0.0008397102355957031 time for calcul the mask position with numpy : 0.008863687515258789 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005085468292236328 time for calcul the mask position with numpy : 0.00857853889465332 nb_pixel_total : 226 time to create 1 rle with old method : 0.00028252601623535156 create new chi : 1.5526630878448486 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 : 0.001956462860107422 batch 1 Loaded 99 chid ids of type : 4230 Number RLEs to save : 11446 TO DO : save crop sub photo not yet done ! save time : 1.0462169647216797 map_output_result : {1337118339: (0.0, 'Should be the crop_list due to order', 0.0), 1337118336: (0.0, 'Should be the crop_list due to order', 0.0), 1337118333: (0.0, 'Should be the crop_list due to order', 0.0), 1337118331: (0.0, 'Should be the crop_list due to order', 0.0), 1337118329: (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 [1337118339, 1337118336, 1337118333, 1337118331, 1337118329] Looping around the photos to save general results len do output : 5 /1337118339.Didn't retrieve data . /1337118336.Didn't retrieve data . /1337118333.Didn't retrieve data . /1337118331.Didn't retrieve data . /1337118329.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, '2579689') ('4234', '20479196', '1337118339', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118336', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118333', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118331', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118329', None, None, None, None, None, '2579689') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.012753963470458984 save_final save missing photos in datou_result : time spend for datou_step_exec : 20.14626407623291 time spend to save output : 0.013317346572875977 total time spend for step 4 : 20.159581422805786 step5:crop_condition Wed Feb 12 18:21:35 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 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 5 ! batch 1 Loaded 473 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 ! map_result returned by crop_photo_return_map_crop : length : 152 About to insert : list_path_to_insert length 152 new photo from crops ! About to upload 152 photos upload in portfolio : 4869462 init cache_photo without model_param we have 152 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739380898_332370 we have uploaded 152 photos in the portfolio 4869462 time of upload the photos Elapsed time : 42.040236473083496 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 ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 60 About to insert : list_path_to_insert length 60 new photo from crops ! About to upload 60 photos upload in portfolio : 4869462 init cache_photo without model_param we have 60 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739380941_332370 we have uploaded 60 photos in the portfolio 4869462 time of upload the photos Elapsed time : 14.85878038406372 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 25 About to insert : list_path_to_insert length 25 new photo from crops ! About to upload 25 photos upload in portfolio : 4869462 init cache_photo without model_param we have 25 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739380957_332370 we have uploaded 25 photos in the portfolio 4869462 time of upload the photos Elapsed time : 17.362377882003784 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 63 About to insert : list_path_to_insert length 63 new photo from crops ! About to upload 63 photos upload in portfolio : 4869462 init cache_photo without model_param we have 63 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739380975_332370 we have uploaded 63 photos in the portfolio 4869462 time of upload the photos Elapsed time : 15.829236030578613 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 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739380991_332370 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.5803744792938232 we have finished the crop for the class : pehd 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 [1337118339, 1337118336, 1337118333, 1337118331, 1337118329] Looping around the photos to save general results len do output : 301 /1337156086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156136Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156137Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156151Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156219Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156221Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156223Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156231Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156232Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156233Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156234Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156236Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156238Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156239Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156240Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156241Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156291Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156295Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156297Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156298Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156300Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156305Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156307Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156309Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156311Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337156567Didn'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, '2579689') ('4234', '20479196', '1337118339', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118336', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118333', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118331', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118329', None, None, None, None, None, '2579689') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 908 time used for this insertion : 0.05155467987060547 save_final save missing photos in datou_result : time spend for datou_step_exec : 97.08808183670044 time spend to save output : 0.0581815242767334 total time spend for step 5 : 97.14626336097717 step6:thcl Wed Feb 12 18:23:12 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 : 0.031736135482788086 time to convert the images to numpy array : 0.0911564826965332 time to import caffe and check if the image exist : 0.022055625915527344 time to convert the images to numpy array : 0.11853146553039551 time to import caffe and check if the image exist : 0.03197169303894043 time to convert the images to numpy array : 0.11405396461486816 time to import caffe and check if the image exist : 0.029642820358276367 time to convert the images to numpy array : 0.11896228790283203 time to import caffe and check if the image exist : 0.027834177017211914 time to convert the images to numpy array : 0.12253689765930176 time to import caffe and check if the image exist : 0.021231889724731445 time to convert the images to numpy array : 0.13532471656799316 time to import caffe and check if the image exist : 0.031150102615356445 time to convert the images to numpy array : 0.1272132396697998 time to import caffe and check if the image exist : 0.030090808868408203 time to convert the images to numpy array : 0.129408597946167 time to import caffe and check if the image exist : 0.0406191349029541 time to convert the images to numpy array : 0.11875510215759277 time to import caffe and check if the image exist : 0.0403745174407959 time to convert the images to numpy array : 0.12042498588562012 total time to convert the images to numpy array : 0.6829817295074463 list photo_ids error: [] list photo_ids correct : [1337156545, 1337156546, 1337156547, 1337156548, 1337156549, 1337156550, 1337156551, 1337156552, 1337156553, 1337156554, 1337156555, 1337156556, 1337156557, 1337156558, 1337156559, 1337156560, 1337156561, 1337156562, 1337156563, 1337156564, 1337156565, 1337156567, 1337156349, 1337156350, 1337156351, 1337156352, 1337156353, 1337156355, 1337156356, 1337156357, 1337156358, 1337156359, 1337156360, 1337156361, 1337156362, 1337156363, 1337156364, 1337156365, 1337156366, 1337156367, 1337156368, 1337156369, 1337156503, 1337156504, 1337156505, 1337156506, 1337156507, 1337156508, 1337156509, 1337156510, 1337156511, 1337156512, 1337156513, 1337156150, 1337156151, 1337156152, 1337156153, 1337156154, 1337156155, 1337156156, 1337156157, 1337156158, 1337156159, 1337156160, 1337156161, 1337156162, 1337156163, 1337156164, 1337156165, 1337156166, 1337156167, 1337156168, 1337156169, 1337156170, 1337156171, 1337156172, 1337156173, 1337156174, 1337156175, 1337156176, 1337156177, 1337156178, 1337156179, 1337156180, 1337156253, 1337156254, 1337156255, 1337156257, 1337156258, 1337156259, 1337156260, 1337156261, 1337156262, 1337156263, 1337156264, 1337156265, 1337156266, 1337156267, 1337156268, 1337156269, 1337156270, 1337156271, 1337156272, 1337156273, 1337156274, 1337156275, 1337156277, 1337156278, 1337156279, 1337156280, 1337156281, 1337156282, 1337156283, 1337156284, 1337156285, 1337156514, 1337156515, 1337156516, 1337156517, 1337156518, 1337156519, 1337156520, 1337156521, 1337156522, 1337156523, 1337156524, 1337156525, 1337156526, 1337156527, 1337156528, 1337156529, 1337156530, 1337156531, 1337156532, 1337156533, 1337156534, 1337156535, 1337156536, 1337156537, 1337156538, 1337156539, 1337156540, 1337156541, 1337156542, 1337156543, 1337156544, 1337156286, 1337156287, 1337156288, 1337156289, 1337156290, 1337156291, 