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 : 2011519 load datou : 4234 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2624523'] with mtr_portfolio_ids : ['20934027'] and first list_photo_ids : [] new path : /proc/2011519/ 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 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 1.1681039333343506 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 Fri Feb 28 17:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 4641 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-28 17:20:32.454249: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-28 17:20:32.483282: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-28 17:20:32.485715: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f24b0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-28 17:20:32.485777: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-28 17:20:32.490736: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-28 17:20:32.752086: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3ca5a810 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-28 17:20:32.752142: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-28 17:20:32.754106: 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 2025-02-28 17:20:32.754860: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-28 17:20:32.760168: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-28 17:20:32.763834: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-28 17:20:32.765408: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-28 17:20:32.769582: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-28 17:20:32.774140: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-28 17:20:32.783747: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-28 17:20:32.785272: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-28 17:20:32.785409: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-28 17:20:32.786193: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-28 17:20:32.786212: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-28 17:20:32.786223: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-28 17:20:32.787562: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4189 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. 2025-02-28 17:20:33.186639: 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 2025-02-28 17:20:33.186768: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-28 17:20:33.186798: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-28 17:20:33.186824: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-28 17:20:33.186848: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-28 17:20:33.186872: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-28 17:20:33.186942: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-28 17:20:33.186973: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-28 17:20:33.188234: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-28 17:20:33.189737: 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 2025-02-28 17:20:33.189934: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-28 17:20:33.189954: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-28 17:20:33.189970: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-28 17:20:33.189985: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-28 17:20:33.190000: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-28 17:20:33.190013: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-28 17:20:33.190029: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-28 17:20:33.191089: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-28 17:20:33.191140: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-28 17:20:33.191151: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-28 17:20:33.191160: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-28 17:20:33.192144: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4189 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 : [] 2025-02-28 17:20:42.560253: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-28 17:20:42.754084: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-28 17:20:44.579189: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:44.579888: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.23G (3471821824 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:44.580552: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.91G (3124639488 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:44.581154: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.62G (2812175360 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.388771: 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. 2025-02-28 17:20:45.447288: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.447407: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB 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. 2025-02-28 17:20:45.448627: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.448675: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB 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. 2025-02-28 17:20:45.457945: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.458018: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB 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. 2025-02-28 17:20:45.458655: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.458676: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB 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. 2025-02-28 17:20:45.465956: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.466039: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB 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. 2025-02-28 17:20:45.466671: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.466689: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB 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. 2025-02-28 17:20:45.555691: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.555800: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB 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. 2025-02-28 17:20:45.556450: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.556468: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB 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. 2025-02-28 17:20:45.557121: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.557142: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB 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. 2025-02-28 17:20:45.557780: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.557797: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB 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. 2025-02-28 17:20:45.566638: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.567361: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.584851: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.585523: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.586235: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.587019: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.591226: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.591907: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.592548: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.593174: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.594350: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.594370: 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. 2025-02-28 17:20:45.605705: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.606383: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.615904: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.616591: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.617373: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.618000: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.618629: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 17:20:45.619422: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.59G (3857580032 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 : 4 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: -114.95391 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 : 0.00010180473327636719 nb_pixel_total : 1336 time to create 1 rle with old method : 0.0023870468139648438 length of segment : 33 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1216 time to create 1 rle with old method : 0.002184629440307617 length of segment : 37 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.0002696514129638672 length of segment : 15 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 2493 time to create 1 rle with old method : 0.016172409057617188 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: -117.67266 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 : 4.9591064453125e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005388259887695312 length of segment : 30 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 2407 time to create 1 rle with old method : 0.003049612045288086 length of segment : 92 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 2365 time to create 1 rle with old method : 0.003109455108642578 length of segment : 55 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.0003819465637207031 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 35.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -72.69219 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 : 5.4836273193359375e-05 nb_pixel_total : 1071 time to create 1 rle with old method : 0.0014789104461669922 length of segment : 21 time for calcul the mask position with numpy : 0.00011444091796875 nb_pixel_total : 2869 time to create 1 rle with old method : 0.003834962844848633 length of segment : 46 time for calcul the mask position with numpy : 0.0001270771026611328 nb_pixel_total : 4135 time to create 1 rle with old method : 0.005428791046142578 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.28594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0008258819580078125 length of segment : 28 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 978 time to create 1 rle with old method : 0.0013477802276611328 length of segment : 39 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1309 time to create 1 rle with old method : 0.0016705989837646484 length of segment : 87 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.00037360191345214844 length of segment : 21 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0008509159088134766 length of segment : 36 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: 149.04922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0007808208465576172 length of segment : 20 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0006024837493896484 length of segment : 29 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 769 time to create 1 rle with old method : 0.0009434223175048828 length of segment : 72 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 1183 time to create 1 rle with old method : 0.0015287399291992188 length of segment : 83 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 1035 time to create 1 rle with old method : 0.001873016357421875 length of segment : 52 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 165 time to create 1 rle with old method : 0.00039839744567871094 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 64.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -46.76641 max: 151.10000 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: -113.71953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 993 time to create 1 rle with old method : 0.0013272762298583984 length of segment : 36 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 2375 time to create 1 rle with old method : 0.003013134002685547 length of segment : 49 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1565 time to create 1 rle with old method : 0.0019741058349609375 length of segment : 60 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 783 time to create 1 rle with old method : 0.001155853271484375 length of segment : 46 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 917 time to create 1 rle with old method : 0.0012118816375732422 length of segment : 38 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002636909484863281 length of segment : 16 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005497932434082031 length of segment : 25 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 369 time to create 1 rle with old method : 0.0005481243133544922 length of segment : 16 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 902 time to create 1 rle with old method : 0.0012559890747070312 length of segment : 41 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002727508544921875 length of segment : 15 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 841 time to create 1 rle with old method : 0.0012559890747070312 length of segment : 37 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0007426738739013672 length of segment : 28 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 890 time to create 1 rle with old method : 0.0012080669403076172 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.68047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.0002827644348144531 length of segment : 12 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.00016880035400390625 length of segment : 8 time for calcul the mask position with numpy : 0.00020051002502441406 nb_pixel_total : 4613 time to create 1 rle with old method : 0.005849123001098633 length of segment : 76 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 700 time to create 1 rle with old method : 0.0009052753448486328 length of segment : 31 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.0003483295440673828 length of segment : 17 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0015840530395507812 length of segment : 29 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001895427703857422 length of segment : 9 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 1946 time to create 1 rle with old method : 0.0025484561920166016 length of segment : 30 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.0001842975616455078 length of segment : 10 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1126 time to create 1 rle with old method : 0.001453399658203125 length of segment : 48 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 1636 time to create 1 rle with old method : 0.0020852088928222656 length of segment : 37 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004169940948486328 length of segment : 20 time for calcul the mask position with numpy : 0.0002562999725341797 nb_pixel_total : 1848 time to create 1 rle with old method : 0.002492189407348633 length of segment : 73 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 634 time to create 1 rle with old method : 0.0009183883666992188 length of segment : 33 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00024247169494628906 length of segment : 10 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005466938018798828 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.09063 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1679 time to create 1 rle with old method : 0.002138853073120117 length of segment : 117 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0008876323699951172 length of segment : 22 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1203 time to create 1 rle with old method : 0.0017435550689697266 length of segment : 41 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1149 time to create 1 rle with old method : 0.00170135498046875 length of segment : 36 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1160 time to create 1 rle with old method : 0.0014829635620117188 length of segment : 39 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 817 time to create 1 rle with old method : 0.001070261001586914 length of segment : 35 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 866 time to create 1 rle with old method : 0.0011434555053710938 length of segment : 37 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 238.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 113.09219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 1753 time to create 1 rle with old method : 0.0022745132446289062 length of segment : 137 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0007262229919433594 length of segment : 29 time for calcul the mask position with numpy : 9.775161743164062e-05 nb_pixel_total : 1761 time to create 1 rle with old method : 0.0023910999298095703 length of segment : 129 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 366 time to create 1 rle with old method : 0.0008575916290283203 length of segment : 35 time for calcul the mask position with numpy : 0.00026035308837890625 nb_pixel_total : 3643 time to create 1 rle with old method : 0.008063554763793945 length of segment : 189 Processing 1 images image shape: (280, 400, 3) min: 56.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0004355907440185547 length of segment : 41 time for calcul the mask position with numpy : 0.0014109611511230469 nb_pixel_total : 102399 time to create 1 rle with old method : 0.12659072875976562 length of segment : 273 Processing 1 images image shape: (280, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.02187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002677440643310547 length of segment : 22 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.000293731689453125 length of segment : 15 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003788471221923828 length of segment : 15 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0008885860443115234 length of segment : 40 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 2994 time to create 1 rle with old method : 0.0037446022033691406 length of segment : 46 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.0002875328063964844 length of segment : 12 time for calcul the mask position with numpy : 0.00013637542724609375 nb_pixel_total : 6744 time to create 1 rle with old method : 0.00797581672668457 length of segment : 102 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 945 time to create 1 rle with old method : 0.0015413761138916016 length of segment : 86 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00018358230590820312 length of segment : 7 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.0011508464813232422 length of segment : 75 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1388 time to create 1 rle with old method : 0.0017120838165283203 length of segment : 78 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 6350 time to create 1 rle with old method : 0.00776219367980957 length of segment : 86 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.0002651214599609375 length of segment : 23 time for calcul the mask position with numpy : 0.0001544952392578125 nb_pixel_total : 4567 time to create 1 rle with old method : 0.0056574344635009766 length of segment : 161 time for calcul the mask position with numpy : 0.0001468658447265625 nb_pixel_total : 4850 time to create 1 rle with old method : 0.0061724185943603516 length of segment : 110 Processing 1 images image shape: (280, 400, 3) min: 8.