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 : 433571 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 : 13>5 please execute split_portfolio.py -i 20268404 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2553113'] with mtr_portfolio_ids : ['20268404'] and first list_photo_ids : [] new path : /proc/433571/ 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 : 0.6196401119232178 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Wed Feb 5 18:20:29 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 : 3366 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-05 18:20:32.196431: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-05 18:20:32.227340: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-05 18:20:32.230092: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f9c3c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-05 18:20:32.230154: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-05 18:20:32.234673: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-05 18:20:32.531549: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1da358e0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-05 18:20:32.531601: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-05 18:20:32.532241: 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 2025-02-05 18:20:32.532620: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 18:20:32.535210: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 18:20:32.537799: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 18:20:32.538245: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 18:20:32.541353: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 18:20:32.542775: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 18:20:32.548607: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 18:20:32.549857: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 18:20:32.549966: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 18:20:32.550593: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-05 18:20:32.550609: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-05 18:20:32.550619: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-05 18:20:32.551676: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2914 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. 2025-02-05 18:20:32.842403: 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 2025-02-05 18:20:32.842570: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 18:20:32.842600: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 18:20:32.842624: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 18:20:32.842645: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 18:20:32.842666: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 18:20:32.842684: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 18:20:32.842705: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 18:20:32.843830: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 18:20:32.845433: 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 2025-02-05 18:20:32.845580: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-05 18:20:32.845603: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 18:20:32.845624: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-05 18:20:32.845643: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-05 18:20:32.845662: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-05 18:20:32.845681: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-05 18:20:32.845701: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 18:20:32.846747: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-05 18:20:32.846799: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-05 18:20:32.846811: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-05 18:20:32.846821: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-05 18:20:32.848017: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2914 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 : [] 2025-02-05 18:20:41.626763: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-05 18:20:41.803988: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-05 18:20:43.201545: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.202125: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.11G (2268581120 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.202162: 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. 2025-02-05 18:20:43.202708: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.202725: 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. 2025-02-05 18:20:43.209859: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.209895: 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. 2025-02-05 18:20:43.210430: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.210446: 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. 2025-02-05 18:20:43.217837: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.217896: 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. 2025-02-05 18:20:43.218442: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.218460: 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. 2025-02-05 18:20:43.250492: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.250589: 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. 2025-02-05 18:20:43.251297: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.251321: 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. 2025-02-05 18:20:43.257756: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.257786: 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. 2025-02-05 18:20:43.258287: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.258302: 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. 2025-02-05 18:20:43.298983: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.299590: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.301544: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.302089: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.343279: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.343849: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.345774: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.346301: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.374573: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.375133: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.376793: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.377336: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.383246: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.383815: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.385742: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.386303: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.392853: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.393652: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.395211: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.395784: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.423287: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.423844: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.424400: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.424946: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.428521: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.429075: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.444972: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.445575: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.446115: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.446675: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.460405: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.460978: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.461530: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.462063: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.467244: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.467807: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.472670: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.473564: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.487008: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.487565: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.491674: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.492221: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.492772: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.493334: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.494084: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.494650: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.505156: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.505725: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.506323: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.506884: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.507486: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.508038: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.524424: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.525021: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.580676: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.581750: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.582765: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.583657: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.593151: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.594015: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.610396: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.611080: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.611770: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.612433: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.616804: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.617341: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.617871: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.618399: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.619399: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.619420: 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. 2025-02-05 18:20:43.630277: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.630839: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.640303: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.640838: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.641383: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.641928: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.642468: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-05 18:20:43.643072: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.35G (2520645632 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: -120.55156 max: 145.19375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0006160736083984375 length of segment : 39 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 15 time to create 1 rle with old method : 0.000141143798828125 length of segment : 7 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 897 time to create 1 rle with old method : 0.0016474723815917969 length of segment : 41 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 940 time to create 1 rle with old method : 0.001756906509399414 length of segment : 42 time for calcul the mask position with numpy : 0.00016927719116210938 nb_pixel_total : 1463 time to create 1 rle with old method : 0.0060291290283203125 length of segment : 54 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.55156 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 897 time to create 1 rle with old method : 0.0012412071228027344 length of segment : 53 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 3039 time to create 1 rle with old method : 0.0037212371826171875 length of segment : 57 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00018477439880371094 length of segment : 10 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 947 time to create 1 rle with old method : 0.0012197494506835938 length of segment : 39 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 40 time to create 1 rle with old method : 8.225440979003906e-05 length of segment : 7 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 930 time to create 1 rle with old method : 0.001168966293334961 length of segment : 36 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.00127410888671875 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -105.81328 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 619 time to create 1 rle with old method : 0.0008623600006103516 length of segment : 23 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0008087158203125 length of segment : 31 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 4139 time to create 1 rle with old method : 0.00516510009765625 length of segment : 72 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 48 time to create 1 rle with old method : 0.00015091896057128906 length of segment : 11 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.00035452842712402344 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.82109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0006182193756103516 length of segment : 21 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 8463 time to create 1 rle with old method : 0.010237455368041992 length of segment : 88 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00016760826110839844 length of segment : 10 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 229.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 117.31484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006351470947265625 length of segment : 19 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1633 time to create 1 rle with old method : 0.0021529197692871094 length of segment : 47 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 711 time to create 1 rle with old method : 0.0009186267852783203 length of segment : 26 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1571 time to create 1 rle with old method : 0.0020363330841064453 length of segment : 40 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005795955657958984 length of segment : 33 time for calcul the mask position with numpy : 0.0001742839813232422 nb_pixel_total : 327 time to create 1 rle with old method : 0.0007007122039794922 length of segment : 19 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.00034356117248535156 length of segment : 38 time for calcul the mask position with numpy : 0.0007202625274658203 nb_pixel_total : 62346 time to create 1 rle with old method : 0.07241964340209961 length of segment : 287 Processing 1 images image shape: (400, 400, 3) min: 18.00000 max: 174.00000 molded_images shape: (1, 640, 640, 3) min: -94.09453 max: 53.87344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.001967191696166992 nb_pixel_total : 154058 time to create 1 rle with new method : 0.0031108856201171875 length of segment : 413 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.53984 max: 136.93047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 752 time to create 1 rle with old method : 0.0010874271392822266 length of segment : 17 time for calcul the mask position with numpy : 0.00017976760864257812 nb_pixel_total : 6924 time to create 1 rle with old method : 0.008189916610717773 length of segment : 89 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0004184246063232422 length of segment : 9 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.0002589225769042969 length of segment : 10 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0007913112640380859 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.11406 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 : 3.790855407714844e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.0002300739288330078 length of segment : 10 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1112 time to create 1 rle with old method : 0.0013432502746582031 length of segment : 52 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.0011470317840576172 length of segment : 33 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.0008816719055175781 length of segment : 28 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 741 time to create 1 rle with old method : 0.0009703636169433594 length of segment : 32 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.39531 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0007479190826416016 length of segment : 26 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 953 time to create 1 rle with old method : 0.0011820793151855469 length of segment : 57 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 2541 time to create 1 rle with old method : 0.002947568893432617 length of segment : 148 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.00019669532775878906 length of segment : 14 time for calcul the mask position with numpy : 0.00017261505126953125 nb_pixel_total : 997 time to create 1 rle with old method : 0.0015981197357177734 length of segment : 93 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 2371 time to create 1 rle with old method : 0.002832651138305664 length of segment : 129 time for calcul the mask position with numpy : 0.00010824203491210938 nb_pixel_total : 2440 time to create 1 rle with old method : 0.002921581268310547 length of segment : 155 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: 142.64297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00025916099548339844 length of segment : 28 time for calcul the mask position with numpy : 0.0001316070556640625 nb_pixel_total : 1062 time to create 1 rle with old method : 0.0014853477478027344 length of segment : 102 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.0003464221954345703 length of segment : 38 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 839 time to create 1 rle with old method : 0.0012025833129882812 length of segment : 34 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 1468 time to create 1 rle with old method : 0.001997709274291992 length of segment : 76 time for calcul the mask position with numpy : 0.0002014636993408203 nb_pixel_total : 4211 time to create 1 rle with old method : 0.005017518997192383 length of segment : 221 Processing 1 images image shape: (280, 400, 3) min: 13.00000 max: 176.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 59.15859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.001085519790649414 nb_pixel_total : 106375 time to create 1 rle with old method : 0.11609125137329102 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: 145.36953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003540515899658203 length of segment : 16 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.0003573894500732422 length of segment : 35 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.0006530284881591797 length of segment : 29 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 539 time to create 1 rle with old method : 0.0007450580596923828 length of segment : 39 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 581 time to create 1 rle with old method : 0.0008318424224853516 length of segment : 28 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 6167 time to create 1 rle with old method : 0.007366180419921875 length of segment : 123 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 996 time to create 1 rle with old method : 0.001251220703125 length of segment : 47 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 987 time to create 1 rle with old method : 0.0012996196746826172 length of segment : 30 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.0001518726348876953 length of segment : 11 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.00039577484130859375 length of segment : 27 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006992816925048828 length of segment : 19 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.00032329559326171875 length of segment : 18 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1592 time to create 1 rle with old method : 0.002076864242553711 length of segment : 48 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 225.