1337156292, 1337156293, 1337156294, 1337156295, 1337156296, 1337156297, 1337156298, 1337156299, 1337156300, 1337156301, 1337156302, 1337156303, 1337156304, 1337156305, 1337156306, 1337156307, 1337156308, 1337156309, 1337156310, 1337156311, 1337156343, 1337156344, 1337156345, 1337156346, 1337156348, 1337156117, 1337156118, 1337156120, 1337156121, 1337156122, 1337156123, 1337156124, 1337156125, 1337156126, 1337156127, 1337156128, 1337156129, 1337156130, 1337156131, 1337156132, 1337156133, 1337156134, 1337156135, 1337156136, 1337156137, 1337156139, 1337156140, 1337156141, 1337156142, 1337156143, 1337156144, 1337156145, 1337156146, 1337156147, 1337156148, 1337156149, 1337156086, 1337156087, 1337156088, 1337156089, 1337156090, 1337156091, 1337156092, 1337156093, 1337156094, 1337156095, 1337156096, 1337156097, 1337156098, 1337156099, 1337156100, 1337156101, 1337156102, 1337156103, 1337156104, 1337156105, 1337156106, 1337156107, 1337156108, 1337156109, 1337156110, 1337156111, 1337156112, 1337156113, 1337156114, 1337156115, 1337156116, 1337156181, 1337156182, 1337156183, 1337156184, 1337156185, 1337156186, 1337156187, 1337156188, 1337156189, 1337156190, 1337156191, 1337156192, 1337156193, 1337156194, 1337156195, 1337156196, 1337156197, 1337156198, 1337156199, 1337156200, 1337156201, 1337156202, 1337156203, 1337156204, 1337156205, 1337156206, 1337156207, 1337156208, 1337156209, 1337156210, 1337156211, 1337156212, 1337156213, 1337156214, 1337156215, 1337156217, 1337156218, 1337156219, 1337156220, 1337156221, 1337156222, 1337156223, 1337156224, 1337156225, 1337156227, 1337156228, 1337156229, 1337156230, 1337156231, 1337156232, 1337156233, 1337156234, 1337156235, 1337156236, 1337156237, 1337156238, 1337156239, 1337156240, 1337156241, 1337156250, 1337156251, 1337156252] number of photos to traite : 301 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 : 3137 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 : 2918 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 1.4812421798706055 time used to do the prediction : 1.2076513767242432 save descriptor for thcl : 3237 time to traite the descriptors : 1.7879986763000488 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1337156545 To insert : 1337156546 To insert : 1337156547 To insert : 1337156548 To insert : 1337156549 To insert : 1337156550 To insert : 1337156551 To insert : 1337156552 To insert : 1337156553 To insert : 1337156554 To insert : 1337156555 To insert : 1337156556 To insert : 1337156557 To insert : 1337156558 To insert : 1337156559 To insert : 1337156560 To insert : 1337156561 To insert : 1337156562 To insert : 1337156563 To insert : 1337156564 To insert : 1337156565 To insert : 1337156567 To insert : 1337156349 To insert : 1337156350 To insert : 1337156351 To insert : 1337156352 To insert : 1337156353 To insert : 1337156355 To insert : 1337156356 To insert : 1337156357 To insert : 1337156358 To insert : 1337156359 To insert : 1337156360 To insert : 1337156361 To insert : 1337156362 To insert : 1337156363 To insert : 1337156364 To insert : 1337156365 To insert : 1337156366 To insert : 1337156367 To insert : 1337156368 To insert : 1337156369 To insert : 1337156503 To insert : 1337156504 To insert : 1337156505 To insert : 1337156506 To insert : 1337156507 To insert : 1337156508 To insert : 1337156509 To insert : 1337156510 To insert : 1337156511 To insert : 1337156512 To insert : 1337156513 To insert : 1337156150 To insert : 1337156151 To insert : 1337156152 To insert : 1337156153 To insert : 1337156154 To insert : 1337156155 To insert : 1337156156 To insert : 1337156157 To insert : 1337156158 To insert : 1337156159 To insert : 1337156160 To insert : 1337156161 To insert : 1337156162 To insert : 1337156163 To insert : 1337156164 To insert : 1337156165 To insert : 1337156166 To insert : 1337156167 To insert : 1337156168 To insert : 1337156169 To insert : 1337156170 To insert : 1337156171 To insert : 1337156172 To insert : 1337156173 To insert : 1337156174 To insert : 1337156175 To insert : 1337156176 To insert : 1337156177 To insert : 1337156178 To insert : 1337156179 To insert : 1337156180 To insert : 1337156253 To insert : 1337156254 To insert : 1337156255 To insert : 1337156257 To insert : 1337156258 To insert : 1337156259 To insert : 1337156260 To insert : 1337156261 To insert : 1337156262 To insert : 1337156263 To insert : 1337156264 To insert : 1337156265 To insert : 1337156266 To insert : 1337156267 To insert : 1337156268 To insert : 1337156269 To insert : 1337156270 To insert : 1337156271 To insert : 1337156272 To insert : 1337156273 To insert : 1337156274 To insert : 1337156275 To insert : 1337156277 To insert : 1337156278 To insert : 1337156279 To insert : 1337156280 To insert : 1337156281 To insert : 1337156282 To insert : 1337156283 To insert : 1337156284 To insert : 1337156285 To insert : 1337156514 To insert : 1337156515 