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.20937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 668 time to create 1 rle with old method : 0.0008726119995117188 length of segment : 50 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0004551410675048828 length of segment : 30 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005717277526855469 length of segment : 24 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0004031658172607422 length of segment : 18 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001773834228515625 length of segment : 13 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 581 time to create 1 rle with old method : 0.0007805824279785156 length of segment : 31 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 2265 time to create 1 rle with old method : 0.003013134002685547 length of segment : 35 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006778240203857422 length of segment : 39 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 2178 time to create 1 rle with old method : 0.002863168716430664 length of segment : 34 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: 149.15078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006592273712158203 length of segment : 22 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00028824806213378906 length of segment : 16 time for calcul the mask position with numpy : 0.00014495849609375 nb_pixel_total : 2804 time to create 1 rle with old method : 0.003587961196899414 length of segment : 145 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.00043201446533203125 length of segment : 33 Processing 1 images image shape: (280, 320, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 16 time to create 1 rle with old method : 7.343292236328125e-05 length of segment : 4 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 503 time to create 1 rle with old method : 0.001009225845336914 length of segment : 31 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: -116.96172 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 : 7.605552673339844e-05 nb_pixel_total : 1375 time to create 1 rle with old method : 0.0029397010803222656 length of segment : 34 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 1039 time to create 1 rle with old method : 0.0024356842041015625 length of segment : 49 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.0001742839813232422 length of segment : 17 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 2339 time to create 1 rle with old method : 0.0029888153076171875 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: -118.21953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0009860992431640625 length of segment : 37 time for calcul the mask position with numpy : 0.00010323524475097656 nb_pixel_total : 2395 time to create 1 rle with old method : 0.004723548889160156 length of segment : 49 time for calcul the mask position with numpy : 0.0001163482666015625 nb_pixel_total : 2267 time to create 1 rle with old method : 0.004934549331665039 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 35.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -74.79766 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1722 time to create 1 rle with old method : 0.002131223678588867 length of segment : 91 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 952 time to create 1 rle with old method : 0.001323699951171875 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.95391 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 : 4.744529724121094e-05 nb_pixel_total : 521 time to create 1 rle with old method : 0.0008921623229980469 length of segment : 29 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 687 time to create 1 rle with old method : 0.0009102821350097656 length of segment : 42 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1176 time to create 1 rle with old method : 0.001445770263671875 length of segment : 88 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0009202957153320312 length of segment : 42 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1317 time to create 1 rle with old method : 0.001589059829711914 length of segment : 86 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: 150.45547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0007116794586181641 length of segment : 18 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00018262863159179688 length of segment : 12 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0009648799896240234 length of segment : 75 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1150 time to create 1 rle with old method : 0.0014405250549316406 length of segment : 88 time for calcul the mask position with numpy : 0.0007562637329101562 nb_pixel_total : 73686 time to create 1 rle with old method : 0.0867455005645752 length of segment : 330 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0005793571472167969 length of segment : 28 time for calcul the mask position with numpy : 0.0004990100860595703 nb_pixel_total : 49355 time to create 1 rle with old method : 0.05578470230102539 length of segment : 232 Processing 1 images image shape: (400, 400, 3) min: 76.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -45.85234 max: 151.10000 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: -112.86406 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 922 time to create 1 rle with old method : 0.001264333724975586 length of segment : 33 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.001293182373046875 length of segment : 39 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 2566 time to create 1 rle with old method : 0.004128456115722656 length of segment : 59 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003705024719238281 length of segment : 21 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004382133483886719 length of segment : 31 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002522468566894531 length of segment : 21 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006186962127685547 length of segment : 27 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.00029730796813964844 length of segment : 18 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005702972412109375 length of segment : 19 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 856 time to create 1 rle with old method : 0.0011210441589355469 length of segment : 26 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.001088857650756836 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.98906 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00034737586975097656 length of segment : 13 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001964569091796875 length of segment : 8 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005788803100585938 length of segment : 43 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.001074075698852539 length of segment : 27 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 675 time to create 1 rle with old method : 0.0008649826049804688 length of segment : 29 time for calcul the mask position with numpy : 0.00018525123596191406 nb_pixel_total : 1763 time to create 1 rle with old method : 0.002895832061767578 length of segment : 86 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00019240379333496094 length of segment : 11 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005645751953125 length of segment : 26 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004532337188720703 length of segment : 21 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 633 time to create 1 rle with old method : 0.0008699893951416016 length of segment : 37 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0010716915130615234 length of segment : 36 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.0005710124969482422 length of segment : 22 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 522 time to create 1 rle with old method : 0.0008215904235839844 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.90703 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 : 9.918212890625e-05 nb_pixel_total : 1398 time to create 1 rle with old method : 0.0018954277038574219 length of segment : 102 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1135 time to create 1 rle with old method : 0.0019044876098632812 length of segment : 36 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 5684 time to create 1 rle with old method : 0.007437944412231445 length of segment : 75 time for calcul the mask position with numpy : 0.0001690387725830078 nb_pixel_total : 7871 time to create 1 rle with old method : 0.010093927383422852 length of segment : 67 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0010673999786376953 length of segment : 23 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0011763572692871094 length of segment : 37 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 230.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 106.09219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 1910 time to create 1 rle with old method : 0.0027370452880859375 length of segment : 123 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.0005185604095458984 length of segment : 27 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005376338958740234 length of segment : 35 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 1777 time to create 1 rle with old method : 0.0034592151641845703 length of segment : 100 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0003466606140136719 length of segment : 26 time for calcul the mask position with numpy : 0.00020503997802734375 nb_pixel_total : 3421 time to create 1 rle with old method : 0.004704952239990234 length of segment : 178 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 904 time to create 1 rle with old method : 0.0013878345489501953 length of segment : 34 Processing 1 images image shape: (280, 400, 3) min: 57.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 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: 150.79531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 2939 time to create 1 rle with old method : 0.005006074905395508 length of segment : 47 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 747 time to create 1 rle with old method : 0.0010006427764892578 length of segment : 45 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.00039768218994140625 length of segment : 13 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002353191375732422 length of segment : 12 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002701282501220703 length of segment : 21 time for calcul the mask position with numpy : 0.00015091896057128906 nb_pixel_total : 6401 time to create 1 rle with old method : 0.008811712265014648 length of segment : 125 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001857280731201172 length of segment : 8 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00025916099548339844 length of segment : 11 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 2321 time to create 1 rle with old method : 0.0031735897064208984 length of segment : 116 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 603 time to create 1 rle with old method : 0.0010221004486083984 length of segment : 52 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 19 time to create 1 rle with old method : 7.200241088867188e-05 length of segment : 5 time for calcul the mask position with numpy : 0.00016307830810546875 nb_pixel_total : 6323 time to create 1 rle with old method : 0.008693933486938477 length of segment : 111 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0004782676696777344 length of segment : 25 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 849 time to create 1 rle with old method : 0.0013093948364257812 length of segment : 69 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 855 time to create 1 rle with old method : 0.0010981559753417969 length of segment : 71 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 251.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.22891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0004372596740722656 length of segment : 28 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1015 time to create 1 rle with old method : 0.0013265609741210938 length of segment : 50 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0004820823669433594 length of segment : 19 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 3354 time to create 1 rle with old method : 0.003989458084106445 length of segment : 78 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 3769 time to create 1 rle with old method : 0.004641294479370117 length of segment : 84 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: 148.95547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 544 time to create 1 rle with old method : 0.0007371902465820312 length of segment : 29 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.00042438507080078125 length of segment : 29 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002932548522949219 length of segment : 25 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 1341 time to create 1 rle with old method : 0.0017151832580566406 length of segment : 107 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 2172 time to create 1 rle with old method : 0.003857851028442383 length of segment : 153 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.00027108192443847656 length of segment : 15 Processing 1 images image shape: (280, 320, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 139.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 15 time to create 1 rle with old method : 7.796287536621094e-05 length of segment : 3 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: -116.75078 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 : 7.700920104980469e-05 nb_pixel_total : 1345 time to create 1 rle with old method : 0.002435445785522461 length of segment : 31 time for calcul the mask position with numpy : 0.0001125335693359375 nb_pixel_total : 1183 time to create 1 rle with old method : 0.002213001251220703 length of segment : 48 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.0002002716064453125 length of segment : 16 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 2338 time to create 1 rle with old method : 0.004240751266479492 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: -117.61797 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 : 5.841255187988281e-05 nb_pixel_total : 1173 time to create 1 rle with old method : 0.00146484375 length of segment : 43 time for calcul the mask position with numpy : 0.00013518333435058594 nb_pixel_total : 2729 time to create 1 rle with old method : 0.003513813018798828 length of segment : 53 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 816 time to create 1 rle with old method : 0.0010390281677246094 length of segment : 37 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0004887580871582031 length of segment : 43 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 2865 time to create 1 rle with old method : 0.003707408905029297 length of segment : 65 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 2793 time to create 1 rle with old method : 0.0035622119903564453 length of segment : 72 Processing 1 images image shape: (400, 400, 3) min: 38.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -85.70000 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 : 7.271766662597656e-05 nb_pixel_total : 1739 time to create 1 rle with old method : 0.002699613571166992 length of segment : 35 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 3197 time to create 1 rle with old method : 0.0043032169342041016 length of segment : 56 time for calcul the mask position with numpy : 0.00011467933654785156 nb_pixel_total : 3521 time to create 1 rle with old method : 0.004407405853271484 length of segment : 115 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.28984 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1122 time to create 1 rle with old method : 0.0013451576232910156 length of segment : 89 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0008203983306884766 length of segment : 29 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 644 time to create 1 rle with old method : 0.0008287429809570312 length of segment : 39 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 690 time to create 1 rle with old method : 0.0009129047393798828 length of segment : 37 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.04141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0007548332214355469 length of segment : 18 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1552 time to create 1 rle with old method : 0.0019702911376953125 length of segment : 89 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1775 time to create 1 rle with old method : 0.0020606517791748047 length of segment : 103 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 745 time to create 1 rle with old method : 0.0009050369262695312 length of segment : 77 time for calcul the mask position with numpy : 0.0005297660827636719 nb_pixel_total : 53847 time to create 1 rle with old method : 0.06439065933227539 length of segment : 242 Processing 1 images image shape: (400, 400, 3) min: 73.