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 92.34844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0006482601165771484 length of segment : 12 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.0003502368927001953 length of segment : 15 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00043845176696777344 length of segment : 10 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.0006754398345947266 length of segment : 34 time for calcul the mask position with numpy : 9.036064147949219e-05 nb_pixel_total : 905 time to create 1 rle with old method : 0.001705169677734375 length of segment : 43 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.0002560615539550781 length of segment : 16 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0003998279571533203 length of segment : 17 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 668 time to create 1 rle with old method : 0.0012946128845214844 length of segment : 23 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0009565353393554688 length of segment : 23 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.00021982192993164062 length of segment : 14 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00030303001403808594 length of segment : 15 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: 147.51406 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 : 432 time to create 1 rle with old method : 0.0005741119384765625 length of segment : 30 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0013403892517089844 length of segment : 61 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00025010108947753906 length of segment : 19 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0006203651428222656 length of segment : 19 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 1659 time to create 1 rle with old method : 0.002172231674194336 length of segment : 87 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.35000 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 : 4 time to create 1 rle with old method : 2.6941299438476562e-05 length of segment : 4 time for calcul the mask position with numpy : 0.0005183219909667969 nb_pixel_total : 53022 time to create 1 rle with old method : 0.05995941162109375 length of segment : 282 time for calcul the mask position with numpy : 0.0004532337188720703 nb_pixel_total : 34682 time to create 1 rle with old method : 0.039319515228271484 length of segment : 393 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: -120.45000 max: 145.71328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.00048613548278808594 length of segment : 29 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 12 time to create 1 rle with old method : 4.291534423828125e-05 length of segment : 4 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 935 time to create 1 rle with old method : 0.0012481212615966797 length of segment : 45 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1378 time to create 1 rle with old method : 0.0019330978393554688 length of segment : 55 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 998 time to create 1 rle with old method : 0.0013380050659179688 length of segment : 45 length of segment : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.54766 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 : 7.343292236328125e-05 nb_pixel_total : 2487 time to create 1 rle with old method : 0.003203868865966797 length of segment : 53 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 593 time to create 1 rle with old method : 0.0008401870727539062 length of segment : 58 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.00015687942504882812 length of segment : 25 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 735 time to create 1 rle with old method : 0.0009877681732177734 length of segment : 34 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 2037 time to create 1 rle with old method : 0.0025665760040283203 length of segment : 82 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 2512 time to create 1 rle with old method : 0.0032444000244140625 length of segment : 54 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 123 time to create 1 rle with old method : 0.00019788742065429688 length of segment : 10 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0008711814880371094 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -102.92656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.22344 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 : 3.314018249511719e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001876354217529297 length of segment : 12 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0006239414215087891 length of segment : 21 time for calcul the mask position with numpy : 0.00012969970703125 nb_pixel_total : 9118 time to create 1 rle with old method : 0.011337518692016602 length of segment : 83 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 119.89297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0009987354278564453 length of segment : 31 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0005204677581787109 length of segment : 33 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0007464885711669922 length of segment : 29 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00024771690368652344 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 176.00000 molded_images shape: (1, 640, 640, 3) min: -97.27813 max: 54.77969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0013310909271240234 nb_pixel_total : 150662 time to create 1 rle with new method : 0.0020105838775634766 length of segment : 400 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.93047 max: 138.45156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 6804 time to create 1 rle with old method : 0.008220434188842773 length of segment : 94 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0011472702026367188 length of segment : 18 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.0009884834289550781 length of segment : 35 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003445148468017578 length of segment : 16 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.00036025047302246094 length of segment : 11 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003867149353027344 length of segment : 8 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 521 time to create 1 rle with old method : 0.0007405281066894531 length of segment : 20 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 2703 time to create 1 rle with old method : 0.003364086151123047 length of segment : 63 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.00017976760864257812 length of segment : 11 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1254 time to create 1 rle with old method : 0.0017266273498535156 length of segment : 32 Processing 1 images image shape: (400, 400, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.78203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1077 time to create 1 rle with old method : 0.0013613700866699219 length of segment : 53 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0007603168487548828 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.97734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 574 time to create 1 rle with old method : 0.0007531642913818359 length of segment : 28 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 731 time to create 1 rle with old method : 0.0010058879852294922 length of segment : 29 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.0002048015594482422 length of segment : 16 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0007069110870361328 length of segment : 39 time for calcul the mask position with numpy : 0.0001373291015625 nb_pixel_total : 4621 time to create 1 rle with old method : 0.0057544708251953125 length of segment : 183 time for calcul the mask position with numpy : 0.0001735687255859375 nb_pixel_total : 4040 time to create 1 rle with old method : 0.004797458648681641 length of segment : 193 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: 145.17422 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00025534629821777344 length of segment : 27 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 784 time to create 1 rle with old method : 0.0010249614715576172 length of segment : 37 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 55 time to create 1 rle with old method : 9.942054748535156e-05 length of segment : 11 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002257823944091797 length of segment : 34 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1627 time to create 1 rle with old method : 0.002040386199951172 length of segment : 80 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0008635520935058594 length of segment : 54 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1349 time to create 1 rle with old method : 0.0017948150634765625 length of segment : 113 time for calcul the mask position with numpy : 0.00016427040100097656 nb_pixel_total : 3517 time to create 1 rle with old method : 0.004462003707885742 length of segment : 219 Processing 1 images image shape: (280, 400, 3) min: 9.00000 max: 180.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 65.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008921623229980469 nb_pixel_total : 106901 time to create 1 rle with old method : 0.11835885047912598 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: 145.88516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.0002837181091308594 length of segment : 9 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 581 time to create 1 rle with old method : 0.0008141994476318359 length of segment : 29 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003440380096435547 length of segment : 22 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.0002841949462890625 length of segment : 10 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 5436 time to create 1 rle with old method : 0.006459236145019531 length of segment : 77 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 980 time to create 1 rle with old method : 0.001333475112915039 length of segment : 42 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005359649658203125 length of segment : 34 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0004067420959472656 length of segment : 14 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00031876564025878906 length of segment : 36 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1986 time to create 1 rle with old method : 0.002481698989868164 length of segment : 57 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.00051116943359375 length of segment : 29 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1299 time to create 1 rle with old method : 0.0015854835510253906 length of segment : 54 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 2153 time to create 1 rle with old method : 0.002864360809326172 length of segment : 73 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1507 time to create 1 rle with old method : 0.0018842220306396484 length of segment : 69 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 210.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 81.13906 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0004153251647949219 length of segment : 11 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00022983551025390625 length of segment : 14 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00020456314086914062 length of segment : 14 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00017404556274414062 length of segment : 17 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 973 time to create 1 rle with old method : 0.0012297630310058594 length of segment : 44 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0006375312805175781 length of segment : 26 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.00040984153747558594 length of segment : 19 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003769397735595703 length of segment : 26 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00033736228942871094 length of segment : 14 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.00022459030151367188 length of segment : 15 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: 147.54141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.0011167526245117188 length of segment : 33 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.00024390220642089844 length of segment : 16 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 39 time to create 1 rle with old method : 0.0001595020294189453 length of segment : 12 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0005061626434326172 length of segment : 18 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003573894500732422 length of segment : 23 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0006389617919921875 nb_pixel_total : 58653 time to create 1 rle with old method : 0.06456255912780762 length of segment : 261 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: -120.70391 max: 145.68594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00042176246643066406 length of segment : 32 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.00047469139099121094 length of segment : 46 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 841 time to create 1 rle with old method : 0.0012226104736328125 length of segment : 38 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0011005401611328125 length of segment : 39 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 738 time to create 1 rle with old method : 0.0010945796966552734 length of segment : 46 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1549 time to create 1 rle with old method : 0.002109527587890625 length of segment : 51 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.25078 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 : 5.221366882324219e-05 nb_pixel_total : 861 time to create 1 rle with old method : 0.0011293888092041016 length of segment : 46 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 938 time to create 1 rle with old method : 0.0012798309326171875 length of segment : 40 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 2559 time to create 1 rle with old method : 0.0032074451446533203 length of segment : 52 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 65 time to create 1 rle with old method : 0.00012564659118652344 length of segment : 18 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.0001919269561767578 length of segment : 10 time for calcul the mask position with numpy : 2.765655517578125e-05 nb_pixel_total : 44 time to create 1 rle with old method : 0.00015282630920410156 length of segment : 7 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 2472 time to create 1 rle with old method : 0.0031042098999023438 length of segment : 51 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002684593200683594 length of segment : 33 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 920 time to create 1 rle with old method : 0.0012135505676269531 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.80547 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 2152 time to create 1 rle with old method : 0.0029277801513671875 length of segment : 55 time for calcul the mask position with numpy : 0.00014638900756835938 nb_pixel_total : 4846 time to create 1 rle with old method : 0.005891323089599609 length of segment : 133 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.50859 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0006577968597412109 length of segment : 20 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.0008764266967773438 length of segment : 29 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0007266998291015625 length of segment : 46 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 241.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 128.33828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 692 time to create 1 rle with old method : 0.0009477138519287109 length of segment : 30 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1902 time to create 1 rle with old method : 0.0023107528686523438 length of segment : 71 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1553 time to create 1 rle with old method : 0.002111673355102539 length of segment : 76 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1264 time to create 1 rle with old method : 0.001604318618774414 length of segment : 131 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005688667297363281 length of segment : 32 time for calcul the mask position with numpy : 0.0007045269012451172 nb_pixel_total : 71752 time to create 1 rle with old method : 0.07929253578186035 length of segment : 272 Processing 1 images image shape: (400, 400, 3) min: 15.00000 max: 176.00000 molded_images shape: (1, 640, 640, 3) min: -97.12188 max: 58.04531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0015609264373779297 nb_pixel_total : 150009 time to create 1 rle with new method : 0.002215147018432617 length of segment : 400 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.03594 max: 137.92656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 769 time to create 1 rle with old method : 0.0010416507720947266 length of segment : 19 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 6691 time to create 1 rle with old method : 0.008196353912353516 length of segment : 90 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0007181167602539062 length of segment : 18 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.00016689300537109375 length of segment : 11 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.00031948089599609375 length of segment : 7 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003502368927001953 length of segment : 9 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 2009 time to create 1 rle with old method : 0.0025184154510498047 length of segment : 52 Processing 1 images image shape: (400, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.32500 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 : 3.838539123535156e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004782676696777344 length of segment : 23 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 1106 time to create 1 rle with old method : 0.0014553070068359375 length of segment : 54 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1451 time to create 1 rle with old method : 0.001817941665649414 length of segment : 47 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0008625984191894531 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.94219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0007762908935546875 length of segment : 27 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.0004360675811767578 length of segment : 25 time for calcul the mask position with numpy : 0.0001709461212158203 nb_pixel_total : 4055 time to create 1 rle with old method : 0.004868984222412109 length of segment : 202 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1543 time to create 1 rle with old method : 0.0022172927856445312 length of segment : 34 time for calcul the mask position with numpy : 0.00013589859008789062 nb_pixel_total : 4645 time to create 1 rle with old method : 0.005805015563964844 length of segment : 205 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: 146.24062 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 : 166 time to create 1 rle with old method : 0.0002410411834716797 length of segment : 27 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1605 time to create 1 rle with old method : 0.0020847320556640625 length of segment : 78 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.00011658668518066406 length of segment : 13 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.00039887428283691406 length of segment : 30 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 747 time to create 1 rle with old method : 0.00107574462890625 length of segment : 36 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 916 time to create 1 rle with old method : 0.0012488365173339844 length of segment : 83 Processing 1 images image shape: (280, 400, 3) min: 7.00000 max: 178.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 61.