To insert : 1337156516 To insert : 1337156517 To insert : 1337156518 To insert : 1337156519 To insert : 1337156520 To insert : 1337156521 To insert : 1337156522 To insert : 1337156523 To insert : 1337156524 To insert : 1337156525 To insert : 1337156526 To insert : 1337156527 To insert : 1337156528 To insert : 1337156529 To insert : 1337156530 To insert : 1337156531 To insert : 1337156532 To insert : 1337156533 To insert : 1337156534 To insert : 1337156535 To insert : 1337156536 To insert : 1337156537 To insert : 1337156538 To insert : 1337156539 To insert : 1337156540 To insert : 1337156541 To insert : 1337156542 To insert : 1337156543 To insert : 1337156544 To insert : 1337156286 To insert : 1337156287 To insert : 1337156288 To insert : 1337156289 To insert : 1337156290 To insert : 1337156291 To insert : 1337156292 To insert : 1337156293 To insert : 1337156294 To insert : 1337156295 To insert : 1337156296 To insert : 1337156297 To insert : 1337156298 To insert : 1337156299 To insert : 1337156300 To insert : 1337156301 To insert : 1337156302 To insert : 1337156303 To insert : 1337156304 To insert : 1337156305 To insert : 1337156306 To insert : 1337156307 To insert : 1337156308 To insert : 1337156309 To insert : 1337156310 To insert : 1337156311 To insert : 1337156343 To insert : 1337156344 To insert : 1337156345 To insert : 1337156346 To insert : 1337156348 To insert : 1337156117 To insert : 1337156118 To insert : 1337156120 To insert : 1337156121 To insert : 1337156122 To insert : 1337156123 To insert : 1337156124 To insert : 1337156125 To insert : 1337156126 To insert : 1337156127 To insert : 1337156128 To insert : 1337156129 To insert : 1337156130 To insert : 1337156131 To insert : 1337156132 To insert : 1337156133 To insert : 1337156134 To insert : 1337156135 To insert : 1337156136 To insert : 1337156137 To insert : 1337156139 To insert : 1337156140 To insert : 1337156141 To insert : 1337156142 To insert : 1337156143 To insert : 1337156144 To insert : 1337156145 To insert : 1337156146 To insert : 1337156147 To insert : 1337156148 To insert : 1337156149 To insert : 1337156086 To insert : 1337156087 To insert : 1337156088 To insert : 1337156089 To insert : 1337156090 To insert : 1337156091 To insert : 1337156092 To insert : 1337156093 To insert : 1337156094 To insert : 1337156095 To insert : 1337156096 To insert : 1337156097 To insert : 1337156098 To insert : 1337156099 To insert : 1337156100 To insert : 1337156101 To insert : 1337156102 To insert : 1337156103 To insert : 1337156104 To insert : 1337156105 To insert : 1337156106 To insert : 1337156107 To insert : 1337156108 To insert : 1337156109 To insert : 1337156110 To insert : 1337156111 To insert : 1337156112 To insert : 1337156113 To insert : 1337156114 To insert : 1337156115 To insert : 1337156116 To insert : 1337156181 To insert : 1337156182 To insert : 1337156183 To insert : 1337156184 To insert : 1337156185 To insert : 1337156186 To insert : 1337156187 To insert : 1337156188 To insert : 1337156189 To insert : 1337156190 To insert : 1337156191 To insert : 1337156192 To insert : 1337156193 To insert : 1337156194 To insert : 1337156195 To insert : 1337156196 To insert : 1337156197 To insert : 1337156198 To insert : 1337156199 To insert : 1337156200 To insert : 1337156201 To insert : 1337156202 To insert : 1337156203 To insert : 1337156204 To insert : 1337156205 To insert : 1337156206 To insert : 1337156207 To insert : 1337156208 To insert : 1337156209 To insert : 1337156210 To insert : 1337156211 To insert : 1337156212 To insert : 1337156213 To insert : 1337156214 To insert : 1337156215 To insert : 1337156217 To insert : 1337156218 To insert : 1337156219 To insert : 1337156220 To insert : 1337156221 To insert : 1337156222 To insert : 1337156223 To insert : 1337156224 To insert : 1337156225 To insert : 1337156227 To insert : 1337156228 To insert : 1337156229 To insert : 1337156230 To insert : 1337156231 To insert : 1337156232 To insert : 1337156233 To insert : 1337156234 To insert : 1337156235 To insert : 1337156236 To insert : 1337156237 To insert : 1337156238 To insert : 1337156239 To insert : 1337156240 To insert : 1337156241 To insert : 1337156250 To insert : 1337156251 To insert : 1337156252 time to insert the descriptors : 77.8761990070343 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 : 452 time used for this insertion : 0.035459041595458984 save missing photos in datou_result : time spend for datou_step_exec : 87.57132697105408 time spend to save output : 0.10440540313720703 total time spend for step 6 : 87.67573237419128 step7:ventilate_hashtags_in_portfolio Wed Feb 12 18:24:39 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 : 20479196 get user id for portfolio 20479196 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`=20479196 