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -47.07109 max: 151.10000 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: -113.66484 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0005786418914794922 length of segment : 13 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 2373 time to create 1 rle with old method : 0.004457950592041016 length of segment : 49 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 782 time to create 1 rle with old method : 0.0014927387237548828 length of segment : 43 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0006606578826904297 length of segment : 24 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 928 time to create 1 rle with old method : 0.0017199516296386719 length of segment : 43 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 1090 time to create 1 rle with old method : 0.0020177364349365234 length of segment : 40 time for calcul the mask position with numpy : 0.00010776519775390625 nb_pixel_total : 2649 time to create 1 rle with old method : 0.0045697689056396484 length of segment : 60 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 372 time to create 1 rle with old method : 0.0006556510925292969 length of segment : 38 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006735324859619141 length of segment : 28 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1444 time to create 1 rle with old method : 0.0017735958099365234 length of segment : 53 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.0011296272277832031 length of segment : 50 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003757476806640625 length of segment : 28 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 887 time to create 1 rle with old method : 0.001157999038696289 length of segment : 39 Processing 1 images image shape: (400, 400, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.17656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0005612373352050781 length of segment : 13 time for calcul the mask position with numpy : 0.00034332275390625 nb_pixel_total : 5870 time to create 1 rle with old method : 0.007590532302856445 length of segment : 82 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 750 time to create 1 rle with old method : 0.0010368824005126953 length of segment : 29 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.0001671314239501953 length of segment : 8 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00018024444580078125 length of segment : 11 time for calcul the mask position with numpy : 0.00022840499877929688 nb_pixel_total : 2226 time to create 1 rle with old method : 0.002924680709838867 length of segment : 90 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0009171962738037109 length of segment : 30 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.0004634857177734375 length of segment : 39 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0004534721374511719 length of segment : 20 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 456 time to create 1 rle with old method : 0.0006082057952880859 length of segment : 28 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.0001659393310546875 length of segment : 10 time for calcul the mask position with numpy : 0.00020194053649902344 nb_pixel_total : 8268 time to create 1 rle with old method : 0.010740995407104492 length of segment : 149 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 685 time to create 1 rle with old method : 0.0009558200836181641 length of segment : 29 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 419 time to create 1 rle with old method : 0.00058746337890625 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.69609 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00017952919006347656 nb_pixel_total : 1700 time to create 1 rle with old method : 0.003489971160888672 length of segment : 126 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 619 time to create 1 rle with old method : 0.0009167194366455078 length of segment : 24 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1140 time to create 1 rle with old method : 0.0015723705291748047 length of segment : 39 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 3379 time to create 1 rle with old method : 0.004278659820556641 length of segment : 90 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1163 time to create 1 rle with old method : 0.001466989517211914 length of segment : 36 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004391670227050781 length of segment : 48 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 779 time to create 1 rle with old method : 0.000995635986328125 length of segment : 35 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 855 time to create 1 rle with old method : 0.0010950565338134766 length of segment : 38 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 107.59219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.0002827644348144531 length of segment : 28 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.000499725341796875 length of segment : 36 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1586 time to create 1 rle with old method : 0.002165079116821289 length of segment : 123 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004324913024902344 length of segment : 29 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 1274 time to create 1 rle with old method : 0.001676321029663086 length of segment : 94 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.00043082237243652344 length of segment : 28 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 916 time to create 1 rle with old method : 0.0011782646179199219 length of segment : 35 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 918 time to create 1 rle with old method : 0.001277923583984375 length of segment : 34 Processing 1 images image shape: (280, 400, 3) min: 59.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009703636169433594 nb_pixel_total : 103760 time to create 1 rle with old method : 0.11692643165588379 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.01016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.000202178955078125 length of segment : 7 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003314018249511719 length of segment : 29 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.0002224445343017578 length of segment : 11 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.00039505958557128906 length of segment : 13 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.0003325939178466797 length of segment : 10 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 691 time to create 1 rle with old method : 0.0009508132934570312 length of segment : 39 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2871 time to create 1 rle with old method : 0.003621339797973633 length of segment : 48 time for calcul the mask position with numpy : 0.0001609325408935547 nb_pixel_total : 6392 time to create 1 rle with old method : 0.008048057556152344 length of segment : 104 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0009996891021728516 length of segment : 48 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003006458282470703 length of segment : 15 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 744 time to create 1 rle with old method : 0.00096893310546875 length of segment : 65 time for calcul the mask position with numpy : 0.00016260147094726562 nb_pixel_total : 6647 time to create 1 rle with old method : 0.008313417434692383 length of segment : 112 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00025272369384765625 length of segment : 24 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.0008075237274169922 length of segment : 55 time for calcul the mask position with numpy : 0.00014257431030273438 nb_pixel_total : 6222 time to create 1 rle with old method : 0.007429599761962891 length of segment : 122 Processing 1 images image shape: (280, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.51406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004496574401855469 length of segment : 19 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 2473 time to create 1 rle with old method : 0.0030717849731445312 length of segment : 87 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 2869 time to create 1 rle with old method : 0.003564119338989258 length of segment : 141 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003981590270996094 length of segment : 28 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00017786026000976562 length of segment : 15 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005404949188232422 length of segment : 19 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.00025963783264160156 length of segment : 16 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.18594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00016617774963378906 nb_pixel_total : 3507 time to create 1 rle with old method : 0.00623631477355957 length of segment : 182 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0003941059112548828 length of segment : 16 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0006716251373291016 length of segment : 29 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.00028204917907714844 length of segment : 13 Processing 1 images image shape: (280, 320, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 139.72500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0005064010620117188 length of segment : 22 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 20 time to create 1 rle with old method : 6.914138793945312e-05 length of segment : 4 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: -117.29375 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 : 7.796287536621094e-05 nb_pixel_total : 1310 time to create 1 rle with old method : 0.0025055408477783203 length of segment : 33 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1248 time to create 1 rle with old method : 0.001687765121459961 length of segment : 38 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.00016045570373535156 length of segment : 16 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 2236 time to create 1 rle with old method : 0.0029773712158203125 length of segment : 52 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.61797 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 : 0.00010704994201660156 nb_pixel_total : 2511 time to create 1 rle with old method : 0.004826545715332031 length of segment : 84 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 2149 time to create 1 rle with old method : 0.004251003265380859 length of segment : 28 time for calcul the mask position with numpy : 0.00017523765563964844 nb_pixel_total : 3337 time to create 1 rle with old method : 0.006459236145019531 length of segment : 56 time for calcul the mask position with numpy : 0.00017142295837402344 nb_pixel_total : 3934 time to create 1 rle with old method : 0.009245157241821289 length of segment : 54 time for calcul the mask position with numpy : 0.0001575946807861328 nb_pixel_total : 3596 time to create 1 rle with old method : 0.005596637725830078 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 30.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -83.93828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1863 time to create 1 rle with old method : 0.002415180206298828 length of segment : 34 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0008671283721923828 length of segment : 20 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 3947 time to create 1 rle with old method : 0.005543708801269531 length of segment : 64 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.47344 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 : 4.649162292480469e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0008070468902587891 length of segment : 28 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1073 time to create 1 rle with old method : 0.0012996196746826172 length of segment : 86 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007781982421875 length of segment : 36 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: 149.79141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0007417201995849609 length of segment : 18 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1453 time to create 1 rle with old method : 0.0018076896667480469 length of segment : 91 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 817 time to create 1 rle with old method : 0.0010104179382324219 length of segment : 77 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 1625 time to create 1 rle with old method : 0.0031228065490722656 length of segment : 51 time for calcul the mask position with numpy : 0.0006363391876220703 nb_pixel_total : 56389 time to create 1 rle with old method : 0.07067227363586426 length of segment : 250 Processing 1 images image shape: (400, 400, 3) min: 68.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -44.83672 max: 151.10000 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: -115.07500 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 : 0.00011849403381347656 nb_pixel_total : 1093 time to create 1 rle with old method : 0.001542806625366211 length of segment : 41 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 700 time to create 1 rle with old method : 0.0009391307830810547 length of segment : 49 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004911422729492188 length of segment : 29 time for calcul the mask position with numpy : 0.00013637542724609375 nb_pixel_total : 2405 time to create 1 rle with old method : 0.00439000129699707 length of segment : 49 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004932880401611328 length of segment : 17 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 694 time to create 1 rle with old method : 0.0009706020355224609 length of segment : 35 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 856 time to create 1 rle with old method : 0.0012362003326416016 length of segment : 42 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00024771690368652344 length of segment : 12 time for calcul the mask position with numpy : 0.00023055076599121094 nb_pixel_total : 7049 time to create 1 rle with old method : 0.008334875106811523 length of segment : 149 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 2367 time to create 1 rle with old method : 0.0036590099334716797 length of segment : 49 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005137920379638672 length of segment : 25 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1258 time to create 1 rle with old method : 0.001600503921508789 length of segment : 50 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0007190704345703125 length of segment : 25 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 685 time to create 1 rle with old method : 0.0009362697601318359 length of segment : 39 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 837 time to create 1 rle with old method : 0.0011608600616455078 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.55156 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003249645233154297 length of segment : 13 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.0001850128173828125 length of segment : 9 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00017452239990234375 length of segment : 10 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 744 time to create 1 rle with old method : 0.0009989738464355469 length of segment : 27 time for calcul the mask position with numpy : 0.00019407272338867188 nb_pixel_total : 6181 time to create 1 rle with old method : 0.007536172866821289 length of segment : 80 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 708 time to create 1 rle with old method : 0.0009357929229736328 length of segment : 30 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0007250308990478516 length of segment : 31 time for calcul the mask position with numpy : 0.000316619873046875 nb_pixel_total : 10164 time to create 1 rle with old method : 0.012171268463134766 length of segment : 201 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.0001952648162841797 length of segment : 26 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0007009506225585938 length of segment : 19 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1051 time to create 1 rle with old method : 0.001325845718383789 length of segment : 59 time for calcul the mask position with numpy : 0.00014901161193847656 nb_pixel_total : 5928 time to create 1 rle with old method : 0.0070841312408447266 length of segment : 113 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0008440017700195312 length of segment : 18 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 487 time to create 1 rle with old method : 0.0007314682006835938 length of segment : 19 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 1965 time to create 1 rle with old method : 0.002520322799682617 length of segment : 67 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 2065 time to create 1 rle with old method : 0.002653837203979492 length of segment : 46 time for calcul the mask position with numpy : 0.0001380443572998047 nb_pixel_total : 4973 time to create 1 rle with old method : 0.0061686038970947266 length of segment : 166 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0007307529449462891 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.80938 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 : 8.440017700195312e-05 nb_pixel_total : 1032 time to create 1 rle with old method : 0.001390218734741211 length of segment : 127 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 611 time to create 1 rle with old method : 0.0008602142333984375 length of segment : 23 time for calcul the mask position with numpy : 0.0001201629638671875 nb_pixel_total : 5858 time to create 1 rle with old method : 0.0073354244232177734 length of segment : 76 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 1205 time to create 1 rle with old method : 0.0020668506622314453 length of segment : 37 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 791 time to create 1 rle with old method : 0.0010242462158203125 length of segment : 34 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1281 time to create 1 rle with old method : 0.0017714500427246094 length of segment : 42 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 108.59219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.00043845176696777344 length of segment : 28 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1553 time to create 1 rle with old method : 0.0021097660064697266 length of segment : 101 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 1539 time to create 1 rle with old method : 0.0021326541900634766 length of segment : 84 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0005862712860107422 length of segment : 35 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 930 time to create 1 rle with old method : 0.0012674331665039062 length of segment : 35 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00030493736267089844 length of segment : 26 time for calcul the mask position with numpy : 0.0002105236053466797 nb_pixel_total : 3323 time to create 1 rle with old method : 0.0041942596435546875 length of segment : 178 Processing 1 images image shape: (280, 400, 3) min: 64.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 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: 151.02187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 0.00012493133544921875 nb_pixel_total : 2980 time to create 1 rle with old method : 0.005130767822265625 length of segment : 47 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0003917217254638672 length of segment : 22 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0005040168762207031 length of segment : 14 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0007131099700927734 length of segment : 29 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00029587745666503906 length of segment : 11 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0005445480346679688 length of segment : 27 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 1098 time to create 1 rle with old method : 0.0019102096557617188 length of segment : 77 time for calcul the mask position with numpy : 0.0002703666687011719 nb_pixel_total : 5421 time to create 1 rle with old method : 0.009180784225463867 length of segment : 130 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 554 time to create 1 rle with old method : 0.0010967254638671875 length of segment : 48 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 762 time to create 1 rle with old method : 0.0013301372528076172 length of segment : 75 time for calcul the mask position with numpy : 0.00019884109497070312 nb_pixel_total : 2774 time to create 1 rle with old method : 0.0055065155029296875 length of segment : 59 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.00034928321838378906 length of segment : 13 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 42 time to create 1 rle with old method : 0.00015163421630859375 length of segment : 14 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.00020384788513183594 length of segment : 7 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 15 time to create 1 rle with old method : 8.249282836914062e-05 length of segment : 4 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00030159950256347656 length of segment : 24 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0004570484161376953 length of segment : 26 Processing 1 images image shape: (280, 400, 3) min: 13.