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008890628814697266 nb_pixel_total : 106015 time to create 1 rle with old method : 0.11794400215148926 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: 148.68594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 557 time to create 1 rle with old method : 0.0007407665252685547 length of segment : 28 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.00028705596923828125 length of segment : 8 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.00042700767517089844 length of segment : 28 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.000354766845703125 length of segment : 13 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005557537078857422 length of segment : 28 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005705356597900391 length of segment : 23 time for calcul the mask position with numpy : 0.00011420249938964844 nb_pixel_total : 7788 time to create 1 rle with old method : 0.009590864181518555 length of segment : 93 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.00035071372985839844 length of segment : 33 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.0010900497436523438 length of segment : 48 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.00037479400634765625 length of segment : 22 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002696514129638672 length of segment : 12 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00035834312438964844 length of segment : 33 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002429485321044922 length of segment : 16 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 206.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 89.79141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0006115436553955078 length of segment : 37 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0004391670227050781 length of segment : 11 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1059 time to create 1 rle with old method : 0.0013942718505859375 length of segment : 44 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001575946807861328 length of segment : 15 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0003497600555419922 length of segment : 7 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0005109310150146484 length of segment : 32 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004165172576904297 length of segment : 28 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.0002455711364746094 length of segment : 14 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.00032591819763183594 length of segment : 15 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004563331604003906 length of segment : 27 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003941059112548828 length of segment : 18 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.00022363662719726562 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: 147.16641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.00025463104248046875 length of segment : 17 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 432 time to create 1 rle with old method : 0.0007071495056152344 length of segment : 63 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003540515899658203 length of segment : 30 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: 138.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005357265472412109 length of segment : 29 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 25 time to create 1 rle with old method : 7.534027099609375e-05 length of segment : 19 time for calcul the mask position with numpy : 0.001116037368774414 nb_pixel_total : 65418 time to create 1 rle with old method : 0.07355690002441406 length of segment : 291 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: -120.41094 max: 145.77187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002663135528564453 length of segment : 23 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0005459785461425781 length of segment : 40 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 897 time to create 1 rle with old method : 0.0012364387512207031 length of segment : 45 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 982 time to create 1 rle with old method : 0.001299142837524414 length of segment : 41 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1397 time to create 1 rle with old method : 0.001958131790161133 length of segment : 55 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.24688 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 : 5.745887756347656e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.001245737075805664 length of segment : 37 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2835 time to create 1 rle with old method : 0.003545045852661133 length of segment : 56 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0009002685546875 length of segment : 43 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001933574676513672 length of segment : 11 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1670 time to create 1 rle with old method : 0.0022516250610351562 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: -101.75078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.00023484230041503906 length of segment : 15 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 2229 time to create 1 rle with old method : 0.0029032230377197266 length of segment : 53 time for calcul the mask position with numpy : 0.00017070770263671875 nb_pixel_total : 4572 time to create 1 rle with old method : 0.005558490753173828 length of segment : 132 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 3361 time to create 1 rle with old method : 0.004166841506958008 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.56719 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0007174015045166016 length of segment : 21 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002307891845703125 length of segment : 20 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0007424354553222656 length of segment : 28 time for calcul the mask position with numpy : 0.0001227855682373047 nb_pixel_total : 8634 time to create 1 rle with old method : 0.010000467300415039 length of segment : 85 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 236.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 116.17031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 742 time to create 1 rle with old method : 0.0010755062103271484 length of segment : 35 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1242 time to create 1 rle with old method : 0.0016396045684814453 length of segment : 68 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 1172 time to create 1 rle with old method : 0.0015223026275634766 length of segment : 40 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002994537353515625 length of segment : 38 time for calcul the mask position with numpy : 0.00011849403381347656 nb_pixel_total : 1866 time to create 1 rle with old method : 0.002298116683959961 length of segment : 107 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1117 time to create 1 rle with old method : 0.0014786720275878906 length of segment : 65 Processing 1 images image shape: (400, 400, 3) min: 20.00000 max: 178.00000 molded_images shape: (1, 640, 640, 3) min: -92.03984 max: 59.77578 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: -120.34063 max: 138.28750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 768 time to create 1 rle with old method : 0.0011119842529296875 length of segment : 19 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 6865 time to create 1 rle with old method : 0.008377790451049805 length of segment : 81 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 10 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 2856 time to create 1 rle with old method : 0.003461599349975586 length of segment : 66 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 586 time to create 1 rle with old method : 0.0007748603820800781 length of segment : 25 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 853 time to create 1 rle with old method : 0.0011582374572753906 length of segment : 37 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.00016641616821289062 length of segment : 11 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.00048732757568359375 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: -113.98125 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1100 time to create 1 rle with old method : 0.0013971328735351562 length of segment : 53 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00023174285888671875 length of segment : 10 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 848 time to create 1 rle with old method : 0.0012352466583251953 length of segment : 41 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0008296966552734375 length of segment : 28 time for calcul the mask position with numpy : 0.0002617835998535156 nb_pixel_total : 12312 time to create 1 rle with old method : 0.01539158821105957 length of segment : 246 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00012636184692382812 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.57500 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0007824897766113281 length of segment : 28 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002875328063964844 length of segment : 47 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.00037598609924316406 length of segment : 36 time for calcul the mask position with numpy : 9.751319885253906e-05 nb_pixel_total : 2229 time to create 1 rle with old method : 0.0029418468475341797 length of segment : 64 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1462 time to create 1 rle with old method : 0.0019063949584960938 length of segment : 138 time for calcul the mask position with numpy : 0.00010728836059570312 nb_pixel_total : 552 time to create 1 rle with old method : 0.0010225772857666016 length of segment : 48 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1498 time to create 1 rle with old method : 0.0021762847900390625 length of segment : 34 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: 145.67422 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002582073211669922 length of segment : 27 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1623 time to create 1 rle with old method : 0.0020639896392822266 length of segment : 79 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003533363342285156 length of segment : 33 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.0010519027709960938 length of segment : 43 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1392 time to create 1 rle with old method : 0.0018305778503417969 length of segment : 115 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 56 time to create 1 rle with old method : 9.918212890625e-05 length of segment : 12 time for calcul the mask position with numpy : 0.00014853477478027344 nb_pixel_total : 3983 time to create 1 rle with old method : 0.0047986507415771484 length of segment : 227 time for calcul the mask position with numpy : 0.00013780593872070312 nb_pixel_total : 3236 time to create 1 rle with old method : 0.003928184509277344 length of segment : 187 Processing 1 images image shape: (280, 400, 3) min: 14.00000 max: 179.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 64.13516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008840560913085938 nb_pixel_total : 104845 time to create 1 rle with old method : 0.11854982376098633 length of segment : 284 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: 148.62734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.0002930164337158203 length of segment : 9 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007874965667724609 length of segment : 29 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1261 time to create 1 rle with old method : 0.0017189979553222656 length of segment : 50 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00042939186096191406 length of segment : 24 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.00043487548828125 length of segment : 28 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 35 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0007226467132568359 length of segment : 27 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.0014216899871826172 length of segment : 41 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.00028705596923828125 length of segment : 29 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 2692 time to create 1 rle with old method : 0.0033063888549804688 length of segment : 43 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.00034880638122558594 length of segment : 35 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1704 time to create 1 rle with old method : 0.002331972122192383 length of segment : 74 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0006165504455566406 length of segment : 30 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 2252 time to create 1 rle with old method : 0.0028276443481445312 length of segment : 60 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.00041413307189941406 length of segment : 22 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1651 time to create 1 rle with old method : 0.0022885799407958984 length of segment : 57 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 212.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 74.09219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.00046443939208984375 length of segment : 29 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00041365623474121094 length of segment : 11 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 992 time to create 1 rle with old method : 0.001260519027709961 length of segment : 47 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 67 time to create 1 rle with old method : 0.0001239776611328125 length of segment : 15 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: 148.00234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00026679039001464844 length of segment : 17 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0005259513854980469 length of segment : 17 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.00030040740966796875 length of segment : 25 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002353191375732422 length of segment : 25 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 135.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005054473876953125 length of segment : 31 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.02031 max: 145.23672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002853870391845703 length of segment : 23 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 902 time to create 1 rle with old method : 0.0012140274047851562 length of segment : 42 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 49 time to create 1 rle with old method : 0.00012993812561035156 length of segment : 12 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1682 time to create 1 rle with old method : 0.0023577213287353516 length of segment : 76 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 886 time to create 1 rle with old method : 0.0012121200561523438 length of segment : 41 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00042629241943359375 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.95781 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 : 7.653236389160156e-05 nb_pixel_total : 2640 time to create 1 rle with old method : 0.0033817291259765625 length of segment : 53 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1066 time to create 1 rle with old method : 0.0013887882232666016 length of segment : 31 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.0009436607360839844 length of segment : 32 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00014781951904296875 length of segment : 18 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00017690658569335938 length of segment : 10 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006392002105712891 length of segment : 37 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1883 time to create 1 rle with old method : 0.0024149417877197266 length of segment : 77 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1896 time to create 1 rle with old method : 0.002289295196533203 length of segment : 85 Processing 1 images image shape: (400, 400, 3) min: 13.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -94.99688 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.92266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0008194446563720703 length of segment : 21 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 518 time to create 1 rle with old method : 0.0008358955383300781 length of segment : 29 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 226.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 106.00234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 860 time to create 1 rle with old method : 0.0010995864868164062 length of segment : 37 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 1355 time to create 1 rle with old method : 0.0016808509826660156 length of segment : 39 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1660 time to create 1 rle with old method : 0.002019643783569336 length of segment : 122 time for calcul the mask position with numpy : 0.0005173683166503906 nb_pixel_total : 52362 time to create 1 rle with old method : 0.05788731575012207 length of segment : 283 Processing 1 images image shape: (400, 400, 3) min: 15.00000 max: 183.00000 molded_images shape: (1, 640, 640, 3) min: -93.94219 max: 65.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.001321554183959961 nb_pixel_total : 152147 time to create 1 rle with new method : 0.0022170543670654297 length of segment : 404 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.12969 max: 138.13750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0006303787231445312 length of segment : 24 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 712 time to create 1 rle with old method : 0.0010592937469482422 length of segment : 18 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 7924 time to create 1 rle with old method : 0.009195804595947266 length of segment : 104 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0007166862487792969 length of segment : 22 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001914501190185547 length of segment : 11 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0006728172302246094 length of segment : 22 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003528594970703125 length of segment : 24 time for calcul the mask position with numpy : 0.00014662742614746094 nb_pixel_total : 8621 time to create 1 rle with old method : 0.010545969009399414 length of segment : 132 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1652 time to create 1 rle with old method : 0.002206087112426758 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 13.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.68438 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 : 7.152557373046875e-05 nb_pixel_total : 1188 time to create 1 rle with old method : 0.0015707015991210938 length of segment : 50 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1107 time to create 1 rle with old method : 0.0013930797576904297 length of segment : 52 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 730 time to create 1 rle with old method : 0.0010445117950439453 length of segment : 33 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1399 time to create 1 rle with old method : 0.001806497573852539 length of segment : 54 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 660 time to create 1 rle with old method : 0.0009014606475830078 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: -118.01250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007357597351074219 length of segment : 28 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0010950565338134766 length of segment : 34 time for calcul the mask position with numpy : 0.00012826919555664062 nb_pixel_total : 4878 time to create 1 rle with old method : 0.00608515739440918 length of segment : 125 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.000194549560546875 length of segment : 14 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: 145.81094 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0004181861877441406 length of segment : 27 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.0005886554718017578 length of segment : 37 time for calcul the mask position with numpy : 0.00011920928955078125 nb_pixel_total : 993 time to create 1 rle with old method : 0.0019674301147460938 length of segment : 85 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 1544 time to create 1 rle with old method : 0.002912282943725586 length of segment : 75 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00018405914306640625 length of segment : 15 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.0004980564117431641 length of segment : 39 Processing 1 images image shape: (280, 400, 3) min: 19.00000 max: 181.