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 : 2498347 load datou : 4234 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 we have a portfolio with more photos than limit : 7>5 please execute split_portfolio.py -i 20937373 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2624816'] with mtr_portfolio_ids : ['20937373'] and first list_photo_ids : [] new path : /proc/2498347/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 0.7607192993164062 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 19:20:29 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 5525 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-28 19:20:31.743969: 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 19:20:31.771052: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-28 19:20:31.773133: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f50b8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-28 19:20:31.773194: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-28 19:20:31.777198: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-28 19:20:31.891746: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3a478460 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-28 19:20:31.891801: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-28 19:20:31.893000: 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 19:20:31.893440: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-28 19:20:31.896591: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-28 19:20:31.899615: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-28 19:20:31.900120: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-28 19:20:31.902692: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-28 19:20:31.903968: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-28 19:20:31.909094: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-28 19:20:31.910493: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-28 19:20:31.910578: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-28 19:20:31.911381: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-28 19:20:31.911410: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-28 19:20:31.911422: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-28 19:20:31.912620: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4907 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 19:20:32.160705: 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 19:20:32.160815: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-28 19:20:32.160838: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-28 19:20:32.160858: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-28 19:20:32.160878: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-28 19:20:32.160901: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-28 19:20:32.160922: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-28 19:20:32.160944: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-28 19:20:32.162128: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-28 19:20:32.163433: 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 19:20:32.163521: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-28 19:20:32.163543: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-28 19:20:32.163563: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-28 19:20:32.163583: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-28 19:20:32.163604: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-28 19:20:32.163624: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-28 19:20:32.163645: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-28 19:20:32.164818: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-28 19:20:32.164858: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-28 19:20:32.164870: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-28 19:20:32.164881: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-28 19:20:32.166141: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4907 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 19:20:40.373322: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-28 19:20:40.610617: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-28 19:20:41.850618: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.851471: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.851991: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.24G (3478923264 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.852501: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3131030784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.853020: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.62G (2817927680 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.853528: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.36G (2536134912 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.854046: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2282521344 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.854088: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.854648: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.854664: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.862476: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.862528: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.863060: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.863078: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.869623: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.869665: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.870192: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.870209: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.903791: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.903856: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.904390: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.904406: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.910316: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.910346: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.910886: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.910917: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-28 19:20:41.949053: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.949677: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.952890: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:41.953431: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.000650: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.001535: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.004470: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.005035: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.034166: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.034719: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.036261: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.036778: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.042667: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.043212: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.044924: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.045417: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.051465: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.052002: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.053462: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.053956: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.080321: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.080880: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.081401: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.081924: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.085448: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.085982: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.102844: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.103422: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.103949: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.104659: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.118376: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.118999: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.119530: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.120089: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.124800: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.125350: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.131182: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.131731: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.144051: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.144582: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.148627: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.149198: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.149935: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.150480: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.151300: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.151976: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.162152: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.162691: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.163249: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.163772: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.164404: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.164938: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.165460: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.165998: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.177873: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.178732: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.185899: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.186421: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.218329: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.218423: 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 19:20:42.219006: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.219548: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.228069: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.228661: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.229187: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.229670: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.238601: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.239183: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.274994: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.279748: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.280718: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.281554: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.286171: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.287043: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.290230: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.291123: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.293488: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.303191: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.304035: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.313562: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.314090: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.314619: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.315320: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.315873: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-28 19:20:42.316392: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 5 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.98516 max: 149.91641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 939 time to create 1 rle with old method : 0.0017316341400146484 length of segment : 34 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 901 time to create 1 rle with old method : 0.00170135498046875 length of segment : 37 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 916 time to create 1 rle with old method : 0.0017218589782714844 length of segment : 37 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1023 time to create 1 rle with old method : 0.0018610954284667969 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.87188 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 : 2456 time to create 1 rle with old method : 0.003045797348022461 length of segment : 53 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 1274 time to create 1 rle with old method : 0.00167083740234375 length of segment : 83 time for calcul the mask position with numpy : 0.00013780593872070312 nb_pixel_total : 2895 time to create 1 rle with old method : 0.0036466121673583984 length of segment : 46 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.00048542022705078125 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.01641 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 : 5714 time to create 1 rle with old method : 0.006601095199584961 length of segment : 98 time for calcul the mask position with numpy : 0.00012063980102539062 nb_pixel_total : 6254 time to create 1 rle with old method : 0.007222890853881836 length of segment : 102 time for calcul the mask position with numpy : 0.0004296302795410156 nb_pixel_total : 7169 time to create 1 rle with old method : 0.009190559387207031 length of segment : 141 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 2191 time to create 1 rle with old method : 0.0035517215728759766 length of segment : 29 time for calcul the mask position with numpy : 0.00045561790466308594 nb_pixel_total : 7696 time to create 1 rle with old method : 0.00942850112915039 length of segment : 188 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 1951 time to create 1 rle with old method : 0.0024154186248779297 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.89922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0009610652923583984 length of segment : 34 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0013473033905029297 length of segment : 39 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1301 time to create 1 rle with old method : 0.0019197463989257812 length of segment : 71 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 544 time to create 1 rle with old method : 0.0007333755493164062 length of segment : 34 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 251.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 127.25234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006794929504394531 length of segment : 18 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1451 time to create 1 rle with old method : 0.0019161701202392578 length of segment : 49 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1215 time to create 1 rle with old method : 0.0014617443084716797 length of segment : 78 time for calcul the mask position with numpy : 0.0007560253143310547 nb_pixel_total : 68220 time to create 1 rle with old method : 0.07877230644226074 length of segment : 339 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 199.00000 molded_images shape: (1, 640, 640, 3) min: -95.53203 max: 80.40078 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: -106.66484 max: 148.54531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0007581710815429688 length of segment : 18 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0011823177337646484 length of segment : 22 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.00046634674072265625 length of segment : 20 time for calcul the mask position with numpy : 0.0004038810729980469 nb_pixel_total : 17225 time to create 1 rle with old method : 0.027483224868774414 length of segment : 182 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 53 time to create 1 rle with old method : 9.846687316894531e-05 length of segment : 8 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0005893707275390625 length of segment : 24 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0004885196685791016 length of segment : 26 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1415 time to create 1 rle with old method : 0.0017647743225097656 length of segment : 57 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003840923309326172 length of segment : 19 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004210472106933594 length of segment : 25 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 626 time to create 1 rle with old method : 0.0009400844573974609 length of segment : 21 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0011904239654541016 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.71563 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1383 time to create 1 rle with old method : 0.0017695426940917969 length of segment : 34 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.00018978118896484375 length of segment : 8 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007879734039306641 length of segment : 33 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0004780292510986328 length of segment : 28 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00015354156494140625 length of segment : 9 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 718 time to create 1 rle with old method : 0.0009567737579345703 length of segment : 29 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0016033649444580078 length of segment : 61 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 847 time to create 1 rle with old method : 0.0011632442474365234 length of segment : 28 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1853 time to create 1 rle with old method : 0.0023615360260009766 length of segment : 38 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.000652313232421875 length of segment : 32 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0003063678741455078 length of segment : 19 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 4647 time to create 1 rle with old method : 0.0057413578033447266 length of segment : 104 time for calcul the mask position with numpy : 0.0001232624053955078 nb_pixel_total : 3636 time to create 1 rle with old method : 0.0043337345123291016 length of segment : 104 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 3806 time to create 1 rle with old method : 0.00461268424987793 length of segment : 106 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1004 time to create 1 rle with old method : 0.0012230873107910156 length of segment : 47 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.00040650367736816406 length of segment : 23 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005295276641845703 length of segment : 26 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2116 time to create 1 rle with old method : 0.0027086734771728516 length of segment : 113 time for calcul the mask position with numpy : 0.0003650188446044922 nb_pixel_total : 20065 time to create 1 rle with old method : 0.022976160049438477 length of segment : 234 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.08281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 0.00010919570922851562 nb_pixel_total : 2197 time to create 1 rle with old method : 0.0038597583770751953 length of segment : 131 time for calcul the mask position with numpy : 0.0001201629638671875 nb_pixel_total : 7615 time to create 1 rle with old method : 0.009138345718383789 length of segment : 75 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 5379 time to create 1 rle with old method : 0.006314992904663086 length of segment : 119 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0008940696716308594 length of segment : 21 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002925395965576172 length of segment : 16 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1198 time to create 1 rle with old method : 0.0015087127685546875 length of segment : 43 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0008337497711181641 length of segment : 33 time for calcul the mask position with numpy : 0.00022721290588378906 nb_pixel_total : 10245 time to create 1 rle with old method : 0.011569499969482422 length of segment : 309 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 837 time to create 1 rle with old method : 0.0011115074157714844 length of segment : 29 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: 133.02187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0005514621734619141 length of segment : 27 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 1562 time to create 1 rle with old method : 0.002910137176513672 length of segment : 130 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003921985626220703 length of segment : 23 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 952 time to create 1 rle with old method : 0.0018191337585449219 length of segment : 35 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 816 time to create 1 rle with old method : 0.00180816650390625 length of segment : 93 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 1785 time to create 1 rle with old method : 0.004390716552734375 length of segment : 87 time for calcul the mask position with numpy : 0.0001049041748046875 nb_pixel_total : 1698 time to create 1 rle with old method : 0.003129720687866211 length of segment : 115 Processing 1 images image shape: (280, 400, 3) min: 8.00000 max: 191.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 63.71719 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 : 106610 time to create 1 rle with old method : 0.12318229675292969 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.13516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0007383823394775391 length of segment : 30 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 3290 time to create 1 rle with old method : 0.004005908966064453 length of segment : 76 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00017881393432617188 length of segment : 16 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00015807151794433594 length of segment : 16 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 1081 time to create 1 rle with old method : 0.0014302730560302734 length of segment : 36 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.00019669532775878906 length of segment : 29 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1589 time to create 1 rle with old method : 0.0019631385803222656 length of segment : 56 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: 149.08828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 30 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 653 time to create 1 rle with old method : 0.0008394718170166016 length of segment : 31 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001780986785888672 length of segment : 9 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 2829 time to create 1 rle with old method : 0.003396272659301758 length of segment : 66 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 482 time to create 1 rle with old method : 0.0007183551788330078 length of segment : 17 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.00014638900756835938 length of segment : 11 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001461505889892578 length of segment : 8 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00021409988403320312 length of segment : 20 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0006887912750244141 length of segment : 19 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 55 time to create 1 rle with old method : 0.00010991096496582031 length of segment : 9 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.00014901161193847656 length of segment : 10 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005481243133544922 length of segment : 24 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003159046173095703 length of segment : 22 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003299713134765625 length of segment : 23 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.00019884109497070312 length of segment : 16 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0007770061492919922 length of segment : 37 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005757808685302734 length of segment : 29 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 970 time to create 1 rle with old method : 0.0012655258178710938 length of segment : 43 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.00028634071350097656 length of segment : 18 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0002994537353515625 length of segment : 20 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0004901885986328125 length of segment : 23 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0008623600006103516 length of segment : 23 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00031304359436035156 length of segment : 20 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0009381771087646484 length of segment : 50 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002868175506591797 length of segment : 16 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003960132598876953 length of segment : 15 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.00017905235290527344 length of segment : 14 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 50 time to create 1 rle with old method : 9.393692016601562e-05 length of segment : 8 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004417896270751953 length of segment : 21 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.00045228004455566406 length of segment : 22 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.000278472900390625 length of segment : 16 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.18594 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 : 114 time to create 1 rle with old method : 0.00018978118896484375 length of segment : 11 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002830028533935547 length of segment : 16 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0003070831298828125 length of segment : 28 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005736351013183594 length of segment : 30 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 1336 time to create 1 rle with old method : 0.001806497573852539 length of segment : 89 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.000644683837890625 length of segment : 58 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.72500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.04766 max: 149.27187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1060 time to create 1 rle with old method : 0.0016484260559082031 length of segment : 33 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 854 time to create 1 rle with old method : 0.0011289119720458984 length of segment : 29 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0008440017700195312 length of segment : 30 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 840 time to create 1 rle with old method : 0.0011219978332519531 length of segment : 32 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 1061 time to create 1 rle with old method : 0.0013613700866699219 length of segment : 30 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 1100 time to create 1 rle with old method : 0.0014111995697021484 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.39922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 2405 time to create 1 rle with old method : 0.002954244613647461 length of segment : 65 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 743 time to create 1 rle with old method : 0.0010135173797607422 length of segment : 21 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005469322204589844 length of segment : 27 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.00023603439331054688 length of segment : 27 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005078315734863281 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.69219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 2138 time to create 1 rle with old method : 0.002626180648803711 length of segment : 46 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 5450 time to create 1 rle with old method : 0.0063343048095703125 length of segment : 101 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0018270015716552734 length of segment : 49 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 606 time to create 1 rle with old method : 0.0009205341339111328 length of segment : 17 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0005178451538085938 length of segment : 17 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 14 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0008013248443603516 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.89922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1162 time to create 1 rle with old method : 0.0014882087707519531 length of segment : 42 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007426738739013672 length of segment : 33 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 3093 time to create 1 rle with old method : 0.0039920806884765625 length of segment : 96 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1097 time to create 1 rle with old