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.70547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00041484832763671875 length of segment : 28 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.0004353523254394531 length of segment : 18 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.0006356239318847656 length of segment : 21 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002720355987548828 length of segment : 12 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 49 time to create 1 rle with old method : 0.0002262592315673828 length of segment : 7 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 369 time to create 1 rle with old method : 0.0004906654357910156 length of segment : 30 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 52 time to create 1 rle with old method : 0.0001556873321533203 length of segment : 6 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0006575584411621094 length of segment : 27 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: 149.15078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00010704994201660156 nb_pixel_total : 1268 time to create 1 rle with old method : 0.001895904541015625 length of segment : 51 time for calcul the mask position with numpy : 0.0001404285430908203 nb_pixel_total : 2205 time to create 1 rle with old method : 0.0029087066650390625 length of segment : 109 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.00038695335388183594 length of segment : 26 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.000263214111328125 length of segment : 14 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 289 time to create 1 rle with old method : 0.0006453990936279297 length of segment : 43 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1369 time to create 1 rle with old method : 0.0017888545989990234 length of segment : 103 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 85 time to create 1 rle with old method : 0.00019478797912597656 length of segment : 18 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.00049591064453125 length of segment : 27 Processing 1 images image shape: (280, 320, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.16250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.0003275871276855469 length of segment : 19 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 18 time to create 1 rle with old method : 5.364418029785156e-05 length of segment : 4 Detection mask done ! Trying to reset tf kernel 2012182 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2647 tf kernel not reseted sub process len(results) : 375 len(list_Values) 375 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 375 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 : 3425 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 375 chid ids of type : 4228 Number RLEs to save : 18432 save missing photos in datou_result : time spend for datou_step_exec : 32.305800437927246 time spend to save output : 1.2664704322814941 total time spend for step 1 : 33.57227087020874 step2:brightness Fri Feb 28 17:21:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1740759627_2011519_1340179760_fff9877111beea918b22bf3cc8e7ea17.jpg treat image : temp/1740759627_2011519_1340179757_0f572a2fcaaa67c68b340e271e41d9e5.jpg treat image : temp/1740759627_2011519_1340179687_f61e2d007e08b711df245bbe09dcb822.jpg treat image : temp/1740759627_2011519_1340179663_240a113cc17fc0b3a72ca7757cbe812e.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 : 4 time used for this insertion : 0.011438846588134766 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.011174917221069336 save missing photos in datou_result : time spend for datou_step_exec : 1.3542699813842773 time spend to save output : 0.027407169342041016 total time spend for step 2 : 1.3816771507263184 step3:blur_detection Fri Feb 28 17:21:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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/1740759627_2011519_1340179760_fff9877111beea918b22bf3cc8e7ea17.jpg resize: (1080, 1920) 1340179760 -7.429770297981256 treat image : temp/1740759627_2011519_1340179757_0f572a2fcaaa67c68b340e271e41d9e5.jpg resize: (1080, 1920) 1340179757 -7.421282420423875 treat image : temp/1740759627_2011519_1340179687_f61e2d007e08b711df245bbe09dcb822.jpg resize: (1080, 1920) 1340179687 -7.404920212409312 treat image : temp/1740759627_2011519_1340179663_240a113cc17fc0b3a72ca7757cbe812e.jpg resize: (1080, 1920) 1340179663 -7.429162021614639 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 : 4 time used for this insertion : 0.010782241821289062 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.011907577514648438 save missing photos in datou_result : time spend for datou_step_exec : 4.464704513549805 time spend to save output : 0.02744889259338379 total time spend for step 3 : 4.4921534061431885 step4:rle_unique_nms_with_priority Fri Feb 28 17:21:08 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 Begin step rle-unique-nms batch 1 Loaded 375 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 95 nb_hashtags : 7 time to prepare the origin masks : 1.1939003467559814 time for calcul the mask position with numpy : 0.08216190338134766 nb_pixel_total : 1881275 time to create 1 rle with new method : 0.11106657981872559 time for calcul the mask position with numpy : 0.009067535400390625 nb_pixel_total : 1336 time to create 1 rle with old method : 0.0027713775634765625 time for calcul the mask position with numpy : 0.009051322937011719 nb_pixel_total : 2493 time to create 1 rle with old method : 0.002866029739379883 time for calcul the mask position with numpy : 0.008731842041015625 nb_pixel_total : 263 time to create 1 rle with old method : 0.00032806396484375 time for calcul the mask position with numpy : 0.00891876220703125 nb_pixel_total : 1216 time to create 1 rle with old method : 0.0016009807586669922 time for calcul the mask position with numpy : 0.009680747985839844 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005724430084228516 time for calcul the mask position with numpy : 0.009865999221801758 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005021095275878906 time for calcul the mask position with numpy : 0.008835792541503906 nb_pixel_total : 2365 time to create 1 rle with old method : 0.0027861595153808594 time for calcul the mask position with numpy : 0.008753061294555664 nb_pixel_total : 1183 time to create 1 rle with old method : 0.0013535022735595703 time for calcul the mask position with numpy : 0.008742570877075195 nb_pixel_total : 1309 time to create 1 rle with old method : 0.0015561580657958984 time for calcul the mask position with numpy : 0.008722066879272461 nb_pixel_total : 244 time to create 1 rle with old method : 0.0003001689910888672 time for calcul the mask position with numpy : 0.008655309677124023 nb_pixel_total : 2407 time to create 1 rle with old method : 0.0027573108673095703 time for calcul the mask position with numpy : 0.008566856384277344 nb_pixel_total : 117 time to create 1 rle with old method : 0.00026488304138183594 time for calcul the mask position with numpy : 0.009402036666870117 nb_pixel_total : 769 time to create 1 rle with old method : 0.0011243820190429688 time for calcul the mask position with numpy : 0.012806177139282227 nb_pixel_total : 1071 time to create 1 rle with old method : 0.0012784004211425781 time for calcul the mask position with numpy : 0.00851297378540039 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006413459777832031 time for calcul the mask position with numpy : 0.008521795272827148 nb_pixel_total : 2869 time to create 1 rle with old method : 0.003403902053833008 time for calcul the mask position with numpy : 0.008585214614868164 nb_pixel_total : 1305 time to create 1 rle with old method : 0.0017094612121582031 time for calcul the mask position with numpy : 0.008546590805053711 nb_pixel_total : 610 time to create 1 rle with old method : 0.0007500648498535156 time for calcul the mask position with numpy : 0.008498668670654297 nb_pixel_total : 978 time to create 1 rle with old method : 0.0011470317840576172 time for calcul the mask position with numpy : 0.008500099182128906 nb_pixel_total : 165 time to create 1 rle with old method : 0.00021696090698242188 time for calcul the mask position with numpy : 0.008519887924194336 nb_pixel_total : 1035 time to create 1 rle with old method : 0.001249551773071289 time for calcul the mask position with numpy : 0.008604049682617188 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006177425384521484 time for calcul the mask position with numpy : 0.008592367172241211 nb_pixel_total : 700 time to create 1 rle with old method : 0.0008022785186767578 time for calcul the mask position with numpy : 0.008576631546020508 nb_pixel_total : 4613 time to create 1 rle with old method : 0.005391120910644531 time for calcul the mask position with numpy : 0.008616209030151367 nb_pixel_total : 53 time to create 1 rle with old method : 0.00010275840759277344 time for calcul the mask position with numpy : 0.008594036102294922 nb_pixel_total : 981 time to create 1 rle with old method : 0.0011675357818603516 time for calcul the mask position with numpy : 0.008604049682617188 nb_pixel_total : 817 time to create 1 rle with old method : 0.0009577274322509766 time for calcul the mask position with numpy : 0.008601188659667969 nb_pixel_total : 30 time to create 1 rle with old method : 6.389617919921875e-05 time for calcul the mask position with numpy : 0.008532524108886719 nb_pixel_total : 139 time to create 1 rle with old method : 0.0001857280731201172 time for calcul the mask position with numpy : 0.008479118347167969 nb_pixel_total : 56 time to create 1 rle with old method : 0.00010585784912109375 time for calcul the mask position with numpy : 0.008474349975585938 nb_pixel_total : 1149 time to create 1 rle with old method : 0.0013208389282226562 time for calcul the mask position with numpy : 0.008469820022583008 nb_pixel_total : 366 time to create 1 rle with old method : 0.00043773651123046875 time for calcul the mask position with numpy : 0.008467435836791992 nb_pixel_total : 302 time to create 1 rle with old method : 0.00035858154296875 time for calcul the mask position with numpy : 0.00841212272644043 nb_pixel_total : 1753 time to create 1 rle with old method : 0.0020580291748046875 time for calcul the mask position with numpy : 0.008519887924194336 nb_pixel_total : 314 time to create 1 rle with old method : 0.000518798828125 time for calcul the mask position with numpy : 0.008403301239013672 nb_pixel_total : 3643 time to create 1 rle with old method : 0.004191160202026367 time for calcul the mask position with numpy : 0.009533166885375977 nb_pixel_total : 620 time to create 1 rle with old method : 0.0007424354553222656 time for calcul the mask position with numpy : 0.008358240127563477 nb_pixel_total : 1679 time to create 1 rle with old method : 0.0019295215606689453 time for calcul the mask position with numpy : 0.008484125137329102 nb_pixel_total : 525 time to create 1 rle with old method : 0.0006134510040283203 time for calcul the mask position with numpy : 0.00853276252746582 nb_pixel_total : 86 time to create 1 rle with old method : 0.0001392364501953125 time for calcul the mask position with numpy : 0.008615493774414062 nb_pixel_total : 1115 time to create 1 rle with old method : 0.001321554183959961 time for calcul the mask position with numpy : 0.00854039192199707 nb_pixel_total : 250 time to create 1 rle with old method : 0.000354766845703125 time for calcul the mask position with numpy : 0.008478879928588867 nb_pixel_total : 2375 time to create 1 rle with old method : 0.002713441848754883 time for calcul the mask position with numpy : 0.008515596389770508 nb_pixel_total : 1203 time to create 1 rle with old method : 0.0014340877532958984 time for calcul the mask position with numpy : 0.008578777313232422 nb_pixel_total : 806 time to create 1 rle with old method : 0.0009870529174804688 time for calcul the mask position with numpy : 0.008519172668457031 nb_pixel_total : 890 time to create 1 rle with old method : 0.0010912418365478516 time for calcul the mask position with numpy : 0.008543968200683594 nb_pixel_total : 993 time to create 1 rle with old method : 0.001135110855102539 time for calcul the mask position with numpy : 0.008530139923095703 nb_pixel_total : 9 time to create 1 rle with old method : 4.100799560546875e-05 time for calcul the mask position with numpy : 0.008519172668457031 nb_pixel_total : 378 time to create 1 rle with old method : 0.00048613548278808594 time for calcul the mask position with numpy : 0.008541584014892578 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001423358917236328 time for calcul the mask position with numpy : 0.00857996940612793 nb_pixel_total : 167 time to create 1 rle with old method : 0.00021386146545410156 time for calcul the mask position with numpy : 0.008519172668457031 nb_pixel_total : 143 time to create 1 rle with old method : 0.00022745132446289062 time for calcul the mask position with numpy : 0.008544683456420898 nb_pixel_total : 783 time to create 1 rle with old method : 0.0009274482727050781 time for calcul the mask position with numpy : 0.00850534439086914 nb_pixel_total : 10 time to create 1 rle with old method : 4.100799560546875e-05 time for calcul the mask position with numpy : 0.008464574813842773 nb_pixel_total : 18 time to create 1 rle with old method : 6.794929504394531e-05 time for calcul the mask position with numpy : 0.008455514907836914 nb_pixel_total : 29 time to create 1 rle with old method : 9.036064147949219e-05 time for calcul the mask position with numpy : 0.008540153503417969 nb_pixel_total : 634 time to create 1 rle with old method : 0.0007481575012207031 time for calcul the mask position with numpy : 0.008524894714355469 nb_pixel_total : 166 time to create 1 rle with old method : 0.00021600723266601562 time for calcul the mask position with numpy : 0.008459091186523438 nb_pixel_total : 1565 time to create 1 rle with old method : 0.0017697811126708984 time for calcul the mask position with numpy : 0.008557796478271484 nb_pixel_total : 369 time to create 1 rle with old method : 0.00045180320739746094 time for calcul the mask position with numpy : 0.008964776992797852 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005083084106445312 time for calcul the mask position with numpy : 0.008404254913330078 nb_pixel_total : 1636 time to create 1 rle with old method : 0.001863718032836914 time for calcul the mask position with numpy : 0.008417844772338867 nb_pixel_total : 235 time to create 1 rle with old method : 0.0002880096435546875 time for calcul the mask position with numpy : 0.008466958999633789 nb_pixel_total : 205 time to create 1 rle with old method : 0.00031304359436035156 time for calcul the mask position with numpy : 0.009810924530029297 nb_pixel_total : 101 time to create 1 rle with old method : 0.00018167495727539062 time for calcul the mask position with numpy : 0.011043310165405273 nb_pixel_total : 2265 time to create 1 rle with old method : 0.004629373550415039 time for calcul the mask position with numpy : 0.01126551628112793 nb_pixel_total : 6350 time to create 1 rle with old method : 0.00738835334777832 time for calcul the mask position with numpy : 0.008549928665161133 nb_pixel_total : 646 time to create 1 rle with old method : 0.0007832050323486328 time for calcul the mask position with numpy : 0.008512496948242188 nb_pixel_total : 75 time to create 1 rle with old method : 0.00010228157043457031 time for calcul the mask position with numpy : 0.008472681045532227 nb_pixel_total : 903 time to create 1 rle with old method : 0.0012500286102294922 time for calcul the mask position with numpy : 0.014032125473022461 nb_pixel_total : 102300 time to create 1 rle with old method : 0.1182560920715332 time for calcul the mask position with numpy : 0.008527994155883789 nb_pixel_total : 2804 time to create 1 rle with old method : 0.0032584667205810547 time for calcul the mask position with numpy : 0.008420467376708984 nb_pixel_total : 945 time to create 1 rle with old method : 0.0011196136474609375 time for calcul the mask position with numpy : 0.008652448654174805 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006518363952636719 time for calcul the mask position with numpy : 0.008577585220336914 nb_pixel_total : 273 time to create 1 rle with old method : 0.0003414154052734375 time for calcul the mask position with numpy : 0.008545398712158203 nb_pixel_total : 516 time to create 1 rle with old method : 0.0005965232849121094 time for calcul the mask position with numpy : 0.008492469787597656 nb_pixel_total : 581 time to create 1 rle with old method : 0.0006957054138183594 time for calcul the mask position with numpy : 0.008581161499023438 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002338886260986328 time for calcul the mask position with numpy : 0.008672475814819336 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.008585214614868164 nb_pixel_total : 2990 time to create 1 rle with old method : 0.003417491912841797 time for calcul the mask position with numpy : 0.008574485778808594 nb_pixel_total : 668 time to create 1 rle with old method : 0.0007739067077636719 time for calcul the mask position with numpy : 0.008722543716430664 nb_pixel_total : 3507 time to create 1 rle with old method : 0.00582122802734375 time for calcul the mask position with numpy : 0.010892152786254883 nb_pixel_total : 1046 time to create 1 rle with old method : 0.0019233226776123047 time for calcul the mask position with numpy : 0.009840250015258789 nb_pixel_total : 142 time to create 1 rle with old method : 0.00026679039001464844 time for calcul the mask position with numpy : 0.00981903076171875 nb_pixel_total : 107 time to create 1 rle with old method : 0.00019931793212890625 time for calcul the mask position with numpy : 0.009516239166259766 nb_pixel_total : 318 time to create 1 rle with old method : 0.0003936290740966797 time for calcul the mask position with numpy : 0.008638620376586914 nb_pixel_total : 6744 time to create 1 rle with old method : 0.007902383804321289 time for calcul the mask position with numpy : 0.008581161499023438 nb_pixel_total : 319 time to create 1 rle with old method : 0.00039458274841308594 time for calcul the mask position with numpy : 0.008520364761352539 nb_pixel_total : 503 time to create 1 rle with old method : 0.0005917549133300781 time for calcul the mask position with numpy : 0.008469104766845703 nb_pixel_total : 16 time to create 1 rle with old method : 3.719329833984375e-05 time for calcul the mask position with numpy : 0.008508443832397461 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005142688751220703 time for calcul the mask position with numpy : 0.008471965789794922 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002472400665283203 time for calcul the mask position with numpy : 