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 64.15859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008854866027832031 nb_pixel_total : 106432 time to create 1 rle with old method : 0.11600947380065918 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: 144.23672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007138252258300781 length of segment : 28 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 918 time to create 1 rle with old method : 0.0012478828430175781 length of segment : 45 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.00029778480529785156 length of segment : 9 time for calcul the mask position with numpy : 0.0001347064971923828 nb_pixel_total : 7396 time to create 1 rle with old method : 0.00859689712524414 length of segment : 84 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1099 time to create 1 rle with old method : 0.0014369487762451172 length of segment : 35 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 1937 time to create 1 rle with old method : 0.0024003982543945312 length of segment : 78 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.0001423358917236328 length of segment : 16 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 2098 time to create 1 rle with old method : 0.0028467178344726562 length of segment : 53 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0008203983306884766 length of segment : 23 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 73.34453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00045299530029296875 length of segment : 12 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.0011107921600341797 length of segment : 43 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00024962425231933594 length of segment : 9 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00042176246643066406 length of segment : 19 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.00023245811462402344 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: 145.81484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0008809566497802734 length of segment : 18 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0011622905731201172 length of segment : 56 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 894 time to create 1 rle with old method : 0.0012145042419433594 length of segment : 56 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.0002760887145996094 length of segment : 18 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00033211708068847656 length of segment : 24 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.00021600723266601562 length of segment : 22 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.00035262107849121094 length of segment : 30 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: 139.16250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0011172294616699219 nb_pixel_total : 47924 time to create 1 rle with old method : 0.061242103576660156 length of segment : 456 Detection mask done ! Trying to reset tf kernel 434266 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2173 tf kernel not reseted sub process len(results) : 392 len(list_Values) 392 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 392 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 : 3125 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 392 chid ids of type : 4228 Number RLEs to save : 21375 save missing photos in datou_result : time spend for datou_step_exec : 31.54324984550476 time spend to save output : 1.5047838687896729 total time spend for step 1 : 33.048033714294434 step2:brightness Wed Feb 5 18:21:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1738776028_433571_1334990972_77eb4d7c31f0eae1bd17cad009eaccfd.jpg treat image : temp/1738776028_433571_1334990941_43e62a0c41e38de14812d0c5b144bd82.jpg treat image : temp/1738776028_433571_1334990938_34cb84ebdb21cd99aab3dd3b2284a921.jpg treat image : temp/1738776028_433571_1334990936_fc59e37c2d4b4d9060dc5d2e05d8ea04.jpg treat image : temp/1738776028_433571_1334990932_b64c70e084744f3c29db974e02b6621c.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 : 0.011879682540893555 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 : 0.012168407440185547 save missing photos in datou_result : time spend for datou_step_exec : 1.3020598888397217 time spend to save output : 0.02930593490600586 total time spend for step 2 : 1.3313658237457275 step3:blur_detection Wed Feb 5 18:21:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1738776028_433571_1334990972_77eb4d7c31f0eae1bd17cad009eaccfd.jpg resize: (1080, 1920) 1334990972 -6.92635230303 treat image : temp/1738776028_433571_1334990941_43e62a0c41e38de14812d0c5b144bd82.jpg resize: (1080, 1920) 1334990941 -6.943749469681027 treat image : temp/1738776028_433571_1334990938_34cb84ebdb21cd99aab3dd3b2284a921.jpg resize: (1080, 1920) 1334990938 -6.949658555806144 treat image : temp/1738776028_433571_1334990936_fc59e37c2d4b4d9060dc5d2e05d8ea04.jpg resize: (1080, 1920) 1334990936 -6.950415806091785 treat image : temp/1738776028_433571_1334990932_b64c70e084744f3c29db974e02b6621c.jpg resize: (1080, 1920) 1334990932 -6.8961854312386635 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 : 0.012647151947021484 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 : 0.011785030364990234 save missing photos in datou_result : time spend for datou_step_exec : 5.533738851547241 time spend to save output : 0.02913379669189453 total time spend for step 3 : 5.562872648239136 step4:rle_unique_nms_with_priority Wed Feb 5 18:21:09 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 392 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 85 nb_hashtags : 6 time to prepare the origin masks : 1.1810777187347412 time for calcul the mask position with numpy : 0.05352497100830078 nb_pixel_total : 1625838 time to create 1 rle with new method : 0.4034876823425293 time for calcul the mask position with numpy : 0.00849151611328125 nb_pixel_total : 397 time to create 1 rle with old method : 0.0004756450653076172 time for calcul the mask position with numpy : 0.00843667984008789 nb_pixel_total : 48 time to create 1 rle with old method : 8.678436279296875e-05 time for calcul the mask position with numpy : 0.00864720344543457 nb_pixel_total : 62346 time to create 1 rle with old method : 0.07399225234985352 time for calcul the mask position with numpy : 0.008110284805297852 nb_pixel_total : 897 time to create 1 rle with old method : 0.0011713504791259766 time for calcul the mask position with numpy : 0.008107662200927734 nb_pixel_total : 1463 time to create 1 rle with old method : 0.0016865730285644531 time for calcul the mask position with numpy : 0.00800180435180664 nb_pixel_total : 282 time to create 1 rle with old method : 0.00031447410583496094 time for calcul the mask position with numpy : 0.008199691772460938 nb_pixel_total : 897 time to create 1 rle with old method : 0.0011148452758789062 time for calcul the mask position with numpy : 0.008157968521118164 nb_pixel_total : 75 time to create 1 rle with old method : 0.00012803077697753906 time for calcul the mask position with numpy : 0.008305549621582031 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001392364501953125 time for calcul the mask position with numpy : 0.00815439224243164 nb_pixel_total : 40 time to create 1 rle with old method : 5.793571472167969e-05 time for calcul the mask position with numpy : 0.008445501327514648 nb_pixel_total : 3039 time to create 1 rle with old method : 0.0035941600799560547 time for calcul the mask position with numpy : 0.008376836776733398 nb_pixel_total : 15 time to create 1 rle with old method : 3.790855407714844e-05 time for calcul the mask position with numpy : 0.008324623107910156 nb_pixel_total : 104 time to create 1 rle with old method : 0.00013446807861328125 time for calcul the mask position with numpy : 0.008281469345092773 nb_pixel_total : 239 time to create 1 rle with old method : 0.0002620220184326172 time for calcul the mask position with numpy : 0.008205652236938477 nb_pixel_total : 91 time to create 1 rle with old method : 0.000110626220703125 time for calcul the mask position with numpy : 0.008166790008544922 nb_pixel_total : 370 time to create 1 rle with old method : 0.0004627704620361328 time for calcul the mask position with numpy : 0.008063077926635742 nb_pixel_total : 947 time to create 1 rle with old method : 0.001051187515258789 time for calcul the mask position with numpy : 0.008069992065429688 nb_pixel_total : 41 time to create 1 rle with old method : 5.650520324707031e-05 time for calcul the mask position with numpy : 0.008201360702514648 nb_pixel_total : 619 time to create 1 rle with old method : 0.0007040500640869141 time for calcul the mask position with numpy : 0.00820159912109375 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003342628479003906 time for calcul the mask position with numpy : 0.008274555206298828 nb_pixel_total : 4139 time to create 1 rle with old method : 0.004805803298950195 time for calcul the mask position with numpy : 0.008285045623779297 nb_pixel_total : 327 time to create 1 rle with old method : 0.0004553794860839844 time for calcul the mask position with numpy : 0.008380651473999023 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002474784851074219 time for calcul the mask position with numpy : 0.008371114730834961 nb_pixel_total : 8463 time to create 1 rle with old method : 0.009353876113891602 time for calcul the mask position with numpy : 0.008426904678344727 nb_pixel_total : 1376 time to create 1 rle with old method : 0.0016293525695800781 time for calcul the mask position with numpy : 0.008415699005126953 nb_pixel_total : 33 time to create 1 rle with old method : 7.915496826171875e-05 time for calcul the mask position with numpy : 0.008388280868530273 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005257129669189453 time for calcul the mask position with numpy : 0.008371114730834961 nb_pixel_total : 630 time to create 1 rle with old method : 0.0006866455078125 time for calcul the mask position with numpy : 0.008912801742553711 nb_pixel_total : 154058 time to create 1 rle with new method : 0.07699036598205566 time for calcul the mask position with numpy : 0.008218050003051758 nb_pixel_total : 765 time to create 1 rle with old method : 0.0008909702301025391 time for calcul the mask position with numpy : 0.008167028427124023 nb_pixel_total : 997 time to create 1 rle with old method : 0.0011606216430664062 time for calcul the mask position with numpy : 0.007920503616333008 nb_pixel_total : 2541 time to create 1 rle with old method : 0.002862215042114258 time for calcul the mask position with numpy : 0.008022785186767578 nb_pixel_total : 632 time to create 1 rle with old method : 0.0007190704345703125 time for calcul the mask position with numpy : 0.00838470458984375 nb_pixel_total : 115 time to create 1 rle with old method : 0.00014495849609375 time for calcul the mask position with numpy : 0.008362770080566406 nb_pixel_total : 72 time to create 1 rle with old method : 0.0001087188720703125 time for calcul the mask position with numpy : 0.008406639099121094 nb_pixel_total : 173 time to create 1 rle with old method : 0.00020647048950195312 time for calcul the mask position with numpy : 0.008468151092529297 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001583099365234375 time for calcul the mask position with numpy : 0.00840902328491211 nb_pixel_total : 6179 time to create 1 rle with old method : 0.006819486618041992 time for calcul the mask position with numpy : 0.008403539657592773 nb_pixel_total : 89 time to create 1 rle with old method : 0.00011730194091796875 time for calcul the mask position with numpy : 0.008725881576538086 nb_pixel_total : 839 time to create 1 rle with old method : 0.0009891986846923828 time for calcul the mask position with numpy : 0.008346319198608398 nb_pixel_total : 121 time to create 1 rle with old method : 0.0001590251922607422 time for calcul the mask position with numpy : 0.008298158645629883 nb_pixel_total : 953 time to create 1 rle with old method : 0.0011005401611328125 time for calcul the mask position with numpy : 0.008315086364746094 nb_pixel_total : 1062 time to create 1 rle with old method : 0.0017826557159423828 time for calcul the mask position with numpy : 0.009522199630737305 nb_pixel_total : 4211 time to create 1 rle with old method : 0.0068471431732177734 time for calcul the mask position with numpy : 0.009552955627441406 nb_pixel_total : 2440 time to create 1 rle with old method : 0.003947019577026367 time for calcul the mask position with numpy : 0.009579181671142578 nb_pixel_total : 1112 time to create 1 rle with old method : 0.001828908920288086 time for calcul the mask position with numpy : 0.009611845016479492 nb_pixel_total : 752 time to create 1 rle with old method : 0.0012285709381103516 time for calcul the mask position with numpy : 0.009641408920288086 nb_pixel_total : 323 time to create 1 rle with old method : 0.0005764961242675781 time for calcul the mask position with numpy : 0.009652137756347656 nb_pixel_total : 212 time to create 1 rle with old method : 0.0003731250762939453 time for calcul the mask position with numpy : 0.008706331253051758 nb_pixel_total : 217 time to create 1 rle with old method : 0.0002617835998535156 time for calcul the mask position with numpy : 0.008052349090576172 nb_pixel_total : 1468 time to create 1 rle with old method : 0.0015821456909179688 time for calcul the mask position with numpy : 0.008206844329833984 nb_pixel_total : 556 time to create 1 rle with old method : 0.0006537437438964844 time for calcul the mask position with numpy : 0.008510351181030273 nb_pixel_total : 106375 time to create 1 rle with old method : 0.11303377151489258 time for calcul the mask position with numpy : 0.008008241653442383 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002543926239013672 time for calcul the mask position with numpy : 0.007923603057861328 nb_pixel_total : 539 time to create 1 rle with old method : 0.0005862712860107422 time for calcul the mask position with numpy : 0.007961034774780273 nb_pixel_total : 581 time to create 1 rle with old method : 0.0006749629974365234 time for calcul the mask position with numpy : 0.008192062377929688 nb_pixel_total : 996 time to create 1 rle with old method : 0.001077413558959961 time for calcul the mask position with numpy : 0.007906198501586914 nb_pixel_total : 53022 time to create 1 rle with old method : 0.05727219581604004 time for calcul the mask position with numpy : 0.008400201797485352 nb_pixel_total : 459 time to create 1 rle with old method : 0.0005772113800048828 time for calcul the mask position with numpy : 0.008174896240234375 nb_pixel_total : 4 time to create 1 rle with old method : 1.1205673217773438e-05 time for calcul the mask position with numpy : 0.008249282836914062 nb_pixel_total : 283 time to create 1 rle with old method : 0.0005121231079101562 time for calcul the mask position with numpy : 0.008227348327636719 nb_pixel_total : 449 time to create 1 rle with old method : 0.0004942417144775391 time for calcul the mask position with numpy : 0.008109569549560547 nb_pixel_total : 266 time to create 1 rle with old method : 0.0002949237823486328 time for calcul the mask position with numpy : 0.0076673030853271484 nb_pixel_total : 958 time to create 1 rle with old method : 0.0011456012725830078 time for calcul the mask position with numpy : 0.00808858871459961 nb_pixel_total : 1592 time to create 1 rle with old method : 0.0018193721771240234 time for calcul the mask position with numpy : 0.008372783660888672 nb_pixel_total : 71 time to create 1 rle with old method : 9.560585021972656e-05 time for calcul the mask position with numpy : 0.008229732513427734 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003066062927246094 time for calcul the mask position with numpy : 0.008275270462036133 nb_pixel_total : 668 time to create 1 rle with old method : 0.0007245540618896484 time for calcul the mask position with numpy : 0.008307695388793945 nb_pixel_total : 104 time to create 1 rle with old method : 0.0001316070556640625 time for calcul the mask position with numpy : 0.008103132247924805 nb_pixel_total : 6 time to create 1 rle with old method : 1.811981201171875e-05 time for calcul the mask position with numpy : 0.008280277252197266 nb_pixel_total : 905 time to create 1 rle with old method : 0.001049041748046875 time for calcul the mask position with numpy : 0.008387327194213867 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001461505889892578 time for calcul the mask position with numpy : 0.00840306282043457 nb_pixel_total : 432 time to create 1 rle with old method : 0.0005021095275878906 time for calcul the mask position with numpy : 0.008358478546142578 nb_pixel_total : 168 time to create 1 rle with old method : 0.0001895427703857422 time for calcul the mask position with numpy : 0.008364200592041016 nb_pixel_total : 226 time to create 1 rle with old method : 0.0002644062042236328 time for calcul the mask position with numpy : 0.008352518081665039 nb_pixel_total : 6167 time to create 1 rle with old method : 0.006680011749267578 time for calcul the mask position with numpy : 0.008386850357055664 nb_pixel_total : 325 time to create 1 rle with old method : 0.0004048347473144531 time for calcul the mask position with numpy : 0.00841212272644043 nb_pixel_total : 471 time to create 1 rle with old method : 0.0005645751953125 time for calcul the mask position with numpy : 0.008411169052124023 nb_pixel_total : 152 time to create 1 rle with old method : 0.00018596649169921875 time for calcul the mask position with numpy : 0.008383750915527344 nb_pixel_total : 124 time to create 1 rle with old method : 0.00015974044799804688 time for calcul the mask position with numpy : 0.008385181427001953 nb_pixel_total : 1527 time to create 1 rle with old method : 0.0017833709716796875 time for calcul the mask position with numpy : 0.008376836776733398 nb_pixel_total : 176 time to create 1 rle with old method : 0.00021028518676757812 time for calcul the mask position with numpy : 0.008369684219360352 nb_pixel_total : 393 time to create 1 rle with old method : 0.0004703998565673828 time for calcul the mask position with numpy : 0.0084075927734375 nb_pixel_total : 888 time to create 1 rle with old method : 0.0010554790496826172 time for calcul the mask position with numpy : 0.008401870727539062 nb_pixel_total : 987 time to create 1 rle with old method : 0.0011224746704101562 create new chi : 1.595120906829834 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 : 0.010141849517822266 batch 1 Loaded 86 chid ids of type : 4230 Number RLEs to save : 9693 TO DO : save crop sub photo not yet done ! save time : 0.6273257732391357 nb_obj : 78 nb_hashtags : 6 time to prepare the origin masks : 2.021667242050171 time for calcul the mask position with numpy : 0.035134077072143555 nb_pixel_total : 1687702 time to create 1 rle with new method : 0.07239270210266113 time for calcul the mask position with numpy : 0.006819725036621094 nb_pixel_total : 373 time to create 1 rle with old method : 0.00046515464782714844 time for calcul the mask position with numpy : 0.006493806838989258 nb_pixel_total : 935 time to create 1 rle with old method : 0.001135110855102539 time for calcul