method : 0.001428842544555664 length of segment : 48 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0006816387176513672 length of segment : 25 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.0005981922149658203 length of segment : 18 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006976127624511719 length of segment : 22 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: 129.95937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0007183551788330078 length of segment : 20 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0009627342224121094 length of segment : 71 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1042 time to create 1 rle with old method : 0.0012316703796386719 length of segment : 69 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 942 time to create 1 rle with old method : 0.0012726783752441406 length of segment : 31 time for calcul the mask position with numpy : 0.0006613731384277344 nb_pixel_total : 66777 time to create 1 rle with old method : 0.07859063148498535 length of segment : 279 time for calcul the mask position with numpy : 0.0006568431854248047 nb_pixel_total : 65017 time to create 1 rle with old method : 0.07275795936584473 length of segment : 252 Processing 1 images image shape: (400, 400, 3) min: 8.00000 max: 195.00000 molded_images shape: (1, 640, 640, 3) min: -93.49297 max: 78.33437 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: -104.25469 max: 147.32266 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0008182525634765625 length of segment : 21 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0003418922424316406 length of segment : 14 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.0005068778991699219 length of segment : 17 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005447864532470703 length of segment : 20 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003170967102050781 length of segment : 21 time for calcul the mask position with numpy : 2.7894973754882812e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.00012230873107910156 length of segment : 10 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.0001742839813232422 length of segment : 12 time for calcul the mask position with numpy : 0.00023126602172851562 nb_pixel_total : 9419 time to create 1 rle with old method : 0.011230945587158203 length of segment : 358 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005142688751220703 length of segment : 26 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 932 time to create 1 rle with old method : 0.0012240409851074219 length of segment : 45 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 937 time to create 1 rle with old method : 0.0011849403381347656 length of segment : 48 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.0001766681671142578 length of segment : 15 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.51250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1367 time to create 1 rle with old method : 0.0017695426940917969 length of segment : 34 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0008380413055419922 length of segment : 33 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001895427703857422 length of segment : 11 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.0002067089080810547 length of segment : 8 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0003161430358886719 length of segment : 19 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 910 time to create 1 rle with old method : 0.0012385845184326172 length of segment : 24 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1302 time to create 1 rle with old method : 0.0016431808471679688 length of segment : 39 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 995 time to create 1 rle with old method : 0.0012295246124267578 length of segment : 55 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.00043320655822753906 length of segment : 19 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004620552062988281 length of segment : 27 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 4381 time to create 1 rle with old method : 0.005425691604614258 length of segment : 101 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002772808074951172 length of segment : 22 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 21 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 4223 time to create 1 rle with old method : 0.005301952362060547 length of segment : 71 time for calcul the mask position with numpy : 0.00015354156494140625 nb_pixel_total : 3489 time to create 1 rle with old method : 0.004225969314575195 length of segment : 98 time for calcul the mask position with numpy : 0.00021409988403320312 nb_pixel_total : 7125 time to create 1 rle with old method : 0.009689807891845703 length of segment : 168 time for calcul the mask position with numpy : 0.00026416778564453125 nb_pixel_total : 11028 time to create 1 rle with old method : 0.013302803039550781 length of segment : 180 time for calcul the mask position with numpy : 0.00028061866760253906 nb_pixel_total : 10768 time to create 1 rle with old method : 0.013152122497558594 length of segment : 169 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 783 time to create 1 rle with old method : 0.0012714862823486328 length of segment : 26 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007290840148925781 length of segment : 32 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003154277801513672 length of segment : 44 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 1588 time to create 1 rle with old method : 0.0019707679748535156 length of segment : 54 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 777 time to create 1 rle with old method : 0.0010950565338134766 length of segment : 26 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.00038242340087890625 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.14531 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 : 0.00010561943054199219 nb_pixel_total : 5228 time to create 1 rle with old method : 0.006827592849731445 length of segment : 117 time for calcul the mask position with numpy : 0.00011420249938964844 nb_pixel_total : 1852 time to create 1 rle with old method : 0.002358675003051758 length of segment : 116 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0009462833404541016 length of segment : 21 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002796649932861328 length of segment : 17 time for calcul the mask position with numpy : 0.0002613067626953125 nb_pixel_total : 8810 time to create 1 rle with old method : 0.010758399963378906 length of segment : 279 time for calcul the mask position with numpy : 0.00015044212341308594 nb_pixel_total : 2229 time to create 1 rle with old method : 0.003213167190551758 length of segment : 90 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 1069 time to create 1 rle with old method : 0.0013873577117919922 length of segment : 43 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 134.14297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0004169940948486328 length of segment : 28 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1926 time to create 1 rle with old method : 0.002485036849975586 length of segment : 154 time for calcul the mask position with numpy : 0.0001266002655029297 nb_pixel_total : 2268 time to create 1 rle with old method : 0.002842426300048828 length of segment : 143 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1805 time to create 1 rle with old method : 0.002216815948486328 length of segment : 86 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.00030422210693359375 length of segment : 23 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 910 time to create 1 rle with old method : 0.0011920928955078125 length of segment : 34 Processing 1 images image shape: (280, 400, 3) min: 5.00000 max: 190.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 63.88516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009405612945556641 nb_pixel_total : 105874 time to create 1 rle with old method : 0.12051582336425781 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.56875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006554126739501953 length of segment : 31 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 3772 time to create 1 rle with old method : 0.0044214725494384766 length of segment : 87 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.00020742416381835938 length of segment : 18 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.00038886070251464844 length of segment : 18 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1569 time to create 1 rle with old method : 0.0018858909606933594 length of segment : 53 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 2937 time to create 1 rle with old method : 0.003581523895263672 length of segment : 46 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001518726348876953 length of segment : 15 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00015473365783691406 length of segment : 24 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00017380714416503906 length of segment : 10 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1449 time to create 1 rle with old method : 0.0018694400787353516 length of segment : 37 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00024199485778808594 length of segment : 28 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 809 time to create 1 rle with old method : 0.0010175704956054688 length of segment : 61 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 1180 time to create 1 rle with old method : 0.0015687942504882812 length of segment : 28 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: 148.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 32 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.000782012939453125 length of segment : 31 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 480 time to create 1 rle with old method : 0.0006449222564697266 length of segment : 30 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.0001316070556640625 length of segment : 10 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001342296600341797 length of segment : 7 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005230903625488281 length of segment : 24 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0006761550903320312 length of segment : 17 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 2641 time to create 1 rle with old method : 0.003129243850708008 length of segment : 64 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0006375312805175781 length of segment : 32 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.0003039836883544922 length of segment : 21 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 46 time to create 1 rle with old method : 9.274482727050781e-05 length of segment : 7 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003457069396972656 length of segment : 18 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00021529197692871094 length of segment : 18 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 769 time to create 1 rle with old method : 0.0009965896606445312 length of segment : 36 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 979 time to create 1 rle with old method : 0.001196146011352539 length of segment : 41 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002384185791015625 length of segment : 20 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0005068778991699219 length of segment : 25 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006988048553466797 length of segment : 26 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.00029730796813964844 length of segment : 16 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00032210350036621094 length of segment : 22 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001838207244873047 length of segment : 10 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.000133514404296875 length of segment : 11 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00022029876708984375 length of segment : 13 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006206035614013672 length of segment : 19 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 664 time to create 1 rle with old method : 0.0009131431579589844 length of segment : 19 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.00044655799865722656 length of segment : 22 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003886222839355469 length of segment : 29 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001633167266845703 length of segment : 10 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.00047397613525390625 length of segment : 23 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006320476531982422 length of segment : 28 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 49 time to create 1 rle with old method : 9.512901306152344e-05 length of segment : 9 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003008842468261719 length of segment : 20 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.00043511390686035156 length of segment : 22 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.40078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.0002562999725341797 length of segment : 11 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00038623809814453125 length of segment : 16 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0005781650543212891 length of segment : 17 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 134.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.36016 max: 149.54531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1065 time to create 1 rle with old method : 0.0013668537139892578 length of segment : 35 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 896 time to create 1 rle with old method : 0.001188039779663086 length of segment : 35 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.0011103153228759766 length of segment : 36 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 924 time to create 1 rle with old method : 0.0012187957763671875 length of segment : 37 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 1128 time to create 1 rle with old method : 0.0013990402221679688 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.62188 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 : 5.5789947509765625e-05 nb_pixel_total : 1377 time to create 1 rle with old method : 0.0016694068908691406 length of segment : 60 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 2057 time to create 1 rle with old method : 0.0026950836181640625 length of segment : 74 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002739429473876953 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.95000 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 : 2461 time to create 1 rle with old method : 0.003222942352294922 length of segment : 73 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 6467 time to create 1 rle with old method : 0.007523298263549805 length of segment : 102 time for calcul the mask position with numpy : 0.00010180473327636719 nb_pixel_total : 4494 time to create 1 rle with old method : 0.005536794662475586 length of segment : 125 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 2073 time to create 1 rle with old method : 0.00262451171875 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.82891 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 687 time to create 1 rle with old method : 0.0013086795806884766 length of segment : 34 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 576 time to create 1 rle with old method : 0.0017123222351074219 length of segment : 36 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0004775524139404297 length of segment : 66 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 3307 time to create 1 rle with old method : 0.004297018051147461 length of segment : 93 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0007772445678710938 length of segment : 39 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 3436 time to create 1 rle with old method : 0.004540681838989258 length of segment : 98 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: 135.46328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0006725788116455078 length of segment : 17 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0006761550903320312 length of segment : 45 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1014 time to create 1 rle with old method : 0.0014634132385253906 length of segment : 39 time for calcul the mask position with numpy : 0.0005135536193847656 nb_pixel_total : 47491 time to create 1 rle with old method : 0.05451631546020508 length of segment : 280 time for calcul the mask position with numpy : 0.0007493495941162109 nb_pixel_total : 72469 time to create 1 rle with old method : 0.08116555213928223 length of segment : 312 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 197.00000 molded_images shape: (1, 640, 640, 3) min: -94.86797 max: 80.08437 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: -112.68047 max: 150.39297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0007929801940917969 length of segment : 18 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003228187561035156 length of segment : 21 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 1034 time to create 1 rle with old method : 0.0013146400451660156 length of segment : 49 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004856586456298828 length of segment : 17 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 2608 time to create 1 rle with old method : 0.0033185482025146484 length of segment : 50 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0006165504455566406 length of segment : 20 time for calcul the mask position with numpy : 0.0001976490020751953 nb_pixel_total : 9251 time to create 1 rle with old method : 0.010999679565429688 length of segment : 150 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.00046896934509277344 length of segment : 31 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002875328063964844 length of segment : 16 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.00025391578674316406 length of segment : 13 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001506805419921875 length of segment : 14 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.00025534629821777344 length of segment : 14 time for calcul the mask position with numpy : 0.00019502639770507812 nb_pixel_total : 8995 time to create 1 rle with old method : 0.010469913482666016 length of segment : 154 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 41 time to create 1 rle with old method : 8.96453857421875e-05 length of segment : 18 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003924369812011719 length of segment : 20 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.00047326087951660156 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: -108.38359 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 1399 time to create 1 rle with old method : 0.0024917125701904297 length of segment : 35 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0005080699920654297 length of segment : 18 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.0002834796905517578 length of segment : 9 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.0002617835998535156 length of segment : 11 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0006277561187744141 length of segment : 28 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 627 time to create 1 rle with old method : 0.0011572837829589844 length of segment : 33 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0003361701965332031 length of segment : 17 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0005733966827392578 length of segment : 21 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1293 time to create 1 rle with old method : 0.002253293991088867 length of segment : 40 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 791 time to create 1 rle with old method : 0.0014393329620361328 length of segment : 27 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0017702579498291016 length of segment : 54 time for calcul the mask position with numpy : 0.00011324882507324219 nb_pixel_total : 3538 time to create 1 rle with old method : 0.005739688873291016 length of segment : 102 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.00014090538024902344 length of segment : 11 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1518 time to create 1 rle with old method : 0.0020885467529296875 length of segment : 50 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 3801 time to create 1 rle with old method : 0.005762338638305664 length of segment : 96 time for calcul the mask position with numpy : 0.0001723766326904297 nb_pixel_total : 6237 time to create 1 rle with old method : 0.007940530776977539 length of segment : 168 time for calcul the mask position with numpy : 0.00018525123596191406 nb_pixel_total : 3506 time to create 1 rle with old method : 0.006172895431518555 length of segment : 103 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00030684471130371094 length of segment : 16 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006818771362304688 length of segment : 33 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 619 time to create 1 rle with old method : 0.0008399486541748047 length of segment : 34 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.00023603439331054688 length of segment : 24 time for calcul the mask position with numpy : 0.0002796649932861328 nb_pixel_total : 7853 time to create 1 rle with old method : 0.00973820686340332 length of segment : 162 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 814 time to create 1 rle with old method : 0.0012545585632324219 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.83281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 2313 time to create 1 rle with old method : 0.002792835235595703 length of segment : 141 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 596 time to create 1 rle with old method : 0.0008909702301025391 length of segment : 21 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0005242824554443359 length of segment : 14 time for calcul the mask position with numpy : 0.00011944770812988281 nb_pixel_total : 5257 time to create 1 rle with old method : 0.006250143051147461 length of segment : 139 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 704 time to create 1 rle with old method : 0.0009670257568359375 length of segment : 33 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00026345252990722656 length of segment : 17 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 847 time to create 1 rle with old method : 0.0012087821960449219 length of segment : 29 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00020647048950195312 length of segment : 17 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0007359981536865234 length of segment : 47 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 2483 time to create 1 rle with old method : 0.0032324790954589844 length of segment : 122 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 5499 time to create 1 rle with old method : 0.006416797637939453 length of segment : 126 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1197 time to create 1 rle with old method : 0.0014913082122802734 length of segment : 40 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.20156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00039839744567871094 length of segment : 28 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1875 time to create 1 rle with old method : 0.0024061203002929688 length of segment : 180 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1895 time to create 1 rle with old method : 0.002458333969116211 length of segment : 126 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 784 time to create 1 rle with old method : 0.0010890960693359375 length of segment : 88 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 874 time to create 1 rle with old method : 0.0011305809020996094 length of segment : 34 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 1806 time to create 1 rle with old method : 0.0022432804107666016 length of segment : 85 Processing 1 images image shape: (280, 400, 3) min: 11.00000 max: 183.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 61.23672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009319782257080078 nb_pixel_total : 104707 time to create 1 rle with old method : 0.1206052303314209 length of segment : 279 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.56094 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0007140636444091797 length of segment : 28 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 3423 time to create 1 rle with old method : 0.004147768020629883 length of segment : 91 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00019550323486328125 length of segment : 18 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.00017452239990234375 length of segment : 10 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003752708435058594 length of segment : 15 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1734 time to create 1 rle with old method : 0.002114534378051758 length of segment : 55 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 2946 time to create 1 rle with old method : 0.003642559051513672 length of segment : 48 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.00046253204345703125 length of segment : 26 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1369 time to create 1 rle with old method : 0.0018177032470703125 length of segment : 46 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.00015163421630859375 length of segment : 15 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1414 time to create 1 rle with old method : 0.001828908920288086 length of segment : 36 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.45156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 37 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00016808509826660156 length of segment : 11 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006203651428222656 length of segment : 31 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0008199214935302734 length of segment : 31 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0006928443908691406 length of segment : 19 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0006489753723144531 length of segment : 16 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005035400390625 length of segment : 23 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.00044155120849609375 length of segment : 20 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 2680 time to create 1 rle with old method : 0.003239870071411133 length of segment : 67 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.0002319812774658203 length of segment : 14 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0009875297546386719 length of segment : 47 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 728 time to create 1 rle with old method : 0.0012373924255371094 length of segment : 21 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 55 time to create 1 rle with old method : 0.00011801719665527344 length of segment : 8 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 745 time to create 1 rle with old method : 0.0010051727294921875 length of segment : 35 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00017189979553222656 length of segment : 12 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.00021576881408691406 length of segment : 19 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0006330013275146484 length of segment : 31 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003173351287841797 length of segment : 21 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.00016427040100097656 length of segment : 14 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00039887428283691406 length of segment : 36 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.00013017654418945312 length of segment : 6 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004487037658691406 length of segment : 21 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 413 time to create 1 rle with old method : 0.0005786418914794922 length of segment : 23 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0003032684326171875 length of segment : 16 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.0002040863037109375 length of segment : 9 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 848 time to create 1 rle with old method : 0.0010390281677246094 length of segment : 42 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.000274658203125 length of segment : 12 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.00010609626770019531 length of segment : 12 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.00031256675720214844 length of segment : 20 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006921291351318359 length of segment : 23 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.00026297569274902344 length of segment : 16 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0008068084716796875 length of segment : 27 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.00031185150146484375 length of segment : 20 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005331039428710938 length of segment : 27 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 938 time to create 1 rle with old method : 0.0011820793151855469 length of segment : 47 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001823902130126953 length of segment : 12 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 841 time to create 1 rle with old method : 0.0010218620300292969 length of segment : 51 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002994537353515625 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: 146.