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre','environnement','refus','pehd','Carton','flou','papier','carton','Film_plastique','PET_fonce','Tetrapak','pet_clair','mal_croppe','PEHD','metal','pet_fonce','Papier','PET_clair')) 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`=20479196 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre','environnement','refus','pehd','Carton','flou','papier','carton','Film_plastique','PET_fonce','Tetrapak','pet_clair','mal_croppe','PEHD','metal','pet_fonce','Papier','PET_clair')) 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`=20479196 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre','environnement','refus','pehd','Carton','flou','papier','carton','Film_plastique','PET_fonce','Tetrapak','pet_clair','mal_croppe','PEHD','metal','pet_fonce','Papier','PET_clair')) 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`=20479196 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre','environnement','refus','pehd','Carton','flou','papier','carton','Film_plastique','PET_fonce','Tetrapak','pet_clair','mal_croppe','PEHD','metal','pet_fonce','Papier','PET_clair')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20485164,20485165,20485166,20485177,20485171,20485169,20485180,20485172,20485179,20485174,20485181,20485176,20485178?tags=autre,environnement,refus,pehd,carton,flou,papier,film_plastique,pet_fonce,tetrapak,pet_clair,mal_croppe,metal&datou_id_consolidate=4235&port_consolidate=20479196 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1337118339, 1337118336, 1337118333, 1337118331, 1337118329] Looping around the photos to save general results len do output : 1 /20479196. 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, '2579689') ('4234', '20479196', '1337118339', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118336', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118333', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118331', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118329', None, None, None, None, None, '2579689') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.01716446876525879 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.4884836673736572 time spend to save output : 0.017428159713745117 total time spend for step 7 : 2.5059118270874023 step8:final Wed Feb 12 18:24:42 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 : {1337118339: ('0.19167712283341812',), 1337118336: ('0.19167712283341812',), 1337118333: ('0.19167712283341812',), 1337118331: ('0.19167712283341812',), 1337118329: ('0.19167712283341812',)} new output for save of step final : {1337118339: ('0.19167712283341812',), 1337118336: ('0.19167712283341812',), 1337118333: ('0.19167712283341812',), 1337118331: ('0.19167712283341812',), 1337118329: ('0.19167712283341812',)} [1337118339, 1337118336, 1337118333, 1337118331, 1337118329] Looping around the photos to save general results len do output : 5 /1337118339.Didn't retrieve data . /1337118336.Didn't retrieve data . /1337118333.Didn't retrieve data . /1337118331.Didn't retrieve data . /1337118329.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, '2579689') ('4234', '20479196', '1337118339', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118336', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118333', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118331', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118329', None, None, None, None, None, '2579689') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.017423152923583984 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.14363598823547363 time spend to save output : 0.0179440975189209 total time spend for step 8 : 0.16158008575439453 step9:velours_tree Wed Feb 12 18:24:42 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 : 20485164,20485165,20485166,20485177,20485171,20485169,20485180,20485172,20485179,20485174,20485181,20485176,20485178 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=20485164 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=20485165 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=20485166 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=20485177 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=20485171 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=20485169 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=20485180 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=20485172 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=20485179 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=20485174 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=20485181 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=20485176 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=20485178 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 301 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [2 5 1 4 4 4 1 0 3 3 4 1 1 0 1 0 0 4 2 4 1 0 1 1 4 4 0 1 0 0 0 1 1 1 4 1 4 1 3 4 3 1 1 0 2 1 0 1 0 2 