0.008574962615966797 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005693435668945312 time for calcul the mask position with numpy : 0.012082338333129883 nb_pixel_total : 241 time to create 1 rle with old method : 0.0005688667297363281 time for calcul the mask position with numpy : 0.011993408203125 nb_pixel_total : 142 time to create 1 rle with old method : 0.00033092498779296875 create new chi : 1.2858219146728516 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 : 0.005755186080932617 batch 1 Loaded 96 chid ids of type : 4230 Number RLEs to save : 8966 TO DO : save crop sub photo not yet done ! save time : 0.5817499160766602 nb_obj : 85 nb_hashtags : 6 time to prepare the origin masks : 2.169006824493408 time for calcul the mask position with numpy : 0.03833770751953125 nb_pixel_total : 1923562 time to create 1 rle with new method : 0.06831574440002441 time for calcul the mask position with numpy : 0.00901174545288086 nb_pixel_total : 73582 time to create 1 rle with old method : 0.10271716117858887 time for calcul the mask position with numpy : 0.007100343704223633 nb_pixel_total : 1722 time to create 1 rle with old method : 0.0021479129791259766 time for calcul the mask position with numpy : 0.006881237030029297 nb_pixel_total : 1375 time to create 1 rle with old method : 0.0016944408416748047 time for calcul the mask position with numpy : 0.006765842437744141 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005459785461425781 time for calcul the mask position with numpy : 0.006761312484741211 nb_pixel_total : 1039 time to create 1 rle with old method : 0.00133514404296875 time for calcul the mask position with numpy : 0.007234334945678711 nb_pixel_total : 2339 time to create 1 rle with old method : 0.002743244171142578 time for calcul the mask position with numpy : 0.007191896438598633 nb_pixel_total : 420 time to create 1 rle with old method : 0.0005495548248291016 time for calcul the mask position with numpy : 0.008000373840332031 nb_pixel_total : 122 time to create 1 rle with old method : 0.00029015541076660156 time for calcul the mask position with numpy : 0.008187055587768555 nb_pixel_total : 2395 time to create 1 rle with old method : 0.003233671188354492 time for calcul the mask position with numpy : 0.007232189178466797 nb_pixel_total : 1150 time to create 1 rle with old method : 0.0016338825225830078 time for calcul the mask position with numpy : 0.007210731506347656 nb_pixel_total : 1176 time to create 1 rle with old method : 0.0014719963073730469 time for calcul the mask position with numpy : 0.006682872772216797 nb_pixel_total : 215 time to create 1 rle with old method : 0.00030040740966796875 time for calcul the mask position with numpy : 0.007611513137817383 nb_pixel_total : 108 time to create 1 rle with old method : 0.0001506805419921875 time for calcul the mask position with numpy : 0.007445812225341797 nb_pixel_total : 758 time to create 1 rle with old method : 0.0010867118835449219 time for calcul the mask position with numpy : 0.0073757171630859375 nb_pixel_total : 952 time to create 1 rle with old method : 0.0012676715850830078 time for calcul the mask position with numpy : 0.007999658584594727 nb_pixel_total : 521 time to create 1 rle with old method : 0.0008006095886230469 time for calcul the mask position with numpy : 0.008115053176879883 nb_pixel_total : 687 time to create 1 rle with old method : 0.0008938312530517578 time for calcul the mask position with numpy : 0.006989002227783203 nb_pixel_total : 28 time to create 1 rle with old method : 7.43865966796875e-05 time for calcul the mask position with numpy : 0.006920576095581055 nb_pixel_total : 73 time to create 1 rle with old method : 0.00022840499877929688 time for calcul the mask position with numpy : 0.008768796920776367 nb_pixel_total : 104 time to create 1 rle with old method : 0.0002110004425048828 time for calcul the mask position with numpy : 0.006737232208251953 nb_pixel_total : 494 time to create 1 rle with old method : 0.0008733272552490234 time for calcul the mask position with numpy : 0.007051944732666016 nb_pixel_total : 706 time to create 1 rle with old method : 0.0012319087982177734 time for calcul the mask position with numpy : 0.006966352462768555 nb_pixel_total : 675 time to create 1 rle with old method : 0.0010998249053955078 time for calcul the mask position with numpy : 0.006974458694458008 nb_pixel_total : 1763 time to create 1 rle with old method : 0.0031409263610839844 time for calcul the mask position with numpy : 0.007084846496582031 nb_pixel_total : 806 time to create 1 rle with old method : 0.0013360977172851562 time for calcul the mask position with numpy : 0.006894588470458984 nb_pixel_total : 197 time to create 1 rle with old method : 0.00034499168395996094 time for calcul the mask position with numpy : 0.007043361663818359 nb_pixel_total : 325 time to create 1 rle with old method : 0.0006160736083984375 time for calcul the mask position with numpy : 0.007227420806884766 nb_pixel_total : 1135 time to create 1 rle with old method : 0.0018832683563232422 time for calcul the mask position with numpy : 0.007771492004394531 nb_pixel_total : 358 time to create 1 rle with old method : 0.0006432533264160156 time for calcul the mask position with numpy : 0.007195472717285156 nb_pixel_total : 316 time to create 1 rle with old method : 0.0003731250762939453 time for calcul the mask position with numpy : 0.007126808166503906 nb_pixel_total : 892 time to create 1 rle with old method : 0.0010368824005126953 time for calcul the mask position with numpy : 0.0073740482330322266 nb_pixel_total : 1910 time to create 1 rle with old method : 0.002187013626098633 time for calcul the mask position with numpy : 0.006877899169921875 nb_pixel_total : 116 time to create 1 rle with old method : 0.00025582313537597656 time for calcul the mask position with numpy : 0.006448030471801758 nb_pixel_total : 522 time to create 1 rle with old method : 0.0006144046783447266 time for calcul the mask position with numpy : 0.0064239501953125 nb_pixel_total : 666 time to create 1 rle with old method : 0.0007953643798828125 time for calcul the mask position with numpy : 0.006785154342651367 nb_pixel_total : 3421 time to create 1 rle with old method : 0.003854036331176758 time for calcul the mask position with numpy : 0.006673574447631836 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005371570587158203 time for calcul the mask position with numpy : 0.0067250728607177734 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001392364501953125 time for calcul the mask position with numpy : 0.0066187381744384766 nb_pixel_total : 1398 time to create 1 rle with old method : 0.0016162395477294922 time for calcul the mask position with numpy : 0.0072095394134521484 nb_pixel_total : 633 time to create 1 rle with old method : 0.0007469654083251953 time for calcul the mask position with numpy : 0.007188558578491211 nb_pixel_total : 2566 time to create 1 rle with old method : 0.0029239654541015625 time for calcul the mask position with numpy : 0.007114887237548828 nb_pixel_total : 798 time to create 1 rle with old method : 0.0009438991546630859 time for calcul the mask position with numpy : 0.0071260929107666016 nb_pixel_total : 856 time to create 1 rle with old method : 0.0010471343994140625 time for calcul the mask position with numpy : 0.007338523864746094 nb_pixel_total : 922 time to create 1 rle with old method : 0.0011143684387207031 time for calcul the mask position with numpy : 0.007219552993774414 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001621246337890625 time for calcul the mask position with numpy : 0.007063388824462891 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002548694610595703 time for calcul the mask position with numpy : 0.007311582565307617 nb_pixel_total : 301 time to create 1 rle with old method : 0.0003705024719238281 time for calcul the mask position with numpy : 0.0074880123138427734 nb_pixel_total : 83 time to create 1 rle with old method : 0.00014853477478027344 time for calcul the mask position with numpy : 0.007417917251586914 nb_pixel_total : 751 time to create 1 rle with old method : 0.0008852481842041016 time for calcul the mask position with numpy : 0.010036230087280273 nb_pixel_total : 82 time to create 1 rle with old method : 0.00011920928955078125 time for calcul the mask position with numpy : 0.01002359390258789 nb_pixel_total : 188 time to create 1 rle with old method : 0.0004246234893798828 time for calcul the mask position with numpy : 0.012762069702148438 nb_pixel_total : 5684 time to create 1 rle with old method : 0.009470224380493164 time for calcul the mask position with numpy : 0.010780572891235352 nb_pixel_total : 2405 time to create 1 rle with old method : 0.003139495849609375 time for calcul the mask position with numpy : 0.01143646240234375 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005021095275878906 time for calcul the mask position with numpy : 0.010596990585327148 nb_pixel_total : 383 time to create 1 rle with old method : 0.0004961490631103516 time for calcul the mask position with numpy : 0.011381387710571289 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005080699920654297 time for calcul the mask position with numpy : 0.016419410705566406 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003218650817871094 time for calcul the mask position with numpy : 0.010846138000488281 nb_pixel_total : 314 time to create 1 rle with old method : 0.0003952980041503906 time for calcul the mask position with numpy : 0.010161638259887695 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001442432403564453 time for calcul the mask position with numpy : 0.010502338409423828 nb_pixel_total : 40 time to create 1 rle with old method : 8.416175842285156e-05 time for calcul the mask position with numpy : 0.010027885437011719 nb_pixel_total : 849 time to create 1 rle with old method : 0.001039743423461914 time for calcul the mask position with numpy : 0.010137319564819336 nb_pixel_total : 295 time to create 1 rle with old method : 0.0003616809844970703 time for calcul the mask position with numpy : 0.009181499481201172 nb_pixel_total : 75 time to create 1 rle with old method : 0.00010728836059570312 time for calcul the mask position with numpy : 0.011857986450195312 nb_pixel_total : 2267 time to create 1 rle with old method : 0.004092693328857422 time for calcul the mask position with numpy : 0.014568805694580078 nb_pixel_total : 19 time to create 1 rle with old method : 5.054473876953125e-05 time for calcul the mask position with numpy : 0.016142606735229492 nb_pixel_total : 747 time to create 1 rle with old method : 0.0011446475982666016 time for calcul the mask position with numpy : 0.01143646240234375 nb_pixel_total : 337 time to create 1 rle with old method : 0.0004382133483886719 time for calcul the mask position with numpy : 0.011574745178222656 nb_pixel_total : 40 time to create 1 rle with old method : 9.417533874511719e-05 time for calcul the mask position with numpy : 0.011311054229736328 nb_pixel_total : 1301 time to create 1 rle with old method : 0.0016450881958007812 time for calcul the mask position with numpy : 0.010170698165893555 nb_pixel_total : 1341 time to create 1 rle with old method : 0.0016193389892578125 time for calcul the mask position with numpy : 0.010691165924072266 nb_pixel_total : 131 time to create 1 rle with old method : 0.00019311904907226562 time for calcul the mask position with numpy : 0.01185297966003418 nb_pixel_total : 177 time to create 1 rle with old method : 0.00025177001953125 time for calcul the mask position with numpy : 0.013419628143310547 nb_pixel_total : 187 time to create 1 rle with old method : 0.00025177001953125 time for calcul the mask position with numpy : 0.01052403450012207 nb_pixel_total : 2939 time to create 1 rle with old method : 0.0034906864166259766 time for calcul the mask position with numpy : 0.011584281921386719 nb_pixel_total : 3841 time to create 1 rle with old method : 0.004531145095825195 time for calcul the mask position with numpy : 0.012305736541748047 nb_pixel_total : 1015 time to create 1 rle with old method : 0.0012240409851074219 time for calcul the mask position with numpy : 0.012286663055419922 nb_pixel_total : 136 time to create 1 rle with old method : 0.00019288063049316406 time for calcul the mask position with numpy : 0.012830257415771484 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006372928619384766 time for calcul the mask position with numpy : 0.012689590454101562 nb_pixel_total : 3338 time to create 1 rle with old method : 0.0044367313385009766 time for calcul the mask position with numpy : 0.009464740753173828 nb_pixel_total : 6323 time to create 1 rle with old method : 0.008069276809692383 time for calcul the mask position with numpy : 0.007875680923461914 nb_pixel_total : 304 time to create 1 rle with old method : 0.0004889965057373047 time for calcul the mask position with numpy : 0.0071675777435302734 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002779960632324219 time for calcul the mask position with numpy : 0.007189273834228516 nb_pixel_total : 15 time to create 1 rle with old method : 5.054473876953125e-05 time for calcul the mask position with numpy : 0.007004976272583008 nb_pixel_total : 544 time to create 1 rle with old method : 0.0007519721984863281 time for calcul the mask position with numpy : 0.00707554817199707 nb_pixel_total : 236 time to create 1 rle with old method : 0.0002999305725097656 create new chi : 1.0652198791503906 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 : 0.0014133453369140625 batch 1 Loaded 86 chid ids of type : 4230 Number RLEs to save : 8468 TO DO : save crop sub photo not yet done ! save time : 1.4306647777557373 nb_obj : 92 nb_hashtags : 8 time to prepare the origin masks : 1.5228683948516846 time for calcul the mask position with numpy : 0.0766146183013916 nb_pixel_total : 1823034 time to create 1 rle with new method : 0.10891580581665039 time for calcul the mask position with numpy : 0.007115840911865234 nb_pixel_total : 53847 time to create 1 rle with old method : 0.06450843811035156 time for calcul the mask position with numpy : 0.0073833465576171875 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003695487976074219 time for calcul the mask position with numpy : 0.006666421890258789 nb_pixel_total : 1183 time to create 1 rle with old method : 0.001971006393432617 time for calcul the mask position with numpy : 0.0070035457611083984 nb_pixel_total : 1345 time to create 1 rle with old method : 0.002237081527709961 time for calcul the mask position with numpy : 0.009768962860107422 nb_pixel_total : 2338 time to create 1 rle with old method : 0.0046269893646240234 time for calcul the mask position with numpy : 0.00910043716430664 nb_pixel_total : 2729 time to create 1 rle with old method : 0.004798173904418945 time for calcul the mask position with numpy : 0.00960993766784668 nb_pixel_total : 173 time to create 1 rle with old method : 0.0004258155822753906 time for calcul the mask position with numpy : 0.01043558120727539 nb_pixel_total : 261 time to create 1 rle with old method : 0.0005881786346435547 time for calcul the mask position with numpy : 0.01159977912902832 nb_pixel_total : 270 time to create 1 rle with old method : 0.0005347728729248047 time for calcul the mask position with numpy : 0.013556241989135742 nb_pixel_total : 1552 time to create 1 rle with old method : 0.002588510513305664 time for calcul the mask position with numpy : 0.007030487060546875 nb_pixel_total : 1122 time to create 1 rle with old method : 0.004755973815917969 time for calcul the mask position with numpy : 0.011892318725585938 nb_pixel_total : 1173 time to create 1 rle with old method : 0.0021538734436035156 time for calcul the mask position with numpy : 0.011396646499633789 nb_pixel_total : 92 time to create 1 rle with old method : 0.00019288063049316406 time for calcul the mask position with numpy : 0.00973057746887207 nb_pixel_total : 745 time to create 1 rle with old method : 0.0061604976654052734 time for calcul the mask position with numpy : 0.010549068450927734 nb_pixel_total : 816 time to create 1 rle with old method : 0.0013747215270996094 time for calcul the mask position with numpy : 0.007418394088745117 nb_pixel_total : 1739 time to create 1 rle with old method : 0.0021758079528808594 time for calcul the mask position with numpy : 0.006910800933837891 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006504058837890625 time for calcul the mask position with numpy : 0.006964206695556641 nb_pixel_total : 3197 time to create 1 rle with old method : 0.0036711692810058594 time for calcul the mask position with numpy : 0.006890773773193359 nb_pixel_total : 52 time to create 1 rle with old method : 0.0001163482666015625 time for calcul the mask position with numpy : 0.007069826126098633 nb_pixel_total : 644 time to create 1 rle with old method : 0.0008146762847900391 time for calcul the mask position with numpy : 0.007194995880126953 nb_pixel_total : 3521 time to create 1 rle with old method : 0.004150390625 time for calcul the mask position with numpy : 0.006961345672607422 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006554126739501953 time for calcul the mask position with numpy : 0.00681757926940918 nb_pixel_total : 702 time to create 1 rle with old method : 0.0008263587951660156 time for calcul the mask position with numpy : 0.006880044937133789 nb_pixel_total : 5870 time to create 1 rle with old method : 0.0067789554595947266 time for calcul the mask position with numpy : 0.0068323612213134766 nb_pixel_total : 343 time to create 1 rle with old method : 0.0004620552062988281 time for calcul the mask position with numpy : 0.00642704963684082 nb_pixel_total : 88 time to create 1 rle with old method : 0.00014162063598632812 time for calcul the mask position with numpy : 0.006612062454223633 nb_pixel_total : 779 time to create 1 rle with old method : 0.0009388923645019531 time for calcul the mask position with numpy : 0.006781816482543945 nb_pixel_total : 188 time to create 1 rle with old method : 0.00023317337036132812 time for calcul the mask position with numpy : 0.007913589477539062 nb_pixel_total : 7718 time to create 1 rle with old method : 0.01186823844909668 time for calcul the mask position with numpy : 0.0066394805908203125 nb_pixel_total : 1163 time to create 1 rle with old method : 0.0015025138854980469 time for calcul the mask position with numpy : 0.007186412811279297 nb_pixel_total : 376 time to create 1 rle with old method : 0.0004546642303466797 time for calcul the mask position with numpy : 0.0066187381744384766 nb_pixel_total : 331 time to create 1 rle with old method : 0.00041961669921875 time for calcul the mask position with numpy : 0.00664973258972168 nb_pixel_total : 1 time to create 1 rle with old method : 2.3603439331054688e-05 time for calcul the mask position with numpy : 0.0069732666015625 nb_pixel_total : 323 time to create 1 rle with old method : 0.00040531158447265625 time for calcul the mask position with numpy : 0.006609678268432617 nb_pixel_total : 632 time to create 1 rle with old method : 0.0008275508880615234 time for calcul the mask position with numpy : 0.006491422653198242 nb_pixel_total : 1586 time