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.0001773834228515625 length of segment : 12 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002911090850830078 length of segment : 17 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007097721099853516 length of segment : 51 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 134.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.06328 max: 149.91641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.001430511474609375 length of segment : 28 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 843 time to create 1 rle with old method : 0.0011305809020996094 length of segment : 35 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0009365081787109375 length of segment : 30 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 788 time to create 1 rle with old method : 0.0010104179382324219 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: -117.02422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1465 time to create 1 rle with old method : 0.0017850399017333984 length of segment : 64 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 2387 time to create 1 rle with old method : 0.0029616355895996094 length of segment : 51 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0006401538848876953 length of segment : 36 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2570 time to create 1 rle with old method : 0.003452777862548828 length of segment : 37 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00034165382385253906 length of segment : 26 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.000331878662109375 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: -118.31719 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 : 0.00011992454528808594 nb_pixel_total : 5334 time to create 1 rle with old method : 0.008993387222290039 length of segment : 104 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 1978 time to create 1 rle with old method : 0.003436565399169922 length of segment : 40 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0004203319549560547 length of segment : 12 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 372 time to create 1 rle with old method : 0.0007615089416503906 length of segment : 13 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0011208057403564453 length of segment : 17 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0006043910980224609 length of segment : 25 time for calcul the mask position with numpy : 0.00023794174194335938 nb_pixel_total : 12581 time to create 1 rle with old method : 0.021244525909423828 length of segment : 117 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.98516 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 : 5.340576171875e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.001085042953491211 length of segment : 36 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0011212825775146484 length of segment : 42 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1020 time to create 1 rle with old method : 0.0021216869354248047 length of segment : 54 time for calcul the mask position with numpy : 0.00012159347534179688 nb_pixel_total : 3196 time to create 1 rle with old method : 0.0057604312896728516 length of segment : 102 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: 127.57266 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 772 time to create 1 rle with old method : 0.0009658336639404297 length of segment : 52 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006775856018066406 length of segment : 16 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0005571842193603516 length of segment : 39 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.0007920265197753906 length of segment : 56 Processing 1 images image shape: (400, 400, 3) min: 14.00000 max: 195.00000 molded_images shape: (1, 640, 640, 3) min: -92.65703 max: 76.58437 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: -109.03984 max: 148.89297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.00030922889709472656 length of segment : 20 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1539 time to create 1 rle with old method : 0.001905202865600586 length of segment : 50 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0004992485046386719 length of segment : 29 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006756782531738281 length of segment : 27 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 63 time to create 1 rle with old method : 0.00011110305786132812 length of segment : 9 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002644062042236328 length of segment : 20 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 563 time to create 1 rle with old method : 0.0008203983306884766 length of segment : 21 time for calcul the mask position with numpy : 0.00020432472229003906 nb_pixel_total : 8883 time to create 1 rle with old method : 0.010558843612670898 length of segment : 218 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.0006585121154785156 length of segment : 22 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004115104675292969 length of segment : 27 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0005195140838623047 length of segment : 17 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006880760192871094 length of segment : 30 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.0012257099151611328 length of segment : 42 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.00020194053649902344 length of segment : 12 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004494190216064453 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.07109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 30 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.00022101402282714844 length of segment : 11 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1517 time to create 1 rle with old method : 0.0019490718841552734 length of segment : 35 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.00015544891357421875 length of segment : 10 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00022530555725097656 length of segment : 9 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0004916191101074219 length of segment : 30 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001850128173828125 length of segment : 13 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 1279 time to create 1 rle with old method : 0.0016224384307861328 length of segment : 39 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0004572868347167969 length of segment : 23 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004429817199707031 length of segment : 31 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.00029397010803222656 length of segment : 20 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 727 time to create 1 rle with old method : 0.0009212493896484375 length of segment : 52 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0005490779876708984 length of segment : 22 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 3828 time to create 1 rle with old method : 0.004660606384277344 length of segment : 103 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1235 time to create 1 rle with old method : 0.0016252994537353516 length of segment : 28 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 57 time to create 1 rle with old method : 0.00010323524475097656 length of segment : 8 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 27 time to create 1 rle with old method : 9.799003601074219e-05 length of segment : 7 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.00037741661071777344 length of segment : 21 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.00027060508728027344 length of segment : 16 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 653 time to create 1 rle with old method : 0.0008668899536132812 length of segment : 36 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00022339820861816406 length of segment : 12 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0006561279296875 length of segment : 26 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0009610652923583984 length of segment : 34 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004723072052001953 length of segment : 28 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005013942718505859 length of segment : 36 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 932 time to create 1 rle with old method : 0.001093149185180664 length of segment : 68 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00029540061950683594 length of segment : 25 time for calcul the mask position with numpy : 0.00013184547424316406 nb_pixel_total : 5487 time to create 1 rle with old method : 0.007157802581787109 length of segment : 80 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003056526184082031 length of segment : 42 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.0011157989501953125 length of segment : 29 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.0011606216430664062 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.60625 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 : 8.940696716308594e-05 nb_pixel_total : 2262 time to create 1 rle with old method : 0.0030591487884521484 length of segment : 137 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 613 time to create 1 rle with old method : 0.0008790493011474609 length of segment : 22 time for calcul the mask position with numpy : 0.00011610984802246094 nb_pixel_total : 5722 time to create 1 rle with old method : 0.0065157413482666016 length of segment : 130 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1173 time to create 1 rle with old method : 0.0014452934265136719 length of segment : 41 time for calcul the mask position with numpy : 0.00012922286987304688 nb_pixel_total : 7311 time to create 1 rle with old method : 0.009053230285644531 length of segment : 84 time for calcul the mask position with numpy : 0.0002498626708984375 nb_pixel_total : 10683 time to create 1 rle with old method : 0.012587308883666992 length of segment : 278 time for calcul the mask position with numpy : 0.00012946128845214844 nb_pixel_total : 6253 time to create 1 rle with old method : 0.006997108459472656 length of segment : 156 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: 132.47109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 1369 time to create 1 rle with old method : 0.0018324851989746094 length of segment : 140 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1781 time to create 1 rle with old method : 0.002826213836669922 length of segment : 86 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1133 time to create 1 rle with old method : 0.0015764236450195312 length of segment : 44 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.00043272972106933594 length of segment : 28 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 956 time to create 1 rle with old method : 0.001855611801147461 length of segment : 100 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.00040984153747558594 length of segment : 28 Processing 1 images image shape: (280, 400, 3) min: 13.00000 max: 181.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 62.74062 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009531974792480469 nb_pixel_total : 104329 time to create 1 rle with old method : 0.11647486686706543 length of segment : 286 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: 136.13516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006132125854492188 length of segment : 31 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 2580 time to create 1 rle with old method : 0.003274202346801758 length of segment : 58 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 1347 time to create 1 rle with old method : 0.0022253990173339844 length of segment : 43 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 2716 time to create 1 rle with old method : 0.003391742706298828 length of segment : 53 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.0002391338348388672 length of segment : 35 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1748 time to create 1 rle with old method : 0.002267122268676758 length of segment : 38 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 871 time to create 1 rle with old method : 0.001089334487915039 length of segment : 45 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0004355907440185547 length of segment : 17 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.00045418739318847656 length of segment : 23 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.67422 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.00046133995056152344 length of segment : 20 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 624 time to create 1 rle with old method : 0.0008177757263183594 length of segment : 31 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0006802082061767578 length of segment : 14 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0009489059448242188 length of segment : 25 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005271434783935547 length of segment : 25 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.00028324127197265625 length of segment : 16 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00034236907958984375 length of segment : 27 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004553794860839844 length of segment : 24 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0006871223449707031 length of segment : 34 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00020170211791992188 length of segment : 13 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0003020763397216797 length of segment : 16 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002257823944091797 length of segment : 18 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.0001976490020751953 length of segment : 14 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004923343658447266 length of segment : 30 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0007810592651367188 length of segment : 35 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005588531494140625 length of segment : 31 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 768 time to create 1 rle with old method : 0.0010285377502441406 length of segment : 53 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0003039836883544922 length of segment : 12 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0003020763397216797 length of segment : 31 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2696 time to create 1 rle with old method : 0.0032689571380615234 length of segment : 66 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 51 time to create 1 rle with old method : 0.00011348724365234375 length of segment : 7 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1628 time to create 1 rle with old method : 0.0020661354064941406 length of segment : 51 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.0001685619354248047 length of segment : 7 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.00014972686767578125 length of segment : 8 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0004706382751464844 length of segment : 27 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1028 time to create 1 rle with old method : 0.0013282299041748047 length of segment : 50 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002231597900390625 length of segment : 20 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002200603485107422 length of segment : 19 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 2592 time to create 1 rle with old method : 0.003053426742553711 length of segment : 61 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.40078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0002033710479736328 length of segment : 13 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002880096435546875 length of segment : 16 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005261898040771484 length of segment : 28 time for calcul the mask position with numpy : 0.00020551681518554688 nb_pixel_total : 15324 time to create 1 rle with old method : 0.017622947692871094 length of segment : 185 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0008111000061035156 length of segment : 34 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.72500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.22734 max: 149.89687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 929 time to create 1 rle with old method : 0.0017638206481933594 length of segment : 32 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 880 time to create 1 rle with old method : 0.0017578601837158203 length of segment : 32 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 854 time to create 1 rle with old method : 0.0017352104187011719 length of segment : 31 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1025 time to create 1 rle with old method : 0.0019245147705078125 length of segment : 30 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 768 time to create 1 rle with old method : 0.0015742778778076172 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.63750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0009834766387939453 length of segment : 30 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 2759 time to create 1 rle with old method : 0.004763126373291016 length of segment : 56 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1035 time to create 1 rle with old method : 0.0018508434295654297 length of segment : 85 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0004372596740722656 length of segment : 25 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 35 time to create 1 rle with old method : 8.96453857421875e-05 length of segment : 7 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.95000 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 : 9.393692016601562e-05 nb_pixel_total : 1385 time to create 1 rle with old method : 0.0019714832305908203 length of segment : 40 time for calcul the mask position with numpy : 0.00011014938354492188 nb_pixel_total : 5752 time to create 1 rle with old method : 0.0067479610443115234 length of segment : 102 time for calcul the mask position with numpy : 0.00013065338134765625 nb_pixel_total : 6159 time to create 1 rle with old method : 0.00729060173034668 length of segment : 103 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.00048279762268066406 length of segment : 16 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0006122589111328125 length of segment : 13 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 553 time to create 1 rle with old method : 0.0008397102355957031 length of segment : 14 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 2100 time to create 1 rle with old method : 0.0025992393493652344 length of segment : 50 time for calcul the mask position with numpy : 0.00011610984802246094 nb_pixel_total : 5264 time to create 1 rle with old method : 0.006345033645629883 length of segment : 102 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.94219 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 : 5.7697296142578125e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.0014491081237792969 length of segment : 40 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 3776 time to create 1 rle with old method : 0.004706382751464844 length of segment : 104 time for calcul the mask position with numpy : 0.00010585784912109375 nb_pixel_total : 3876 time to create 1 rle with old method : 0.004874706268310547 length of segment : 105 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 251.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 128.06875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0007443428039550781 length of segment : 19 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0006017684936523438 length of segment : 45 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1643 time to create 1 rle with old method : 0.0020961761474609375 length of segment : 86 time for calcul the mask position with numpy : 0.000690460205078125 nb_pixel_total : 68698 time to create 1 rle with old method : 0.07889270782470703 length of segment : 319 Processing 1 images image shape: (400, 400, 3) min: 2.00000 max: 194.00000 molded_images shape: (1, 640, 640, 3) min: -99.70781 max: 75.33437 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: -116.62578 max: 150.20937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.0007843971252441406 length of segment : 18 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0004467964172363281 length of segment : 20 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0007359981536865234 length of segment : 22 time for calcul the mask position with numpy : 0.0002970695495605469 nb_pixel_total : 15055 time to create 1 rle with old method : 0.01728343963623047 length of segment : 276 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005838871002197266 length of segment : 43 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 435 time to create 1 rle with old method : 0.0006780624389648438 length of segment : 26 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005891323089599609 length of segment : 28 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0010771751403808594 length of segment : 47 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 539 time to create 1 rle with old method : 0.0007274150848388672 length of segment : 56 time for calcul the mask position with numpy : 2.7894973754882812e-05 nb_pixel_total : 46 time to create 1 rle with old method : 9.489059448242188e-05 length of segment : 19 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 50 time to create 1 rle with old method : 0.00013828277587890625 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.06328 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.0003600120544433594 length of segment : 9 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.0009062290191650391 length of segment : 35 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004749298095703125 length of segment : 27 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.00016355514526367188 length of segment : 9 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1432 time to create 1 rle with old method : 0.0018546581268310547 length of segment : 29 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00018715858459472656 length of segment : 10 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.00022149085998535156 length of segment : 17 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1441 time to create 1 rle with old method : 0.0018329620361328125 length of segment : 32 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0007927417755126953 length of segment : 26 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 3336 time to create 1 rle with old method : 0.003984928131103516 length of segment : 100 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006315708160400391 length of segment : 27 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1005 time to create 1 rle with old method : 0.0013079643249511719 length of segment : 49 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 1264 time to create 1 rle with old method : 0.002067089080810547 length of segment : 37 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.00032591819763183594 length of segment : 17 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1725 time to create 1 rle with old method : 0.0021266937255859375 length of segment : 47 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 676 time to create 1 rle with old method : 0.0008633136749267578 length of segment : 47 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0002841949462890625 length of segment : 18 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004856586456298828 length of segment : 29 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006206035614013672 length of segment : 33 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 3288 time to create 1 rle with old method : 0.003826141357421875 length of segment : 93 time for calcul the mask position with numpy : 0.00016617774963378906 nb_pixel_total : 8318 time to create 1 rle with old method : 0.010249853134155273 length of segment : 122 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005621910095214844 length of segment : 42 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 568 time to create 1 rle with old method : 0.0007150173187255859 length of segment : 35 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.0011417865753173828 length of segment : 35 time for calcul the mask position with numpy : 0.00017142295837402344 nb_pixel_total : 7048 time to create 1 rle with old method : 0.008884668350219727 length of segment : 109 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0005893707275390625 length of segment : 29 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1521 time to create 1 rle with old method : 0.0018475055694580078 length of segment : 31 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 4949 time to create 1 rle with old method : 0.006089687347412109 length of segment : 108 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0004730224609375 length of segment : 44 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.08281 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 : 8.821487426757812e-05 nb_pixel_total : 2166 time to create 1 rle with old method : 0.002773284912109375 length of segment : 138 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1135 time to create 1 rle with old method : 0.0014090538024902344 length of segment : 40 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 5585 time to create 1 rle with old method : 0.0065653324127197266 length of segment : 128 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 596 time to create 1 rle with old method : 0.0008759498596191406 length of segment : 22 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 725 time to create 1 rle with old method : 0.0009644031524658203 length of segment : 33 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.0011775493621826172 length of segment : 30 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 5380 time to create 1 rle with old method : 0.006254434585571289 length of segment : 113 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 134.14297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.00039696693420410156 length of segment : 27 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1604 time to create 1 rle with old method : 0.002131938934326172 length of segment : 140 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1647 time to create 1 rle with old method : 0.0021436214447021484 length of segment : 128 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 1793 time to create 1 rle with old method : 0.00223541259765625 length of segment : 85 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 906 time to create 1 rle with old method : 0.0011997222900390625 length of segment : 80 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 928 time to create 1 rle with old method : 0.0012698173522949219 length of segment : 38 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0002887248992919922 length of segment : 23 Processing 1 images image shape: (280, 400, 3) min: 15.00000 max: 182.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 63.