the mask position with numpy : 0.006308555603027344 nb_pixel_total : 1378 time to create 1 rle with old method : 0.0017604827880859375 time for calcul the mask position with numpy : 0.006322622299194336 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005185604095458984 time for calcul the mask position with numpy : 0.006390571594238281 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001614093780517578 time for calcul the mask position with numpy : 0.006026029586791992 nb_pixel_total : 593 time to create 1 rle with old method : 0.0007536411285400391 time for calcul the mask position with numpy : 0.0068700313568115234 nb_pixel_total : 99 time to create 1 rle with old method : 0.00015425682067871094 time for calcul the mask position with numpy : 0.006372690200805664 nb_pixel_total : 83 time to create 1 rle with old method : 0.00011420249938964844 time for calcul the mask position with numpy : 0.006239175796508789 nb_pixel_total : 128 time to create 1 rle with old method : 0.0002002716064453125 time for calcul the mask position with numpy : 0.007633209228515625 nb_pixel_total : 2487 time to create 1 rle with old method : 0.003663778305053711 time for calcul the mask position with numpy : 0.0065097808837890625 nb_pixel_total : 12 time to create 1 rle with old method : 3.0279159545898438e-05 time for calcul the mask position with numpy : 0.006449699401855469 nb_pixel_total : 123 time to create 1 rle with old method : 0.00017309188842773438 time for calcul the mask position with numpy : 0.00603175163269043 nb_pixel_total : 188 time to create 1 rle with old method : 0.00023436546325683594 time for calcul the mask position with numpy : 0.0060465335845947266 nb_pixel_total : 1388 time to create 1 rle with old method : 0.0016450881958007812 time for calcul the mask position with numpy : 0.0061779022216796875 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005044937133789062 time for calcul the mask position with numpy : 0.006075143814086914 nb_pixel_total : 735 time to create 1 rle with old method : 0.0008280277252197266 time for calcul the mask position with numpy : 0.0062487125396728516 nb_pixel_total : 112 time to create 1 rle with old method : 0.00014734268188476562 time for calcul the mask position with numpy : 0.0063018798828125 nb_pixel_total : 587 time to create 1 rle with old method : 0.0006964206695556641 time for calcul the mask position with numpy : 0.006070137023925781 nb_pixel_total : 9118 time to create 1 rle with old method : 0.00994563102722168 time for calcul the mask position with numpy : 0.006139278411865234 nb_pixel_total : 806 time to create 1 rle with old method : 0.0010068416595458984 time for calcul the mask position with numpy : 0.007223367691040039 nb_pixel_total : 150662 time to create 1 rle with new method : 0.029268741607666016 time for calcul the mask position with numpy : 0.006001949310302734 nb_pixel_total : 630 time to create 1 rle with old method : 0.0007266998291015625 time for calcul the mask position with numpy : 0.006035804748535156 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002257823944091797 time for calcul the mask position with numpy : 0.006784200668334961 nb_pixel_total : 55 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.006325244903564453 nb_pixel_total : 12 time to create 1 rle with old method : 5.7697296142578125e-05 time for calcul the mask position with numpy : 0.006953239440917969 nb_pixel_total : 731 time to create 1 rle with old method : 0.0009448528289794922 time for calcul the mask position with numpy : 0.007129669189453125 nb_pixel_total : 590 time to create 1 rle with old method : 0.0008499622344970703 time for calcul the mask position with numpy : 0.006117582321166992 nb_pixel_total : 107 time to create 1 rle with old method : 0.00014710426330566406 time for calcul the mask position with numpy : 0.010183095932006836 nb_pixel_total : 4621 time to create 1 rle with old method : 0.005843639373779297 time for calcul the mask position with numpy : 0.00622248649597168 nb_pixel_total : 784 time to create 1 rle with old method : 0.0009119510650634766 time for calcul the mask position with numpy : 0.0060422420501708984 nb_pixel_total : 6804 time to create 1 rle with old method : 0.0075337886810302734 time for calcul the mask position with numpy : 0.006369113922119141 nb_pixel_total : 1349 time to create 1 rle with old method : 0.0017163753509521484 time for calcul the mask position with numpy : 0.006319761276245117 nb_pixel_total : 3517 time to create 1 rle with old method : 0.003936052322387695 time for calcul the mask position with numpy : 0.006131887435913086 nb_pixel_total : 628 time to create 1 rle with old method : 0.0007598400115966797 time for calcul the mask position with numpy : 0.006111621856689453 nb_pixel_total : 1077 time to create 1 rle with old method : 0.0013229846954345703 time for calcul the mask position with numpy : 0.006208658218383789 nb_pixel_total : 28 time to create 1 rle with old method : 7.748603820800781e-05 time for calcul the mask position with numpy : 0.00629878044128418 nb_pixel_total : 216 time to create 1 rle with old method : 0.00033092498779296875 time for calcul the mask position with numpy : 0.006458282470703125 nb_pixel_total : 225 time to create 1 rle with old method : 0.0002872943878173828 time for calcul the mask position with numpy : 0.006356954574584961 nb_pixel_total : 300 time to create 1 rle with old method : 0.00037479400634765625 time for calcul the mask position with numpy : 0.006313323974609375 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002646446228027344 time for calcul the mask position with numpy : 0.00628352165222168 nb_pixel_total : 1254 time to create 1 rle with old method : 0.0015430450439453125 time for calcul the mask position with numpy : 0.006361961364746094 nb_pixel_total : 156 time to create 1 rle with old method : 0.00019240379333496094 time for calcul the mask position with numpy : 0.006097316741943359 nb_pixel_total : 470 time to create 1 rle with old method : 0.0005693435668945312 time for calcul the mask position with numpy : 0.006163358688354492 nb_pixel_total : 1627 time to create 1 rle with old method : 0.0018897056579589844 time for calcul the mask position with numpy : 0.006054401397705078 nb_pixel_total : 789 time to create 1 rle with old method : 0.0009238719940185547 time for calcul the mask position with numpy : 0.006456136703491211 nb_pixel_total : 2703 time to create 1 rle with old method : 0.0032372474670410156 time for calcul the mask position with numpy : 0.006300449371337891 nb_pixel_total : 574 time to create 1 rle with old method : 0.0007188320159912109 time for calcul the mask position with numpy : 0.0070874691009521484 nb_pixel_total : 106901 time to create 1 rle with old method : 0.13624811172485352 time for calcul the mask position with numpy : 0.007475614547729492 nb_pixel_total : 158 time to create 1 rle with old method : 0.0003485679626464844 time for calcul the mask position with numpy : 0.007300138473510742 nb_pixel_total : 177 time to create 1 rle with old method : 0.0003361701965332031 time for calcul the mask position with numpy : 0.007894515991210938 nb_pixel_total : 581 time to create 1 rle with old method : 0.0009846687316894531 time for calcul the mask position with numpy : 0.008161783218383789 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003705024719238281 time for calcul the mask position with numpy : 0.0067098140716552734 nb_pixel_total : 980 time to create 1 rle with old method : 0.0012967586517333984 time for calcul the mask position with numpy : 0.007015705108642578 nb_pixel_total : 129 time to create 1 rle with old method : 0.0001735687255859375 time for calcul the mask position with numpy : 0.006474971771240234 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003123283386230469 time for calcul the mask position with numpy : 0.00754237174987793 nb_pixel_total : 1299 time to create 1 rle with old method : 0.0015594959259033203 time for calcul the mask position with numpy : 0.006955623626708984 nb_pixel_total : 58653 time to create 1 rle with old method : 0.06700539588928223 time for calcul the mask position with numpy : 0.006632328033447266 nb_pixel_total : 370 time to create 1 rle with old method : 0.00044274330139160156 time for calcul the mask position with numpy : 0.006231069564819336 nb_pixel_total : 237 time to create 1 rle with old method : 0.00028586387634277344 time for calcul the mask position with numpy : 0.006110191345214844 nb_pixel_total : 2153 time to create 1 rle with old method : 0.0024957656860351562 time for calcul the mask position with numpy : 0.006261110305786133 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003075599670410156 time for calcul the mask position with numpy : 0.006191730499267578 nb_pixel_total : 1986 time to create 1 rle with old method : 0.0022695064544677734 time for calcul the mask position with numpy : 0.0062754154205322266 nb_pixel_total : 100 time to create 1 rle with old method : 0.0001430511474609375 time for calcul the mask position with numpy : 0.0060749053955078125 nb_pixel_total : 315 time to create 1 rle with old method : 0.00040793418884277344 time for calcul the mask position with numpy : 0.006082057952880859 nb_pixel_total : 213 time to create 1 rle with old method : 0.0002815723419189453 time for calcul the mask position with numpy : 0.00605010986328125 nb_pixel_total : 973 time to create 1 rle with old method : 0.0011355876922607422 time for calcul the mask position with numpy : 0.006208658218383789 nb_pixel_total : 278 time to create 1 rle with old method : 0.0003561973571777344 time for calcul the mask position with numpy : 0.006161928176879883 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003077983856201172 time for calcul the mask position with numpy : 0.007229328155517578 nb_pixel_total : 148 time to create 1 rle with old method : 0.0001933574676513672 time for calcul the mask position with numpy : 0.0065326690673828125 nb_pixel_total : 5436 time to create 1 rle with old method : 0.006067514419555664 time for calcul the mask position with numpy : 0.007306098937988281 nb_pixel_total : 39 time to create 1 rle with old method : 9.34600830078125e-05 time for calcul the mask position with numpy : 0.0065386295318603516 nb_pixel_total : 1507 time to create 1 rle with old method : 0.0017628669738769531 time for calcul the mask position with numpy : 0.007107973098754883 nb_pixel_total : 267 time to create 1 rle with old method : 0.000335693359375 time for calcul the mask position with numpy : 0.006574869155883789 nb_pixel_total : 137 time to create 1 rle with old method : 0.00017952919006347656 time for calcul the mask position with numpy : 0.006386995315551758 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004496574401855469 time for calcul the mask position with numpy : 0.006368875503540039 nb_pixel_total : 826 time to create 1 rle with old method : 0.000980377197265625 time for calcul the mask position with numpy : 0.0063359737396240234 nb_pixel_total : 146 time to create 1 rle with old method : 0.0001914501190185547 time for calcul the mask position with numpy : 0.006189823150634766 nb_pixel_total : 162 time to create 1 rle with old method : 0.00020956993103027344 create new chi : 0.9371521472930908 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 : 0.0012285709381103516 batch 1 Loaded 79 chid ids of type : 4230 Number RLEs to save : 8684 TO DO : save crop sub photo not yet done ! save time : 0.5578713417053223 nb_obj : 81 nb_hashtags : 6 time to prepare the origin masks : 1.377485752105713 time for calcul the mask position with numpy : 0.2294297218322754 nb_pixel_total : 1619950 time to create 1 rle with new method : 0.2211599349975586 time for calcul the mask position with numpy : 0.006943941116333008 nb_pixel_total : 325 time to create 1 rle with old method : 0.0006413459777832031 time for calcul the mask position with numpy : 0.0068209171295166016 nb_pixel_total : 71714 time to create 1 rle with old method : 0.08264422416687012 time for calcul the mask position with numpy : 0.006582021713256836 nb_pixel_total : 1264 time to create 1 rle with old method : 0.001604318618774414 time for calcul the mask position with numpy : 0.006608724594116211 nb_pixel_total : 59 time to create 1 rle with old method : 0.00011706352233886719 time for calcul the mask position with numpy : 0.006426572799682617 nb_pixel_total : 841 time to create 1 rle with old method : 0.0010957717895507812 time for calcul the mask position with numpy : 0.008214235305786133 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002338886260986328 time for calcul the mask position with numpy : 0.006940126419067383 nb_pixel_total : 1549 time to create 1 rle with old method : 0.0018780231475830078 time for calcul the mask position with numpy : 0.006972551345825195 nb_pixel_total : 861 time to create 1 rle with old method : 0.0011086463928222656 time for calcul the mask position with numpy : 0.006683826446533203 nb_pixel_total : 22 time to create 1 rle with old method : 5.9604644775390625e-05 time for calcul the mask position with numpy : 0.0066530704498291016 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003001689910888672 time for calcul the mask position with numpy : 0.006393909454345703 nb_pixel_total : 65 time to create 1 rle with old method : 0.00012946128845214844 time for calcul the mask position with numpy : 0.0063953399658203125 nb_pixel_total : 10 time to create 1 rle with old method : 6.508827209472656e-05 time for calcul the mask position with numpy : 0.006436824798583984 nb_pixel_total : 44 time to create 1 rle with old method : 7.62939453125e-05 time for calcul the mask position with numpy : 0.006047248840332031 nb_pixel_total : 49 time to create 1 rle with old method : 0.00012946128845214844 time for calcul the mask position with numpy : 0.006601810455322266 nb_pixel_total : 2559 time to create 1 rle with old method : 0.0030922889709472656 time for calcul the mask position with numpy : 0.0059282779693603516 nb_pixel_total : 122 time to create 1 rle with old method : 0.00015592575073242188 time for calcul the mask position with numpy : 0.006534576416015625 nb_pixel_total : 650 time to create 1 rle with old method : 0.0007281303405761719 time for calcul the mask position with numpy : 0.0062618255615234375 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005128383636474609 time for calcul the mask position with numpy : 0.005970478057861328 nb_pixel_total : 938 time to create 1 rle with old method : 0.0010557174682617188 time for calcul the mask position with numpy : 0.006120443344116211 nb_pixel_total : 9 time to create 1 rle with old method : 4.673004150390625e-05 time for calcul the mask position with numpy : 0.006166934967041016 nb_pixel_total : 528 time to create 1 rle with old method : 0.0008828639984130859 time for calcul the mask position with numpy : 0.006623029708862305 nb_pixel_total : 2152 time to create 1 rle with old method : 0.0025501251220703125 time for calcul the mask position with numpy : 0.006165981292724609 nb_pixel_total : 4846 time to create 1 rle with old method : 0.005696773529052734 time for calcul the mask position with numpy : 0.006747007369995117 nb_pixel_total : 1860 time to create 1 rle with old method : 0.0021827220916748047 time for calcul the mask position with numpy : 0.00654911994934082 nb_pixel_total : 14 time to create 1 rle with old method : 7.390975952148438e-05 time for calcul the mask position with numpy : 0.006824016571044922 nb_pixel_total : 692 time to create 1 rle with old method : 0.0008840560913085938 time for calcul the mask position with numpy : 0.008219003677368164 nb_pixel_total : 150009 time to create 1 rle with new method : 0.08052659034729004 time for calcul the mask position with numpy : 0.0064775943756103516 nb_pixel_total : 1451 time to create 1 rle with old method : 0.0017075538635253906 time for calcul the mask position with numpy : 0.006314992904663086 nb_pixel_total : 1543 time to create 1 rle with old method : 0.0019655227661132812 time for calcul the mask position with numpy : 0.0070705413818359375 nb_pixel_total : 650 time to create 1 rle with old method : 0.0007927417755126953 time for calcul the mask position with numpy : 0.006262302398681641 nb_pixel_total : 166 time to create 1 rle with old method : 0.0002071857452392578 time for calcul the mask position with numpy : 0.006194591522216797 nb_pixel_total : 4055 time to create 1 rle with old method : 0.0047223567962646484 time for calcul the mask position with numpy : 0.00605010986328125 nb_pixel_total : 340 time to create 1 rle with old method : 0.0003914833068847656 time for calcul the mask position with numpy : 0.006062507629394531 nb_pixel_total : 1310 time to create 1 rle with old method : 0.00165557861328125 time for calcul the mask position with numpy : 0.006173849105834961 nb_pixel_total : 69 time to create 1 rle with old method : 0.00015211105346679688 time for calcul the mask position with numpy : 0.006040096282958984 nb_pixel_total : 98 time to create 1 rle with old method : 0.00013065338134765625 time for calcul the mask position with numpy : 0.0061299800872802734 nb_pixel_total : 5924 time to create 1 rle with old method : 0.006802082061767578 time for calcul the mask position with numpy : 0.006022930145263672 nb_pixel_total : 747 time to create 1 rle with old method : 0.0008513927459716797 time for calcul the mask position with numpy : 0.0060689449310302734 nb_pixel_total : 303 time to create 1 rle with old method : 0.0003635883331298828 time for calcul the mask position with numpy : 0.006033420562744141 nb_pixel_total : 916 time to create 1 rle with old method : 0.0010786056518554688 time for calcul the mask position with numpy : 0.005728721618652344 nb_pixel_total : 1106 time to create 1 rle with old method : 0.0011343955993652344 time for calcul the mask position with numpy : 0.005919218063354492 nb_pixel_total : 769 time to create 1 rle with old method : 0.00086212158203125 time for calcul the mask position with numpy : 0.0059947967529296875 nb_pixel_total : 163 time to create 1 rle with old method : 0.0002231597900390625 time for calcul the mask position with numpy : 0.0060727596282958984 nb_pixel_total : 484 time to create 1 rle with old method : 0.0005984306335449219 time for calcul the mask position with numpy : 0.006124734878540039 nb_pixel_total : 3 time to create 1 rle with old method : 2.6226043701171875e-05 time for calcul the mask position with numpy : 0.006130218505859375 nb_pixel_total : 285 time to create 1 rle with old method : 0.0003643035888671875 time for calcul the mask position with numpy : 0.006956338882446289 nb_pixel_total : 1605 time to create 1 rle with old method : 0.001992464065551758 time for calcul the mask position with numpy : 0.0065021514892578125 nb_pixel_total : 2009 time to create 1 rle with old method : 0.0023458003997802734 time for calcul the mask position with numpy : 0.007040977478027344 nb_pixel_total : 602 time to create 1 rle with old method : 0.0007703304290771484 time for calcul the mask position with numpy : 0.007505893707275391 nb_pixel_total : 106015 time to create 1 rle with old method : 0.1575946807861328 time for calcul the mask position with numpy : 0.0061533451080322266 nb_pixel_total : 149 time to create 1 rle with old method : 0.00019502639770507812 time for calcul the mask position with numpy : 0.006203889846801758 nb_pixel_total : 159 time to create 1 rle with old method : 0.00020837783813476562 time for calcul the mask position with numpy : 0.006528139114379883 nb_pixel_total : 311 time to create 1 rle with old method : 0.0003714561462402344 time for calcul the mask position with numpy : 0.006445169448852539 nb_pixel_total : 557 time to create 1 rle with old method : 0.000667572021484375 time for calcul the mask position with numpy : 0.006443500518798828 nb_pixel_total : 832 time to create 1 rle with old method : 0.0010759830474853516 time for calcul the mask position with numpy : 0.0075109004974365234 nb_pixel_total : 65162 time to create 1 rle with old method : 0.07002520561218262 time for calcul the mask position with numpy : 0.005998849868774414 nb_pixel_total : 159 time to create 1 rle with old