1 1 1 1 0 4 4 1 1 0 0 2 1 4 1 1 4 3 3 4 1 0 1 1 2 1 0 0 2 4 2 1 1 1 0 2 1 4 4 1 1 1 1 1 4 4 1 1 1 3 3 4 1 0 1 0 0 4 2 1 4 1 1 2 1 0 4 4 0 1 0 0 1 4 1 1 4 2 3 3 4 1 1 1 1 1 0 1 1 0 4 2 1 1 1 0 0 4 4 0 1 0 5 1 2 2 2 2 2 1 3 3 1 1 3 0 2 5 0 2 2 2 2 2 2 2 2 1 1 1 4 3 2 5 0 2 2 2 2 1 2 3 3 1 2 5 2 2 1 3 3 1 2 5 2 2 2 1 3 3 3 2 0 3 1 1 4 0 0 0 0 1 0 0 1 0 0 0 0 1 1 1 0 0 4 0 0 2 0 1 0 0 0 0 5 0 2 5 1 1 2 0 0 0 5 2 0 2 5 1 3 1 1 0 0 0 0 0 5 2 0 0 0 2 5 1 1 2 4 0 0 0 2 5 2 0 0 2 3 1 2 0 0 0 2 2 0 5 2 0 0] Elapsed time: 0.06573057174682617 graph_id used : 78200 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20485164,20485165,20485166,20485177,20485171,20485169,20485180,20485172,20485179,20485174,20485181,20485176,20485178?tags=autre,environnement,refus,pehd,carton,flou,papier,film_plastique,pet_fonce,tetrapak,pet_clair,mal_croppe,metal&datou_id_consolidate=4235&port_consolidate=20479196&tree_id=78200 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1337118339, 1337118336, 1337118333, 1337118331, 1337118329] Looping around the photos to save general results len do output : 1 /20479196Didn'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, '2579689') ('4234', '20479196', '1337118339', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118336', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118333', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118331', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118329', None, None, None, None, None, '2579689') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.015301704406738281 save_final save missing photos in datou_result : time spend for datou_step_exec : 21.899924516677856 time spend to save output : 0.01571369171142578 total time spend for step 9 : 21.915638208389282 step10:send_mail_cod Wed Feb 12 18:25:04 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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_P20479196_12-02-2025_18_25_04.pdf 20485146 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 .imagette204851461739381104 20485148 imagette204851481739381105 20485159 change filename to text .imagette204851591739381105 20485153 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 .imagette204851531739381105 20485151 imagette204851511739381106 20485162 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 .imagette204851621739381106 20485154 imagette204851541739381107 20485161 imagette204851611739381107 20485156 imagette204851561739381107 20485163 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 .imagette204851631739381107 20485158 imagette204851581739381108 20485160 imagette204851601739381108 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20479196 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20485164,20485165,20485166,20485177,20485171,20485169,20485180,20485172,20485179,20485174,20485181,20485176,20485178?tags=autre,environnement,refus,pehd,carton,flou,papier,film_plastique,pet_fonce,tetrapak,pet_clair,mal_croppe,metal&datou_id_consolidate=4235&port_consolidate=20479196&tree_id=78200 your option no_mail is active, we will not send the real mail to your client args[1337118339] : ((1337118339, -7.804511933549772, 492609224), (1337118339, -0.4606990162239655, 496442774), '0.19167712283341812') apple ((1337118339, -7.804511933549772, 492609224), (1337118339, -0.4606990162239655, 496442774), '0.19167712283341812') We are sending mail with results at cod@fotonower.com args[1337118336] : ((1337118336, -7.782289418624392, 492609224), (1337118336, -0.4914998201762635, 501862349), '0.19167712283341812') apple ((1337118336, -7.782289418624392, 492609224), (1337118336, -0.4914998201762635, 501862349), '0.19167712283341812') We are sending mail with results at cod@fotonower.com args[1337118333] : ((1337118333, -7.789489584782072, 492609224), (1337118333, -0.4702219306619733, 496442774), '0.19167712283341812') apple ((1337118333, -7.789489584782072, 492609224), (1337118333, -0.4702219306619733, 496442774), '0.19167712283341812') We are sending mail with results at cod@fotonower.com args[1337118331] : ((1337118331, -7.791605882568465, 492609224), (1337118331, -0.4489341279873905, 496442774), '0.19167712283341812') apple ((1337118331, -7.791605882568465, 492609224), (1337118331, -0.4489341279873905, 496442774), '0.19167712283341812') We are sending mail with results at cod@fotonower.com args[1337118329] : ((1337118329, -7.773127011043167, 492609224), (1337118329, -0.4772476121736768, 496442774), '0.19167712283341812') apple ((1337118329, -7.773127011043167, 492609224), (1337118329, -0.4772476121736768, 496442774), '0.19167712283341812') We are sending mail with results at cod@fotonower.com refus_total : 0.19167712283341812 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=20479196 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_P20479196_12-02-2025_18_25_04.pdf results_Qualipapia_P20479196_12-02-2025_18_25_04.