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008959770202636719 nb_pixel_total : 105835 time to create 1 rle with old method : 0.12505745887756348 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.51016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 126 time to create 1 rle with old method : 0.00018930435180664062 length of segment : 17 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.0006680488586425781 length of segment : 31 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 2009 time to create 1 rle with old method : 0.0025696754455566406 length of segment : 85 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 12 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00015807151794433594 length of segment : 15 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00012159347534179688 length of segment : 9 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.00024080276489257812 length of segment : 23 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 1155 time to create 1 rle with old method : 0.001505136489868164 length of segment : 31 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.0004258155822753906 length of segment : 24 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 2935 time to create 1 rle with old method : 0.0036351680755615234 length of segment : 47 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0009250640869140625 length of segment : 41 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: 139.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 25 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.00032210350036621094 length of segment : 16 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 821 time to create 1 rle with old method : 0.0010519027709960938 length of segment : 39 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003666877746582031 length of segment : 23 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00023102760314941406 length of segment : 9 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00023555755615234375 length of segment : 20 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 2772 time to create 1 rle with old method : 0.003353118896484375 length of segment : 67 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.00046372413635253906 length of segment : 24 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.00067901611328125 length of segment : 35 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0006248950958251953 length of segment : 27 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 435 time to create 1 rle with old method : 0.0006537437438964844 length of segment : 16 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0006418228149414062 length of segment : 32 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0009362697601318359 length of segment : 28 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.0001881122589111328 length of segment : 24 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.0001862049102783203 length of segment : 13 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.00046563148498535156 length of segment : 33 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 802 time to create 1 rle with old method : 0.0010101795196533203 length of segment : 51 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005462169647216797 length of segment : 36 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 652 time to create 1 rle with old method : 0.0009343624114990234 length of segment : 28 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.00035381317138671875 length of segment : 14 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1031 time to create 1 rle with old method : 0.0012867450714111328 length of segment : 41 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.00016689300537109375 length of segment : 9 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.00027441978454589844 length of segment : 16 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 785 time to create 1 rle with old method : 0.0010085105895996094 length of segment : 26 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003006458282470703 length of segment : 18 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0009031295776367188 length of segment : 28 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.53750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.0003037452697753906 length of segment : 18 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001842975616455078 length of segment : 11 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.00038361549377441406 length of segment : 21 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.72500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0003304481506347656 length of segment : 57 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 15 time to create 1 rle with old method : 5.6743621826171875e-05 length of segment : 3 Detection mask done ! Trying to reset tf kernel 2499099 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 555 tf kernel not reseted sub process len(results) : 622 len(list_Values) 622 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 622 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 : 1748 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 622 chid ids of type : 4228 Number RLEs to save : 29748 save missing photos in datou_result : time spend for datou_step_exec : 33.132739305496216 time spend to save output : 1.9626493453979492 total time spend for step 1 : 35.095388650894165 step2:brightness Fri Feb 28 19:21:04 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1740766828_2498347_1340194667_053e7eb9d09cb4b33503b60c20c6e308.jpg treat image : temp/1740766828_2498347_1340194634_6c6569c701ff87dfbec066e5eb9de314.jpg treat image : temp/1740766828_2498347_1340194633_d04b0da1f07cc89a02b1269da1c07990.jpg treat image : temp/1740766828_2498347_1340194631_7a3bbc550d7ef98d238e993455865014.jpg treat image : temp/1740766828_2498347_1340194629_f5d0c3b130f2586882c1c5bb05939733.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 5 time used for this insertion : 0.013215303421020508 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.011995553970336914 save missing photos in datou_result : time spend for datou_step_exec : 1.1649696826934814 time spend to save output : 0.029882192611694336 total time spend for step 2 : 1.1948518753051758 step3:blur_detection Fri Feb 28 19:21:05 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/1740766828_2498347_1340194667_053e7eb9d09cb4b33503b60c20c6e308.jpg resize: (1080, 1920) 1340194667 -7.464140137890274 treat image : temp/1740766828_2498347_1340194634_6c6569c701ff87dfbec066e5eb9de314.jpg resize: (1080, 1920) 1340194634 -7.459631868159406 treat image : temp/1740766828_2498347_1340194633_d04b0da1f07cc89a02b1269da1c07990.jpg resize: (1080, 1920) 1340194633 -7.462934700874498 treat image : temp/1740766828_2498347_1340194631_7a3bbc550d7ef98d238e993455865014.jpg resize: (1080, 1920) 1340194631 -7.428419252086979 treat image : temp/1740766828_2498347_1340194629_f5d0c3b130f2586882c1c5bb05939733.jpg resize: (1080, 1920) 1340194629 -7.53777598596925 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 5 time used for this insertion : 0.013700485229492188 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.011708259582519531 save missing photos in datou_result : time spend for datou_step_exec : 5.294062376022339 time spend to save output : 0.030156612396240234 total time spend for step 3 : 5.324218988418579 step4:rle_unique_nms_with_priority Fri Feb 28 19:21:10 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 622 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 113 nb_hashtags : 6 time to prepare the origin masks : 1.138998031616211 time for calcul the mask position with numpy : 0.33281517028808594 nb_pixel_total : 1743208 time to create 1 rle with new method : 0.09712362289428711 time for calcul the mask position with numpy : 0.008725881576538086 nb_pixel_total : 6254 time to create 1 rle with old method : 0.0069239139556884766 time for calcul the mask position with numpy : 0.008898735046386719 nb_pixel_total : 7169 time to create 1 rle with old method : 0.008559942245483398 time for calcul the mask position with numpy : 0.009020090103149414 nb_pixel_total : 2857 time to create 1 rle with old method : 0.003556966781616211 time for calcul the mask position with numpy : 0.009145259857177734 nb_pixel_total : 68220 time to create 1 rle with old method : 0.08251667022705078 time for calcul the mask position with numpy : 0.00831460952758789 nb_pixel_total : 901 time to create 1 rle with old method : 0.0010592937469482422 time for calcul the mask position with numpy : 0.008142232894897461 nb_pixel_total : 939 time to create 1 rle with old method : 0.0010433197021484375 time for calcul the mask position with numpy : 0.008166313171386719 nb_pixel_total : 354 time to create 1 rle with old method : 0.0003962516784667969 time for calcul the mask position with numpy : 0.008249998092651367 nb_pixel_total : 141 time to create 1 rle with old method : 0.00019288063049316406 time for calcul the mask position with numpy : 0.00812077522277832 nb_pixel_total : 85 time to create 1 rle with old method : 0.00011515617370605469 time for calcul the mask position with numpy : 0.008061885833740234 nb_pixel_total : 2456 time to create 1 rle with old method : 0.0026557445526123047 time for calcul the mask position with numpy : 0.008023262023925781 nb_pixel_total : 1274 time to create 1 rle with old method : 0.0013380050659179688 time for calcul the mask position with numpy : 0.007911443710327148 nb_pixel_total : 1215 time to create 1 rle with old method : 0.0012209415435791016 time for calcul the mask position with numpy : 0.00818490982055664 nb_pixel_total : 544 time to create 1 rle with old method : 0.0005815029144287109 time for calcul the mask position with numpy : 0.008366107940673828 nb_pixel_total : 604 time to create 1 rle with old method : 0.0006763935089111328 time for calcul the mask position with numpy : 0.00839853286743164 nb_pixel_total : 2895 time to create 1 rle with old method : 0.0032377243041992188 time for calcul the mask position with numpy : 0.008278131484985352 nb_pixel_total : 5714 time to create 1 rle with old method : 0.006130218505859375 time for calcul the mask position with numpy : 0.008023738861083984 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0011527538299560547 time for calcul the mask position with numpy : 0.008148908615112305 nb_pixel_total : 1451 time to create 1 rle with old method : 0.0016460418701171875 time for calcul the mask position with numpy : 0.007806539535522461 nb_pixel_total : 1301 time to create 1 rle with old method : 0.0014634132385253906 time for calcul the mask position with numpy : 0.008104801177978516 nb_pixel_total : 2191 time to create 1 rle with old method : 0.0022826194763183594 time for calcul the mask position with numpy : 0.008357524871826172 nb_pixel_total : 46 time to create 1 rle with old method : 0.00011539459228515625 time for calcul the mask position with numpy : 0.00821828842163086 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005199909210205078 time for calcul the mask position with numpy : 0.008311033248901367 nb_pixel_total : 17872 time to create 1 rle with old method : 0.01940464973449707 time for calcul the mask position with numpy : 0.008051633834838867 nb_pixel_total : 10245 time to create 1 rle with old method : 0.011657238006591797 time for calcul the mask position with numpy : 0.008097410202026367 nb_pixel_total : 598 time to create 1 rle with old method : 0.0006394386291503906 time for calcul the mask position with numpy : 0.008167743682861328 nb_pixel_total : 1853 time to create 1 rle with old method : 0.002154827117919922 time for calcul the mask position with numpy : 0.008536815643310547 nb_pixel_total : 578 time to create 1 rle with old method : 0.0006890296936035156 time for calcul the mask position with numpy : 0.008384466171264648 nb_pixel_total : 5379 time to create 1 rle with old method : 0.005852222442626953 time for calcul the mask position with numpy : 0.008093833923339844 nb_pixel_total : 383 time to create 1 rle with old method : 0.0004677772521972656 time for calcul the mask position with numpy : 0.007948875427246094 nb_pixel_total : 53 time to create 1 rle with old method : 6.4849853515625e-05 time for calcul the mask position with numpy : 0.00805521011352539 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002613067626953125 time for calcul the mask position with numpy : 0.008130311965942383 nb_pixel_total : 3636 time to create 1 rle with old method : 0.003907918930053711 time for calcul the mask position with numpy : 0.008091211318969727 nb_pixel_total : 626 time to create 1 rle with old method : 0.0007033348083496094 time for calcul the mask position with numpy : 0.007871150970458984 nb_pixel_total : 718 time to create 1 rle with old method : 0.0008130073547363281 time for calcul the mask position with numpy : 0.00795125961303711 nb_pixel_total : 2116 time to create 1 rle with old method : 0.0023941993713378906 time for calcul the mask position with numpy : 0.008217573165893555 nb_pixel_total : 1198 time to create 1 rle with old method : 0.0012941360473632812 time for calcul the mask position with numpy : 0.008316993713378906 nb_pixel_total : 198 time to create 1 rle with old method : 0.00022649765014648438 time for calcul the mask position with numpy : 0.008010387420654297 nb_pixel_total : 1004 time to create 1 rle with old method : 0.0010333061218261719 time for calcul the mask position with numpy : 0.00807499885559082 nb_pixel_total : 17225 time to create 1 rle with old method : 0.020218849182128906 time for calcul the mask position with numpy : 0.009337902069091797 nb_pixel_total : 283 time to create 1 rle with old method : 0.00037217140197753906 time for calcul the mask position with numpy : 0.008037567138671875 nb_pixel_total : 933 time to create 1 rle with old method : 0.0010449886322021484 time for calcul the mask position with numpy : 0.008253335952758789 nb_pixel_total : 816 time to create 1 rle with old method : 0.0009658336639404297 time for calcul the mask position with numpy : 0.008269071578979492 nb_pixel_total : 1562 time to create 1 rle with old method : 0.0018436908721923828 time for calcul the mask position with numpy : 0.008191585540771484 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005147457122802734 time for calcul the mask position with numpy : 0.008080005645751953 nb_pixel_total : 2197 time to create 1 rle with old method : 0.002397298812866211 time for calcul the mask position with numpy : 0.00817251205444336 nb_pixel_total : 293 time to create 1 rle with old method : 0.0003077983856201172 time for calcul the mask position with numpy : 0.008026838302612305 nb_pixel_total : 105 time to create 1 rle with old method : 0.00011658668518066406 time for calcul the mask position with numpy : 0.008226871490478516 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002040863037109375 time for calcul the mask position with numpy : 0.008178949356079102 nb_pixel_total : 212 time to create 1 rle with old method : 0.0002281665802001953 time for calcul the mask position with numpy : 0.008157014846801758 nb_pixel_total : 389 time to create 1 rle with old method : 0.0004146099090576172 time for calcul the mask position with numpy : 0.008154630661010742 nb_pixel_total : 371 time to create 1 rle with old method : 0.0004448890686035156 time for calcul the mask position with numpy : 0.008292675018310547 nb_pixel_total : 346 time to create 1 rle with old method : 0.00040531158447265625 time for calcul the mask position with numpy : 0.008282661437988281 nb_pixel_total : 587 time to create 1 rle with old method : 0.0006353855133056641 time for calcul the mask position with numpy : 0.007972240447998047 nb_pixel_total : 847 time to create 1 rle with old method : 0.0009579658508300781 time for calcul the mask position with numpy : 0.008086919784545898 nb_pixel_total : 837 time to create 1 rle with old method : 0.0009634494781494141 time for calcul the mask position with numpy : 0.008192777633666992 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0014808177947998047 time for calcul the mask position with numpy : 0.008272647857666016 nb_pixel_total : 595 time to create 1 rle with old method : 0.0006780624389648438 time for calcul the mask position with numpy : 0.008011579513549805 nb_pixel_total : 1785 time to create 1 rle with old method : 0.002017498016357422 time for calcul the mask position with numpy : 0.008072614669799805 nb_pixel_total : 407 time to create 1 rle with old method : 0.0004935264587402344 time for calcul the mask position with numpy : 0.008024215698242188 nb_pixel_total : 260 time to create 1 rle with old method : 0.0002815723419189453 time for calcul the mask position with numpy : 0.008126258850097656 nb_pixel_total : 7615 time to create 1 rle with old method : 0.008062362670898438 time for calcul the mask position with numpy : 0.008195877075195312 nb_pixel_total : 4647 time to create 1 rle with old method : 0.005153179168701172 time for calcul the mask position with numpy : 0.00818634033203125 nb_pixel_total : 310 time to create 1 rle with old method : 0.0003552436828613281 time for calcul the mask position with numpy : 0.008105754852294922 nb_pixel_total : 1415 time to create 1 rle with old method : 0.0015797615051269531 time for calcul the mask position with numpy : 0.008261442184448242 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002613067626953125 time for calcul the mask position with numpy : 0.008377313613891602 nb_pixel_total : 91 time to create 1 rle with old method : 0.00010347366333007812 time for calcul the mask position with numpy : 0.008173227310180664 nb_pixel_total : 1383 time to create 1 rle with old method : 0.0016355514526367188 time for calcul the mask position with numpy : 0.007965803146362305 nb_pixel_total : 358 time to create 1 rle with old method : 0.0004062652587890625 time for calcul the mask position with numpy : 0.00815582275390625 nb_pixel_total : 459 time to create 1 rle with old method : 0.0005583763122558594 time for calcul the mask position with numpy : 0.008595943450927734 nb_pixel_total : 106610 time to create 1 rle with old method : 0.11289119720458984 time for calcul the mask position with numpy : 0.008081674575805664 nb_pixel_total : 211 time to create 1 rle with old method : 0.00021982192993164062 time for calcul the mask position with numpy : 0.008193016052246094 nb_pixel_total : 542 time to create 1 rle with old method : 0.0005736351013183594 time for calcul the mask position with numpy : 0.008205890655517578 nb_pixel_total : 50 time to create 1 rle with old method : 6.341934204101562e-05 time for calcul the mask position with numpy : 0.008287191390991211 nb_pixel_total : 493 time to create 1 rle with old method : 0.0005650520324707031 time for calcul the mask position with numpy : 0.008112907409667969 nb_pixel_total : 109 time to create 1 rle with old method : 0.000125885009765625 time for calcul the mask position with numpy : 0.00798797607421875 nb_pixel_total : 88 time to create 1 rle with old method : 0.00010585784912109375 time for calcul the mask position with numpy : 0.009023427963256836 nb_pixel_total : 114 time to create 1 rle with old method : 0.00013184547424316406 time for calcul the mask position with numpy : 0.007955551147460938 nb_pixel_total : 1589 time to create 1 rle with old method : 0.001766204833984375 time for calcul the mask position with numpy : 0.008067846298217773 nb_pixel_total : 621 time to create 1 rle with old method : 0.0006871223449707031 time for calcul the mask position with numpy : 0.007903575897216797 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0013744831085205078 time for calcul the mask position with numpy : 0.007866382598876953 nb_pixel_total : 1081 time to create 1 rle with old method : 0.0011861324310302734 time for calcul the mask position with numpy : 0.008048534393310547 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003361701965332031 time for calcul the mask position with numpy : 0.009608268737792969 nb_pixel_total : 28 time to create 1 rle with old method : 6.461143493652344e-05 time for calcul the mask position with numpy : 0.009576082229614258 nb_pixel_total : 373 time to create 1 rle with old method : 0.0006096363067626953 time for calcul the mask position with numpy : 0.009656190872192383 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003273487091064453 time for calcul the mask position with numpy : 0.009629249572753906 nb_pixel_total : 125 time to create 1 rle with old method : 0.000209808349609375 time for calcul the mask position with numpy : 0.009603500366210938 nb_pixel_total : 86 time to create 1 rle with old method : 0.00015091896057128906 time for calcul the mask position with numpy : 0.009582996368408203 nb_pixel_total : 101 time to create 1 rle with old method : 0.0001709461212158203 time for calcul the mask position with numpy : 0.009643316268920898 nb_pixel_total : 123 time to create 1 rle with old method : 0.00021505355834960938 time for calcul the mask position with numpy : 0.009655952453613281 nb_pixel_total : 653 time to create 1 rle with old method : 0.0010726451873779297 time for calcul the mask position with numpy : 0.008876323699951172 nb_pixel_total : 227 time to create 1 rle with old method : 0.000255584716796875 time for calcul the mask position with numpy : 0.008095026016235352 nb_pixel_total : 55 time to create 1 rle with old method : 6.604194641113281e-05 time for calcul the mask position with numpy : 0.008122682571411133 nb_pixel_total : 272 time to create 1 rle with old method : 0.00032067298889160156 time for calcul the mask position with numpy : 0.00808405876159668 nb_pixel_total : 970 time to create 1 rle with old method : 0.0011048316955566406 time for calcul the mask position with numpy : 0.007931709289550781 nb_pixel_total : 148 time to create 1 rle with old method : 0.0001938343048095703 time for calcul the mask position with numpy : 0.00791621208190918 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001285076141357422 time for calcul the mask position with numpy : 0.007826566696166992 nb_pixel_total : 77 time to create 1 rle with old method : 9.393692016601562e-05 time for calcul the mask position with numpy : 0.00785064697265625 nb_pixel_total : 386 time to create 1 rle with old method : 0.00041365623474121094 time for calcul the mask position with numpy : 0.008195638656616211 nb_pixel_total : 3290 time to create 1 rle with old method : 0.003627300262451172 time for calcul the mask position with numpy : 0.007916927337646484 nb_pixel_total : 427 time to create 1 rle with old method : 0.000457763671875 time for calcul the mask position with numpy : 0.008252620697021484 nb_pixel_total : 10 time to create 1 rle with old method : 2.5987625122070312e-05 time for calcul the mask position with numpy : 0.008121967315673828 nb_pixel_total : 312 time to create 1 rle with old method : 0.00036716461181640625 time for calcul the mask position with numpy : 0.008119344711303711 nb_pixel_total : 226 time to create 1 rle with old method : 0.0002560615539550781 time for calcul the mask position with numpy : 0.008215665817260742 nb_pixel_total : 392 time to create 1 rle with old method : 0.0004649162292480469 time for calcul the mask position with numpy : 0.008111715316772461 nb_pixel_total : 733 time to create 1 rle with old method : 0.0007624626159667969 time for calcul the mask position with numpy : 0.008193731307983398 nb_pixel_total : 2829 time to create 1 rle with old method : 0.003052949905395508 time for calcul the mask position with numpy : 0.008174419403076172 nb_pixel_total : 482 time to create 1 rle with old method : 0.0005810260772705078 time for calcul the mask position with numpy : 0.008156776428222656 nb_pixel_total : 129 time to create 1 rle with old method : 0.0001437664031982422 time for calcul the mask position with numpy : 0.008006572723388672 nb_pixel_total : 392 time to create 1 rle with old method : 0.0004189014434814453 time for calcul the mask position with numpy : 0.007816076278686523 nb_pixel_total : 231 time to create 1 rle with old method : 0.00024271011352539062 time for calcul the mask position with numpy : 0.008144855499267578 nb_pixel_total : 187 time to create 1 rle with old method : 0.00020623207092285156 time for calcul the mask position with numpy : 0.007947921752929688 nb_pixel_total : 597 time to create 1 rle with old method : 0.0006136894226074219 time for calcul the mask position with numpy : 0.00811767578125 nb_pixel_total : 11 time to create 1 rle with old method : 2.9325485229492188e-05 create new chi : 1.7490484714508057 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 : 0.009979963302612305 batch 1 Loaded 114 chid ids of type : 4230 Number RLEs to save : 12087 TO DO : save crop sub photo not yet done ! save time : 0.7036116123199463 nb_obj : 129 nb_hashtags : 7 time to prepare the origin masks : 2.178419828414917 time for calcul the mask position with numpy : 0.5200273990631104 nb_pixel_total : 1771031 time to create 1 rle with new method : 0.09666848182678223 time for calcul the mask position with numpy : 0.006908416748046875 nb_pixel_total : 66777 time to create 1 rle with old method : 0.07414007186889648 time for calcul the mask position with numpy : 0.006230831146240234 nb_pixel_total : 96 time to create 1 rle with old method : 0.00015735626220703125 time for calcul the mask position with numpy : 0.006232261657714844 nb_pixel_total : 410 time to create 1 rle with old method : 0.0004754066467285156 time for calcul the mask position with numpy : 0.006346225738525391 nb_pixel_total : 1060 time to create 1 rle with old method : 0.0011174678802490234 time for calcul the mask position with numpy : 0.005941629409790039 nb_pixel_total : 13 time to create 1 rle with old method : 5.91278076171875e-05 time for calcul the mask position with numpy : 0.005975008010864258 nb_pixel_total : 854 time to create 1 rle with old method : 0.0009369850158691406 time for calcul the mask position with numpy : 0.006052255630493164 nb_pixel_total : 390 time to create 1 rle with old method : 0.0004508495330810547 time for calcul the mask position with numpy : 0.006233692169189453 nb_pixel_total : 30 time to create 1 rle with old method : 6.866455078125e-05 time for calcul the mask position with numpy : 0.006392002105712891 nb_pixel_total : 32 time to create 1 rle with old method : 7.581710815429688e-05 time for calcul the mask position with numpy : 0.006514310836791992 nb_pixel_total : 7593 time to create 1 rle with old method : 0.00826406478881836 time for calcul the mask position with numpy : 0.00615382194519043 nb_pixel_total : 2405 time to create 1 rle with old method : 0.0026204586029052734 time for calcul the mask position with numpy : 0.00596165657043457 nb_pixel_total : 532 time to create 1 rle with old method : 0.0006461143493652344 time for calcul the mask position with numpy : 0.006381034851074219 nb_pixel_total : 102 time to create 1 rle with old method : 0.000152587890625 time for calcul the mask position with numpy : 0.00612950325012207 nb_pixel_total : 740 time to create 1 rle with old method : 0.0008783340454101562 time for calcul the mask position with numpy : 0.006033897399902344 nb_pixel_total : 578 time to create 1 rle with old method : 0.00069427490234375 time for calcul the mask position with numpy : 0.006178855895996094 nb_pixel_total : 743 time to create 1 rle with old method : 0.0008966922760009766 time for calcul the mask position with numpy : 0.00608515739440918 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005214214324951172 time for calcul the mask position with numpy : 0.005982875823974609 nb_pixel_total : 379 time to create 1 rle with old method : 0.00044655799865722656 time for calcul the mask position with numpy : 0.006249666213989258 nb_pixel_total : 5450 time to create 1 rle with old method : 0.005894660949707031 time for calcul the mask position with numpy : 0.0062825679779052734 nb_pixel_total : 460 time to create 1 rle with old method : 0.0005221366882324219 time for calcul the mask position with numpy : 0.00590968132019043 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0014090538024902344 time for calcul the mask position with numpy : 0.00608372688293457 nb_pixel_total : 67 time to create 1 rle with old method : 0.0001251697540283203 time for calcul the mask position with numpy : 0.006021261215209961 nb_pixel_total : 1162 time to create 1 rle with old method : 0.0013012886047363281 time for calcul the mask position with numpy : 0.005997896194458008 nb_pixel_total : 3093 time to create 1 rle with old method : 0.0036613941192626953 time for calcul the mask position with numpy : 0.006270170211791992 nb_pixel_total : 942 time to create 1 rle with old method : 0.0010886192321777344 time for calcul the mask position with numpy : 0.006132364273071289 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002522468566894531 time for calcul the mask position with numpy : 0.00608372688293457 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004010200500488281 time for calcul the mask