to create 1 rle with old method : 0.0018680095672607422 time for calcul the mask position with numpy : 0.006596088409423828 nb_pixel_total : 29 time to create 1 rle with old method : 9.441375732421875e-05 time for calcul the mask position with numpy : 0.006519317626953125 nb_pixel_total : 174 time to create 1 rle with old method : 0.0003197193145751953 time for calcul the mask position with numpy : 0.0067138671875 nb_pixel_total : 645 time to create 1 rle with old method : 0.0007967948913574219 time for calcul the mask position with numpy : 0.00677800178527832 nb_pixel_total : 619 time to create 1 rle with old method : 0.0007493495941162109 time for calcul the mask position with numpy : 0.008002996444702148 nb_pixel_total : 1700 time to create 1 rle with old method : 0.002836942672729492 time for calcul the mask position with numpy : 0.006612539291381836 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006339550018310547 time for calcul the mask position with numpy : 0.0065839290618896484 nb_pixel_total : 83 time to create 1 rle with old method : 0.00012302398681640625 time for calcul the mask position with numpy : 0.006811380386352539 nb_pixel_total : 2649 time to create 1 rle with old method : 0.0031507015228271484 time for calcul the mask position with numpy : 0.0072727203369140625 nb_pixel_total : 2373 time to create 1 rle with old method : 0.0029206275939941406 time for calcul the mask position with numpy : 0.0071179866790771484 nb_pixel_total : 241 time to create 1 rle with old method : 0.00031065940856933594 time for calcul the mask position with numpy : 0.008046388626098633 nb_pixel_total : 750 time to create 1 rle with old method : 0.0008881092071533203 time for calcul the mask position with numpy : 0.0069997310638427734 nb_pixel_total : 1140 time to create 1 rle with old method : 0.0014462471008300781 time for calcul the mask position with numpy : 0.0069239139556884766 nb_pixel_total : 1090 time to create 1 rle with old method : 0.0012867450714111328 time for calcul the mask position with numpy : 0.00707244873046875 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003361701965332031 time for calcul the mask position with numpy : 0.007167816162109375 nb_pixel_total : 6 time to create 1 rle with old method : 4.172325134277344e-05 time for calcul the mask position with numpy : 0.007241725921630859 nb_pixel_total : 108 time to create 1 rle with old method : 0.000164031982421875 time for calcul the mask position with numpy : 0.007018566131591797 nb_pixel_total : 340 time to create 1 rle with old method : 0.00041031837463378906 time for calcul the mask position with numpy : 0.007115840911865234 nb_pixel_total : 18 time to create 1 rle with old method : 8.630752563476562e-05 time for calcul the mask position with numpy : 0.006773948669433594 nb_pixel_total : 782 time to create 1 rle with old method : 0.0009591579437255859 time for calcul the mask position with numpy : 0.006493091583251953 nb_pixel_total : 174 time to create 1 rle with old method : 0.00025534629821777344 time for calcul the mask position with numpy : 0.006350994110107422 nb_pixel_total : 71 time to create 1 rle with old method : 0.0001461505889892578 time for calcul the mask position with numpy : 0.006409883499145508 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002532005310058594 time for calcul the mask position with numpy : 0.006680727005004883 nb_pixel_total : 3379 time to create 1 rle with old method : 0.0041463375091552734 time for calcul the mask position with numpy : 0.007115602493286133 nb_pixel_total : 1444 time to create 1 rle with old method : 0.0017631053924560547 time for calcul the mask position with numpy : 0.006527423858642578 nb_pixel_total : 355 time to create 1 rle with old method : 0.00048542022705078125 time for calcul the mask position with numpy : 0.007131814956665039 nb_pixel_total : 316 time to create 1 rle with old method : 0.0004131793975830078 time for calcul the mask position with numpy : 0.006834983825683594 nb_pixel_total : 456 time to create 1 rle with old method : 0.000568389892578125 time for calcul the mask position with numpy : 0.006412506103515625 nb_pixel_total : 6 time to create 1 rle with old method : 4.1484832763671875e-05 time for calcul the mask position with numpy : 0.0064432621002197266 nb_pixel_total : 318 time to create 1 rle with old method : 0.0003921985626220703 time for calcul the mask position with numpy : 0.007947444915771484 nb_pixel_total : 103760 time to create 1 rle with old method : 0.1529710292816162 time for calcul the mask position with numpy : 0.007467031478881836 nb_pixel_total : 186 time to create 1 rle with old method : 0.0003452301025390625 time for calcul the mask position with numpy : 0.007866859436035156 nb_pixel_total : 112 time to create 1 rle with old method : 0.00020599365234375 time for calcul the mask position with numpy : 0.007976055145263672 nb_pixel_total : 691 time to create 1 rle with old method : 0.0011758804321289062 time for calcul the mask position with numpy : 0.007860422134399414 nb_pixel_total : 744 time to create 1 rle with old method : 0.0012054443359375 time for calcul the mask position with numpy : 0.0075931549072265625 nb_pixel_total : 3507 time to create 1 rle with old method : 0.005689144134521484 time for calcul the mask position with numpy : 0.008247613906860352 nb_pixel_total : 2473 time to create 1 rle with old method : 0.004077911376953125 time for calcul the mask position with numpy : 0.007659912109375 nb_pixel_total : 760 time to create 1 rle with old method : 0.0012350082397460938 time for calcul the mask position with numpy : 0.007652759552001953 nb_pixel_total : 558 time to create 1 rle with old method : 0.0009443759918212891 time for calcul the mask position with numpy : 0.007932901382446289 nb_pixel_total : 286 time to create 1 rle with old method : 0.0005109310150146484 time for calcul the mask position with numpy : 0.00830984115600586 nb_pixel_total : 228 time to create 1 rle with old method : 0.00040268898010253906 time for calcul the mask position with numpy : 0.00852203369140625 nb_pixel_total : 140 time to create 1 rle with old method : 0.0002510547637939453 time for calcul the mask position with numpy : 0.007988929748535156 nb_pixel_total : 184 time to create 1 rle with old method : 0.000324249267578125 time for calcul the mask position with numpy : 0.008488893508911133 nb_pixel_total : 2871 time to create 1 rle with old method : 0.00504302978515625 time for calcul the mask position with numpy : 0.007292747497558594 nb_pixel_total : 4123 time to create 1 rle with old method : 0.004921674728393555 time for calcul the mask position with numpy : 0.006989479064941406 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003743171691894531 time for calcul the mask position with numpy : 0.006581783294677734 nb_pixel_total : 132 time to create 1 rle with old method : 0.0001728534698486328 time for calcul the mask position with numpy : 0.008871316909790039 nb_pixel_total : 2869 time to create 1 rle with old method : 0.0034062862396240234 time for calcul the mask position with numpy : 0.009125471115112305 nb_pixel_total : 6392 time to create 1 rle with old method : 0.0074062347412109375 time for calcul the mask position with numpy : 0.009976387023925781 nb_pixel_total : 275 time to create 1 rle with old method : 0.000720977783203125 time for calcul the mask position with numpy : 0.014023542404174805 nb_pixel_total : 346 time to create 1 rle with old method : 0.0007371902465820312 time for calcul the mask position with numpy : 0.012887716293334961 nb_pixel_total : 254 time to create 1 rle with old method : 0.0004904270172119141 time for calcul the mask position with numpy : 0.013757705688476562 nb_pixel_total : 20 time to create 1 rle with old method : 6.580352783203125e-05 time for calcul the mask position with numpy : 0.012325048446655273 nb_pixel_total : 165 time to create 1 rle with old method : 0.0003235340118408203 time for calcul the mask position with numpy : 0.011193990707397461 nb_pixel_total : 228 time to create 1 rle with old method : 0.0004200935363769531 time for calcul the mask position with numpy : 0.011023998260498047 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002887248992919922 time for calcul the mask position with numpy : 0.011303186416625977 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005915164947509766 create new chi : 1.2902638912200928 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 : 0.0025115013122558594 batch 1 Loaded 93 chid ids of type : 4230 Number RLEs to save : 9577 TO DO : save crop sub photo not yet done ! save time : 0.6677579879760742 nb_obj : 99 nb_hashtags : 7 time to prepare the origin masks : 1.4231462478637695 time for calcul the mask position with numpy : 0.1793653964996338 nb_pixel_total : 1906677 time to create 1 rle with new method : 0.11703085899353027 time for calcul the mask position with numpy : 0.008124828338623047 nb_pixel_total : 56389 time to create 1 rle with old method : 0.07396936416625977 time for calcul the mask position with numpy : 0.012228727340698242 nb_pixel_total : 1310 time to create 1 rle with old method : 0.0023446083068847656 time for calcul the mask position with numpy : 0.01288747787475586 nb_pixel_total : 1248 time to create 1 rle with old method : 0.0020704269409179688 time for calcul the mask position with numpy : 0.012929677963256836 nb_pixel_total : 2236 time to create 1 rle with old method : 0.0041692256927490234 time for calcul the mask position with numpy : 0.01560354232788086 nb_pixel_total : 668 time to create 1 rle with old method : 0.0015637874603271484 time for calcul the mask position with numpy : 0.014030933380126953 nb_pixel_total : 3337 time to create 1 rle with old method : 0.005917787551879883 time for calcul the mask position with numpy : 0.01562356948852539 nb_pixel_total : 1453 time to create 1 rle with old method : 0.0024306774139404297 time for calcul the mask position with numpy : 0.008337020874023438 nb_pixel_total : 1073 time to create 1 rle with old method : 0.0017626285552978516 time for calcul the mask position with numpy : 0.009740114212036133 nb_pixel_total : 5 time to create 1 rle with old method : 6.318092346191406e-05 time for calcul the mask position with numpy : 0.009612321853637695 nb_pixel_total : 2149 time to create 1 rle with old method : 0.004409313201904297 time for calcul the mask position with numpy : 0.008960485458374023 nb_pixel_total : 2511 time to create 1 rle with old method : 0.005103111267089844 time for calcul the mask position with numpy : 0.008115053176879883 nb_pixel_total : 92 time to create 1 rle with old method : 0.0001900196075439453 time for calcul the mask position with numpy : 0.008173942565917969 nb_pixel_total : 817 time to create 1 rle with old method : 0.0013546943664550781 time for calcul the mask position with numpy : 0.007899284362792969 nb_pixel_total : 1863 time to create 1 rle with old method : 0.0031805038452148438 time for calcul the mask position with numpy : 0.009183406829833984 nb_pixel_total : 620 time to create 1 rle with old method : 0.0011343955993652344 time for calcul the mask position with numpy : 0.007947206497192383 nb_pixel_total : 496 time to create 1 rle with old method : 0.0009093284606933594 time for calcul the mask position with numpy : 0.007995843887329102 nb_pixel_total : 3947 time to create 1 rle with old method : 0.006742238998413086 time for calcul the mask position with numpy : 0.008700370788574219 nb_pixel_total : 594 time to create 1 rle with old method : 0.0010526180267333984 time for calcul the mask position with numpy : 0.008325815200805664 nb_pixel_total : 1625 time to create 1 rle with old method : 0.00274658203125 time for calcul the mask position with numpy : 0.007507801055908203 nb_pixel_total : 502 time to create 1 rle with old method : 0.0009200572967529297 time for calcul the mask position with numpy : 0.008085012435913086 nb_pixel_total : 2065 time to create 1 rle with old method : 0.0023241043090820312 time for calcul the mask position with numpy : 0.00715327262878418 nb_pixel_total : 708 time to create 1 rle with old method : 0.0008356571197509766 time for calcul the mask position with numpy : 0.007223844528198242 nb_pixel_total : 6181 time to create 1 rle with old method : 0.007162332534790039 time for calcul the mask position with numpy : 0.0070629119873046875 nb_pixel_total : 791 time to create 1 rle with old method : 0.0009164810180664062 time for calcul the mask position with numpy : 0.00680232048034668 nb_pixel_total : 196 time to create 1 rle with old method : 0.00023937225341796875 time for calcul the mask position with numpy : 0.006683826446533203 nb_pixel_total : 1965 time to create 1 rle with old method : 0.0022449493408203125 time for calcul the mask position with numpy : 0.006823301315307617 nb_pixel_total : 9413 time to create 1 rle with old method : 0.010919332504272461 time for calcul the mask position with numpy : 0.006615400314331055 nb_pixel_total : 15 time to create 1 rle with old method : 7.510185241699219e-05 time for calcul the mask position with numpy : 0.007039070129394531 nb_pixel_total : 493 time to create 1 rle with old method : 0.0005903244018554688 time for calcul the mask position with numpy : 0.006634950637817383 nb_pixel_total : 118 time to create 1 rle with old method : 0.00016045570373535156 time for calcul the mask position with numpy : 0.00654149055480957 nb_pixel_total : 1205 time to create 1 rle with old method : 0.001486063003540039 time for calcul the mask position with numpy : 0.006513118743896484 nb_pixel_total : 326 time to create 1 rle with old method : 0.00046706199645996094 time for calcul the mask position with numpy : 0.0064411163330078125 nb_pixel_total : 19 time to create 1 rle with old method : 6.67572021484375e-05 time for calcul the mask position with numpy : 0.0067293643951416016 nb_pixel_total : 700 time to create 1 rle with old method : 0.00080108642578125 time for calcul the mask position with numpy : 0.006686210632324219 nb_pixel_total : 323 time to create 1 rle with old method : 0.00038170814514160156 time for calcul the mask position with numpy : 0.006518125534057617 nb_pixel_total : 7049 time to create 1 rle with old method : 0.007929086685180664 time for calcul the mask position with numpy : 0.006507396697998047 nb_pixel_total : 119 time to create 1 rle with old method : 0.0001621246337890625 time for calcul the mask position with numpy : 0.006787776947021484 nb_pixel_total : 929 time to create 1 rle with old method : 0.0011138916015625 time for calcul the mask position with numpy : 0.006733417510986328 nb_pixel_total : 1051 time to create 1 rle with old method : 0.0012085437774658203 time for calcul the mask position with numpy : 0.006468534469604492 nb_pixel_total : 1553 time to create 1 rle with old method : 0.0018270015716552734 time for calcul the mask position with numpy : 0.006487846374511719 nb_pixel_total : 3323 time to create 1 rle with old method : 0.003854990005493164 time for calcul the mask position with numpy : 0.006309032440185547 nb_pixel_total : 127 time to create 1 rle with old method : 0.00025391578674316406 time for calcul the mask position with numpy : 0.0065577030181884766 nb_pixel_total : 611 time to create 1 rle with old method : 0.000720977783203125 time for calcul the mask position with numpy : 0.006589174270629883 nb_pixel_total : 1032 time to create 1 rle with old method : 0.0012195110321044922 time for calcul the mask position with numpy : 0.0066204071044921875 nb_pixel_total : 5928 time to create 1 rle with old method : 0.006746530532836914 time for calcul the mask position with numpy : 0.006782054901123047 nb_pixel_total : 279 time to create 1 rle with old method : 0.0004086494445800781 time for calcul the mask position with numpy : 0.006317615509033203 nb_pixel_total : 99 time to create 1 rle with old method : 0.00013828277587890625 time for calcul the mask position with numpy : 0.006680727005004883 nb_pixel_total : 2405 time to create 1 rle with old method : 0.002827167510986328 time for calcul the mask position with numpy : 0.007606983184814453 nb_pixel_total : 30 time to create 1 rle with old method : 0.00013518333435058594 time for calcul the mask position with numpy : 0.008209943771362305 nb_pixel_total : 744 time to create 1 rle with old method : 0.0008993148803710938 time for calcul the mask position with numpy : 0.00808572769165039 nb_pixel_total : 534 time to create 1 rle with old method : 0.0006330013275146484 time for calcul the mask position with numpy : 0.007285594940185547 nb_pixel_total : 1093 time to create 1 rle with old method : 0.0012896060943603516 time for calcul the mask position with numpy : 0.007000446319580078 nb_pixel_total : 323 time to create 1 rle with old method : 0.00040602684020996094 time for calcul the mask position with numpy : 0.0072040557861328125 nb_pixel_total : 97 time to create 1 rle with old method : 0.00015115737915039062 time for calcul the mask position with numpy : 0.007317066192626953 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005087852478027344 time for calcul the mask position with numpy : 0.006810426712036133 nb_pixel_total : 314 time to create 1 rle with old method : 0.00038933753967285156 time for calcul the mask position with numpy : 0.006723880767822266 nb_pixel_total : 817 time to create 1 rle with old method : 0.0009510517120361328 time for calcul the mask position with numpy : 0.0066335201263427734 nb_pixel_total : 11 time to create 1 rle with old method : 6.079673767089844e-05 time for calcul the mask position with numpy : 0.0067517757415771484 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002484321594238281 time for calcul the mask position with numpy : 0.006436824798583984 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0014510154724121094 time for calcul the mask position with numpy : 0.006369829177856445 nb_pixel_total : 5858 time to create 1 rle with old method : 0.00679469108581543 time for calcul the mask position with numpy : 0.006692647933959961 nb_pixel_total : 694 time to create 1 rle with old method : 0.000820159912109375 time for calcul the mask position with numpy : 0.006426572799682617 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006368160247802734 time for calcul the mask position with numpy : 0.006476879119873047 nb_pixel_total : 148 time to create 1 rle with old method : 0.00018596649169921875 time for calcul the mask position with numpy : 0.00663447380065918 nb_pixel_total : 52 time to create 1 rle with old method : 7.510185241699219e-05 time for calcul the mask position with numpy : 0.006705045700073242 nb_pixel_total : 72 time to create 1 rle with old method : 0.00010704994201660156 time for calcul the mask position with numpy : 0.00667262077331543 nb_pixel_total : 762 time to create 1 rle with old method : 0.0009279251098632812 time for calcul the mask position with numpy : 0.0068132877349853516 nb_pixel_total : 363 time to create 1 rle with old method : 0.00046753883361816406 time for calcul the mask position with numpy : 0.006639719009399414 nb_pixel_total : 298 time to create 1 rle with old method : 0.0003497600555419922 time for calcul the mask position with numpy : 0.0075113773345947266 nb_pixel_total : 42 time to create 1 rle with old method : 