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479196_12-02-2025_18_25_04.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','20479196','results_Qualipapia_P20479196_12-02-2025_18_25_04.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479196_12-02-2025_18_25_04.pdf','pdf','','0.18','0.19167712283341812') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1337118339, 1337118336, 1337118333, 1337118331, 1337118329] 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, '2579689') ('4234', '20479196', '1337118339', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118336', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118333', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118331', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118329', None, None, None, None, None, '2579689') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.014928340911865234 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.032650470733643 time spend to save output : 0.015166282653808594 total time spend for step 10 : 5.047816753387451 step11:split_time_score Wed Feb 12 18:25:09 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'}] (('13', 6),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 12022025 20479196 Nombre de photos uploadées : 6 / 23040 (0%) 12022025 20479196 Nombre de photos taguées (types de déchets): 6 / 6 (100%) 12022025 20479196 Nombre de photos taguées (volume) : 0 / 6 (0%) elapsed_time : load_data_split_time_score 2.1457672119140625e-06 elapsed_time : order_list_meta_photo_and_scores 5.7220458984375e-06 ?????? elapsed_time : fill_and_build_computed_from_old_data 0.0003845691680908203 elapsed_time : insert_dashboard_record_day_entry 0.026916027069091797 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 : 0.15829996426485274 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20470706_12-02-2025_10_17_40.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20470706 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`=20470706 AND mptpi.`type`=4230 To do Qualite : 0.2571924266909986 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20474222_12-02-2025_11_47_45.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20474222 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`=20474222 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476682 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476683 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476684 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476685 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476686 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476321 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476322 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476323 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476324 order by id desc limit 1 Qualite : 0.17840314144925185 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20476325_12-02-2025_12_46_55.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476325 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`=20476325 AND mptpi.`type`=4230 To do Qualite : 0.23342179416285125 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20476326_12-02-2025_12_36_03.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476326 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`=20476326 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476687 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476688 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476689 order by id desc limit 1 Qualite : 0.1924295939903281 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20476690_12-02-2025_13_32_08.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476690 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`=20476690 AND mptpi.`type`=4230 To do Qualite : 0.2119568776018645 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20476691_12-02-2025_13_23_51.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476691 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`=20476691 AND mptpi.`type`=4230 To do Qualite : 0.154875790367845 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20476692_12-02-2025_13_17_01.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20476692 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`=20476692 AND mptpi.`type`=4230 To do Qualite : 0.19008527192762648 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20477040_12-02-2025_13_51_47.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20477040 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`=20477040 AND mptpi.`type`=4230 To do Qualite : 0.19050715192060547 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20477041_12-02-2025_13_39_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20477041 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`=20477041 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20477469 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20477470 order by id desc limit 1 Qualite : 0.22219744748095124 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20477471_12-02-2025_15_33_55.