position with numpy : 0.0062944889068603516 nb_pixel_total : 2138 time to create 1 rle with old method : 0.002450227737426758 time for calcul the mask position with numpy : 0.006418466567993164 nb_pixel_total : 606 time to create 1 rle with old method : 0.0007390975952148438 time for calcul the mask position with numpy : 0.006052732467651367 nb_pixel_total : 504 time to create 1 rle with old method : 0.0006062984466552734 time for calcul the mask position with numpy : 0.0067234039306640625 nb_pixel_total : 152 time to create 1 rle with old method : 0.00028705596923828125 time for calcul the mask position with numpy : 0.00989532470703125 nb_pixel_total : 910 time to create 1 rle with old method : 0.0011126995086669922 time for calcul the mask position with numpy : 0.009770870208740234 nb_pixel_total : 3611 time to create 1 rle with old method : 0.0041773319244384766 time for calcul the mask position with numpy : 0.009015321731567383 nb_pixel_total : 4381 time to create 1 rle with old method : 0.004849910736083984 time for calcul the mask position with numpy : 0.008722066879272461 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007417201995849609 time for calcul the mask position with numpy : 0.009590864181518555 nb_pixel_total : 8810 time to create 1 rle with old method : 0.014217376708984375 time for calcul the mask position with numpy : 0.011451244354248047 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003795623779296875 time for calcul the mask position with numpy : 0.01095128059387207 nb_pixel_total : 1302 time to create 1 rle with old method : 0.002174854278564453 time for calcul the mask position with numpy : 0.011132955551147461 nb_pixel_total : 59 time to create 1 rle with old method : 0.00012350082397460938 time for calcul the mask position with numpy : 0.011349678039550781 nb_pixel_total : 5228 time to create 1 rle with old method : 0.008689403533935547 time for calcul the mask position with numpy : 0.010847091674804688 nb_pixel_total : 3486 time to create 1 rle with old method : 0.0039038658142089844 time for calcul the mask position with numpy : 0.009323835372924805 nb_pixel_total : 7940 time to create 1 rle with old method : 0.008538961410522461 time for calcul the mask position with numpy : 0.006969451904296875 nb_pixel_total : 1069 time to create 1 rle with old method : 0.0011146068572998047 time for calcul the mask position with numpy : 0.007794857025146484 nb_pixel_total : 1588 time to create 1 rle with old method : 0.0017049312591552734 time for calcul the mask position with numpy : 0.008541345596313477 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004878044128417969 time for calcul the mask position with numpy : 0.008785009384155273 nb_pixel_total : 205 time to create 1 rle with old method : 0.00024437904357910156 time for calcul the mask position with numpy : 0.008075714111328125 nb_pixel_total : 9419 time to create 1 rle with old method : 0.010167121887207031 time for calcul the mask position with numpy : 0.006040334701538086 nb_pixel_total : 167 time to create 1 rle with old method : 0.00020647048950195312 time for calcul the mask position with numpy : 0.005766391754150391 nb_pixel_total : 304 time to create 1 rle with old method : 0.0003237724304199219 time for calcul the mask position with numpy : 0.005818605422973633 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003006458282470703 time for calcul the mask position with numpy : 0.0058820247650146484 nb_pixel_total : 1926 time to create 1 rle with old method : 0.002048015594482422 time for calcul the mask position with numpy : 0.005913972854614258 nb_pixel_total : 695 time to create 1 rle with old method : 0.0008747577667236328 time for calcul the mask position with numpy : 0.005822420120239258 nb_pixel_total : 249 time to create 1 rle with old method : 0.00027871131896972656 time for calcul the mask position with numpy : 0.00577855110168457 nb_pixel_total : 1852 time to create 1 rle with old method : 0.001995563507080078 time for calcul the mask position with numpy : 0.005791902542114258 nb_pixel_total : 26 time to create 1 rle with old method : 6.127357482910156e-05 time for calcul the mask position with numpy : 0.005725860595703125 nb_pixel_total : 117 time to create 1 rle with old method : 0.00014090538024902344 time for calcul the mask position with numpy : 0.005750417709350586 nb_pixel_total : 43 time to create 1 rle with old method : 6.437301635742188e-05 time for calcul the mask position with numpy : 0.005676984786987305 nb_pixel_total : 540 time to create 1 rle with old method : 0.0005788803100585938 time for calcul the mask position with numpy : 0.005610227584838867 nb_pixel_total : 161 time to create 1 rle with old method : 0.00019693374633789062 time for calcul the mask position with numpy : 0.0056269168853759766 nb_pixel_total : 291 time to create 1 rle with old method : 0.0003266334533691406 time for calcul the mask position with numpy : 0.0055370330810546875 nb_pixel_total : 390 time to create 1 rle with old method : 0.00042724609375 time for calcul the mask position with numpy : 0.005705356597900391 nb_pixel_total : 354 time to create 1 rle with old method : 0.0003955364227294922 time for calcul the mask position with numpy : 0.005998373031616211 nb_pixel_total : 323 time to create 1 rle with old method : 0.0003535747528076172 time for calcul the mask position with numpy : 0.0062313079833984375 nb_pixel_total : 783 time to create 1 rle with old method : 0.0008966922760009766 time for calcul the mask position with numpy : 0.006151914596557617 nb_pixel_total : 12 time to create 1 rle with old method : 6.151199340820312e-05 time for calcul the mask position with numpy : 0.006139039993286133 nb_pixel_total : 995 time to create 1 rle with old method : 0.0011336803436279297 time for calcul the mask position with numpy : 0.0060117244720458984 nb_pixel_total : 559 time to create 1 rle with old method : 0.0006887912750244141 time for calcul the mask position with numpy : 0.006035566329956055 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005133152008056641 time for calcul the mask position with numpy : 0.006081104278564453 nb_pixel_total : 1805 time to create 1 rle with old method : 0.0019123554229736328 time for calcul the mask position with numpy : 0.009480714797973633 nb_pixel_total : 106 time to create 1 rle with old method : 0.0002384185791015625 time for calcul the mask position with numpy : 0.00747370719909668 nb_pixel_total : 78 time to create 1 rle with old method : 0.00011897087097167969 time for calcul the mask position with numpy : 0.005936861038208008 nb_pixel_total : 4223 time to create 1 rle with old method : 0.004527091979980469 time for calcul the mask position with numpy : 0.0059206485748291016 nb_pixel_total : 2229 time to create 1 rle with old method : 0.0024309158325195312 time for calcul the mask position with numpy : 0.005728244781494141 nb_pixel_total : 937 time to create 1 rle with old method : 0.0009963512420654297 time for calcul the mask position with numpy : 0.006040334701538086 nb_pixel_total : 210 time to create 1 rle with old method : 0.0002624988555908203 time for calcul the mask position with numpy : 0.0061681270599365234 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001399517059326172 time for calcul the mask position with numpy : 0.006071567535400391 nb_pixel_total : 1367 time to create 1 rle with old method : 0.0015573501586914062 time for calcul the mask position with numpy : 0.00701141357421875 nb_pixel_total : 171 time to create 1 rle with old method : 0.00030994415283203125 time for calcul the mask position with numpy : 0.007220745086669922 nb_pixel_total : 620 time to create 1 rle with old method : 0.0010497570037841797 time for calcul the mask position with numpy : 0.007149457931518555 nb_pixel_total : 167 time to create 1 rle with old method : 0.0003008842468261719 time for calcul the mask position with numpy : 0.008532285690307617 nb_pixel_total : 105874 time to create 1 rle with old method : 0.13175368309020996 time for calcul the mask position with numpy : 0.005905866622924805 nb_pixel_total : 97 time to create 1 rle with old method : 0.00012564659118652344 time for calcul the mask position with numpy : 0.005696535110473633 nb_pixel_total : 473 time to create 1 rle with old method : 0.0005176067352294922 time for calcul the mask position with numpy : 0.005750894546508789 nb_pixel_total : 49 time to create 1 rle with old method : 7.414817810058594e-05 time for calcul the mask position with numpy : 0.005807161331176758 nb_pixel_total : 68 time to create 1 rle with old method : 0.00010013580322265625 time for calcul the mask position with numpy : 0.005753993988037109 nb_pixel_total : 77 time to create 1 rle with old method : 0.00017213821411132812 time for calcul the mask position with numpy : 0.005776405334472656 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001361370086669922 time for calcul the mask position with numpy : 0.005704641342163086 nb_pixel_total : 444 time to create 1 rle with old method : 0.0004901885986328125 time for calcul the mask position with numpy : 0.005769014358520508 nb_pixel_total : 365 time to create 1 rle with old method : 0.0004057884216308594 time for calcul the mask position with numpy : 0.005891561508178711 nb_pixel_total : 117 time to create 1 rle with old method : 0.0001780986785888672 time for calcul the mask position with numpy : 0.0059528350830078125 nb_pixel_total : 1569 time to create 1 rle with old method : 0.001764535903930664 time for calcul the mask position with numpy : 0.005978107452392578 nb_pixel_total : 664 time to create 1 rle with old method : 0.0007188320159912109 time for calcul the mask position with numpy : 0.006067037582397461 nb_pixel_total : 214 time to create 1 rle with old method : 0.0002779960632324219 time for calcul the mask position with numpy : 0.005847930908203125 nb_pixel_total : 8 time to create 1 rle with old method : 3.0994415283203125e-05 time for calcul the mask position with numpy : 0.005935192108154297 nb_pixel_total : 349 time to create 1 rle with old method : 0.00042724609375 time for calcul the mask position with numpy : 0.0061130523681640625 nb_pixel_total : 196 time to create 1 rle with old method : 0.00021910667419433594 time for calcul the mask position with numpy : 0.005773067474365234 nb_pixel_total : 143 time to create 1 rle with old method : 0.00018930435180664062 time for calcul the mask position with numpy : 0.00568842887878418 nb_pixel_total : 2937 time to create 1 rle with old method : 0.0031659603118896484 time for calcul the mask position with numpy : 0.005817413330078125 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001246929168701172 time for calcul the mask position with numpy : 0.0058193206787109375 nb_pixel_total : 76 time to create 1 rle with old method : 9.775161743164062e-05 time for calcul the mask position with numpy : 0.005772113800048828 nb_pixel_total : 98 time to create 1 rle with old method : 0.00012946128845214844 time for calcul the mask position with numpy : 0.005913734436035156 nb_pixel_total : 141 time to create 1 rle with old method : 0.00016570091247558594 time for calcul the mask position with numpy : 0.006201267242431641 nb_pixel_total : 637 time to create 1 rle with old method : 0.0007791519165039062 time for calcul the mask position with numpy : 0.0063250064849853516 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006561279296875 time for calcul the mask position with numpy : 0.006467103958129883 nb_pixel_total : 1180 time to create 1 rle with old method : 0.0014569759368896484 time for calcul the mask position with numpy : 0.006356239318847656 nb_pixel_total : 46 time to create 1 rle with old method : 8.0108642578125e-05 time for calcul the mask position with numpy : 0.006509304046630859 nb_pixel_total : 979 time to create 1 rle with old method : 0.001237630844116211 time for calcul the mask position with numpy : 0.010070323944091797 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002579689025878906 time for calcul the mask position with numpy : 0.008363485336303711 nb_pixel_total : 101 time to create 1 rle with old method : 0.0002446174621582031 time for calcul the mask position with numpy : 0.006963014602661133 nb_pixel_total : 3772 time to create 1 rle with old method : 0.004334688186645508 time for calcul the mask position with numpy : 0.006352424621582031 nb_pixel_total : 385 time to create 1 rle with old method : 0.00043845176696777344 time for calcul the mask position with numpy : 0.006377696990966797 nb_pixel_total : 77 time to create 1 rle with old method : 9.799003601074219e-05 time for calcul the mask position with numpy : 0.008630514144897461 nb_pixel_total : 480 time to create 1 rle with old method : 0.0005750656127929688 time for calcul the mask position with numpy : 0.008467435836791992 nb_pixel_total : 240 time to create 1 rle with old method : 0.00029921531677246094 time for calcul the mask position with numpy : 0.008450031280517578 nb_pixel_total : 18 time to create 1 rle with old method : 8.296966552734375e-05 time for calcul the mask position with numpy : 0.008414268493652344 nb_pixel_total : 318 time to create 1 rle with old method : 0.00035858154296875 time for calcul the mask position with numpy : 0.008406400680541992 nb_pixel_total : 1449 time to create 1 rle with old method : 0.0016674995422363281 time for calcul the mask position with numpy : 0.008964776992797852 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003306865692138672 time for calcul the mask position with numpy : 0.008173942565917969 nb_pixel_total : 208 time to create 1 rle with old method : 0.00024700164794921875 time for calcul the mask position with numpy : 0.008298397064208984 nb_pixel_total : 2641 time to create 1 rle with old method : 0.002988576889038086 time for calcul the mask position with numpy : 0.008249759674072266 nb_pixel_total : 448 time to create 1 rle with old method : 0.0005319118499755859 time for calcul the mask position with numpy : 0.00804901123046875 nb_pixel_total : 809 time to create 1 rle with old method : 0.0008292198181152344 time for calcul the mask position with numpy : 0.008082866668701172 nb_pixel_total : 77 time to create 1 rle with old method : 8.797645568847656e-05 time for calcul the mask position with numpy : 0.00799703598022461 nb_pixel_total : 205 time to create 1 rle with old method : 0.00021982192993164062 time for calcul the mask position with numpy : 0.008175373077392578 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003097057342529297 time for calcul the mask position with numpy : 0.008094072341918945 nb_pixel_total : 769 time to create 1 rle with old method : 0.0008323192596435547 time for calcul the mask position with numpy : 0.008222579956054688 nb_pixel_total : 490 time to create 1 rle with old method : 0.0005664825439453125 time for calcul the mask position with numpy : 0.008231163024902344 nb_pixel_total : 211 time to create 1 rle with old method : 0.0002655982971191406 time for calcul the mask position with numpy : 0.008110761642456055 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005435943603515625 create new chi : 1.8814904689788818 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 : 0.0017621517181396484 batch 1 Loaded 130 chid ids of type : 4230 Number RLEs to save : 11918 TO DO : save crop sub photo not yet done ! save time : 0.7034084796905518 nb_obj : 132 nb_hashtags : 6 time to prepare the origin masks : 1.8762617111206055 time for calcul the mask position with numpy : 0.23060989379882812 nb_pixel_total : 1771446 time to create 1 rle with new method : 0.1054224967956543 time for calcul the mask position with numpy : 0.006444454193115234 nb_pixel_total : 25970 time to create 1 rle with old method : 0.028599977493286133 time for calcul the mask position with numpy : 0.006205081939697266 nb_pixel_total : 57 time to create 1 rle with old method : 0.00011086463928222656 time for calcul the mask position with numpy : 0.006294965744018555 nb_pixel_total : 1065 time to create 1 rle with old method : 0.0011644363403320312 time for calcul the mask position with numpy : 0.005867481231689453 nb_pixel_total : 896 time to create 1 rle with old method : 0.0010406970977783203 time for calcul the mask position with numpy : 0.006125688552856445 nb_pixel_total : 84 time to create 1 rle with old method : 0.00018310546875 time for calcul the mask position with numpy : 0.00641179084777832 nb_pixel_total : 31 time to create 1 rle with old method : 8.416175842285156e-05 time for calcul the mask position with numpy : 0.005970478057861328 nb_pixel_total : 193 time to create 1 rle with old method : 0.00024628639221191406 time for calcul the mask position with numpy : 0.006009578704833984 nb_pixel_total : 2057 time to create 1 rle with old method : 0.0023055076599121094 time for calcul the mask position with numpy : 0.0061719417572021484 nb_pixel_total : 47491 time to create 1 rle with old method : 0.05130434036254883 time for calcul the mask position with numpy : 0.005912303924560547 nb_pixel_total : 1377 time to create 1 rle with old method : 0.0014867782592773438 time for calcul the mask position with numpy : 0.008150815963745117 nb_pixel_total : 597 time to create 1 rle with old method : 0.0006504058837890625 time for calcul the mask position with numpy : 0.009271383285522461 nb_pixel_total : 533 time to create 1 rle with old method : 0.0006346702575683594 time for calcul the mask position with numpy : 0.014110803604125977 nb_pixel_total : 576 time to create 1 rle with old method : 0.0006415843963623047 time for calcul the mask position with numpy : 0.009261369705200195 nb_pixel_total : 349 time to create 1 rle with old method : 0.000453948974609375 time for calcul the mask position with numpy : 0.00901651382446289 nb_pixel_total : 6467 time to create 1 rle with old method : 0.006975412368774414 time for calcul the mask position with numpy : 0.00940084457397461 nb_pixel_total : 2461 time to create 1 rle with old method : 0.0027227401733398438 time for calcul the mask position with numpy : 0.009351730346679688 nb_pixel_total : 4494 time to create 1 rle with old method : 0.005034208297729492 time for calcul the mask position with numpy : 0.009216785430908203 nb_pixel_total : 228 time to create 1 rle with old method : 0.0004661083221435547 time for calcul the mask position with numpy : 0.01059579849243164 nb_pixel_total : 687 time to create 1 rle with old method : 0.0008075237274169922 time for calcul the mask position with numpy : 0.00975346565246582 nb_pixel_total : 3307 time to create 1 rle with old method : 0.003667593002319336 time for calcul the mask position with numpy : 0.009282827377319336 nb_pixel_total : 1014 time to create 1 rle with old method : 0.001168966293334961 time for calcul the mask position with numpy : 0.011262893676757812 nb_pixel_total : 2068 time to create 1 rle with old method : 0.002283334732055664 time for calcul the mask position with numpy : 0.009799480438232422 nb_pixel_total : 474 time to create 1 rle with old method : 0.0005784034729003906 time for calcul the mask position with numpy : 0.010182619094848633 nb_pixel_total : 1518 time to create 1 rle with old method : 0.0017056465148925781 time for calcul the mask position with numpy : 0.009736061096191406 nb_pixel_total : 5264 time to create 1 rle with old method : 0.005672454833984375 time for calcul the mask position with numpy : 0.00934290885925293 nb_pixel_total : 596 time to create 1 rle with old method : 0.0007109642028808594 time for calcul the mask position with numpy : 0.009862422943115234 nb_pixel_total : 1293 time to create 1 rle with old method : 0.0014281272888183594 time for calcul the mask position with numpy : 0.009679317474365234 nb_pixel_total : 555 time to create 1 rle with old method : 0.0006623268127441406 time for calcul the mask position with numpy : 0.009798765182495117 nb_pixel_total : 90 time to create 1 rle with old method : 0.00011658668518066406 time for calcul the mask position with numpy : 0.009680509567260742 nb_pixel_total : 5257 time to create 1 rle with old method : 0.005698204040527344 time for calcul the mask position with numpy : 0.009772777557373047 nb_pixel_total : 628 time to create 1 rle with old method : 0.0007646083831787109 time for calcul the mask position with numpy : 0.00937795639038086 nb_pixel_total : 3525 time to create 1 rle with old method : 0.003849029541015625 time for calcul the mask position with numpy : 0.0091552734375 nb_pixel_total : 169 time to create 1 rle with old method : 0.000194549560546875 time for calcul the mask position with numpy : 0.009493112564086914 nb_pixel_total : 110 time to create 1 rle with old method : 0.0001690387725830078 time for calcul the mask position with numpy : 0.008498430252075195 nb_pixel_total : 9251 time to create 1 rle with old method : 0.009914875030517578 time for calcul the mask position with numpy : 0.009518861770629883 nb_pixel_total : 7101 time to create 1 rle with old method : 0.00746917724609375 time for calcul the mask position with numpy : 0.008722066879272461 nb_pixel_total : 1197 time to create 1 rle with old method : 0.0012373924255371094 time for calcul the mask position with numpy : 0.008237123489379883 nb_pixel_total : 132 time to create 1 rle with old method : 0.0003123283386230469 time for calcul the mask position with numpy : 0.008984804153442383 nb_pixel_total : 168 time to create 1 rle with old method : 0.00020813941955566406 time for calcul the mask position with numpy : 0.009539365768432617 nb_pixel_total : 132 time to create 1 rle with old method : 0.00015997886657714844 time for calcul the mask position with numpy : 0.013481378555297852 nb_pixel_total : 469 time to create 1 rle with old method : 0.0005741119384765625 time for calcul the mask position with numpy : 0.009353399276733398 nb_pixel_total : 300 time to create 1 rle with old method : 0.00034737586975097656 time for calcul the mask position with numpy : 0.007838964462280273 nb_pixel_total : 784 time to create 1 rle with old method : 0.0008435249328613281 time for calcul the mask position with numpy : 0.009342670440673828 nb_pixel_total : 835 time to create 1 rle with old method : 0.0009241104125976562 time for calcul the mask position with numpy : 0.009147405624389648 nb_pixel_total : 1875 time to create 1 rle with old method : 0.0020148754119873047 time for calcul the mask position with numpy : 0.00905919075012207 nb_pixel_total : 596 time to create 1 rle with old method : 0.0007686614990234375 time for calcul the mask position with numpy : 0.009499311447143555 nb_pixel_total : 2313 time to create 1 rle with old method : 0.0026018619537353516 time for calcul the mask position with numpy : 0.00960683822631836 nb_pixel_total : 298 time to create 1 rle with old method : 0.0003566741943359375 time for calcul the mask position with numpy : 0.00988316535949707 nb_pixel_total : 118 time to create 1 rle with old method : 0.00015211105346679688 time for calcul the mask position with numpy : 0.009603738784790039 nb_pixel_total : 29 time to create 1 rle with old method : 5.745887756347656e-05 time for calcul the mask position with numpy : 0.00980377197265625 nb_pixel_total : 516 time to create 1 rle with old method : 0.0005884170532226562 time for calcul the mask position with numpy : 0.011197090148925781 nb_pixel_total : 148 time to create 1 rle with old method : 0.00020384788513183594 time for calcul the mask position with numpy : 0.009406089782714844 nb_pixel_total : 153 time to create 1 rle with old method : 0.0001761913299560547 time for calcul the mask position with numpy : 0.009351730346679688 nb_pixel_total : 619 time to create 1 rle with old method : 0.0006546974182128906 time for calcul the mask position with numpy : 0.009467840194702148 nb_pixel_total : 348 time to create 1 rle with old method : 0.0003802776336669922 time for calcul the mask position with numpy : 0.009313344955444336 nb_pixel_total : 2608 time to create 1 rle with old method : 0.002761363983154297 time for calcul the mask position with numpy : 0.009484529495239258 nb_pixel_total : 330 time to create 1 rle with old method : 0.0003879070281982422 time for calcul the mask position with numpy : 0.008618831634521484 nb_pixel_total : 704 time to create 1 rle with old method : 0.0007693767547607422 time for calcul the mask position with numpy : 0.006375789642333984 nb_pixel_total : 791 time to create 1 rle with old method : 0.0008997917175292969 time for calcul the mask position with numpy : 0.0060498714447021484 nb_pixel_total : 847 time to create 1 rle with old method : 0.0009167194366455078 time for calcul the mask position with numpy : 0.0059680938720703125 nb_pixel_total : 1024 time to create 1 rle with old method : 0.001074075698852539 time for calcul the mask position with numpy : 0.009731531143188477 nb_pixel_total : 532 time to create 1 rle with old method : 0.0006699562072753906 time for calcul the mask position with numpy : 0.009540557861328125 nb_pixel_total : 1806 time to create 1 rle with old method : 0.0018596649169921875 time for calcul the mask position with numpy : 0.009722232818603516 nb_pixel_total : 453 time to create 1 rle with old method : 0.00047850608825683594 time for calcul the mask position with numpy : 0.009974002838134766 nb_pixel_total : 181 time to create 1 rle with old method : 0.00023221969604492188 time for calcul the mask position with numpy : 0.009930133819580078 nb_pixel_total : 321 time to create 1 rle with old method : 0.0003707408905029297 time for calcul the mask position with numpy : 0.009820938110351562 nb_pixel_total : 2449 time to create 1 rle with old method : 0.002765655517578125 time for calcul the mask position with numpy : 0.009480476379394531 nb_pixel_total : 347 time to create 1 rle with old method : 0.00039315223693847656 time for calcul the mask position with numpy : 0.009169340133666992 nb_pixel_total : 3783 time to create 1 rle with old method : 0.004133701324462891 time for calcul the mask position with numpy : 0.009279489517211914 nb_pixel_total : 1034 time to create 1 rle with old method : 0.0011277198791503906 time for calcul the mask position with numpy : 0.009336233139038086 nb_pixel_total : 218 time to create 1 rle with old method : 0.0002579689025878906 time for calcul the mask position with numpy : 0.009414196014404297 nb_pixel_total : 106 time to create 1 rle with old method : 0.00013017654418945312 time for calcul the mask position with numpy : 0.009271621704101562 nb_pixel_total : 1399 time to create 1 rle with old method : 0.0015683174133300781 time for calcul the mask position with numpy : 0.008956670761108398 nb_pixel_total : 40 time to create 1 rle with old method : 7.343292236328125e-05 time for calcul the mask position with numpy : 0.00597691535949707 nb_pixel_total : 78 time to create 1 rle with old method : 0.00011396408081054688 time for calcul the mask position with numpy : 0.005825042724609375 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003077983856201172 time for calcul the mask position with numpy : 0.0058748722076416016 nb_pixel_total : 39 time to create 1 rle with old method : 7.319450378417969e-05 time for calcul the mask position with numpy : 0.006075382232666016 nb_pixel_total : 627 time to create 1 rle with old method : 0.0007321834564208984 time for calcul the mask position with numpy : 0.005989551544189453 nb_pixel_total : 250 time to create 1 rle with old method : 0.00032258033752441406 time for calcul the mask position with numpy : 0.006555795669555664 nb_pixel_total : 150 time to create 1 rle with old method : 0.00020122528076171875 time for calcul the mask position with numpy : 0.0071599483489990234 nb_pixel_total : 104707 time to create 1 rle with old method : 0.12036752700805664 time for calcul the mask position with numpy : 0.0065250396728515625 nb_pixel_total : 103 time to create 1 rle with old method : 0.0001513957977294922 time for calcul the mask position with numpy : 0.0068318843841552734 nb_pixel_total : 127 time to create 1 rle with old method : 0.00016617774963378906 time for calcul the mask position with numpy : 0.007064342498779297 nb_pixel_total : 59 time to create 1 rle with old method : 9.131431579589844e-05 time for calcul the mask position with numpy : 0.006647586822509766 nb_pixel_total : 508 time to create 1 rle with old method : 0.0005941390991210938 time for calcul the mask position with numpy : 0.006915569305419922 nb_pixel_total : 514 time to create 1 rle with old method : 0.0008726119995117188 time for calcul the mask position with numpy : 0.007032155990600586 nb_pixel_total : 496 time to create 1 rle with old method : 0.000843048095703125 time for calcul the mask position with numpy : 0.007144927978515625 nb_pixel_total : 388 time to create 1 rle with old method : 0.0006690025329589844 time for calcul the mask position with numpy : 0.006792306900024414 nb_pixel_total : 110 time to create 1 rle with old method : 0.0001995563507080078 time for calcul