method : 0.00026607513427734375 time for calcul the mask position with numpy : 0.00677490234375 nb_pixel_total : 25 time to create 1 rle with old method : 5.53131103515625e-05 time for calcul the mask position with numpy : 0.0059549808502197266 nb_pixel_total : 257 time to create 1 rle with old method : 0.00030493736267089844 time for calcul the mask position with numpy : 0.006167411804199219 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005288124084472656 time for calcul the mask position with numpy : 0.006129026412963867 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005033016204833984 time for calcul the mask position with numpy : 0.005970001220703125 nb_pixel_total : 240 time to create 1 rle with old method : 0.0002808570861816406 time for calcul the mask position with numpy : 0.0060541629791259766 nb_pixel_total : 10 time to create 1 rle with old method : 2.3365020751953125e-05 time for calcul the mask position with numpy : 0.0060176849365234375 nb_pixel_total : 258 time to create 1 rle with old method : 0.00032401084899902344 time for calcul the mask position with numpy : 0.006186246871948242 nb_pixel_total : 422 time to create 1 rle with old method : 0.0005130767822265625 time for calcul the mask position with numpy : 0.006292581558227539 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001246929168701172 time for calcul the mask position with numpy : 0.006451129913330078 nb_pixel_total : 374 time to create 1 rle with old method : 0.00044918060302734375 time for calcul the mask position with numpy : 0.006392478942871094 nb_pixel_total : 1059 time to create 1 rle with old method : 0.001314401626586914 time for calcul the mask position with numpy : 0.00651097297668457 nb_pixel_total : 432 time to create 1 rle with old method : 0.0005369186401367188 time for calcul the mask position with numpy : 0.0065996646881103516 nb_pixel_total : 143 time to create 1 rle with old method : 0.00021004676818847656 time for calcul the mask position with numpy : 0.006753683090209961 nb_pixel_total : 8 time to create 1 rle with old method : 3.5762786865234375e-05 time for calcul the mask position with numpy : 0.006472349166870117 nb_pixel_total : 149 time to create 1 rle with old method : 0.00019884109497070312 time for calcul the mask position with numpy : 0.0070416927337646484 nb_pixel_total : 159 time to create 1 rle with old method : 0.0003199577331542969 time for calcul the mask position with numpy : 0.007904052734375 nb_pixel_total : 7788 time to create 1 rle with old method : 0.01226806640625 time for calcul the mask position with numpy : 0.0066258907318115234 nb_pixel_total : 384 time to create 1 rle with old method : 0.0006377696990966797 time for calcul the mask position with numpy : 0.006615400314331055 nb_pixel_total : 37 time to create 1 rle with old method : 0.00011420249938964844 time for calcul the mask position with numpy : 0.006609916687011719 nb_pixel_total : 302 time to create 1 rle with old method : 0.0005064010620117188 time for calcul the mask position with numpy : 0.009622573852539062 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002574920654296875 time for calcul the mask position with numpy : 0.009630441665649414 nb_pixel_total : 275 time to create 1 rle with old method : 0.0004570484161376953 time for calcul the mask position with numpy : 0.00970315933227539 nb_pixel_total : 163 time to create 1 rle with old method : 0.0002925395965576172 time for calcul the mask position with numpy : 0.00946354866027832 nb_pixel_total : 201 time to create 1 rle with old method : 0.0002593994140625 create new chi : 1.4696907997131348 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 : 0.0013303756713867188 batch 1 Loaded 82 chid ids of type : 4230 Number RLEs to save : 8779 TO DO : save crop sub photo not yet done ! save time : 0.5266952514648438 nb_obj : 79 nb_hashtags : 6 time to prepare the origin masks : 1.1547787189483643 time for calcul the mask position with numpy : 0.023644208908081055 nb_pixel_total : 1881566 time to create 1 rle with new method : 0.12198567390441895 time for calcul the mask position with numpy : 0.010500192642211914 nb_pixel_total : 99 time to create 1 rle with old method : 0.00015664100646972656 time for calcul the mask position with numpy : 0.00602412223815918 nb_pixel_total : 897 time to create 1 rle with old method : 0.0010895729064941406 time for calcul the mask position with numpy : 0.006000518798828125 nb_pixel_total : 119 time to create 1 rle with old method : 0.0002551078796386719 time for calcul the mask position with numpy : 0.006071805953979492 nb_pixel_total : 1397 time to create 1 rle with old method : 0.0016772747039794922 time for calcul the mask position with numpy : 0.006046295166015625 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006537437438964844 time for calcul the mask position with numpy : 0.005982160568237305 nb_pixel_total : 194 time to create 1 rle with old method : 0.00024056434631347656 time for calcul the mask position with numpy : 0.006005764007568359 nb_pixel_total : 162 time to create 1 rle with old method : 0.0002295970916748047 time for calcul the mask position with numpy : 0.006119966506958008 nb_pixel_total : 2835 time to create 1 rle with old method : 0.003240823745727539 time for calcul the mask position with numpy : 0.009961128234863281 nb_pixel_total : 112 time to create 1 rle with old method : 0.00015664100646972656 time for calcul the mask position with numpy : 0.009998559951782227 nb_pixel_total : 1670 time to create 1 rle with old method : 0.0019767284393310547 time for calcul the mask position with numpy : 0.009952783584594727 nb_pixel_total : 200 time to create 1 rle with old method : 0.00025463104248046875 time for calcul the mask position with numpy : 0.00986480712890625 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005433559417724609 time for calcul the mask position with numpy : 0.0058135986328125 nb_pixel_total : 888 time to create 1 rle with old method : 0.0010433197021484375 time for calcul the mask position with numpy : 0.00642848014831543 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006155967712402344 time for calcul the mask position with numpy : 0.006123781204223633 nb_pixel_total : 1208 time to create 1 rle with old method : 0.0015616416931152344 time for calcul the mask position with numpy : 0.006168842315673828 nb_pixel_total : 2229 time to create 1 rle with old method : 0.002440214157104492 time for calcul the mask position with numpy : 0.00619959831237793 nb_pixel_total : 1866 time to create 1 rle with old method : 0.0021872520446777344 time for calcul the mask position with numpy : 0.00728607177734375 nb_pixel_total : 148 time to create 1 rle with old method : 0.0001919269561767578 time for calcul the mask position with numpy : 0.006902933120727539 nb_pixel_total : 4572 time to create 1 rle with old method : 0.005341053009033203 time for calcul the mask position with numpy : 0.006171703338623047 nb_pixel_total : 8634 time to create 1 rle with old method : 0.009731292724609375 time for calcul the mask position with numpy : 0.006072282791137695 nb_pixel_total : 117 time to create 1 rle with old method : 0.00017333030700683594 time for calcul the mask position with numpy : 0.006031513214111328 nb_pixel_total : 1149 time to create 1 rle with old method : 0.0013637542724609375 time for calcul the mask position with numpy : 0.005982637405395508 nb_pixel_total : 145 time to create 1 rle with old method : 0.00021982192993164062 time for calcul the mask position with numpy : 0.005939483642578125 nb_pixel_total : 742 time to create 1 rle with old method : 0.0008196830749511719 time for calcul the mask position with numpy : 0.005858659744262695 nb_pixel_total : 848 time to create 1 rle with old method : 0.0009403228759765625 time for calcul the mask position with numpy : 0.0058825016021728516 nb_pixel_total : 12312 time to create 1 rle with old method : 0.014533281326293945 time for calcul the mask position with numpy : 0.0062215328216552734 nb_pixel_total : 1498 time to create 1 rle with old method : 0.0017979145050048828 time for calcul the mask position with numpy : 0.006007671356201172 nb_pixel_total : 666 time to create 1 rle with old method : 0.0007843971252441406 time for calcul the mask position with numpy : 0.006195545196533203 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002186298370361328 time for calcul the mask position with numpy : 0.0062541961669921875 nb_pixel_total : 552 time to create 1 rle with old method : 0.0007257461547851562 time for calcul the mask position with numpy : 0.006008148193359375 nb_pixel_total : 56 time to create 1 rle with old method : 8.845329284667969e-05 time for calcul the mask position with numpy : 0.006056070327758789 nb_pixel_total : 262 time to create 1 rle with old method : 0.00032591819763183594 time for calcul the mask position with numpy : 0.0059964656829833984 nb_pixel_total : 105 time to create 1 rle with old method : 0.0001404285430908203 time for calcul the mask position with numpy : 0.0064487457275390625 nb_pixel_total : 798 time to create 1 rle with old method : 0.001026153564453125 time for calcul the mask position with numpy : 0.006135225296020508 nb_pixel_total : 1392 time to create 1 rle with old method : 0.0015916824340820312 time for calcul the mask position with numpy : 0.006132602691650391 nb_pixel_total : 119 time to create 1 rle with old method : 0.00016999244689941406 time for calcul the mask position with numpy : 0.006046295166015625 nb_pixel_total : 6103 time to create 1 rle with old method : 0.006876945495605469 time for calcul the mask position with numpy : 0.0058765411376953125 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002598762512207031 time for calcul the mask position with numpy : 0.0060503482818603516 nb_pixel_total : 3983 time to create 1 rle with old method : 0.004732847213745117 time for calcul the mask position with numpy : 0.007265567779541016 nb_pixel_total : 1462 time to create 1 rle with old method : 0.0021514892578125 time for calcul the mask position with numpy : 0.006552696228027344 nb_pixel_total : 217 time to create 1 rle with old method : 0.00039267539978027344 time for calcul the mask position with numpy : 0.006295442581176758 nb_pixel_total : 1100 time to create 1 rle with old method : 0.0013759136199951172 time for calcul the mask position with numpy : 0.0074748992919921875 nb_pixel_total : 768 time to create 1 rle with old method : 0.0009903907775878906 time for calcul the mask position with numpy : 0.006606101989746094 nb_pixel_total : 68 time to create 1 rle with old method : 0.00012159347534179688 time for calcul the mask position with numpy : 0.006698131561279297 nb_pixel_total : 2229 time to create 1 rle with old method : 0.0025734901428222656 time for calcul the mask position with numpy : 0.006155729293823242 nb_pixel_total : 349 time to create 1 rle with old method : 0.0004372596740722656 time for calcul the mask position with numpy : 0.006275177001953125 nb_pixel_total : 239 time to create 1 rle with old method : 0.0002846717834472656 time for calcul the mask position with numpy : 0.006147861480712891 nb_pixel_total : 251 time to create 1 rle with old method : 0.00030875205993652344 time for calcul the mask position with numpy : 0.006166696548461914 nb_pixel_total : 1623 time to create 1 rle with old method : 0.0018663406372070312 time for calcul the mask position with numpy : 0.006043910980224609 nb_pixel_total : 853 time to create 1 rle with old method : 0.0010044574737548828 time for calcul the mask position with numpy : 0.006047725677490234 nb_pixel_total : 2856 time to create 1 rle with old method : 0.0030977725982666016 time for calcul the mask position with numpy : 0.005902290344238281 nb_pixel_total : 573 time to create 1 rle with old method : 0.0007162094116210938 time for calcul the mask position with numpy : 0.0058515071868896484 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004367828369140625 time for calcul the mask position with numpy : 0.006746053695678711 nb_pixel_total : 104845 time to create 1 rle with old method : 0.11242842674255371 time for calcul the mask position with numpy : 0.006055355072021484 nb_pixel_total : 166 time to create 1 rle with old method : 0.00023555755615234375 time for calcul the mask position with numpy : 0.005904197692871094 nb_pixel_total : 578 time to create 1 rle with old method : 0.0006437301635742188 time for calcul the mask position with numpy : 0.005952596664428711 nb_pixel_total : 832 time to create 1 rle with old method : 0.0010523796081542969 time for calcul the mask position with numpy : 0.006066560745239258 nb_pixel_total : 303 time to create 1 rle with old method : 0.0003905296325683594 time for calcul the mask position with numpy : 0.00589752197265625 nb_pixel_total : 8 time to create 1 rle with old method : 4.506111145019531e-05 time for calcul the mask position with numpy : 0.0062220096588134766 nb_pixel_total : 1261 time to create 1 rle with old method : 0.0013675689697265625 time for calcul the mask position with numpy : 0.0059375762939453125 nb_pixel_total : 422 time to create 1 rle with old method : 0.000507354736328125 time for calcul the mask position with numpy : 0.006304025650024414 nb_pixel_total : 300 time to create 1 rle with old method : 0.00037097930908203125 time for calcul the mask position with numpy : 0.005990743637084961 nb_pixel_total : 4 time to create 1 rle with old method : 3.24249267578125e-05 time for calcul the mask position with numpy : 0.0060770511627197266 nb_pixel_total : 273 time to create 1 rle with old method : 0.00033211708068847656 time for calcul the mask position with numpy : 0.005965232849121094 nb_pixel_total : 210 time to create 1 rle with old method : 0.0002605915069580078 time for calcul the mask position with numpy : 0.005914926528930664 nb_pixel_total : 1704 time to create 1 rle with old method : 0.0018572807312011719 time for calcul the mask position with numpy : 0.006067752838134766 nb_pixel_total : 255 time to create 1 rle with old method : 0.0003180503845214844 time for calcul the mask position with numpy : 0.005852699279785156 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002281665802001953 time for calcul the mask position with numpy : 0.005940675735473633 nb_pixel_total : 2252 time to create 1 rle with old method : 0.0026443004608154297 time for calcul the mask position with numpy : 0.0064868927001953125 nb_pixel_total : 67 time to create 1 rle with old method : 0.0001010894775390625 time for calcul the mask position with numpy : 0.006300687789916992 nb_pixel_total : 448 time to create 1 rle with old method : 0.0005216598510742188 time for calcul the mask position with numpy : 0.006090641021728516 nb_pixel_total : 992 time to create 1 rle with old method : 0.0011818408966064453 time for calcul the mask position with numpy : 0.007168769836425781 nb_pixel_total : 210 time to create 1 rle with old method : 0.00024890899658203125 time for calcul the mask position with numpy : 0.006211042404174805 nb_pixel_total : 13 time to create 1 rle with old method : 4.076957702636719e-05 time for calcul the mask position with numpy : 0.006434202194213867 nb_pixel_total : 379 time to create 1 rle with old method : 0.00046181678771972656 time for calcul the mask position with numpy : 0.006227731704711914 nb_pixel_total : 326 time to create 1 rle with old method : 0.0003814697265625 time for calcul the mask position with numpy : 0.006182432174682617 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004374980926513672 time for calcul the mask position with numpy : 0.006404876708984375 nb_pixel_total : 2692 time to create 1 rle with old method : 0.0031359195709228516 time for calcul the mask position with numpy : 0.006318569183349609 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002155303955078125 create new chi : 0.879910945892334 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 : 0.0012614727020263672 batch 1 Loaded 80 chid ids of type : 4230 Number RLEs to save : 8463 TO DO : save crop sub photo not yet done ! save time : 0.5369126796722412 nb_obj : 67 nb_hashtags : 7 time to prepare the origin masks : 1.393261194229126 time for calcul the mask position with numpy : 0.017156600952148438 nb_pixel_total : 1655591 time to create 1 rle with new method : 0.03269624710083008 time for calcul the mask position with numpy : 0.00649714469909668 nb_pixel_total : 52362 time to create 1 rle with old method : 0.05583381652832031 time for calcul the mask position with numpy : 0.006416797637939453 nb_pixel_total : 1660 time to create 1 rle with old method : 0.0019483566284179688 time for calcul the mask position with numpy : 0.006204366683959961 nb_pixel_total : 902 time to create 1 rle with old method : 0.001129150390625 time for calcul the mask position with numpy : 0.006308317184448242 nb_pixel_total : 1682 time to create 1 rle with old method : 0.0021080970764160156 time for calcul the mask position with numpy : 0.006332874298095703 nb_pixel_total : 1066 time to create 1 rle with old method : 0.0012879371643066406 time for calcul the mask position with numpy : 0.006308078765869141 nb_pixel_total : 49 time to create 1 rle with old method : 0.00010991096496582031 time for calcul the mask position with numpy : 0.007561206817626953 nb_pixel_total : 126 time to create 1 rle with old method : 0.00018453598022460938 time for calcul the mask position with numpy : 0.006238460540771484 nb_pixel_total : 205 time to create 1 rle with old method : 0.00026035308837890625 time for calcul the mask position with numpy : 0.006546497344970703 nb_pixel_total : 2640 time to create 1 rle with old method : 0.003088712692260742 time for calcul the mask position with numpy : 0.006433010101318359 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011038780212402344 time for calcul the mask position with numpy : 0.006330013275146484 nb_pixel_total : 49 time to create 1 rle with old method : 8.106231689453125e-05 time for calcul the mask position with numpy : 0.006177425384521484 nb_pixel_total : 8 time to create 1 rle with old method : 4.2438507080078125e-05 time for calcul the mask position with numpy : 0.006383419036865234 nb_pixel_total : 101 time to create 1 rle with old method : 0.0001456737518310547 time for calcul the mask position with numpy : 0.006240129470825195 nb_pixel_total : 180 time to create 1 rle with old method : 0.00024962425231933594 time for calcul the mask position with numpy : 0.006216526031494141 nb_pixel_total : 1184 time to create 1 rle with old method : 0.0015406608581542969 time for calcul the mask position with numpy : 0.006033420562744141 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004622936248779297 time for calcul the mask position with numpy : 0.006104230880737305 nb_pixel_total : 713 time to create 1 rle with old method : 0.0008223056793212891 time for calcul the mask position with numpy : 0.0063245296478271484 nb_pixel_total : 518 time to create 1 rle with old method : 0.0006866455078125 time for calcul the mask position with numpy : 0.00626826286315918 nb_pixel_total : 1355 time to create 1 rle with old method : 0.0017125606536865234 time for calcul the mask position with numpy : 0.006557941436767578 nb_pixel_total : 860 time to create 1 rle with old method : 0.0011882781982421875 time for calcul the mask position with numpy : 0.0068471431732177734 nb_pixel_total : 152147 time to create 1 rle with new method : 0.030826330184936523 time for calcul the mask position with numpy : 0.0061833858489990234 nb_pixel_total : 1188 time to create 1 rle with old method : 0.0014574527740478516 time for calcul the mask position with numpy : 0.00615382194519043 nb_pixel_total : 660 time to create 1 rle with old method : 0.0007762908935546875 time for calcul the mask position with numpy : 0.0061647891998291016 nb_pixel_total : 175 time to create 1 rle with old method : 0.00021791458129882812 time for calcul the mask position with numpy : 0.0059964656829833984 nb_pixel_total : 66 time to create 1 rle with old method : 9.918212890625e-05 time for calcul the mask position with numpy : 0.006003856658935547 nb_pixel_total : 171 time to create 1 rle with old method : 0.00021886825561523438 time for