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20477471 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`=20477471 AND mptpi.`type`=4230 To do Qualite : 0.213374648572307 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20477472_12-02-2025_14_47_07.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20477472 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`=20477472 AND mptpi.`type`=4230 To do Qualite : 0.2080923629286091 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20477473_12-02-2025_14_17_51.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20477473 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`=20477473 AND mptpi.`type`=4230 To do Qualite : 0.21079772282942882 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20477474_12-02-2025_14_32_10.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20477474 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`=20477474 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479190 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479191 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479192 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479193 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479194 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479195 order by id desc limit 1 Qualite : 0.19167712283341812 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479196_12-02-2025_18_25_04.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479196 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`=20479196 AND mptpi.`type`=4230 To do Qualite : 0.19000694400268564 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479197_12-02-2025_16_50_30.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479197 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`=20479197 AND mptpi.`type`=4230 To do Qualite : 0.23257386904434174 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479199_12-02-2025_17_34_28.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479199 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`=20479199 AND mptpi.`type`=4230 To do Qualite : 0.26488945635035177 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479200_12-02-2025_17_47_03.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479200 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`=20479200 AND mptpi.`type`=4230 To do Qualite : 0.20732146131397367 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479201_12-02-2025_15_48_28.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479201 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`=20479201 AND mptpi.`type`=4230 To do Qualite : 0.22406120432686213 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479443_12-02-2025_16_22_41.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479443 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`=20479443 AND mptpi.`type`=4230 To do Qualite : 0.1665337497911145 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479444_12-02-2025_16_17_51.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479444 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`=20479444 AND mptpi.`type`=4230 To do Qualite : 0.14940220555870873 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20479445_12-02-2025_16_04_36.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20479445 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`=20479445 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'12022025': {'nb_upload': 6, 'nb_taggue_class': 6, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1337118339, 1337118336, 1337118333, 1337118331, 1337118329] Looping around the photos to save general results len do output : 1 /20479196Didn'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, '2579689') ('4234', '20479196', '1337118339', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118336', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118333', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118331', None, None, None, None, None, '2579689') ('4234', None, None, None, None, None, None, None, '2579689') ('4234', '20479196', '1337118329', None, None, None, None, None, '2579689') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.0163877010345459 save_final save missing photos in datou_result : time spend for datou_step_exec : 19.062583923339844 time spend to save output : 0.016689062118530273 total time spend for step 11 : 19.079272985458374 caffe_path_current : About to save ! 2 After save, about to update current ! update_current_state 61.21user 40.09system 5:03.10elapsed 33%CPU (0avgtext+0avgdata 2417272maxresident)k 1907168inputs+22624outputs (8649major+3726144minor)pagefaults 0swaps