the mask position with numpy : 0.006559133529663086 nb_pixel_total : 1734 time to create 1 rle with old method : 0.0028672218322753906 time for calcul the mask position with numpy : 0.0066738128662109375 nb_pixel_total : 728 time to create 1 rle with old method : 0.0012810230255126953 time for calcul the mask position with numpy : 0.006479024887084961 nb_pixel_total : 219 time to create 1 rle with old method : 0.0003845691680908203 time for calcul the mask position with numpy : 0.006550788879394531 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003962516784667969 time for calcul the mask position with numpy : 0.0064754486083984375 nb_pixel_total : 3 time to create 1 rle with old method : 3.886222839355469e-05 time for calcul the mask position with numpy : 0.006601095199584961 nb_pixel_total : 215 time to create 1 rle with old method : 0.0003650188446044922 time for calcul the mask position with numpy : 0.006219387054443359 nb_pixel_total : 136 time to create 1 rle with old method : 0.00018072128295898438 time for calcul the mask position with numpy : 0.00618290901184082 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003094673156738281 time for calcul the mask position with numpy : 0.009349584579467773 nb_pixel_total : 2946 time to create 1 rle with old method : 0.0031235218048095703 time for calcul the mask position with numpy : 0.006036043167114258 nb_pixel_total : 604 time to create 1 rle with old method : 0.0007157325744628906 time for calcul the mask position with numpy : 0.005982160568237305 nb_pixel_total : 109 time to create 1 rle with old method : 0.00014781951904296875 time for calcul the mask position with numpy : 0.0060710906982421875 nb_pixel_total : 91 time to create 1 rle with old method : 0.00012183189392089844 time for calcul the mask position with numpy : 0.007243156433105469 nb_pixel_total : 99 time to create 1 rle with old method : 0.00016021728515625 time for calcul the mask position with numpy : 0.007384300231933594 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002949237823486328 time for calcul the mask position with numpy : 0.006444692611694336 nb_pixel_total : 110 time to create 1 rle with old method : 0.00014901161193847656 time for calcul the mask position with numpy : 0.006251811981201172 nb_pixel_total : 643 time to create 1 rle with old method : 0.0007600784301757812 time for calcul the mask position with numpy : 0.006152153015136719 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001418590545654297 time for calcul the mask position with numpy : 0.006070375442504883 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0017485618591308594 time for calcul the mask position with numpy : 0.0062253475189208984 nb_pixel_total : 55 time to create 1 rle with old method : 8.58306884765625e-05 time for calcul the mask position with numpy : 0.006089687347412109 nb_pixel_total : 828 time to create 1 rle with old method : 0.0009474754333496094 time for calcul the mask position with numpy : 0.0066149234771728516 nb_pixel_total : 144 time to create 1 rle with old method : 0.00019240379333496094 time for calcul the mask position with numpy : 0.006173849105834961 nb_pixel_total : 481 time to create 1 rle with old method : 0.0005693435668945312 time for calcul the mask position with numpy : 0.006609201431274414 nb_pixel_total : 102 time to create 1 rle with old method : 0.00013756752014160156 time for calcul the mask position with numpy : 0.006465911865234375 nb_pixel_total : 3423 time to create 1 rle with old method : 0.0039331912994384766 time for calcul the mask position with numpy : 0.006371974945068359 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002224445343017578 time for calcul the mask position with numpy : 0.006417512893676758 nb_pixel_total : 368 time to create 1 rle with old method : 0.0004360675811767578 time for calcul the mask position with numpy : 0.006549358367919922 nb_pixel_total : 74 time to create 1 rle with old method : 0.00015091896057128906 time for calcul the mask position with numpy : 0.006598472595214844 nb_pixel_total : 460 time to create 1 rle with old method : 0.0005376338958740234 time for calcul the mask position with numpy : 0.00640869140625 nb_pixel_total : 938 time to create 1 rle with old method : 0.0011200904846191406 time for calcul the mask position with numpy : 0.0065457820892333984 nb_pixel_total : 841 time to create 1 rle with old method : 0.0009779930114746094 time for calcul the mask position with numpy : 0.006577491760253906 nb_pixel_total : 312 time to create 1 rle with old method : 0.0003802776336669922 time for calcul the mask position with numpy : 0.0063245296478271484 nb_pixel_total : 321 time to create 1 rle with old method : 0.0003802776336669922 time for calcul the mask position with numpy : 0.006582021713256836 nb_pixel_total : 1369 time to create 1 rle with old method : 0.0015828609466552734 time for calcul the mask position with numpy : 0.006570577621459961 nb_pixel_total : 566 time to create 1 rle with old method : 0.0006947517395019531 time for calcul the mask position with numpy : 0.00675654411315918 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004131793975830078 time for calcul the mask position with numpy : 0.0068817138671875 nb_pixel_total : 2680 time to create 1 rle with old method : 0.0030336380004882812 time for calcul the mask position with numpy : 0.010237932205200195 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005359649658203125 time for calcul the mask position with numpy : 0.006566762924194336 nb_pixel_total : 12 time to create 1 rle with old method : 4.649162292480469e-05 time for calcul the mask position with numpy : 0.006211280822753906 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002467632293701172 time for calcul the mask position with numpy : 0.006222724914550781 nb_pixel_total : 241 time to create 1 rle with old method : 0.00030803680419921875 time for calcul the mask position with numpy : 0.006277561187744141 nb_pixel_total : 597 time to create 1 rle with old method : 0.0007026195526123047 time for calcul the mask position with numpy : 0.008473873138427734 nb_pixel_total : 745 time to create 1 rle with old method : 0.0008764266967773438 time for calcul the mask position with numpy : 0.00844264030456543 nb_pixel_total : 413 time to create 1 rle with old method : 0.0004975795745849609 create new chi : 1.7430000305175781 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 : 0.002138853073120117 batch 1 Loaded 133 chid ids of type : 4230 Number RLEs to save : 12323 TO DO : save crop sub photo not yet done ! save time : 0.7010688781738281 nb_obj : 127 nb_hashtags : 7 time to prepare the origin masks : 1.9414088726043701 time for calcul the mask position with numpy : 0.02888321876525879 nb_pixel_total : 1824282 time to create 1 rle with new method : 0.08161783218383789 time for calcul the mask position with numpy : 0.010820388793945312 nb_pixel_total : 502 time to create 1 rle with old method : 0.0006005764007568359 time for calcul the mask position with numpy : 0.01062774658203125 nb_pixel_total : 843 time to create 1 rle with old method : 0.0009751319885253906 time for calcul the mask position with numpy : 0.006653547286987305 nb_pixel_total : 36 time to create 1 rle with old method : 8.440017700195312e-05 time for calcul the mask position with numpy : 0.00663304328918457 nb_pixel_total : 86 time to create 1 rle with old method : 0.00013589859008789062 time for calcul the mask position with numpy : 0.006386995315551758 nb_pixel_total : 884 time to create 1 rle with old method : 0.0010159015655517578 time for calcul the mask position with numpy : 0.010639429092407227 nb_pixel_total : 2387 time to create 1 rle with old method : 0.0027475357055664062 time for calcul the mask position with numpy : 0.014127492904663086 nb_pixel_total : 1465 time to create 1 rle with old method : 0.0017750263214111328 time for calcul the mask position with numpy : 0.011046171188354492 nb_pixel_total : 772 time to create 1 rle with old method : 0.0010983943939208984 time for calcul the mask position with numpy : 0.010066986083984375 nb_pixel_total : 620 time to create 1 rle with old method : 0.0007505416870117188 time for calcul the mask position with numpy : 0.011987924575805664 nb_pixel_total : 434 time to create 1 rle with old method : 0.0005435943603515625 time for calcul the mask position with numpy : 0.010924816131591797 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003032684326171875 time for calcul the mask position with numpy : 0.010405540466308594 nb_pixel_total : 19 time to create 1 rle with old method : 5.841255187988281e-05 time for calcul the mask position with numpy : 0.010655879974365234 nb_pixel_total : 598 time to create 1 rle with old method : 0.0007314682006835938 time for calcul the mask position with numpy : 0.01061868667602539 nb_pixel_total : 2570 time to create 1 rle with old method : 0.002943277359008789 time for calcul the mask position with numpy : 0.010811567306518555 nb_pixel_total : 372 time to create 1 rle with old method : 0.00047707557678222656 time for calcul the mask position with numpy : 0.010721445083618164 nb_pixel_total : 5334 time to create 1 rle with old method : 0.006010293960571289 time for calcul the mask position with numpy : 0.01133871078491211 nb_pixel_total : 254 time to create 1 rle with old method : 0.00033092498779296875 time for calcul the mask position with numpy : 0.01036834716796875 nb_pixel_total : 10803 time to create 1 rle with old method : 0.01177668571472168 time for calcul the mask position with numpy : 0.005972385406494141 nb_pixel_total : 2859 time to create 1 rle with old method : 0.003131866455078125 time for calcul the mask position with numpy : 0.006018161773681641 nb_pixel_total : 548 time to create 1 rle with old method : 0.0006175041198730469 time for calcul the mask position with numpy : 0.00607609748840332 nb_pixel_total : 185 time to create 1 rle with old method : 0.00024819374084472656 time for calcul the mask position with numpy : 0.005966901779174805 nb_pixel_total : 1978 time to create 1 rle with old method : 0.00229644775390625 time for calcul the mask position with numpy : 0.006070852279663086 nb_pixel_total : 525 time to create 1 rle with old method : 0.0006573200225830078 time for calcul the mask position with numpy : 0.006083250045776367 nb_pixel_total : 1020 time to create 1 rle with old method : 0.0011799335479736328 time for calcul the mask position with numpy : 0.00960397720336914 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005981922149658203 time for calcul the mask position with numpy : 0.006017446517944336 nb_pixel_total : 1235 time to create 1 rle with old method : 0.0013842582702636719 time for calcul the mask position with numpy : 0.006159067153930664 nb_pixel_total : 5487 time to create 1 rle with old method : 0.006045818328857422 time for calcul the mask position with numpy : 0.006136894226074219 nb_pixel_total : 613 time to create 1 rle with old method : 0.0007255077362060547 time for calcul the mask position with numpy : 0.0061473846435546875 nb_pixel_total : 10683 time to create 1 rle with old method : 0.011933088302612305 time for calcul the mask position with numpy : 0.006194591522216797 nb_pixel_total : 232 time to create 1 rle with old method : 0.00028896331787109375 time for calcul the mask position with numpy : 0.006117343902587891 nb_pixel_total : 63 time to create 1 rle with old method : 9.489059448242188e-05 time for calcul the mask position with numpy : 0.0061604976654052734 nb_pixel_total : 1279 time to create 1 rle with old method : 0.001493692398071289 time for calcul the mask position with numpy : 0.006144285202026367 nb_pixel_total : 656 time to create 1 rle with old method : 0.0008041858673095703 time for calcul the mask position with numpy : 0.006352424621582031 nb_pixel_total : 5722 time to create 1 rle with old method : 0.006486415863037109 time for calcul the mask position with numpy : 0.006699323654174805 nb_pixel_total : 908 time to create 1 rle with old method : 0.0012631416320800781 time for calcul the mask position with numpy : 0.006642341613769531 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006308555603027344 time for calcul the mask position with numpy : 0.0073397159576416016 nb_pixel_total : 3828 time to create 1 rle with old method : 0.0066030025482177734 time for calcul the mask position with numpy : 0.007334232330322266 nb_pixel_total : 1173 time to create 1 rle with old method : 0.0013344287872314453 time for calcul the mask position with numpy : 0.006630897521972656 nb_pixel_total : 8883 time to create 1 rle with old method : 0.010891437530517578 time for calcul the mask position with numpy : 0.006824016571044922 nb_pixel_total : 316 time to create 1 rle with old method : 0.00038313865661621094 time for calcul the mask position with numpy : 0.006528139114379883 nb_pixel_total : 956 time to create 1 rle with old method : 0.0013663768768310547 time for calcul the mask position with numpy : 0.006787776947021484 nb_pixel_total : 1009 time to create 1 rle with old method : 0.001245737075805664 time for calcul the mask position with numpy : 0.006417512893676758 nb_pixel_total : 130 time to create 1 rle with old method : 0.0001800060272216797 time for calcul the mask position with numpy : 0.0066530704498291016 nb_pixel_total : 3 time to create 1 rle with old method : 2.47955322265625e-05 time for calcul the mask position with numpy : 0.008774518966674805 nb_pixel_total : 329 time to create 1 rle with old method : 0.0004589557647705078 time for calcul the mask position with numpy : 0.006944417953491211 nb_pixel_total : 1369 time to create 1 rle with old method : 0.002286672592163086 time for calcul the mask position with numpy : 0.011008024215698242 nb_pixel_total : 500 time to create 1 rle with old method : 0.0009279251098632812 time for calcul the mask position with numpy : 0.0070343017578125 nb_pixel_total : 477 time to create 1 rle with old method : 0.0008845329284667969 time for calcul the mask position with numpy : 0.006844282150268555 nb_pixel_total : 381 time to create 1 rle with old method : 0.0006823539733886719 time for calcul the mask position with numpy : 0.006700992584228516 nb_pixel_total : 779 time to create 1 rle with old method : 0.0013422966003417969 time for calcul the mask position with numpy : 0.006871938705444336 nb_pixel_total : 2262 time to create 1 rle with old method : 0.003798961639404297 time for calcul the mask position with numpy : 0.006838798522949219 nb_pixel_total : 365 time to create 1 rle with old method : 0.0007157325744628906 time for calcul the mask position with numpy : 0.0067675113677978516 nb_pixel_total : 132 time to create 1 rle with old method : 0.0002484321594238281 time for calcul the mask position with numpy : 0.007269382476806641 nb_pixel_total : 79 time to create 1 rle with old method : 0.00016570091247558594 time for calcul the mask position with numpy : 0.006939411163330078 nb_pixel_total : 363 time to create 1 rle with old method : 0.0006442070007324219 time for calcul the mask position with numpy : 0.012121200561523438 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006232261657714844 time for calcul the mask position with numpy : 0.011812210083007812 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002415180206298828 time for calcul the mask position with numpy : 0.01040506362915039 nb_pixel_total : 652 time to create 1 rle with old method : 0.0007638931274414062 time for calcul the mask position with numpy : 0.01042795181274414 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004131793975830078 time for calcul the mask position with numpy : 0.010675668716430664 nb_pixel_total : 270 time to create 1 rle with old method : 0.00033974647521972656 time for calcul the mask position with numpy : 0.010921955108642578 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004398822784423828 time for calcul the mask position with numpy : 0.010596275329589844 nb_pixel_total : 828 time to create 1 rle with old method : 0.0009500980377197266 time for calcul the mask position with numpy : 0.0102081298828125 nb_pixel_total : 682 time to create 1 rle with old method : 0.0009417533874511719 time for calcul the mask position with numpy : 0.0188601016998291 nb_pixel_total : 563 time to create 1 rle with old method : 0.001070261001586914 time for calcul the mask position with numpy : 0.016543149948120117 nb_pixel_total : 1781 time to create 1 rle with old method : 0.002446413040161133 time for calcul the mask position with numpy : 0.014444351196289062 nb_pixel_total : 68 time to create 1 rle with old method : 0.00013017654418945312 time for calcul the mask position with numpy : 0.011746406555175781 nb_pixel_total : 440 time to create 1 rle with old method : 0.0008442401885986328 time for calcul the mask position with numpy : 0.012404203414916992 nb_pixel_total : 121 time to create 1 rle with old method : 0.0001881122589111328 time for calcul the mask position with numpy : 0.010657548904418945 nb_pixel_total : 157 time to create 1 rle with old method : 0.00021338462829589844 time for calcul the mask position with numpy : 0.01167440414428711 nb_pixel_total : 336 time to create 1 rle with old method : 0.00040650367736816406 time for calcul the mask position with numpy : 0.010069131851196289 nb_pixel_total : 7311 time to create 1 rle with old method : 0.008073091506958008 time for calcul the mask position with numpy : 0.009970903396606445 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003418922424316406 time for calcul the mask position with numpy : 0.010518312454223633 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001544952392578125 time for calcul the mask position with numpy : 0.009980201721191406 nb_pixel_total : 1539 time to create 1 rle with old method : 0.0018191337585449219 time for calcul the mask position with numpy : 0.010992288589477539 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002543926239013672 time for calcul the mask position with numpy : 0.011126518249511719 nb_pixel_total : 92 time to create 1 rle with old method : 0.00013828277587890625 time for calcul the mask position with numpy : 0.01137852668762207 nb_pixel_total : 1517 time to create 1 rle with old method : 0.0017347335815429688 time for calcul the mask position with numpy : 0.011015176773071289 nb_pixel_total : 27 time to create 1 rle with old method : 5.745887756347656e-05 time for calcul the mask position with numpy : 0.01133418083190918 nb_pixel_total : 57 time to create 1 rle with old method : 8.296966552734375e-05 time for calcul the mask position with numpy : 0.010529756546020508 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002455711364746094 time for calcul the mask position with numpy : 0.011279582977294922 nb_pixel_total : 335 time to create 1 rle with old method : 0.000453948974609375 time for calcul the mask position with numpy : 0.011061906814575195 nb_pixel_total : 182 time to create 1 rle with old method : 0.00023937225341796875 time for calcul the mask position with numpy : 0.014732837677001953 nb_pixel_total : 127 time to create 1 rle with old method : 0.0001990795135498047 time for calcul the mask position with numpy : 0.0118560791015625 nb_pixel_total : 104329 time to create 1 rle with old method : 0.13073492050170898 time for calcul the mask position with numpy : 0.01332712173461914 nb_pixel_total : 444 time to create 1 rle with old method : 0.0007653236389160156 time for calcul the mask position with numpy : 0.013223648071289062 nb_pixel_total : 146 time to create 1 rle with old method : 0.00028896331787109375 time for calcul the mask position with numpy : 0.012098073959350586 nb_pixel_total : 402 time to create 1 rle with old method : 0.0004963874816894531 time for calcul the mask position with numpy : 0.011259794235229492 nb_pixel_total : 87 time to create 1 rle with old method : 0.0001373291015625 time for calcul the mask position with numpy : 0.017024755477905273 nb_pixel_total : 192 time to create 1 rle with old method : 0.00042438507080078125 time for calcul the mask position with numpy : 0.011752843856811523 nb_pixel_total : 356 time to create 1 rle with old method : 0.0003974437713623047 time for calcul the mask position with numpy : 0.011133432388305664 nb_pixel_total : 125 time to create 1 rle with old method : 0.000171661376953125 time for calcul the mask position with numpy : 0.010647058486938477 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002453327178955078 time for calcul the mask position with numpy : 0.0104827880859375 nb_pixel_total : 2716 time to create 1 rle with old method : 0.002937793731689453 time for calcul the mask position with numpy : 0.011188507080078125 nb_pixel_total : 120 time to create 1 rle with old method : 0.0002512931823730469 time for calcul the mask position with numpy : 0.010146617889404297 nb_pixel_total : 385 time to create 1 rle with old method : 0.000476837158203125 time for calcul the mask position with numpy : 0.010986804962158203 nb_pixel_total : 624 time to create 1 rle with old method : 0.0011057853698730469 time for calcul the mask position with numpy : 0.010777950286865234 nb_pixel_total : 15324 time to create 1 rle with old method : 0.017039775848388672 time for calcul the mask position with numpy : 0.010082483291625977 nb_pixel_total : 51 time to create 1 rle with old method : 7.987022399902344e-05 time for calcul the mask position with numpy : 0.015424966812133789 nb_pixel_total : 1628 time to create 1 rle with old method : 0.003358125686645508 time for calcul the mask position with numpy : 0.010714530944824219 nb_pixel_total : 1028 time to create 1 rle with old method : 0.0011935234069824219 time for calcul the mask position with numpy : 0.010515928268432617 nb_pixel_total : 153 time to create 1 rle with old method : 0.00022029876708984375 time for calcul the mask position with numpy : 0.010138988494873047 nb_pixel_total : 123 time to create 1 rle with old method : 0.00017213821411132812 time for calcul the mask position with numpy : 0.010080575942993164 nb_pixel_total : 4 time to create 1 rle with old method : 3.528594970703125e-05 time for calcul the mask position with numpy : 0.010344743728637695 nb_pixel_total : 78 time to create 1 rle with old method : 0.0001125335693359375 time for calcul the mask position with numpy : 0.010206222534179688 nb_pixel_total : 340 time to create 1 rle with old method : 0.00039124488830566406 time for calcul the mask position with numpy : 0.010403633117675781 nb_pixel_total : 1347 time to create 1 rle with old method : 0.0015404224395751953 time for calcul the mask position with numpy : 0.010118484497070312 nb_pixel_total : 804 time to create 1 rle with old method : 0.0009448528289794922 time for calcul the mask position with numpy : 0.009995460510253906 nb_pixel_total : 583 time to create 1 rle with old method : 0.0006647109985351562 time for calcul the mask position with numpy : 0.010092020034790039 nb_pixel_total : 1748 time to create 1 rle with old method : 0.0020630359649658203 time for calcul the mask position with numpy : 0.010001182556152344 nb_pixel_total : 326 time to create 1 rle with old method : 0.0003974437713623047 time for calcul the mask position with numpy : 0.010158061981201172 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002467632293701172 time for calcul the mask position with numpy : 0.010205268859863281 nb_pixel_total : 384 time to create 1 rle with old method : 0.0004432201385498047 time for calcul the mask position with numpy : 0.01012110710144043 nb_pixel_total : 2696 time to create 1 rle with old method : 0.0030798912048339844 time for calcul the mask position with numpy : 0.011561870574951172 nb_pixel_total : 768 time to create 1 rle with old method : 0.0009088516235351562 time for calcul the mask position with numpy : 0.010390281677246094 nb_pixel_total : 2580 time to create 1 rle with old method : 0.0029060840606689453 time for calcul the mask position with numpy : 0.012783288955688477 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002593994140625 time for calcul the mask position with numpy : 0.010132551193237305 nb_pixel_total : 63 time to create 1 rle with old method : 0.00011801719665527344 time for calcul the mask position with numpy : 0.010097265243530273 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005280971527099609 time for calcul the mask position with numpy : 0.010103225708007812 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002760887145996094 time for calcul the mask position with numpy : 0.01148080825805664 nb_pixel_total : 348 time to create 1 rle with old method : 0.0003998279571533203 time for calcul the mask position with numpy : 0.010126829147338867 nb_pixel_total : 243 time to create 1 rle with old method : 0.0002913475036621094 time for calcul the mask position with numpy : 0.010184526443481445 nb_pixel_total : 314 time to create 1 rle with old method : 0.00038552284240722656 time for calcul the mask position with numpy : 0.010020971298217773 nb_pixel_total : 358 time to create 1 rle with old method : 0.000431060791015625 time for calcul the mask position with numpy : 0.010187864303588867 nb_pixel_total : 189 time to create 1 rle with old method : 0.00023984909057617188 time for calcul the mask position with numpy : 0.010112762451171875 nb_pixel_total : 257 time to create 1 rle with old method : 0.00031948089599609375 time for calcul the mask position with numpy : 0.010123491287231445 nb_pixel_total : 522 time to create 1 rle with old method : 0.0006186962127685547 time for calcul the mask position with numpy : 0.01010894775390625 nb_pixel_total : 136 time to create 1 rle with old method : 0.00021219253540039062 create new chi : 1.6690311431884766 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 : 0.003169536590576172 batch 1 Loaded 128 chid ids of type : 4230 Number RLEs to save : 11422 TO DO : save crop sub photo not yet done ! save time : 0.672095537185669 nb_obj : 121 nb_hashtags : 6 time to prepare the origin masks : 1.7727859020233154 time for calcul the mask position with numpy : 0.025620698928833008 nb_pixel_total : 1786210 time to create 1 rle with new method : 0.048201799392700195 time for calcul the mask position with numpy : 0.010738611221313477 nb_pixel_total : 125 time to create 1 rle with old method : 0.0001933574676513672 time for calcul the mask position with numpy : 0.00913548469543457 nb_pixel_total : 6159 time to create 1 rle with old method : 0.006827831268310547 time for calcul the mask position with numpy : 0.01035928726196289 nb_pixel_total : 68698 time to create 1 rle with old method : 0.07740926742553711 time for calcul the mask position with numpy : 0.006422519683837891 nb_pixel_total : 203 time to create 1 rle with old method : 0.00028705596923828125 time for calcul the mask position with numpy : 0.006272077560424805 nb_pixel_total : 542 time to create 1 rle with old method : 0.000614166259765625 time for calcul the mask position with numpy : 0.007862567901611328 nb_pixel_total : 880 time to create 1 rle with old method : 0.001009225845336914 time for calcul the mask position with numpy : 0.00613713264465332 nb_pixel_total : 48 time to create 1 rle with old method : 0.00010013580322265625 time for calcul the mask position with numpy : 0.006170749664306641 nb_pixel_total : 4 time to create 1 rle with old method : 3.457069396972656e-05 time for calcul the mask position with numpy : 0.006288766860961914 nb_pixel_total : 929 time to create 1 rle with old method : 0.0010464191436767578 time for calcul the mask position with numpy : 0.009775161743164062 nb_pixel_total : 227 time to create 1 rle with old method : 0.00027632713317871094 time for calcul the mask position with numpy : 0.006265401840209961 nb_pixel_total : 2759 time to create 1 rle with old method : 0.003106832504272461 time for calcul the mask position with numpy : 0.006342649459838867 nb_pixel_total : 35 time to create 1 rle with old method : 0.00013899803161621094 time for calcul the mask position with numpy : 0.006264448165893555 nb_pixel_total : 1035 time to create 1 rle with old method : 0.0012581348419189453 time for calcul the mask position with numpy : 0.006364345550537109 nb_pixel_total : 490 time to create 1 rle with old method : 0.0005898475646972656 time for calcul the mask position with numpy : 0.006467103958129883 nb_pixel_total : 408 time to create 1 rle with old method : 0.0004744529724121094 time for calcul the mask position with numpy : 0.00629425048828125 nb_pixel_total : 5752 time to create 1 rle with old method : 0.00710749626159668 time for calcul the mask position with numpy : 0.006410360336303711 nb_pixel_total : 1385 time to create 1 rle with old method : 0.001676797866821289 time for calcul the mask position with numpy : 0.006739139556884766 nb_pixel_total : 913 time to create 1 rle with old method : 0.0010650157928466797 time for calcul the mask position with numpy : 0.006922245025634766 nb_pixel_total : 3776 time to