8.034706115722656e-05 time for calcul the mask position with numpy : 0.007566213607788086 nb_pixel_total : 15 time to create 1 rle with old method : 4.00543212890625e-05 time for calcul the mask position with numpy : 0.007091045379638672 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002052783966064453 time for calcul the mask position with numpy : 0.007192373275756836 nb_pixel_total : 1098 time to create 1 rle with old method : 0.0012555122375488281 time for calcul the mask position with numpy : 0.0067937374114990234 nb_pixel_total : 2205 time to create 1 rle with old method : 0.0026519298553466797 time for calcul the mask position with numpy : 0.007380485534667969 nb_pixel_total : 554 time to create 1 rle with old method : 0.0010230541229248047 time for calcul the mask position with numpy : 0.008156299591064453 nb_pixel_total : 285 time to create 1 rle with old method : 0.0006070137023925781 time for calcul the mask position with numpy : 0.007877588272094727 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002453327178955078 time for calcul the mask position with numpy : 0.008419036865234375 nb_pixel_total : 194 time to create 1 rle with old method : 0.0004584789276123047 time for calcul the mask position with numpy : 0.008756637573242188 nb_pixel_total : 175 time to create 1 rle with old method : 0.0003535747528076172 time for calcul the mask position with numpy : 0.007942676544189453 nb_pixel_total : 2980 time to create 1 rle with old method : 0.005420684814453125 time for calcul the mask position with numpy : 0.007256031036376953 nb_pixel_total : 4074 time to create 1 rle with old method : 0.007205963134765625 time for calcul the mask position with numpy : 0.007243156433105469 nb_pixel_total : 155 time to create 1 rle with old method : 0.00029540061950683594 time for calcul the mask position with numpy : 0.007555723190307617 nb_pixel_total : 194 time to create 1 rle with old method : 0.00045180320739746094 time for calcul the mask position with numpy : 0.00810861587524414 nb_pixel_total : 2774 time to create 1 rle with old method : 0.004951953887939453 time for calcul the mask position with numpy : 0.007842540740966797 nb_pixel_total : 290 time to create 1 rle with old method : 0.0007250308990478516 time for calcul the mask position with numpy : 0.0077097415924072266 nb_pixel_total : 282 time to create 1 rle with old method : 0.00048613548278808594 time for calcul the mask position with numpy : 0.008269309997558594 nb_pixel_total : 65 time to create 1 rle with old method : 0.00016808509826660156 time for calcul the mask position with numpy : 0.007801055908203125 nb_pixel_total : 139 time to create 1 rle with old method : 0.0002944469451904297 time for calcul the mask position with numpy : 0.009047269821166992 nb_pixel_total : 1369 time to create 1 rle with old method : 0.0022411346435546875 time for calcul the mask position with numpy : 0.007130861282348633 nb_pixel_total : 18 time to create 1 rle with old method : 4.172325134277344e-05 time for calcul the mask position with numpy : 0.0068476200103759766 nb_pixel_total : 289 time to create 1 rle with old method : 0.00040984153747558594 time for calcul the mask position with numpy : 0.00690913200378418 nb_pixel_total : 324 time to create 1 rle with old method : 0.0003936290740966797 time for calcul the mask position with numpy : 0.006534576416015625 nb_pixel_total : 1268 time to create 1 rle with old method : 0.0014688968658447266 time for calcul the mask position with numpy : 0.008553266525268555 nb_pixel_total : 369 time to create 1 rle with old method : 0.0004241466522216797 time for calcul the mask position with numpy : 0.008638858795166016 nb_pixel_total : 85 time to create 1 rle with old method : 0.0001456737518310547 time for calcul the mask position with numpy : 0.009209632873535156 nb_pixel_total : 239 time to create 1 rle with old method : 0.0004584789276123047 time for calcul the mask position with numpy : 0.011708974838256836 nb_pixel_total : 49 time to create 1 rle with old method : 0.0001316070556640625 time for calcul the mask position with numpy : 0.010268211364746094 nb_pixel_total : 139 time to create 1 rle with old method : 0.0002684593200683594 time for calcul the mask position with numpy : 0.01193547248840332 nb_pixel_total : 445 time to create 1 rle with old method : 0.0009622573852539062 create new chi : 1.3212449550628662 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 : 0.002675294876098633 batch 1 Loaded 100 chid ids of type : 4230 Number RLEs to save : 9593 TO DO : save crop sub photo not yet done ! save time : 0.6980485916137695 map_output_result : {1340179760: (0.0, 'Should be the crop_list due to order', 0.0), 1340179757: (0.0, 'Should be the crop_list due to order', 0.0), 1340179687: (0.0, 'Should be the crop_list due to order', 0.0), 1340179663: (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 [1340179760, 1340179757, 1340179687, 1340179663] Looping around the photos to save general results len do output : 4 /1340179760.Didn't retrieve data . /1340179757.Didn't retrieve data . /1340179687.Didn't retrieve data . /1340179663.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, '2624523') ('4234', '20934027', '1340179760', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179757', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179687', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179663', None, None, None, None, None, '2624523') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.013045310974121094 save_final save missing photos in datou_result : time spend for datou_step_exec : 15.187536001205444 time spend to save output : 0.013445377349853516 total time spend for step 4 : 15.200981378555298 step5:crop_condition Fri Feb 28 17:21:23 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 : 4 ! batch 1 Loaded 375 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 ! map_result returned by crop_photo_return_map_crop : length : 128 About to insert : list_path_to_insert length 128 new photo from crops ! About to upload 128 photos upload in portfolio : 4869462 init cache_photo without model_param we have 128 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740759686_2011519 we have uploaded 128 photos in the portfolio 4869462 time of upload the photos Elapsed time : 35.62238812446594 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 ! map_result returned by crop_photo_return_map_crop : length : 56 About to insert : list_path_to_insert length 56 new photo from crops ! About to upload 56 photos upload in portfolio : 4869462 init cache_photo without model_param we have 56 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740759722_2011519 we have uploaded 56 photos in the portfolio 4869462 time of upload the photos Elapsed time : 17.345354318618774 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 ! map_result returned by crop_photo_return_map_crop : length : 17 About to insert : list_path_to_insert length 17 new photo from crops ! About to upload 17 photos upload in portfolio : 4869462 init cache_photo without model_param we have 17 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740759740_2011519 we have uploaded 17 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.95981240272522 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 ! map_result returned by crop_photo_return_map_crop : length : 44 About to insert : list_path_to_insert length 44 new photo from crops ! About to upload 44 photos upload in portfolio : 4869462 init cache_photo without model_param we have 44 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740759747_2011519 we have uploaded 44 photos in the portfolio 4869462 time of upload the photos Elapsed time : 11.088437557220459 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 ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740759758_2011519 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9028162956237793 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 [1340179760, 1340179757, 1340179687, 1340179663] Looping around the photos to save general results len do output : 247 /1340184905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340184999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185151Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340185219Didn'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, '2624523') ('4234', '20934027', '1340179760', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179757', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179687', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179663', None, None, None, None, None, '2624523') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 745 time used for this insertion : 0.04786276817321777 save_final save missing photos in datou_result : time spend for datou_step_exec : 75.68240356445312 time spend to save output : 0.22825264930725098 total time spend for step 5 : 75.91065621376038 step6:thcl Fri Feb 28 17:22:39 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 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 : 0.017250776290893555 time to convert the images to numpy array : 0.0892035961151123 time to import caffe and check if the image exist : 0.02099299430847168 time to convert the images to numpy array : 0.0899965763092041 time to import caffe and check if the image exist : 0.03266191482543945 time to convert the images to numpy array : 0.08037805557250977 time to import caffe and check if the image exist : 0.028336048126220703 time to convert the images to numpy array : 0.08581399917602539 time to import caffe and check if the image exist : 0.018996238708496094 time to convert the images to numpy array : 0.09643745422363281 time to import caffe and check if the image exist : 0.0206298828125 time to convert the images to numpy array : 0.09371685981750488 time to import caffe and check if the image exist : 0.02123236656188965 time to convert the images to numpy array : 0.0945887565612793 time to import caffe and check if the image exist : 0.01903843879699707 time to convert the images to numpy array : 0.09941554069519043 time to import caffe and check if the image exist : 0.0394895076751709 time to convert the images to numpy array : 0.08095717430114746 time to import caffe and check if the image exist : 0.04685401916503906 time to convert the images to numpy array : 0.0740056037902832 total time to convert the images to numpy array : 0.404634952545166 list photo_ids error: [] list photo_ids correct : [1340184985, 1340184986, 1340184987, 1340184988, 1340184989, 1340184990, 1340184991, 1340184992, 1340184993, 1340184994, 1340184995, 1340184996, 1340184997, 1340184998, 1340184999, 1340185000, 1340185001, 1340185002, 1340185003, 1340185004, 1340185005, 1340185006, 1340185007, 1340185008, 1340185009, 1340185036, 1340185037, 1340185038, 1340185062, 1340185063, 1340185064, 1340185065, 1340185066, 1340185067, 1340185068, 1340185069, 1340185070, 1340185071, 1340185073, 1340185074, 1340185075, 1340185076, 1340185077, 1340185078, 1340185079, 1340185080, 1340185081, 1340185082, 1340185083, 1340185084, 1340185010, 1340185011, 1340185012, 1340185013, 1340185014, 1340185015, 1340185016, 1340185017, 1340185018, 1340185019, 1340185020, 1340185021, 1340185022, 1340185023, 1340185024, 1340185025, 1340185026, 1340185027, 1340185028, 1340185030, 1340185031, 1340185032, 1340185033, 1340185034, 1340185035, 1340185085, 1340185086, 1340185087, 1340185088, 1340185089, 1340185090, 1340185091, 1340185092, 1340185093, 1340185094, 1340185095, 1340185096, 1340185097, 1340185098, 1340185099, 1340185100, 1340185101, 1340185103, 1340185107, 1340185108, 1340185109, 1340185110, 1340185111, 1340185112, 1340185113, 1340184905, 1340184906, 1340184908, 1340184909, 1340184910, 1340184911, 1340184912, 1340184913, 1340184914, 1340184915, 1340184916, 1340184917, 1340184918, 1340184919, 1340184920, 1340184921, 1340184922, 1340184923, 1340184924, 1340184925, 1340184926, 1340184927, 1340184928, 1340184929, 1340184930, 1340185193, 1340185194, 1340185195, 1340185196, 1340185197, 1340185198, 1340185199, 1340185201, 1340185202, 1340185204, 1340185205, 1340185206, 1340185207, 1340185208, 1340185211, 1340185212, 1340185213, 1340185214, 1340185215, 1340185216, 1340185218, 1340185219, 1340185114, 1340185116, 1340185117, 1340185118, 1340185119, 1340185120, 1340185121, 1340185123, 1340185124, 1340185138, 1340185139, 1340185140, 1340185141, 1340185142, 1340185143, 1340185144, 1340185145, 1340185146, 1340185147, 1340185148, 1340185149, 1340185150, 1340185151, 1340185152, 1340185153, 1340185154, 1340185168, 1340185169, 1340185170, 1340185171, 1340185172, 1340185173, 1340185174, 1340185175, 1340185177, 1340185178, 1340185179, 1340185180, 1340185181, 1340185182, 1340185183, 1340185184, 1340185185, 1340185186, 1340185187, 1340185188, 1340185189, 1340185190, 1340185191, 1340185192, 1340184931, 1340184932, 1340184933, 1340184934, 1340184935, 1340184936, 1340184937, 1340184938, 1340184939, 1340184940, 1340184942, 1340184943, 1340184944, 1340184945, 1340184946, 1340184947, 1340184948, 1340184949, 1340184950, 1340184951, 1340184952, 1340184954, 1340184955, 1340184956, 1340184957, 1340184958, 1340184959, 1340184960, 1340184961, 1340184962, 1340184963, 1340184964, 1340184965, 1340184966, 1340184967, 1340184969, 1340184970, 1340184971, 1340184972, 1340184973, 1340184974, 1340184975, 1340184976, 1340184977, 1340184978, 1340184979, 1340184980, 1340184982, 1340184983, 1340184984] number of photos to traite : 247 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 : 4641 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 : 4422 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 1.3174850940704346 time used to do the prediction : 1.2034938335418701 save descriptor for thcl : 3237 time to traite the descriptors : 1.6908366680145264 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1340184985 To insert : 1340184986 To insert : 1340184987 To insert : 1340184988 To insert : 1340184989 To insert : 1340184990 To insert : 1340184991 To insert : 1340184992 To insert : 1340184993 To insert : 1340184994 To insert : 1340184995 To insert : 1340184996 To insert : 1340184997 To insert : 1340184998 To insert : 1340184999 To insert : 1340185000 To insert : 1340185001 To insert : 1340185002 To insert : 1340185003 To insert : 1340185004 To insert : 1340185005 To insert : 1340185006 To insert : 1340185007 To insert : 1340185008 To insert : 1340185009 To insert : 1340185036 To insert : 1340185037 To insert : 1340185038 To insert : 1340185062 To insert : 1340185063 To insert : 1340185064 To insert : 1340185065 To insert : 1340185066 To insert : 1340185067 To insert : 1340185068 To insert : 1340185069 To insert : 1340185070 To insert : 1340185071 To insert : 1340185073 To insert : 1340185074 To insert : 1340185075 To insert : 1340185076 To insert : 1340185077 To insert : 1340185078 To insert : 1340185079 To insert : 1340185080 To insert : 1340185081 To insert : 1340185082 To insert : 1340185083 To insert : 1340185084 To insert : 1340185010 To insert : 1340185011 To insert : 1340185012 To insert : 1340185013 To insert : 1340185014 To insert : 1340185015 To insert : 1340185016 To insert : 1340185017 To insert : 1340185018 To insert : 1340185019 To insert : 1340185020 To insert : 1340185021 To insert : 1340185022 To insert : 1340185023 To insert : 1340185024 To insert : 1340185025 To insert : 1340185026 To insert : 1340185027 To insert : 1340185028 To insert : 1340185030 To insert : 1340185031 To insert : 1340185032 To insert : 1340185033 To insert : 1340185034 To insert : 1340185035 To insert : 1340185085 To insert : 1340185086 To insert : 1340185087 To insert : 1340185088 To insert : 1340185089 To insert : 1340185090 To insert : 1340185091 To insert : 1340185092 To insert : 1340185093 To insert : 1340185094 To insert : 1340185095 To insert : 1340185096 To insert : 1340185097 To insert : 1340185098 To insert : 1340185099 To insert : 1340185100 To insert : 1340185101 To insert : 1340185103 To insert : 1340185107 To insert : 1340185108 To insert : 1340185109 To insert : 1340185110 To insert : 1340185111 To insert : 1340185112 To insert : 1340185113 To insert : 1340184905 To insert : 1340184906 To insert : 1340184908 To insert : 1340184909 To insert : 1340184910 To insert : 1340184911 To insert : 1340184912 To insert : 1340184913 To insert : 1340184914 To insert : 1340184915 To insert : 1340184916 To insert : 1340184917 To insert : 1340184918 To insert : 1340184919 To insert : 1340184920 To insert : 1340184921 To insert : 1340184922 To insert : 1340184923 To insert : 1340184924 To insert : 1340184925 To insert : 1340184926 To insert : 1340184927 To insert : 1340184928 To insert : 1340184929 To insert : 1340184930 To insert : 1340185193 To insert : 1340185194 To insert : 1340185195 To insert : 1340185196 To insert : 1340185197 To insert : 1340185198 To insert : 1340185199 To insert : 1340185201 To insert : 1340185202 To insert : 1340185204 To insert : 1340185205 To insert : 1340185206 To insert : 1340185207 To insert : 1340185208 To insert : 1340185211 To insert : 1340185212 To insert : 1340185213 To insert : 1340185214 To insert : 1340185215 To insert : 1340185216 To insert : 1340185218 To insert : 1340185219 To insert : 1340185114 To insert : 1340185116 To insert : 1340185117 To insert : 1340185118 To insert : 1340185119 To insert : 1340185120 To insert : 1340185121 To insert : 1340185123 To insert : 1340185124 To insert : 1340185138 To insert : 1340185139 To insert : 1340185140 To insert : 1340185141 To insert : 1340185142 To insert : 1340185143 To insert : 1340185144 To insert : 1340185145 To insert : 1340185146 To insert : 1340185147 To insert : 1340185148 To insert : 1340185149 To insert : 1340185150 To insert : 1340185151 To insert : 1340185152 To insert : 1340185153 To insert : 1340185154 To insert : 1340185168 To insert : 1340185169 To insert : 1340185170 To insert : 1340185171 To insert : 1340185172 To insert : 1340185173 To insert : 1340185174 To insert : 1340185175 To insert : 1340185177 To insert : 1340185178 To insert : 1340185179 To insert : 1340185180 To insert : 1340185181 To insert : 1340185182 To insert : 1340185183 To insert : 1340185184 To insert : 1340185185 To insert : 1340185186 To insert : 1340185187 To insert : 1340185188 To insert : 1340185189 To insert : 1340185190 To insert : 1340185191 To insert : 1340185192 To insert : 1340184931 To insert : 1340184932 To insert : 1340184933 To insert : 1340184934 To insert : 1340184935 To insert : 1340184936 To insert : 1340184937 To insert : 1340184938 To insert : 1340184939 To insert : 1340184940 To insert : 1340184942 To insert : 1340184943 To insert : 1340184944 To insert : 1340184945 To insert : 1340184946 To insert : 1340184947 To insert : 1340184948 To insert : 1340184949 To insert : 1340184950 To insert : 1340184951 To insert : 1340184952 To insert : 1340184954 To insert : 1340184955 To insert : 1340184956 To insert : 1340184957 To insert : 1340184958 To insert : 1340184959 To insert : 1340184960 To insert : 1340184961 To insert : 1340184962 To insert : 1340184963 To insert : 1340184964 To insert : 1340184965 To insert : 1340184966 To insert : 1340184967 To insert : 1340184969 To insert : 1340184970 To insert : 1340184971 To insert : 1340184972 To insert : 1340184973 To insert : 1340184974 To insert : 1340184975 To insert : 1340184976 To insert : 1340184977 To insert : 1340184978 To insert : 1340184979 To insert : 1340184980 To insert : 1340184982 To insert : 1340184983 To insert : 1340184984 time to insert the descriptors : 53.99522304534912 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 : 390 time used for this insertion : 0.02814030647277832 save missing photos in datou_result : time spend for datou_step_exec : 62.98735809326172 time spend to save output : 0.07957720756530762 total time spend for step 6 : 63.066935300827026 step7:ventilate_hashtags_in_portfolio Fri Feb 28 17:23:42 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 ! 