create 1 rle with old method : 0.006114006042480469 time for calcul the mask position with numpy : 0.006211519241333008 nb_pixel_total : 367 time to create 1 rle with old method : 0.000560760498046875 time for calcul the mask position with numpy : 0.00651097297668457 nb_pixel_total : 1643 time to create 1 rle with old method : 0.0019817352294921875 time for calcul the mask position with numpy : 0.006943941116333008 nb_pixel_total : 317 time to create 1 rle with old method : 0.0006356239318847656 time for calcul the mask position with numpy : 0.007002353668212891 nb_pixel_total : 2100 time to create 1 rle with old method : 0.002447366714477539 time for calcul the mask position with numpy : 0.006310701370239258 nb_pixel_total : 553 time to create 1 rle with old method : 0.0006728172302246094 time for calcul the mask position with numpy : 0.006165027618408203 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006220340728759766 time for calcul the mask position with numpy : 0.00665593147277832 nb_pixel_total : 1516 time to create 1 rle with old method : 0.0018718242645263672 time for calcul the mask position with numpy : 0.006520748138427734 nb_pixel_total : 118 time to create 1 rle with old method : 0.0003352165222167969 time for calcul the mask position with numpy : 0.0066263675689697266 nb_pixel_total : 8318 time to create 1 rle with old method : 0.009427547454833984 time for calcul the mask position with numpy : 0.0066912174224853516 nb_pixel_total : 596 time to create 1 rle with old method : 0.0007078647613525391 time for calcul the mask position with numpy : 0.006479978561401367 nb_pixel_total : 184 time to create 1 rle with old method : 0.00026345252990722656 time for calcul the mask position with numpy : 0.0064923763275146484 nb_pixel_total : 1264 time to create 1 rle with old method : 0.0014982223510742188 time for calcul the mask position with numpy : 0.006711006164550781 nb_pixel_total : 335 time to create 1 rle with old method : 0.00043702125549316406 time for calcul the mask position with numpy : 0.006594419479370117 nb_pixel_total : 209 time to create 1 rle with old method : 0.0003933906555175781 time for calcul the mask position with numpy : 0.006487131118774414 nb_pixel_total : 5585 time to create 1 rle with old method : 0.006284236907958984 time for calcul the mask position with numpy : 0.0068569183349609375 nb_pixel_total : 3336 time to create 1 rle with old method : 0.003758668899536133 time for calcul the mask position with numpy : 0.006312370300292969 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002334117889404297 time for calcul the mask position with numpy : 0.006242990493774414 nb_pixel_total : 1135 time to create 1 rle with old method : 0.001264333724975586 time for calcul the mask position with numpy : 0.006094932556152344 nb_pixel_total : 202 time to create 1 rle with old method : 0.00024700164794921875 time for calcul the mask position with numpy : 0.006072998046875 nb_pixel_total : 1724 time to create 1 rle with old method : 0.0019652843475341797 time for calcul the mask position with numpy : 0.006349086761474609 nb_pixel_total : 15049 time to create 1 rle with old method : 0.017667770385742188 time for calcul the mask position with numpy : 0.006107807159423828 nb_pixel_total : 206 time to create 1 rle with old method : 0.00025582313537597656 time for calcul the mask position with numpy : 0.005894184112548828 nb_pixel_total : 303 time to create 1 rle with old method : 0.000370025634765625 time for calcul the mask position with numpy : 0.00628209114074707 nb_pixel_total : 471 time to create 1 rle with old method : 0.0005359649658203125 time for calcul the mask position with numpy : 0.006377220153808594 nb_pixel_total : 763 time to create 1 rle with old method : 0.0008909702301025391 time for calcul the mask position with numpy : 0.0064852237701416016 nb_pixel_total : 1604 time to create 1 rle with old method : 0.0018661022186279297 time for calcul the mask position with numpy : 0.006404876708984375 nb_pixel_total : 450 time to create 1 rle with old method : 0.0005331039428710938 time for calcul the mask position with numpy : 0.006305694580078125 nb_pixel_total : 293 time to create 1 rle with old method : 0.0006563663482666016 time for calcul the mask position with numpy : 0.006811857223510742 nb_pixel_total : 159 time to create 1 rle with old method : 0.00021767616271972656 time for calcul the mask position with numpy : 0.0070896148681640625 nb_pixel_total : 2166 time to create 1 rle with old method : 0.002457141876220703 time for calcul the mask position with numpy : 0.00676274299621582 nb_pixel_total : 131 time to create 1 rle with old method : 0.00017762184143066406 time for calcul the mask position with numpy : 0.006333351135253906 nb_pixel_total : 568 time to create 1 rle with old method : 0.0006999969482421875 time for calcul the mask position with numpy : 0.006213188171386719 nb_pixel_total : 506 time to create 1 rle with old method : 0.0005941390991210938 time for calcul the mask position with numpy : 0.005944252014160156 nb_pixel_total : 476 time to create 1 rle with old method : 0.0005507469177246094 time for calcul the mask position with numpy : 0.005882740020751953 nb_pixel_total : 865 time to create 1 rle with old method : 0.0009984970092773438 time for calcul the mask position with numpy : 0.00606226921081543 nb_pixel_total : 676 time to create 1 rle with old method : 0.0007805824279785156 time for calcul the mask position with numpy : 0.010560274124145508 nb_pixel_total : 705 time to create 1 rle with old method : 0.0008068084716796875 time for calcul the mask position with numpy : 0.009865999221801758 nb_pixel_total : 344 time to create 1 rle with old method : 0.00041413307189941406 time for calcul the mask position with numpy : 0.012987136840820312 nb_pixel_total : 725 time to create 1 rle with old method : 0.0008573532104492188 time for calcul the mask position with numpy : 0.009758472442626953 nb_pixel_total : 602 time to create 1 rle with old method : 0.0006978511810302734 time for calcul the mask position with numpy : 0.00993204116821289 nb_pixel_total : 11 time to create 1 rle with old method : 4.1484832763671875e-05 time for calcul the mask position with numpy : 0.01015162467956543 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005013942718505859 time for calcul the mask position with numpy : 0.009615182876586914 nb_pixel_total : 826 time to create 1 rle with old method : 0.0009429454803466797 time for calcul the mask position with numpy : 0.009980201721191406 nb_pixel_total : 1005 time to create 1 rle with old method : 0.0011663436889648438 time for calcul the mask position with numpy : 0.010513544082641602 nb_pixel_total : 336 time to create 1 rle with old method : 0.00038433074951171875 time for calcul the mask position with numpy : 0.010451555252075195 nb_pixel_total : 528 time to create 1 rle with old method : 0.0006377696990966797 time for calcul the mask position with numpy : 0.010061264038085938 nb_pixel_total : 296 time to create 1 rle with old method : 0.000461578369140625 time for calcul the mask position with numpy : 0.010738849639892578 nb_pixel_total : 1793 time to create 1 rle with old method : 0.0020318031311035156 time for calcul the mask position with numpy : 0.010499954223632812 nb_pixel_total : 50 time to create 1 rle with old method : 9.107589721679688e-05 time for calcul the mask position with numpy : 0.010315418243408203 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005316734313964844 time for calcul the mask position with numpy : 0.010584115982055664 nb_pixel_total : 539 time to create 1 rle with old method : 0.0006442070007324219 time for calcul the mask position with numpy : 0.010689020156860352 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.010221481323242188 nb_pixel_total : 95 time to create 1 rle with old method : 0.00012445449829101562 time for calcul the mask position with numpy : 0.010092973709106445 nb_pixel_total : 1432 time to create 1 rle with old method : 0.0015597343444824219 time for calcul the mask position with numpy : 0.010067462921142578 nb_pixel_total : 79 time to create 1 rle with old method : 0.00013327598571777344 time for calcul the mask position with numpy : 0.010132074356079102 nb_pixel_total : 46 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.009768247604370117 nb_pixel_total : 210 time to create 1 rle with old method : 0.0002536773681640625 time for calcul the mask position with numpy : 0.010019779205322266 nb_pixel_total : 23 time to create 1 rle with old method : 5.507469177246094e-05 time for calcul the mask position with numpy : 0.010000467300415039 nb_pixel_total : 435 time to create 1 rle with old method : 0.0004911422729492188 time for calcul the mask position with numpy : 0.01007533073425293 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001423358917236328 time for calcul the mask position with numpy : 0.010810613632202148 nb_pixel_total : 105835 time to create 1 rle with old method : 0.12005996704101562 time for calcul the mask position with numpy : 0.009907960891723633 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002601146697998047 time for calcul the mask position with numpy : 0.009863615036010742 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002551078796386719 time for calcul the mask position with numpy : 0.00970458984375 nb_pixel_total : 485 time to create 1 rle with old method : 0.0005598068237304688 time for calcul the mask position with numpy : 0.009885072708129883 nb_pixel_total : 66 time to create 1 rle with old method : 9.274482727050781e-05 time for calcul the mask position with numpy : 0.014193534851074219 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001456737518310547 time for calcul the mask position with numpy : 0.011337995529174805 nb_pixel_total : 136 time to create 1 rle with old method : 0.00022411346435546875 time for calcul the mask position with numpy : 0.010802984237670898 nb_pixel_total : 214 time to create 1 rle with old method : 0.0002999305725097656 time for calcul the mask position with numpy : 0.010554075241088867 nb_pixel_total : 126 time to create 1 rle with old method : 0.00016808509826660156 time for calcul the mask position with numpy : 0.010830163955688477 nb_pixel_total : 652 time to create 1 rle with old method : 0.0007624626159667969 time for calcul the mask position with numpy : 0.010349035263061523 nb_pixel_total : 247 time to create 1 rle with old method : 0.00029850006103515625 time for calcul the mask position with numpy : 0.006833076477050781 nb_pixel_total : 50 time to create 1 rle with old method : 0.0001461505889892578 time for calcul the mask position with numpy : 0.006269216537475586 nb_pixel_total : 2935 time to create 1 rle with old method : 0.0031824111938476562 time for calcul the mask position with numpy : 0.006491899490356445 nb_pixel_total : 104 time to create 1 rle with old method : 0.0001347064971923828 time for calcul the mask position with numpy : 0.006293773651123047 nb_pixel_total : 122 time to create 1 rle with old method : 0.00015282630920410156 time for calcul the mask position with numpy : 0.006617307662963867 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002281665802001953 time for calcul the mask position with numpy : 0.006805896759033203 nb_pixel_total : 688 time to create 1 rle with old method : 0.0008223056793212891 time for calcul the mask position with numpy : 0.006841897964477539 nb_pixel_total : 1146 time to create 1 rle with old method : 0.0012898445129394531 time for calcul the mask position with numpy : 0.006441831588745117 nb_pixel_total : 785 time to create 1 rle with old method : 0.0009276866912841797 time for calcul the mask position with numpy : 0.006356239318847656 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005903244018554688 time for calcul the mask position with numpy : 0.006411552429199219 nb_pixel_total : 95 time to create 1 rle with old method : 0.00012731552124023438 time for calcul the mask position with numpy : 0.0057985782623291016 nb_pixel_total : 2009 time to create 1 rle with old method : 0.002205371856689453 time for calcul the mask position with numpy : 0.006066083908081055 nb_pixel_total : 1031 time to create 1 rle with old method : 0.0011539459228515625 time for calcul the mask position with numpy : 0.006284952163696289 nb_pixel_total : 218 time to create 1 rle with old method : 0.0002872943878173828 time for calcul the mask position with numpy : 0.006041288375854492 nb_pixel_total : 457 time to create 1 rle with old method : 0.0004930496215820312 time for calcul the mask position with numpy : 0.0064427852630615234 nb_pixel_total : 303 time to create 1 rle with old method : 0.00038123130798339844 time for calcul the mask position with numpy : 0.0063054561614990234 nb_pixel_total : 334 time to create 1 rle with old method : 0.00041961669921875 time for calcul the mask position with numpy : 0.006063938140869141 nb_pixel_total : 129 time to create 1 rle with old method : 0.00015997886657714844 time for calcul the mask position with numpy : 0.006083011627197266 nb_pixel_total : 15 time to create 1 rle with old method : 3.933906555175781e-05 time for calcul the mask position with numpy : 0.005884408950805664 nb_pixel_total : 802 time to create 1 rle with old method : 0.0009620189666748047 time for calcul the mask position with numpy : 0.006409645080566406 nb_pixel_total : 2772 time to create 1 rle with old method : 0.003129243850708008 time for calcul the mask position with numpy : 0.005866050720214844 nb_pixel_total : 204 time to create 1 rle with old method : 0.00025272369384765625 time for calcul the mask position with numpy : 0.005898714065551758 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006477832794189453 time for calcul the mask position with numpy : 0.006073951721191406 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004489421844482422 time for calcul the mask position with numpy : 0.0060482025146484375 nb_pixel_total : 435 time to create 1 rle with old method : 0.0005245208740234375 time for calcul the mask position with numpy : 0.006034135818481445 nb_pixel_total : 258 time to create 1 rle with old method : 0.00030303001403808594 time for calcul the mask position with numpy : 0.006036043167114258 nb_pixel_total : 821 time to create 1 rle with old method : 0.0009653568267822266 time for calcul the mask position with numpy : 0.006005525588989258 nb_pixel_total : 232 time to create 1 rle with old method : 0.0002884864807128906 time for calcul the mask position with numpy : 0.006080150604248047 nb_pixel_total : 206 time to create 1 rle with old method : 0.00024628639221191406 time for calcul the mask position with numpy : 0.006052494049072266 nb_pixel_total : 525 time to create 1 rle with old method : 0.0005574226379394531 time for calcul the mask position with numpy : 0.005807161331176758 nb_pixel_total : 397 time to create 1 rle with old method : 0.00043392181396484375 time for calcul the mask position with numpy : 0.005930662155151367 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002448558807373047 create new chi : 1.3365769386291504 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 : 0.0018329620361328125 batch 1 Loaded 122 chid ids of type : 4230 Number RLEs to save : 11218 TO DO : save crop sub photo not yet done ! save time : 0.6805582046508789 map_output_result : {1340194667: (0.0, 'Should be the crop_list due to order', 0.0), 1340194634: (0.0, 'Should be the crop_list due to order', 0.0), 1340194633: (0.0, 'Should be the crop_list due to order', 0.0), 1340194631: (0.0, 'Should be the crop_list due to order', 0.0), 1340194629: (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 [1340194667, 1340194634, 1340194633, 1340194631, 1340194629] Looping around the photos to save general results len do output : 5 /1340194667.Didn't retrieve data . /1340194634.Didn't retrieve data . /1340194633.Didn't retrieve data . /1340194631.Didn't retrieve data . /1340194629.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, '2624816') ('4234', '20937373', '1340194667', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194634', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194633', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194631', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194629', None, None, None, None, None, '2624816') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.018704652786254883 save_final save missing photos in datou_result : time spend for datou_step_exec : 21.371893644332886 time spend to save output : 0.019024133682250977 total time spend for step 4 : 21.390917778015137 step5:crop_condition Fri Feb 28 19:21:32 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 5 ! batch 1 Loaded 627 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 236 About to insert : list_path_to_insert length 236 new photo from crops ! About to upload 236 photos upload in portfolio : 4869462 init cache_photo without model_param we have 236 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740766895_2498347 we have uploaded 236 photos in the portfolio 4869462 time of upload the photos Elapsed time : 56.92750954627991 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 106 About to insert : list_path_to_insert length 106 new photo from crops ! About to upload 106 photos upload in portfolio : 4869462 init cache_photo without model_param we have 106 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740766954_2498347 we have uploaded 106 photos in the portfolio 4869462 time of upload the photos Elapsed time : 26.848207712173462 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 4869462 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740766981_2498347 we have uploaded 3 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9654459953308105 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 11 About to insert : list_path_to_insert length 11 new photo from crops ! About to upload 11 photos upload in portfolio : 4869462 init cache_photo without model_param we have 11 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740766982_2498347 we have uploaded 11 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.0724499225616455 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 80 About to insert : list_path_to_insert length 80 new photo from crops ! About to upload 80 photos upload in portfolio : 4869462 init cache_photo without model_param we have 80 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740766987_2498347 we have uploaded 80 photos in the portfolio 4869462 time of upload the photos Elapsed time : 25.193260669708252 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1340194667, 1340194634, 1340194633, 1340194631, 1340194629] Looping around the photos to save general results len do output : 436 /1340200089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200136Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200137Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200219Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200221Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200223Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200226Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200231Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200232Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200233Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200234Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200236Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200239Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200240Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200241Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200242Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200243Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200244Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200246Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200248Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200295Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200298Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200300Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200305Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200307Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200309Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200311Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200317Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200320Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200321Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200342Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200392Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200394Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200396Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200398Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200399Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200401Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200404Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200405Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200406Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200407Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200408Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200409Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200410Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200412Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200413Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200414Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200415Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200416Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200417Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200418Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200419Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200420Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200421Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200422Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200423Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200424Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200425Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200426Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200427Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200460Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200474Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340200781Didn'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, '2624816') ('4234', '20937373', '1340194667', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194634', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194633', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194631', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194629', None, None, None, None, None, '2624816') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1313 time used for this insertion : 0.06165623664855957 save_final save missing photos in datou_result : time spend for datou_step_exec : 120.50266313552856 time spend to save output : 0.07263374328613281 total time spend for step 5 : 120.5752968788147 step6:thcl Fri Feb 28 19:23:32 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 : 0.027053356170654297 time to convert the images to numpy array : 0.10175275802612305 time to import caffe and check if the image exist : 0.02619338035583496 time to convert the images to numpy array : 0.10989832878112793 time to import caffe and check if the image exist : 0.022623300552368164 time to convert the images to numpy array : 0.11521744728088379 time to import caffe and check if the image exist : 0.032007694244384766 time to convert the images to numpy array : 0.1099855899810791 time to import caffe and check if the image exist : 0.02954244613647461 time to convert the images to numpy array : 0.11514830589294434 time to import caffe and check if the image exist : 0.03330230712890625 time to convert the images to numpy array : 0.11681890487670898 time to import caffe and check if the image exist : 0.0388791561126709 time to convert the images to numpy array : 0.11846613883972168 time to import caffe and check if the image exist : 0.03416037559509277 time to convert the images to numpy array : 0.12918877601623535 time to import caffe and check if the image exist : 0.03810930252075195 time to convert the images to numpy array : 0.12752318382263184 time to import caffe and check if the image exist : 0.04301643371582031 time to convert the images to numpy array : 0.12439274787902832 total time to convert the images to numpy array : 0.5209298133850098 list photo_ids error: [] list photo_ids correct : [1340200332, 1340200333, 1340200334, 1340200335, 1340200336, 1340200337, 1340200338, 1340200339, 1340200340, 1340200341, 1340200342, 1340200343, 1340200344, 1340200345, 1340200346, 1340200347, 1340200365, 1340200366, 1340200367, 1340200368, 1340200369, 1340200370, 1340200371, 1340200372, 1340200373, 1340200374, 1340200375, 1340200376, 1340200377, 1340200378, 1340200379, 1340200380, 1340200381, 1340200382, 1340200383, 1340200384, 1340200385, 1340200386, 1340200387, 1340200388, 1340200389, 1340200390, 1340200391, 1340200392, 1340200661, 1340200665, 1340200669, 1340200672, 1340200676, 1340200680, 1340200684, 1340200688, 1340200692, 1340200696, 1340200700, 1340200703, 1340200707, 1340200711, 1340200714, 1340200718, 1340200722, 1340200725, 1340200729, 1340200733, 1340200735, 1340200736, 1340200737, 1340200738, 1340200739, 1340200740, 1340200741, 1340200742, 1340200743, 1340200744, 1340200746, 1340200750, 1340200754, 1340200758, 1340200762, 1340200766, 1340200769, 1340200773, 1340200777, 1340200781, 1340200089, 1340200090, 1340200092, 1340200093, 1340200094, 1340200095, 1340200096, 1340200097, 1340200098, 1340200099, 1340200100, 1340200101, 1340200102, 1340200103, 1340200104, 1340200105, 1340200106, 1340200107, 1340200108, 1340200109, 1340200110, 1340200111, 1340200112, 1340200113, 1340200114, 1340200115, 1340200116, 1340200117, 1340200118, 1340200119, 1340200120, 1340200121, 1340200122, 1340200123, 1340200124, 1340200126, 1340200127, 1340200128, 1340200129, 1340200130, 1340200131, 1340200132, 1340200133, 1340200135, 1340200482, 1340200483, 1340200484, 1340200485, 1340200498, 1340200499, 1340200501, 1340200502, 1340200503, 1340200504, 1340200505, 1340200506, 1340200507, 1340200508, 1340200509, 1340200510, 1340200511, 1340200512, 1340200513, 1340200516, 1340200520, 1340200522, 1340200525, 1340200529, 1340200533, 1340200537, 1340200589, 1340200593, 1340200597, 1340200601, 1340200605, 1340200609, 1340200614, 1340200618, 1340200622, 1340200626, 1340200630, 1340200634, 1340200638, 1340200640, 1340200642, 1340200646, 1340200650, 1340200657, 1340200282, 1340200283, 1340200284, 1340200285, 1340200286, 1340200287, 1340200288, 1340200289, 1340200292, 1340200293, 1340200294, 1340200295, 1340200296, 1340200298, 1340200300, 1340200301, 1340200302, 1340200303, 1340200305, 1340200306, 1340200307, 1340200308, 1340200309, 1340200310, 1340200311, 1340200312, 1340200313, 1340200314, 1340200316, 1340200317, 1340200318, 1340200319, 1340200320, 1340200321, 1340200322, 1340200323, 1340200324, 1340200325, 1340200326, 1340200327, 1340200328, 1340200329, 1340200330, 1340200331, 1340200185, 1340200186, 1340200187, 1340200188, 1340200189, 1340200190, 1340200192, 1340200193, 1340200194, 1340200195, 1340200196, 1340200197, 1340200198, 1340200199, 1340200200, 1340200202, 1340200203, 1340200204, 1340200205, 1340200206, 1340200207, 1340200208, 1340200209, 1340200210, 1340200211, 1340200212, 1340200213, 1340200214, 1340200215, 1340200216, 1340200217, 1340200218, 1340200219, 1340200220, 1340200221, 1340200223, 1340200224, 1340200225, 1340200226, 1340200227, 1340200228, 1340200229, 1340200230, 1340200231, 1340200393, 1340200394, 1340200395, 1340200396, 1340200397, 1340200398, 1340200399, 1340200400, 1340200401, 1340200402, 1340200403, 1340200404, 1340200405, 1340200406, 1340200407, 1340200408, 1340200409, 1340200410, 1340200411, 1340200412, 1340200413, 1340200414, 1340200415, 1340200416, 1340200417, 1340200418, 1340200419, 1340200420, 1340200421, 1340200422, 1340200423, 1340200424, 1340200425, 1340200426, 1340200427, 1340200429, 1340200430, 1340200431, 1340200432, 1340200433, 1340200434, 1340200435, 1340200436, 1340200437, 1340200136, 1340200137, 1340200138, 1340200139, 1340200140, 1340200141, 1340200142, 1340200143, 1340200144, 1340200145, 1340200146, 1340200147, 1340200148, 1340200149, 1340200150, 1340200152, 1340200153, 1340200154, 1340200155, 1340200156, 1340200157, 1340200158, 1340200159, 1340200160, 1340200161, 1340200162, 1340200163, 1340200164, 1340200165, 1340200166, 1340200167, 1340200168, 1340200169, 1340200170, 1340200171, 1340200172, 1340200173, 1340200174, 1340200175, 1340200176, 1340200177, 1340200181, 1340200182, 1340200183, 1340200438, 1340200439, 1340200440, 1340200441, 1340200442, 1340200443, 1340200444, 1340200445, 1340200446, 1340200447, 1340200448, 1340200449, 1340200450, 1340200451, 1340200452, 1340200453, 1340200454, 1340200455, 1340200456, 1340200457, 1340200458, 1340200459, 1340200460, 1340200461, 1340200462, 1340200463, 1340200464, 1340200465, 1340200466, 1340200467, 1340200468, 1340200469, 1340200470, 1340200471, 1340200472, 1340200473, 1340200474, 1340200475, 1340200476, 1340200477, 1340200478, 1340200479, 1340200480, 1340200481, 1340200232, 1340200233, 1340200234, 1340200235, 1340200236, 1340200239, 1340200240, 1340200241, 1340200242, 1340200243, 1340200244, 1340200246, 1340200247, 1340200248, 1340200249, 1340200250, 1340200251, 1340200253, 1340200254, 1340200255, 1340200256, 1340200257, 1340200258, 1340200259, 1340200260, 1340200261, 1340200262, 1340200263, 1340200265, 1340200267, 1340200268, 1340200269, 1340200270, 1340200271, 1340200272, 1340200273, 1340200274, 1340200275, 1340200276, 1340200277, 1340200278, 1340200279, 1340200280, 1340200281] number of photos to traite : 436 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 : 5525 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 : 5306 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 2.0723788738250732 time used to do the prediction : 1.552426815032959 save descriptor for thcl : 3237 time to traite the descriptors : 2.47179913520813 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1340200332 To insert : 1340200333 To insert : 1340200334 To insert : 1340200335 To insert : 1340200336 To insert : 1340200337 To insert : 1340200338 To insert : 1340200339 To insert : 1340200340 To insert : 1340200341 To insert : 1340200342 To insert : 1340200343 To insert : 1340200344 To insert : 1340200345 To insert : 1340200346 To insert : 1340200347 To insert : 1340200365 To insert : 1340200366 To insert : 1340200367 To insert : 1340200368 To insert : 1340200369 To insert : 1340200370 To insert : 1340200371 To insert : 1340200372 To insert : 1340200373 To insert : 1340200374 To insert : 1340200375 To insert : 1340200376 To insert : 1340200377 To insert : 1340200378 To insert : 1340200379 To insert : 1340200380 To insert : 1340200381 To insert : 1340200382 To insert : 1340200383 To insert : 1340200384 To insert : 1340200385 To insert : 1340200386 To insert : 1340200387 To insert : 1340200388 To insert : 1340200389 To insert : 1340200390 To insert : 1340200391 To insert : 1340200392 To insert : 1340200661 To insert : 1340200665 To insert : 1340200669 To insert : 1340200672 To insert : 1340200676 To insert : 1340200680 To insert : 1340200684 To insert : 1340200688 To insert : 1340200692 To insert : 1340200696 To insert : 1340200700 To insert : 1340200703 To insert : 1340200707 To insert : 1340200711 To insert : 1340200714 To insert : 1340200718 To insert : 1340200722 To insert : 1340200725 To insert : 1340200729 To insert : 1340200733 To insert : 1340200735 To insert : 1340200736 To insert : 1340200737 To insert : 1340200738 To insert : 1340200739 To insert : 1340200740 To insert : 1340200741 To insert : 1340200742 To insert : 1340200743 To insert : 1340200744 To insert : 1340200746 To insert : 1340200750 To insert : 1340200754 To insert : 1340200758 To insert : 1340200762 To insert : 1340200766 To insert : 1340200769 To insert : 1340200773 To insert : 1340200777 To insert : 1340200781 To insert : 1340200089 To insert : 1340200090 To insert : 1340200092 To insert : 1340200093 To insert : 1340200094 To insert : 1340200095 To insert : 1340200096 To insert : 1340200097 To insert : 1340200098 To insert : 1340200099 To insert : 1340200100 To insert : 1340200101 To insert : 1340200102 To insert : 1340200103 To insert : 1340200104 To insert : 1340200105 To insert : 1340200106 To insert : 1340200107 To insert : 1340200108 To insert : 1340200109 To insert : 1340200110 To insert : 1340200111 To insert : 1340200112 To insert : 1340200113 To insert : 1340200114 To insert : 1340200115 To insert : 1340200116 To insert : 1340200117 To insert : 1340200118 To insert : 1340200119 To insert : 1340200120 To insert : 1340200121 To insert : 1340200122 To insert : 1340200123 To insert : 1340200124 To insert : 1340200126 To insert : 1340200127 To insert : 1340200128 To insert : 1340200129 To insert : 1340200130 To insert : 1340200131 To insert : 1340200132 To insert : 1340200133 To insert : 1340200135 To insert : 1340200482 To insert : 1340200483 To insert : 1340200484 To insert : 1340200485 To insert : 1340200498 To insert : 1340200499 To insert : 1340200501 To insert : 1340200502 To insert : 1340200503 To insert : 1340200504 To insert : 1340200505 To insert : 1340200506 To insert : 1340200507 To insert : 1340200508 To insert : 1340200509 To insert : 1340200510 To insert : 1340200511 To insert : 1340200512 To insert : 1340200513 To insert : 1340200516 To insert : 1340200520 To insert : 1340200522 To insert : 1340200525 To insert : 1340200529 To insert : 1340200533 To insert : 1340200537 To insert : 1340200589 To insert : 1340200593 To insert : 1340200597 To insert : 1340200601 To insert : 1340200605 To insert : 1340200609 To insert : 1340200614 To insert : 1340200618 To insert : 1340200622 To insert : 1340200626 To insert : 1340200630 To insert : 1340200634 To insert : 1340200638 To insert : 1340200640 To insert : 1340200642 To insert : 1340200646 To insert : 1340200650 To insert : 1340200657 To insert : 1340200282 To insert : 1340200283 To insert : 1340200284 To insert : 1340200285 To insert : 1340200286 To insert : 1340200287 To insert : 1340200288 To insert : 1340200289 To insert : 1340200292 To insert : 1340200293 To insert : 1340200294 To insert : 1340200295 To insert : 1340200296 To insert : 1340200298 To insert : 1340200300 To insert : 1340200301 To insert : 1340200302 To insert : 1340200303 To insert : 1340200305 To insert : 1340200306 To insert : 1340200307 To insert : 1340200308 To insert : 1340200309 To insert : 1340200310 To insert : 1340200311 To insert : 1340200312 To insert : 1340200313 To insert : 1340200314 To insert : 1340200316 To insert : 1340200317 To insert : 1340200318 To insert : 1340200319 To insert : 1340200320 To insert : 1340200321 To insert : 1340200322 To insert : 1340200323 To insert : 1340200324 To insert : 1340200325 To insert : 1340200326 To insert : 1340200327 To insert : 1340200328 To insert : 1340200329 To insert : 1340200330 To insert : 1340200331 To insert : 1340200185 To insert : 1340200186 To insert : 1340200187 To insert : 1340200188 To insert : 1340200189 To insert : 1340200190 To insert : 1340200192 To insert : 1340200193 To insert : 1340200194 To insert : 1340200195 To insert : 1340200196 To insert : 1340200197 To insert : 1340200198 To insert : 1340200199 To insert : 1340200200 To insert : 1340200202 To insert : 1340200203 To insert : 1340200204 To insert : 1340200205 To insert : 1340200206 To insert : 1340200207 To insert : 1340200208 To insert : 1340200209 To insert : 1340200210 To insert : 1340200211 To insert : 1340200212 To insert : 1340200213 To insert : 1340200214 To insert : 1340200215 To insert : 1340200216 To insert : 1340200217 To insert : 1340200218 To insert : 1340200219 To insert : 1340200220 To insert : 1340200221 To insert : 1340200223 To insert : 1340200224 To insert : 1340200225 To insert : 1340200226 To insert : 1340200227 To insert : 1340200228 To insert : 1340200229 To insert : 1340200230 To insert : 1340200231 To insert : 1340200393 To insert : 1340200394 To insert : 1340200395 To insert : 1340200396 To insert : 1340200397 To insert : 1340200398 To insert : 1340200399 To insert : 1340200400 To insert : 1340200401 To insert : 1340200402 To insert : 1340200403 To insert : 1340200404 To insert : 1340200405 To insert : 1340200406 To insert : 1340200407 To insert : 1340200408 To insert : 1340200409 To insert : 1340200410 To insert : 1340200411 To insert : 1340200412 To insert : 1340200413 To insert : 1340200414 To insert : 1340200415 To insert : 1340200416 To insert : 1340200417 To insert : 1340200418 To insert : 1340200419 To insert : 1340200420 To insert : 1340200421 To insert : 1340200422 To insert : 1340200423 To insert : 1340200424 To insert : 1340200425 To insert : 1340200426 To insert : 1340200427 To insert : 1340200429 To insert : 1340200430 To insert : 1340200431 To insert : 1340200432 To insert : 1340200433 To insert : 1340200434 To insert : 1340200435 To insert : 1340200436 To insert : 1340200437 To insert : 1340200136 To insert : 1340200137 To insert : 1340200138 To insert : 1340200139 To insert : 1340200140 To insert : 1340200141 To insert : 1340200142 To insert : 1340200143 To insert : 1340200144 To insert : 1340200145 To insert : 1340200146 To insert : 1340200147 To insert : 1340200148 To insert : 1340200149 To insert : 1340200150 To insert : 1340200152 To insert : 1340200153 To insert : 1340200154 To insert : 1340200155 To insert : 1340200156 To insert : 1340200157 To insert : 1340200158 To insert : 1340200159 To insert : 1340200160 To insert : 1340200161 To insert : 1340200162 To insert : 1340200163 To insert : 1340200164 To insert : 1340200165 To insert : 1340200166 To insert : 1340200167 To insert : 1340200168 To insert : 1340200169 To insert : 1340200170 To insert : 1340200171 To insert : 1340200172 To insert : 1340200173 To insert : 1340200174 To insert : 1340200175 To insert : 1340200176 To insert : 1340200177 To insert : 1340200181 To insert : 1340200182 To insert : 1340200183 To insert : 1340200438 To insert : 1340200439 To insert : 1340200440 To insert : 1340200441 To insert : 1340200442 To insert : 1340200443 To insert : 1340200444 To insert : 1340200445 To insert : 1340200446 To insert : 1340200447 To insert : 1340200448 To insert : 1340200449 To insert : 1340200450 To insert : 1340200451 To insert : 1340200452 To insert : 1340200453 To insert : 1340200454 To insert : 1340200455 To insert : 1340200456 To insert : 1340200457 To insert : 1340200458 To insert : 1340200459 To insert : 1340200460 To insert : 1340200461 To insert : 1340200462 To insert : 1340200463 To insert : 1340200464 To insert : 1340200465 To insert : 1340200466 To insert : 1340200467 To insert : 1340200468 To insert : 1340200469 To insert : 1340200470 To insert : 1340200471 To insert : 1340200472 To insert : 1340200473 To insert : 1340200474 To insert : 1340200475 To insert : 1340200476 To insert : 1340200477 To insert : 1340200478 To insert : 1340200479 To insert : 1340200480 To insert : 1340200481 To insert : 1340200232 To insert : 1340200233 To insert : 1340200234 To insert : 1340200235 To insert : 1340200236 To insert : 1340200239 To insert : 1340200240 To insert : 1340200241 To insert : 1340200242 To insert : 1340200243 To insert : 1340200244 To insert : 1340200246 To insert : 1340200247 To insert : 1340200248 To insert : 1340200249 To insert : 1340200250 To insert : 1340200251 To insert : 1340200253 To insert : 1340200254 To insert : 1340200255 To insert : 1340200256 To insert : 1340200257 To insert : 1340200258 To insert : 1340200259 To insert : 1340200260 To insert : 1340200261 To insert : 1340200262 To insert : 1340200263 To insert : 1340200265 To insert : 1340200267 To insert : 1340200268 To insert : 1340200269 To insert : 1340200270 To insert : 1340200271 To insert : 1340200272 To insert : 1340200273 To insert : 1340200274 To insert : 1340200275 To insert : 1340200276 To insert : 1340200277 To insert : 1340200278 To insert : 1340200279 To insert : 1340200280 To insert : 1340200281 time to insert the descriptors : 99.93457841873169 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 : 700 time used for this insertion : 0.13378453254699707 save missing photos in datou_result : time spend for datou_step_exec : 110.72451066970825 time spend to save output : 0.1911001205444336 total time spend for step 6 : 110.91561079025269 step7:ventilate_hashtags_in_portfolio Fri Feb 28 19:25:23 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 ! 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 : 20937373 get user id for portfolio 20937373 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`=20937373 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('carton','autre','pet_clair','Film_plastique','papier','metal','mal_croppe','pet_fonce','environnement','PET_fonce','Carton','PET_clair','Tetrapak','refus','PEHD','Papier','flou','pehd')) 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`=20937373 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('carton','autre','pet_clair','Film_plastique','papier','metal','mal_croppe','pet_fonce','environnement','PET_fonce','Carton','PET_clair','Tetrapak','refus','PEHD','Papier','flou','pehd')) 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`=20937373 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('carton','autre','pet_clair','Film_plastique','papier','metal','mal_croppe','pet_fonce','environnement','PET_fonce','Carton','PET_clair','Tetrapak','refus','PEHD','Papier','flou','pehd')) 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`=20937373 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('carton','autre','pet_clair','Film_plastique','papier','metal','mal_croppe','pet_fonce','environnement','PET_fonce','Carton','PET_clair','Tetrapak','refus','PEHD','Papier','flou','pehd')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20938102,20938093,20938103,20938095,20938107,20938097,20938098,20938101,20938100,20938104,20938105,20938109,20938108?tags=carton,autre,pet_clair,film_plastique,papier,metal,mal_croppe,pet_fonce,environnement,tetrapak,refus,pehd,flou&datou_id_consolidate=4235&port_consolidate=20937373 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1340194667, 1340194634, 1340194633, 1340194631, 1340194629] Looping around the photos to save general results len do output : 1 /20937373. 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, '2624816') ('4234', '20937373', '1340194667', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194634', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194633', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194631', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194629', None, None, None, None, None, '2624816') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.01212620735168457 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.690889358520508 time spend to save output : 0.01234579086303711 total time spend for step 7 : 2.703235149383545 step8:final Fri Feb 28 19:25:26 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 : {1340194667: ('0.24052638260334624',), 1340194634: ('0.24052638260334624',), 1340194633: ('0.24052638260334624',), 1340194631: ('0.24052638260334624',), 1340194629: ('0.24052638260334624',)} new output for save of step final : {1340194667: ('0.24052638260334624',), 1340194634: ('0.24052638260334624',), 1340194633: ('0.24052638260334624',), 1340194631: ('0.24052638260334624',), 1340194629: ('0.24052638260334624',)} [1340194667, 1340194634, 1340194633, 1340194631, 1340194629] Looping around the photos to save general results len do output : 5 /1340194667.Didn't retrieve data . /1340194634.Didn't retrieve data . /1340194633.Didn't retrieve data . /1340194631.Didn't retrieve data . /1340194629.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, '2624816') ('4234', '20937373', '1340194667', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194634', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194633', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194631', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194629', None, None, None, None, None, '2624816') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.012518644332885742 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12275910377502441 time spend to save output : 0.01282191276550293 total time spend for step 8 : 0.13558101654052734 step9:velours_tree Fri Feb 28 19:25:26 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 : 20938102,20938093,20938103,20938095,20938107,20938097,20938098,20938101,20938100,20938104,20938105,20938109,20938108 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=20938102 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=20938093 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=20938103 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=20938095 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=20938107 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=20938097 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=20938098 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=20938101 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=20938100 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=20938104 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=20938105 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=20938109 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=20938108 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 436 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [5 1 2 2 2 4 4 0 0 0 2 0 2 4 0 1 4 4 2 0 2 2 1 0 3 0 2 4 0 4 4 2 3 3 2 3 4 2 1 1 1 2 2 3 2 2 1 2 2 4 4 0 0 0 2 2 4 0 4 4 1 2 2 2 3 4 0 1 0 2 0 4 0 2 0 4 2 0 1 4 4 2 3 4 2 2 0 2 3 2 1 2 2 2 4 1 2 2 2 4 2 0 0 0 2 2 4 0 4 4 4 1 2 2 3 2 0 1 0 2 4 2 4 2 4 2 2 0 1 4 4 3 3 3 2 4 2 1 3 1 2 2 2 2 2 0 0 0 0 2 0 2 4 4 4 2 2 0 2 4 2 0 2 0 2 4 4 4 4 2 2 2 4 0 2 0 3 2 0 1 4 2 2 4 3 4 2 0 2 3 1 2 2 2 4 4 0 0 0 0 2 4 3 4 1 2 2 0 5 0 2 2 2 2 2 0 0 4 2 2 4 3 0 2 0 1 4 2 2 2 3 4 2 3 0 2 5 1 1 2 0 2 2 2 0 2 4 0 1 1 1 1 1 4 0 2 5 5 1 2 2 2 0 1 2 2 2 2 2 2 3 3 1 1 1 4 1 3 2 5 5 1 2 2 0 4 2 2 0 1 3 3 0 1 3 1 4 0 3 2 5 5 0 1 1 1 5 2 4 2 2 4 4 0 3 2 3 1 1 1 1 4 0 1 2 5 5 1 4 2 4 2 0 1 2 0 1 1 1 4 3 2 0 3 0 0 0 2 0 0 4 2 0 4 2 2 1 4 3 3 0 2 4 2 3 3 3 5 3 3 3 3 5 1 0 4 4 3 0 4 3 1 3 3 3 3 3 3 5 1 3 3 0 5 3 0 1 0 3 1 5 3 3 3 3 1 2 4 1 0 3 1 3 3 4 3 3 3 3 3 3 3 5 5 1 3 3 4 3 4 3 3 3 3 3 3] Elapsed time: 0.15782475471496582 graph_id used : 80699 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20938102,20938093,20938103,20938095,20938107,20938097,20938098,20938101,20938100,20938104,20938105,20938109,20938108?tags=carton,autre,pet_clair,film_plastique,papier,metal,mal_croppe,pet_fonce,environnement,tetrapak,refus,pehd,flou&datou_id_consolidate=4235&port_consolidate=20937373&tree_id=80699 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1340194667, 1340194634, 1340194633, 1340194631, 1340194629] Looping around the photos to save general results len do output : 1 /20937373Didn'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, '2624816') ('4234', '20937373', '1340194667', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194634', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194633', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194631', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194629', None, None, None, None, None, '2624816') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.012985467910766602 save_final save missing photos in datou_result : time spend for datou_step_exec : 29.533342123031616 time spend to save output : 0.013466358184814453 total time spend for step 9 : 29.54680848121643 step10:send_mail_cod Fri Feb 28 19:25:55 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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_P20937373_28-02-2025_19_25_55.pdf 20938084 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 .imagette209380841740767155 20938075 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 .imagette209380751740767156 20938085 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 .imagette209380851740767157 20938077 imagette209380771740767158 20938089 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 .imagette209380891740767158 20938079 change filename to text .change filename to text .change filename to text .imagette209380791740767160 20938080 imagette209380801740767160 20938083 imagette209380831740767160 20938086 imagette209380861740767160 20938087 imagette209380871740767160 20938091 imagette209380911740767160 20938090 imagette209380901740767160 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20937373 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20938102,20938093,20938103,20938095,20938107,20938097,20938098,20938101,20938100,20938104,20938105,20938109,20938108?tags=carton,autre,pet_clair,film_plastique,papier,metal,mal_croppe,pet_fonce,environnement,tetrapak,refus,pehd,flou&datou_id_consolidate=4235&port_consolidate=20937373&tree_id=80699 your option no_mail is active, we will not send the real mail to your client args[1340194667] : ((1340194667, -7.464140137890274, 492609224), (1340194667, -0.5044674697870984, 501862349), '0.24052638260334624') We are sending mail with results at cod@fotonower.com args[1340194634] : ((1340194634, -7.459631868159406, 492609224), (1340194634, -0.49534349512444337, 501862349), '0.24052638260334624') We are sending mail with results at cod@fotonower.com args[1340194633] : ((1340194633, -7.462934700874498, 492609224), (1340194633, -0.49667405294579164, 501862349), '0.24052638260334624') We are sending mail with results at cod@fotonower.com args[1340194631] : ((1340194631, -7.428419252086979, 492609224), (1340194631, -0.5143736695871324, 501862349), '0.24052638260334624') We are sending mail with results at cod@fotonower.com args[1340194629] : ((1340194629, -7.53777598596925, 492609224), (1340194629, -0.5139005404098937, 501862349), '0.24052638260334624') We are sending mail with results at cod@fotonower.com refus_total : 0.24052638260334624 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=20937373 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_P20937373_28-02-2025_19_25_55.pdf results_Qualipapia_P20937373_28-02-2025_19_25_55.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20937373_28-02-2025_19_25_55.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','20937373','results_Qualipapia_P20937373_28-02-2025_19_25_55.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20937373_28-02-2025_19_25_55.pdf','pdf','','0.18','0.24052638260334624') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1340194667, 1340194634, 1340194633, 1340194631, 1340194629] 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, '2624816') ('4234', '20937373', '1340194667', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194634', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194633', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194631', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194629', None, None, None, None, None, '2624816') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012015581130981445 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.30446457862854 time spend to save output : 0.012261629104614258 total time spend for step 10 : 5.316726207733154 step11:split_time_score Fri Feb 28 19:26:01 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'}] (('17', 7),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 28022025 20937373 Nombre de photos uploadées : 7 / 23040 (0%) 28022025 20937373 Nombre de photos taguées (types de déchets): 7 / 7 (100%) 28022025 20937373 Nombre de photos taguées (volume) : 0 / 7 (0%) elapsed_time : load_data_split_time_score 3.0994415283203125e-06 elapsed_time : order_list_meta_photo_and_scores 6.67572021484375e-06 ??????? elapsed_time : fill_and_build_computed_from_old_data 0.00043892860412597656 elapsed_time : insert_dashboard_record_day_entry 0.024081945419311523 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 Qualite : 0.19136356371699506 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926288_28-02-2025_17_55_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926288 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`=20926288 AND mptpi.`type`=4230 To do Qualite : 0.18230722131056523 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926289_28-02-2025_17_49_50.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926289 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`=20926289 AND mptpi.`type`=4230 To do Qualite : 0.28319271719456496 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926290_28-02-2025_17_52_39.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926290 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`=20926290 AND mptpi.`type`=4230 To do Qualite : 0.20152453678282414 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20926291_28-02-2025_18_00_24.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20926291 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`=20926291 AND mptpi.`type`=4230 To do 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 Qualite : 0.0970633201854936 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20934025_28-02-2025_17_32_40.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934025 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`=20934025 AND mptpi.`type`=4230 To do 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 Qualite : 0.1639586909166268 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20934028_28-02-2025_17_26_17.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20934028 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`=20934028 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20935529 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20935530 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20935531 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20935532 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936067 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936068 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936069 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936070 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936071 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936072 order by id desc limit 1 Qualite : 0.15966075121649642 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20936073_28-02-2025_18_37_03.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936073 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`=20936073 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936074 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936075 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936076 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936462 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936463 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936464 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936465 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936466 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936467 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936468 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936469 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936470 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936471 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936472 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936473 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936474 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936475 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936476 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936477 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936478 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936479 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936480 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20936481 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20937371 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20937372 order by id desc limit 1 Qualite : 0.24052638260334624 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20937373_28-02-2025_19_25_55.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20937373 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`=20937373 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20937374 order by id desc limit 1 NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'28022025': {'nb_upload': 7, 'nb_taggue_class': 7, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1340194667, 1340194634, 1340194633, 1340194631, 1340194629] Looping around the photos to save general results len do output : 1 /20937373Didn'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, '2624816') ('4234', '20937373', '1340194667', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194634', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194633', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194631', None, None, None, None, None, '2624816') ('4234', None, None, None, None, None, None, None, '2624816') ('4234', '20937373', '1340194629', None, None, None, None, None, '2624816') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.011895418167114258 save_final save missing photos in datou_result : time spend for datou_step_exec : 57.40257239341736 time spend to save output : 0.012063741683959961 total time spend for step 11 : 57.41463613510132 caffe_path_current : About to save ! 2 After save, about to update current ! update_current_state 66.14user 40.07system 6:34.01elapsed 26%CPU (0avgtext+0avgdata 2609240maxresident)k 894088inputs+27624outputs (1036major+4599003minor)pagefaults 0swaps