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 : 20934027 get user id for portfolio 20934027 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`=20934027 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','PET_clair','Tetrapak','Carton','refus','Papier','papier','environnement','pet_fonce','metal','carton','pet_clair','PEHD','PET_fonce','autre','pehd','mal_croppe','Film_plastique')) 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`=20934027 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','PET_clair','Tetrapak','Carton','refus','Papier','papier','environnement','pet_fonce','metal','carton','pet_clair','PEHD','PET_fonce','autre','pehd','mal_croppe','Film_plastique')) 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`=20934027 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','PET_clair','Tetrapak','Carton','refus','Papier','papier','environnement','pet_fonce','metal','carton','pet_clair','PEHD','PET_fonce','autre','pehd','mal_croppe','Film_plastique')) 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`=20934027 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','PET_clair','Tetrapak','Carton','refus','Papier','papier','environnement','pet_fonce','metal','carton','pet_clair','PEHD','PET_fonce','autre','pehd','mal_croppe','Film_plastique')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20935261,20935272,20935263,20935271,20935265,20935267,20935268,20935274,20935270,20935276,20935275,20935277,20935278?tags=flou,pet_clair,tetrapak,carton,refus,papier,environnement,pet_fonce,metal,pehd,autre,mal_croppe,film_plastique&datou_id_consolidate=4235&port_consolidate=20934027 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1340179760, 1340179757, 1340179687, 1340179663] Looping around the photos to save general results len do output : 1 /20934027. 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, '2624523') ('4234', '20934027', '1340179760', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179757', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179687', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179663', None, None, None, None, None, '2624523') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.015697956085205078 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.072930335998535 time spend to save output : 0.01609969139099121 total time spend for step 7 : 3.0890300273895264 step8:final Fri Feb 28 17:23:45 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 : {1340179760: ('0.16967650816069063',), 1340179757: ('0.16967650816069063',), 1340179687: ('0.16967650816069063',), 1340179663: ('0.16967650816069063',)} new output for save of step final : {1340179760: ('0.16967650816069063',), 1340179757: ('0.16967650816069063',), 1340179687: ('0.16967650816069063',), 1340179663: ('0.16967650816069063',)} [1340179760, 1340179757, 1340179687, 1340179663] Looping around the photos to save general results len do output : 4 /1340179760.Didn't retrieve data . /1340179757.Didn't retrieve data . /1340179687.Didn't retrieve data . /1340179663.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, '2624523') ('4234', '20934027', '1340179760', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179757', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179687', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179663', None, None, None, None, None, '2624523') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.01305246353149414 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12391781806945801 time spend to save output : 0.013349533081054688 total time spend for step 8 : 0.1372673511505127 step9:velours_tree Fri Feb 28 17:23:45 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 : 20935261,20935272,20935263,20935271,20935265,20935267,20935268,20935274,20935270,20935276,20935275,20935277,20935278 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=20935261 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=20935272 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=20935263 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=20935271 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=20935265 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=20935267 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=20935268 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=20935274 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=20935270 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=20935276 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=20935275 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=20935277 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=20935278 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 247 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [2 2 4 2 4 3 0 2 3 0 2 2 0 2 2 0 1 2 2 3 2 2 1 2 1 3 1 3 3 0 1 0 0 2 2 0 2 4 2 4 1 3 2 3 3 0 3 0 2 2 2 0 1 2 2 3 2 2 1 3 2 1 0 0 2 2 0 2 2 4 4 1 2 4 3 2 0 3 0 3 2 0 1 2 3 3 2 1 2 1 3 3 3 1 2 0 2 2 2 2 4 3 4 1 2 3 3 0 2 3 2 2 0 0 2 2 1 2 2 3 2 2 1 3 3 3 2 0 5 5 2 0 2 0 2 3 3 2 0 0 3 2 5 5 2 2 2 0 0 2 3 2 5 5 2 2 0 2 3 3 2 0 0 0 2 0 0 3 2 5 5 0 2 0 2 2 2 0 0 0 2 0 3 2 1 3 2 2 3 2 2 3 4 3 2 3 3 2 3 0 3 3 2 0 3 3 3 3 1 1 2 3 3 3 0 1 1 1 1 3 3 3 0 0 3 3 2 3 1 1 1 3 3 3 0 3 0 2 2 1 1 1 3 2 3 2 2] Elapsed time: 0.041628360748291016 graph_id used : 80685 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20935261,20935272,20935263,20935271,20935265,20935267,20935268,20935274,20935270,20935276,20935275,20935277,20935278?tags=flou,pet_clair,tetrapak,carton,refus,papier,environnement,pet_fonce,metal,pehd,autre,mal_croppe,film_plastique&datou_id_consolidate=4235&port_consolidate=20934027&tree_id=80685 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1340179760, 1340179757, 1340179687, 1340179663] Looping around the photos to save general results len do output : 1 /20934027Didn'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, '2624523') ('4234', '20934027', '1340179760', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179757', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179687', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179663', None, None, None, None, None, '2624523') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.01241612434387207 save_final save missing photos in datou_result : time spend for datou_step_exec : 16.332478761672974 time spend to save output : 0.012862443923950195 total time spend for step 9 : 16.345341205596924 step10:send_mail_cod Fri Feb 28 17:24:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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_P20934027_28-02-2025_17_24_02.pdf 20935243 imagette209352431740759842 20935254 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 .imagette209352541740759842 20935245 imagette209352451740759842 20935253 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 .imagette209352531740759842 20935247 imagette209352471740759843 20935249 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 .imagette209352491740759843 20935256 imagette209352561740759844 20935252 imagette209352521740759844 20935258 change filename to text .change filename to text .imagette209352581740759844 20935257 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 .imagette209352571740759844 20935259 imagette209352591740759845 20935260 imagette209352601740759845 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20934027 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20935261,20935272,20935263,20935271,20935265,20935267,20935268,20935274,20935270,20935276,20935275,20935277,20935278?tags=flou,pet_clair,tetrapak,carton,refus,papier,environnement,pet_fonce,metal,pehd,autre,mal_croppe,film_plastique&datou_id_consolidate=4235&port_consolidate=20934027&tree_id=80685 your option no_mail is active, we will not send the real mail to your client args[1340179760] : ((1340179760, -7.429770297981256, 492609224), (1340179760, 0.15621293465141683, 2107752395), '0.16967650816069063') We are sending mail with results at cod@fotonower.com args[1340179757] : ((1340179757, -7.421282420423875, 492609224), (1340179757, 0.18843585314385858, 2107752395), '0.16967650816069063') We are sending mail with results at cod@fotonower.com args[1340179687] : ((1340179687, -7.404920212409312, 492609224), (1340179687, 0.20883585421466402, 2107752395), '0.16967650816069063') We are sending mail with results at cod@fotonower.com args[1340179663] : ((1340179663, -7.429162021614639, 492609224), (1340179663, 0.21832374631129028, 2107752395), '0.16967650816069063') We are sending mail with results at cod@fotonower.com refus_total : 0.16967650816069063 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=20934027 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_P20934027_28-02-2025_17_24_02.pdf results_Qualipapia_P20934027_28-02-2025_17_24_02.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20934027_28-02-2025_17_24_02.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','20934027','results_Qualipapia_P20934027_28-02-2025_17_24_02.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20934027_28-02-2025_17_24_02.pdf','pdf','','0.17','0.16967650816069063') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1340179760, 1340179757, 1340179687, 1340179663] 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, '2624523') ('4234', '20934027', '1340179760', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179757', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179687', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179663', None, None, None, None, None, '2624523') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.011975765228271484 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.718808174133301 time spend to save output : 0.012208223342895508 total time spend for step 10 : 4.731016397476196 step11:split_time_score Fri Feb 28 17:24:06 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'}] (('15', 4),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 28022025 20934027 Nombre de photos uploadées : 4 / 23040 (0%) 28022025 20934027 Nombre de photos taguées (types de déchets): 4 / 4 (100%) 28022025 20934027 Nombre de photos taguées (volume) : 0 / 4 (0%) elapsed_time : load_data_split_time_score 3.337860107421875e-06 elapsed_time : order_list_meta_photo_and_scores 9.059906005859375e-06 ???? elapsed_time : fill_and_build_computed_from_old_data 0.0003218650817871094 elapsed_time : insert_dashboard_record_day_entry 0.02219533920288086 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925313 order by id desc limit 1 Qualite : 0.2389124139495338 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20925314_28-02-2025_16_27_31.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925314 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`=20925314 AND mptpi.`type`=4230 To do Qualite : 0.20097250357084048 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20925315_28-02-2025_16_33_01.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925315 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`=20925315 AND mptpi.`type`=4230 To do Qualite : 0.17175854819984712 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20925316_28-02-2025_16_37_38.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925316 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`=20925316 AND mptpi.`type`=4230 To do Qualite : 0.14603092887147903 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20925317_28-02-2025_16_48_17.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925317 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`=20925317 AND mptpi.`type`=4230 To do Qualite : 0.14537379123310024 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20925318_28-02-2025_16_47_51.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925318 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`=20925318 AND mptpi.`type`=4230 To do Qualite : 0.13834991985174483 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20925319_28-02-2025_16_53_23.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925319 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`=20925319 AND mptpi.`type`=4230 To do Qualite : 0.20701680283651394 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20925320_28-02-2025_12_19_22.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925320 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`=20925320 AND mptpi.`type`=4230 To do Qualite : 0.20965568130120157 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20925322_28-02-2025_12_35_22.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20925322 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`=20925322 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926288 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926289 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926290 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926291 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926292 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926293 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926294 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926295 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926296 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926297 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926298 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926299 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926300 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926680 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926681 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926682 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926683 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926684 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926685 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926686 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926687 order by id desc limit 1 Qualite : 0.15869362550655408 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926688_28-02-2025_13_30_01.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926688 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`=20926688 AND mptpi.`type`=4230 To do Qualite : 0.195875078609268 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926689_28-02-2025_13_45_55.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926689 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`=20926689 AND mptpi.`type`=4230 To do Qualite : 0.20091742580903377 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926959_28-02-2025_15_57_44.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926959 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`=20926959 AND mptpi.`type`=4230 To do Qualite : 0.19808442389049616 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926960_28-02-2025_13_47_22.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926960 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`=20926960 AND mptpi.`type`=4230 To do Qualite : 0.1789930776371666 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926961_28-02-2025_14_35_53.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926961 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`=20926961 AND mptpi.`type`=4230 To do Qualite : 0.23665664333760855 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926962_28-02-2025_14_58_44.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926962 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`=20926962 AND mptpi.`type`=4230 To do Qualite : 0.2286496649991992 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20931435_28-02-2025_16_31_36.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20931435 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`=20931435 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20932896 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20932897 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20932898 order by id desc limit 1 Qualite : 0.13881388279873863 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20932899_28-02-2025_16_46_45.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20932899 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`=20932899 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20932900 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934012 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934013 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934014 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934015 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934016 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934017 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934018 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934019 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934020 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934021 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934022 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934023 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934024 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934025 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934026 order by id desc limit 1 Qualite : 0.16967650816069063 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20934027_28-02-2025_17_24_02.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934027 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`=20934027 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934028 order by id desc limit 1 NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'28022025': {'nb_upload': 4, 'nb_taggue_class': 4, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1340179760, 1340179757, 1340179687, 1340179663] Looping around the photos to save general results len do output : 1 /20934027Didn'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, '2624523') ('4234', '20934027', '1340179760', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179757', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179687', None, None, None, None, None, '2624523') ('4234', None, None, None, None, None, None, None, '2624523') ('4234', '20934027', '1340179663', None, None, None, None, None, '2624523') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012775897979736328 save_final save missing photos in datou_result : time spend for datou_step_exec : 37.20843982696533 time spend to save output : 0.013051509857177734 total time spend for step 11 : 37.22149133682251 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 4 set_done_treatment 53.62user 32.23system 4:19.48elapsed 33%CPU (0avgtext+0avgdata 2432792maxresident)k 1217336inputs+16976outputs (4165major+2602637minor)pagefaults 0swaps