calcul the mask position with numpy : 0.00603938102722168 nb_pixel_total : 834 time to create 1 rle with old method : 0.0009765625 time for calcul the mask position with numpy : 0.00603485107421875 nb_pixel_total : 695 time to create 1 rle with old method : 0.0009069442749023438 time for calcul the mask position with numpy : 0.0060083866119384766 nb_pixel_total : 7212 time to create 1 rle with old method : 0.008327960968017578 time for calcul the mask position with numpy : 0.0060329437255859375 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001480579376220703 time for calcul the mask position with numpy : 0.006209373474121094 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005290508270263672 time for calcul the mask position with numpy : 0.006957292556762695 nb_pixel_total : 993 time to create 1 rle with old method : 0.0011806488037109375 time for calcul the mask position with numpy : 0.007214546203613281 nb_pixel_total : 4878 time to create 1 rle with old method : 0.005381107330322266 time for calcul the mask position with numpy : 0.006228208541870117 nb_pixel_total : 712 time to create 1 rle with old method : 0.0009038448333740234 time for calcul the mask position with numpy : 0.00624847412109375 nb_pixel_total : 1107 time to create 1 rle with old method : 0.0013191699981689453 time for calcul the mask position with numpy : 0.006289243698120117 nb_pixel_total : 730 time to create 1 rle with old method : 0.0009992122650146484 time for calcul the mask position with numpy : 0.0064775943756103516 nb_pixel_total : 517 time to create 1 rle with old method : 0.0006349086761474609 time for calcul the mask position with numpy : 0.006361961364746094 nb_pixel_total : 31 time to create 1 rle with old method : 7.796287536621094e-05 time for calcul the mask position with numpy : 0.006290912628173828 nb_pixel_total : 1652 time to create 1 rle with old method : 0.0020155906677246094 time for calcul the mask position with numpy : 0.006407976150512695 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003223419189453125 time for calcul the mask position with numpy : 0.006232023239135742 nb_pixel_total : 1399 time to create 1 rle with old method : 0.001688241958618164 time for calcul the mask position with numpy : 0.006114482879638672 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003476142883300781 time for calcul the mask position with numpy : 0.0062673091888427734 nb_pixel_total : 1544 time to create 1 rle with old method : 0.0017838478088378906 time for calcul the mask position with numpy : 0.006183624267578125 nb_pixel_total : 566 time to create 1 rle with old method : 0.0006747245788574219 time for calcul the mask position with numpy : 0.0067365169525146484 nb_pixel_total : 106432 time to create 1 rle with old method : 0.11439180374145508 time for calcul the mask position with numpy : 0.006580352783203125 nb_pixel_total : 160 time to create 1 rle with old method : 0.00021910667419433594 time for calcul the mask position with numpy : 0.006227254867553711 nb_pixel_total : 540 time to create 1 rle with old method : 0.0006444454193115234 time for calcul the mask position with numpy : 0.0061528682708740234 nb_pixel_total : 918 time to create 1 rle with old method : 0.0010998249053955078 time for calcul the mask position with numpy : 0.006409406661987305 nb_pixel_total : 47924 time to create 1 rle with old method : 0.052886962890625 time for calcul the mask position with numpy : 0.007036685943603516 nb_pixel_total : 571 time to create 1 rle with old method : 0.0006773471832275391 time for calcul the mask position with numpy : 0.006156444549560547 nb_pixel_total : 79 time to create 1 rle with old method : 0.00011181831359863281 time for calcul the mask position with numpy : 0.006310462951660156 nb_pixel_total : 137 time to create 1 rle with old method : 0.00017786026000976562 time for calcul the mask position with numpy : 0.006030082702636719 nb_pixel_total : 1937 time to create 1 rle with old method : 0.0024871826171875 time for calcul the mask position with numpy : 0.006214618682861328 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003292560577392578 time for calcul the mask position with numpy : 0.006178617477416992 nb_pixel_total : 2098 time to create 1 rle with old method : 0.002475261688232422 time for calcul the mask position with numpy : 0.006345033645629883 nb_pixel_total : 884 time to create 1 rle with old method : 0.0010724067687988281 time for calcul the mask position with numpy : 0.006430149078369141 nb_pixel_total : 894 time to create 1 rle with old method : 0.001171112060546875 time for calcul the mask position with numpy : 0.006376504898071289 nb_pixel_total : 103 time to create 1 rle with old method : 0.0001380443572998047 time for calcul the mask position with numpy : 0.005986452102661133 nb_pixel_total : 150 time to create 1 rle with old method : 0.00020694732666015625 time for calcul the mask position with numpy : 0.00641632080078125 nb_pixel_total : 7396 time to create 1 rle with old method : 0.008472681045532227 time for calcul the mask position with numpy : 0.006223917007446289 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002491474151611328 time for calcul the mask position with numpy : 0.006126880645751953 nb_pixel_total : 152 time to create 1 rle with old method : 0.0001957416534423828 time for calcul the mask position with numpy : 0.00609135627746582 nb_pixel_total : 238 time to create 1 rle with old method : 0.00029969215393066406 time for calcul the mask position with numpy : 0.009940385818481445 nb_pixel_total : 408 time to create 1 rle with old method : 0.0005061626434326172 time for calcul the mask position with numpy : 0.006247520446777344 nb_pixel_total : 794 time to create 1 rle with old method : 0.0013148784637451172 time for calcul the mask position with numpy : 0.0062618255615234375 nb_pixel_total : 1085 time to create 1 rle with old method : 0.0016887187957763672 time for calcul the mask position with numpy : 0.006147146224975586 nb_pixel_total : 179 time to create 1 rle with old method : 0.0002257823944091797 create new chi : 0.8052513599395752 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 : 0.0017139911651611328 batch 1 Loaded 68 chid ids of type : 4230 Number RLEs to save : 8617 TO DO : save crop sub photo not yet done ! save time : 0.5394086837768555 map_output_result : {1334990972: (0.0, 'Should be the crop_list due to order', 0.0), 1334990941: (0.0, 'Should be the crop_list due to order', 0.0), 1334990938: (0.0, 'Should be the crop_list due to order', 0.0), 1334990936: (0.0, 'Should be the crop_list due to order', 0.0), 1334990932: (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 [1334990972, 1334990941, 1334990938, 1334990936, 1334990932] Looping around the photos to save general results len do output : 5 /1334990972.Didn't retrieve data . /1334990941.Didn't retrieve data . /1334990938.Didn't retrieve data . /1334990936.Didn't retrieve data . /1334990932.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, '2553113') ('4234', '20268404', '1334990972', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990941', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990938', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990936', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990932', None, None, None, None, None, '2553113') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.011859655380249023 save_final save missing photos in datou_result : time spend for datou_step_exec : 16.131492853164673 time spend to save output : 0.012191534042358398 total time spend for step 4 : 16.14368438720703 step5:crop_condition Wed Feb 5 18:21:25 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 395 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 ! map_result returned by crop_photo_return_map_crop : length : 115 About to insert : list_path_to_insert length 115 new photo from crops ! About to upload 115 photos upload in portfolio : 4869462 init cache_photo without model_param we have 115 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738776087_433571 we have uploaded 115 photos in the portfolio 4869462 time of upload the photos Elapsed time : 25.302799701690674 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 60 About to insert : list_path_to_insert length 60 new photo from crops ! About to upload 60 photos upload in portfolio : 4869462 init cache_photo without model_param we have 60 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738776113_433571 we have uploaded 60 photos in the portfolio 4869462 time of upload the photos Elapsed time : 15.471059322357178 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 ! Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 4869462 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738776129_433571 we have uploaded 4 photos in the portfolio 4869462 time of upload the photos Elapsed time : 1.7040283679962158 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 14 About to insert : list_path_to_insert length 14 new photo from crops ! About to upload 14 photos upload in portfolio : 4869462 init cache_photo without model_param we have 14 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738776131_433571 we have uploaded 14 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.085200548171997 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 ! map_result returned by crop_photo_return_map_crop : length : 77 About to insert : list_path_to_insert length 77 new photo from crops ! About to upload 77 photos upload in portfolio : 4869462 init cache_photo without model_param we have 77 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738776136_433571 we have uploaded 77 photos in the portfolio 4869462 time of upload the photos Elapsed time : 17.78202176094055 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 [1334990972, 1334990941, 1334990938, 1334990936, 1334990932] Looping around the photos to save general results len do output : 270 /1334995870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334995999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996136Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996137Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334996227Didn'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, '2553113') ('4234', '20268404', '1334990972', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990941', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990938', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990936', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990932', None, None, None, None, None, '2553113') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 815 time used for this insertion : 0.04421353340148926 save_final save missing photos in datou_result : time spend for datou_step_exec : 69.16704154014587 time spend to save output : 0.05192232131958008 total time spend for step 5 : 69.21896386146545 step6:thcl Wed Feb 5 18:22:34 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 : 0.0124664306640625 time to convert the images to numpy array : 0.07106637954711914 time to import caffe and check if the image exist : 0.015489816665649414 time to convert the images to numpy array : 0.08301949501037598 time to import caffe and check if the image exist : 0.026185274124145508 time to convert the images to numpy array : 0.07901406288146973 time to import caffe and check if the image exist : 0.02059316635131836 time to convert the images to numpy array : 0.08609247207641602 time to import caffe and check if the image exist : 0.027825117111206055 time to convert the images to numpy array : 0.08432555198669434 time to import caffe and check if the image exist : 0.02397465705871582 time to convert the images to numpy array : 0.08888459205627441 time to import caffe and check if the image exist : 0.024982213973999023 time to convert the images to numpy array : 0.08782601356506348 time to import caffe and check if the image exist : 0.03217816352844238 time to convert the images to numpy array : 0.08325624465942383 time to import caffe and check if the image exist : 0.028853416442871094 time to convert the images to numpy array : 0.08529353141784668 time to import caffe and check if the image exist : 0.030727148056030273 time to convert the images to numpy array : 0.08667707443237305 total time to convert the images to numpy array : 0.36754631996154785 list photo_ids error: [] list photo_ids correct : [1334995870, 1334995871, 1334995872, 1334995873, 1334995874, 1334995875, 1334995876, 1334995877, 1334995878, 1334995879, 1334995880, 1334995881, 1334995882, 1334995883, 1334995884, 1334995885, 1334995886, 1334995887, 1334995888, 1334995889, 1334995890, 1334995891, 1334995892, 1334995893, 1334995894, 1334995895, 1334995897, 1334996149, 1334996150, 1334996152, 1334996153, 1334996154, 1334996155, 1334996156, 1334996157, 1334996158, 1334996159, 1334996160, 1334996161, 1334996162, 1334996163, 1334996164, 1334996165, 1334996166, 1334996167, 1334996168, 1334996169, 1334996170, 1334996171, 1334996172, 1334996174, 1334996175, 1334996176, 1334996177, 1334996040, 1334996041, 1334996042, 1334996043, 1334996044, 1334996045, 1334996046, 1334996047, 1334996048, 1334996049, 1334996050, 1334996051, 1334996052, 1334996053, 1334996054, 1334996055, 1334996056, 1334996057, 1334996058, 1334996059, 1334996060, 1334996061, 1334996062, 1334996063, 1334996064, 1334996065, 1334996066, 1334996067, 1334996068, 1334996069, 1334996070, 1334996125, 1334996126, 1334996127, 1334996128, 1334996129, 1334996130, 1334996131, 1334996132, 1334996133, 1334996134, 1334996135, 1334996136, 1334996137, 1334996138, 1334996139, 1334996140, 1334996141, 1334996142, 1334996143, 1334996144, 1334996145, 1334996146, 1334996148, 1334995979, 1334995980, 1334995981, 1334995982, 1334995983, 1334995985, 1334995986, 1334995993, 1334995994, 1334995995, 1334995996, 1334995997, 1334995998, 1334995999, 1334996000, 1334996001, 1334996002, 1334996003, 1334996004, 1334996005, 1334996006, 1334996007, 1334996008, 1334996009, 1334996010, 1334996011, 1334996012, 1334995898, 1334995899, 1334995900, 1334995901, 1334995902, 1334995903, 1334995904, 1334995905, 1334995906, 1334995907, 1334995908, 1334995909, 1334995910, 1334995911, 1334995912, 1334995913, 1334995914, 1334995915, 1334995916, 1334995917, 1334995918, 1334995919, 1334995920, 1334995921, 1334995922, 1334995923, 1334995924, 1334996013, 1334996014, 1334996015, 1334996016, 1334996017, 1334996018, 1334996019, 1334996020, 1334996021, 1334996022, 1334996023, 1334996024, 1334996025, 1334996026, 1334996027, 1334996028, 1334996029, 1334996030, 1334996031, 1334996032, 1334996033, 1334996034, 1334996035, 1334996036, 1334996037, 1334996038, 1334996039, 1334995925, 1334995926, 1334995927, 1334995928, 1334995929, 1334995930, 1334995931, 1334995932, 1334995933, 1334995934, 1334995935, 1334995936, 1334995937, 1334995938, 1334995939, 1334995940, 1334995941, 1334995942, 1334995943, 1334995944, 1334995945, 1334995946, 1334995947, 1334995948, 1334995949, 1334995950, 1334995951, 1334996178, 1334996179, 1334996180, 1334996181, 1334996182, 1334996184, 1334996186, 1334996188, 1334996190, 1334996192, 1334996194, 1334996196, 1334996198, 1334996200, 1334996202, 1334996204, 1334996206, 1334996208, 1334996210, 1334996212, 1334996214, 1334996216, 1334996218, 1334996220, 1334996222, 1334996225, 1334996227, 1334995952, 1334995953, 1334995954, 1334995955, 1334995956, 1334995957, 1334995958, 1334995959, 1334995960, 1334995961, 1334995962, 1334995963, 1334995964, 1334995965, 1334995966, 1334995967, 1334995968, 1334995969, 1334995970, 1334995971, 1334995972, 1334995973, 1334995974, 1334995975, 1334995976, 1334995977, 1334995978] number of photos to traite : 270 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 : 3075 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 havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 2348 wait 20 seconds l 3637 free memory gpu now : 2348 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 1.3421614170074463 time used to do the prediction : 1.1113057136535645 save descriptor for thcl : 3237 time to traite the descriptors : 1.5587224960327148 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1334995870 To insert : 1334995871 To insert : 1334995872 To insert : 1334995873 To insert : 1334995874 To insert : 1334995875 To insert : 1334995876 To insert : 1334995877 To insert : 1334995878 To insert : 1334995879 To insert : 1334995880 To insert : 1334995881 To insert : 1334995882 To insert : 1334995883 To insert : 1334995884 To insert : 1334995885 To insert : 1334995886 To insert : 1334995887 To insert : 1334995888 To insert : 1334995889 To insert : 1334995890 To insert : 1334995891 To insert : 1334995892 To insert : 1334995893 To insert : 1334995894 To insert : 1334995895 To insert : 1334995897 To insert : 1334996149 To insert : 1334996150 To insert : 1334996152 To insert : 1334996153 To insert : 1334996154 To insert : 1334996155 To insert : 1334996156 To insert : 1334996157 To insert : 1334996158 To insert : 1334996159 To insert : 1334996160 To insert : 1334996161 To insert : 1334996162 To insert : 1334996163 To insert : 1334996164 To insert : 1334996165 To insert : 1334996166 To insert : 1334996167 To insert : 1334996168 To insert : 1334996169 To insert : 1334996170 To insert : 1334996171 To insert : 1334996172 To insert : 1334996174 To insert : 1334996175 To insert : 1334996176 To insert : 1334996177 To insert : 1334996040 To insert : 1334996041 To insert : 1334996042 To insert : 1334996043 To insert : 1334996044 To insert : 1334996045 To insert : 1334996046 To insert : 1334996047 To insert : 1334996048 To insert : 1334996049 To insert : 1334996050 To insert : 1334996051 To insert : 1334996052 To insert : 1334996053 To insert : 1334996054 To insert : 1334996055 To insert : 1334996056 To insert : 1334996057 To insert : 1334996058 To insert : 1334996059 To insert : 1334996060 To insert : 1334996061 To insert : 1334996062 To insert : 1334996063 To insert : 1334996064 To insert : 1334996065 To insert : 1334996066 To insert : 1334996067 To insert : 1334996068 To insert : 1334996069 To insert : 1334996070 To insert : 1334996125 To insert : 1334996126 To insert : 1334996127 To insert : 1334996128 To insert : 1334996129 To insert : 1334996130 To insert : 1334996131 To insert : 1334996132 To insert : 1334996133 To insert : 1334996134 To insert : 1334996135 To insert : 1334996136 To insert : 1334996137 To insert : 1334996138 To insert : 1334996139 To insert : 1334996140 To insert : 1334996141 To insert : 1334996142 To insert : 1334996143 To insert : 1334996144 To insert : 1334996145 To insert : 1334996146 To insert : 1334996148 To insert : 1334995979 To insert : 1334995980 To insert : 1334995981 To insert : 1334995982 To insert : 1334995983 To insert : 1334995985 To insert : 1334995986 To insert : 1334995993 To insert : 1334995994 To insert : 1334995995 To insert : 1334995996 To insert : 1334995997 To insert : 1334995998 To insert : 1334995999 To insert : 1334996000 To insert : 1334996001 To insert : 1334996002 To insert : 1334996003 To insert : 1334996004 To insert : 1334996005 To insert : 1334996006 To insert : 1334996007 To insert : 1334996008 To insert : 1334996009 To insert : 1334996010 To insert : 1334996011 To insert : 1334996012 To insert : 1334995898 To insert : 1334995899 To insert : 1334995900 To insert : 1334995901 To insert : 1334995902 To insert : 1334995903 To insert : 1334995904 To insert : 1334995905 To insert : 1334995906 To insert : 1334995907 To insert : 1334995908 To insert : 1334995909 To insert : 1334995910 To insert : 1334995911 To insert : 1334995912 To insert : 1334995913 To insert : 1334995914 To insert : 1334995915 To insert : 1334995916 To insert : 1334995917 To insert : 1334995918 To insert : 1334995919 To insert : 1334995920 To insert : 1334995921 To insert : 1334995922 To insert : 1334995923 To insert : 1334995924 To insert : 1334996013 To insert : 1334996014 To insert : 1334996015 To insert : 1334996016 To insert : 1334996017 To insert : 1334996018 To insert : 1334996019 To insert : 1334996020 To insert : 1334996021 To insert : 1334996022 To insert : 1334996023 To insert : 1334996024 To insert : 1334996025 To insert : 1334996026 To insert : 1334996027 To insert : 1334996028 To insert : 1334996029 To insert : 1334996030 To insert : 1334996031 To insert : 1334996032 To insert : 1334996033 To insert : 1334996034 To insert : 1334996035 To insert : 1334996036 To insert : 1334996037 To insert : 1334996038 To insert : 1334996039 To insert : 1334995925 To insert : 1334995926 To insert : 1334995927 To insert : 1334995928 To insert : 1334995929 To insert : 1334995930 To insert : 1334995931 To insert : 1334995932 To insert : 1334995933 To insert : 1334995934 To insert : 1334995935 To insert : 1334995936 To insert : 1334995937 To insert : 1334995938 To insert : 1334995939 To insert : 1334995940 To insert : 1334995941 To insert : 1334995942 To insert : 1334995943 To insert : 1334995944 To insert : 1334995945 To insert : 1334995946 To insert : 1334995947 To insert : 1334995948 To insert : 1334995949 To insert : 1334995950 To insert : 1334995951 To insert : 1334996178 To insert : 1334996179 To insert : 1334996180 To insert : 1334996181 To insert : 1334996182 To insert : 1334996184 To insert : 1334996186 To insert : 1334996188 To insert : 1334996190 To insert : 1334996192 To insert : 1334996194 To insert : 1334996196 To insert : 1334996198 To insert : 1334996200 To insert : 1334996202 To insert : 1334996204 To insert : 1334996206 To insert : 1334996208 To insert : 1334996210 To insert : 1334996212 To insert : 1334996214 To insert : 1334996216 To insert : 1334996218 To insert : 1334996220 To insert : 1334996222 To insert : 1334996225 To insert : 1334996227 To insert : 1334995952 To insert : 1334995953 To insert : 1334995954 To insert : 1334995955 To insert : 1334995956 To insert : 1334995957 To insert : 1334995958 To insert : 1334995959 To insert : 1334995960 To insert : 1334995961 To insert : 1334995962 To insert : 1334995963 To insert : 1334995964 To insert : 1334995965 To insert : 1334995966 To insert : 1334995967 To insert : 1334995968 To insert : 1334995969 To insert : 1334995970 To insert : 1334995971 To insert : 1334995972 To insert : 1334995973 To insert : 1334995974 To insert : 1334995975 To insert : 1334995976 To insert : 1334995977 To insert : 1334995978 time to insert the descriptors : 52.1929235458374 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 : 447 time used for this insertion : 0.035669565200805664 save missing photos in datou_result : time spend for datou_step_exec : 80.54851794242859 time spend to save output : 0.09012103080749512 total time spend for step 6 : 80.63863897323608 step7:ventilate_hashtags_in_portfolio Wed Feb 5 18:23:55 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure beginning of datou step ventilate_hashtags_in_portfolio : To implement ! Iterating over portfolio : 20268404 get user id for portfolio 20268404 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`=20268404 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Film_plastique','PEHD','papier','pet_clair','pehd','flou','carton','environnement','refus','mal_croppe','PET_clair','Tetrapak','autre','metal','PET_fonce','Carton','Papier','pet_fonce')) AND mptpi.`min_score`=0.6 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=20268404 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Film_plastique','PEHD','papier','pet_clair','pehd','flou','carton','environnement','refus','mal_croppe','PET_clair','Tetrapak','autre','metal','PET_fonce','Carton','Papier','pet_fonce')) AND mptpi.`min_score`=0.6 To do Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=20268404 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Film_plastique','PEHD','papier','pet_clair','pehd','flou','carton','environnement','refus','mal_croppe','PET_clair','Tetrapak','autre','metal','PET_fonce','Carton','Papier','pet_fonce')) AND mptpi.`min_score`=0.6 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=20268404 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Film_plastique','PEHD','papier','pet_clair','pehd','flou','carton','environnement','refus','mal_croppe','PET_clair','Tetrapak','autre','metal','PET_fonce','Carton','Papier','pet_fonce')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20268862,20268866,20268878,20268872,20268867,20268877,20268869,20268870,20268871,20268873,20268874,20268875,20268879?tags=film_plastique,pehd,papier,pet_clair,flou,carton,environnement,refus,mal_croppe,tetrapak,autre,metal,pet_fonce&datou_id_consolidate=4235&port_consolidate=20268404 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1334990972, 1334990941, 1334990938, 1334990936, 1334990932] Looping around the photos to save general results len do output : 1 /20268404. 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, '2553113') ('4234', '20268404', '1334990972', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990941', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990938', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990936', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990932', None, None, None, None, None, '2553113') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.014978170394897461 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.828181743621826 time spend to save output : 0.015295982360839844 total time spend for step 7 : 3.843477725982666 step8:final Wed Feb 5 18:23:59 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : {1334990972: ('0.20653110844289468',), 1334990941: ('0.20653110844289468',), 1334990938: ('0.20653110844289468',), 1334990936: ('0.20653110844289468',), 1334990932: ('0.20653110844289468',)} new output for save of step final : {1334990972: ('0.20653110844289468',), 1334990941: ('0.20653110844289468',), 1334990938: ('0.20653110844289468',), 1334990936: ('0.20653110844289468',), 1334990932: ('0.20653110844289468',)} [1334990972, 1334990941, 1334990938, 1334990936, 1334990932] Looping around the photos to save general results len do output : 5 /1334990972.Didn't retrieve data . /1334990941.Didn't retrieve data . /1334990938.Didn't retrieve data . /1334990936.Didn't retrieve data . /1334990932.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, '2553113') ('4234', '20268404', '1334990972', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990941', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990938', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990936', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990932', None, None, None, None, None, '2553113') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.01941967010498047 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.1226494312286377 time spend to save output : 0.01984119415283203 total time spend for step 8 : 0.14249062538146973 step9:velours_tree Wed Feb 5 18:23:59 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure list_portfolios : 20268862,20268866,20268878,20268872,20268867,20268877,20268869,20268870,20268871,20268873,20268874,20268875,20268879 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=20268862 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=20268866 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=20268878 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=20268872 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=20268867 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=20268877 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=20268869 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=20268870 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=20268871 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=20268873 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=20268874 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=20268875 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=20268879 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 270 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [1 0 5 0 0 0 0 0 0 0 2 0 2 2 0 1 2 0 0 2 0 0 1 0 5 0 0 3 1 0 1 0 0 1 0 0 0 0 0 2 0 0 1 1 2 2 0 0 0 0 1 0 5 4 0 0 1 0 2 1 0 0 0 0 0 0 0 2 2 2 0 0 0 0 0 0 1 2 0 0 0 1 0 0 2 0 0 2 2 0 0 0 0 0 0 0 1 5 2 0 0 0 0 0 0 0 2 2 0 1 0 0 0 0 0 2 4 0 3 4 4 0 0 0 0 2 1 2 1 1 4 3 2 4 2 0 0 4 0 4 0 2 1 4 3 4 2 0 0 4 0 0 2 0 3 0 4 3 4 4 0 0 0 0 1 1 1 4 3 4 4 0 0 0 1 0 0 0 0 0 2 0 2 0 0 0 0 0 2 0 0 1 0 1 2 1 3 4 0 2 0 2 2 0 2 0 2 1 2 2 0 1 2 1 0 0 2 3 0 2 0 2 2 2 2 2 0 2 1 1 0 2 2 3 4 0 2 2 2 0 2 2 0 1 2 2 0 3 0 2 0 0 0 2 2 2 0 1 2 1 2 0 2 3 4 0 2 2 2 2] Elapsed time: 0.044877052307128906 graph_id used : 76361 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20268862,20268866,20268878,20268872,20268867,20268877,20268869,20268870,20268871,20268873,20268874,20268875,20268879?tags=film_plastique,pehd,papier,pet_clair,flou,carton,environnement,refus,mal_croppe,tetrapak,autre,metal,pet_fonce&datou_id_consolidate=4235&port_consolidate=20268404&tree_id=76361 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1334990972, 1334990941, 1334990938, 1334990936, 1334990932] Looping around the photos to save general results len do output : 1 /20268404Didn'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, '2553113') ('4234', '20268404', '1334990972', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990941', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990938', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990936', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990932', None, None, None, None, None, '2553113') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.013260364532470703 save_final save missing photos in datou_result : time spend for datou_step_exec : 19.14032554626465 time spend to save output : 0.013549566268920898 total time spend for step 9 : 19.15387511253357 step10:send_mail_cod Wed Feb 5 18:24:18 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_P20268404_05-02-2025_18_24_18.pdf 20268844 imagette202688441738776258 20268848 imagette202688481738776258 20268860 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette202688601738776258 20268854 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette202688541738776259 20268849 imagette202688491738776260 20268859 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette202688591738776260 20268852 imagette202688521738776261 20268853 imagette202688531738776261 20268855 imagette202688551738776261 20268856 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette202688561738776261 20268857 change filename to text .change filename to text .change filename to text .change filename to text .imagette202688571738776262 20268861 imagette202688611738776262 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20268404 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20268862,20268866,20268878,20268872,20268867,20268877,20268869,20268870,20268871,20268873,20268874,20268875,20268879?tags=film_plastique,pehd,papier,pet_clair,flou,carton,environnement,refus,mal_croppe,tetrapak,autre,metal,pet_fonce&datou_id_consolidate=4235&port_consolidate=20268404&tree_id=76361 your option no_mail is active, we will not send the real mail to your client args[1334990972] : ((1334990972, -6.92635230303, 492609224), (1334990972, -0.8359706601978673, 501862349), '0.20653110844289468') apple ((1334990972, -6.92635230303, 492609224), (1334990972, -0.8359706601978673, 501862349), '0.20653110844289468') We are sending mail with results at cod@fotonower.com args[1334990941] : ((1334990941, -6.943749469681027, 492609224), (1334990941, -0.8100816719982847, 501862349), '0.20653110844289468') apple ((1334990941, -6.943749469681027, 492609224), (1334990941, -0.8100816719982847, 501862349), '0.20653110844289468') We are sending mail with results at cod@fotonower.com args[1334990938] : ((1334990938, -6.949658555806144, 492609224), (1334990938, -0.7914319912652441, 501862349), '0.20653110844289468') apple ((1334990938, -6.949658555806144, 492609224), (1334990938, -0.7914319912652441, 501862349), '0.20653110844289468') We are sending mail with results at cod@fotonower.com args[1334990936] : ((1334990936, -6.950415806091785, 492609224), (1334990936, -0.774083591709552, 501862349), '0.20653110844289468') apple ((1334990936, -6.950415806091785, 492609224), (1334990936, -0.774083591709552, 501862349), '0.20653110844289468') We are sending mail with results at cod@fotonower.com args[1334990932] : ((1334990932, -6.8961854312386635, 492609224), (1334990932, -0.7518738751919767, 501862349), '0.20653110844289468') apple ((1334990932, -6.8961854312386635, 492609224), (1334990932, -0.7518738751919767, 501862349), '0.20653110844289468') We are sending mail with results at cod@fotonower.com refus_total : 0.20653110844289468 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=20268404 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_P20268404_05-02-2025_18_24_18.pdf results_Qualipapia_P20268404_05-02-2025_18_24_18.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20268404_05-02-2025_18_24_18.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','20268404','results_Qualipapia_P20268404_05-02-2025_18_24_18.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20268404_05-02-2025_18_24_18.pdf','pdf','','0.17','0.20653110844289468') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1334990972, 1334990941, 1334990938, 1334990936, 1334990932] 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, '2553113') ('4234', '20268404', '1334990972', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990941', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990938', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990936', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990932', None, None, None, None, None, '2553113') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012964248657226562 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.290637493133545 time spend to save output : 0.01317596435546875 total time spend for step 10 : 5.303813457489014 step11:split_time_score Wed Feb 5 18:24:23 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 complete output_args for input 0 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 3442, 'mtr_user_id': 31, 'name': 'classifieur_2camions_valcor_021122_v1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'deux_camions,camion_droite,camion_gauche,pas_de_camion', 'svm_portfolios_learning': '7659379,7659034,7657685,7657114', 'photo_hashtag_type': 4458, 'photo_desc_type': 5723, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107760533,2107760534,2107760535,2107760536'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('15', 13),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 05022025 20268404 Nombre de photos uploadées : 13 / 23040 (0%) 05022025 20268404 Nombre de photos taguées (types de déchets): 13 / 13 (100%) 05022025 20268404 Nombre de photos taguées (volume) : 0 / 13 (0%) elapsed_time : load_data_split_time_score 5.245208740234375e-06 elapsed_time : order_list_meta_photo_and_scores 6.9141387939453125e-06 ????????????? elapsed_time : fill_and_build_computed_from_old_data 0.00060272216796875 elapsed_time : insert_dashboard_record_day_entry 0.023634910583496094 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 = 20256405 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20256408 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20256411 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20256413 order by id desc limit 1 Qualite : 0.261680923423937 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20256415_05-02-2025_12_47_56.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20256415 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`=20256415 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257100 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257102 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257104 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257106 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257107 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257108 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257110 order by id desc limit 1 Qualite : 0.13910553763920894 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20257112_05-02-2025_15_47_36.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257112 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`=20257112 AND mptpi.`type`=4230 To do Qualite : 0.15447490550984141 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20257114_05-02-2025_13_34_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257114 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`=20257114 AND mptpi.`type`=4230 To do Qualite : 0.17537954361119074 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20257116_05-02-2025_15_37_54.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257116 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`=20257116 AND mptpi.`type`=4230 To do Qualite : 0.1755375447284788 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20257118_05-02-2025_13_30_01.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257118 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`=20257118 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257645 order by id desc limit 1 Qualite : 0.17035650420251705 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20257647_05-02-2025_13_49_26.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20257647 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`=20257647 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20264776 order by id desc limit 1 Qualite : 0.2035277140763347 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20263670_05-02-2025_16_43_44.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20263670 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`=20263670 AND mptpi.`type`=4230 To do Qualite : 0.21553806376896342 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20263671_05-02-2025_16_07_54.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20263671 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`=20263671 AND mptpi.`type`=4230 To do Qualite : 0.19536132896941727 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20263672_05-02-2025_16_19_38.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20263672 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`=20263672 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20263673 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20264777 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20264778 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20264779 order by id desc limit 1 Qualite : 0.19859936113021315 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20264780_05-02-2025_16_49_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20264780 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`=20264780 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266804 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266805 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266806 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266807 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266808 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266037 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266039 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266041 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266043 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266045 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266047 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266049 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266054 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266056 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266058 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266060 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266062 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266064 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266066 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266069 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266071 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266072 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266073 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266074 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266809 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266810 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266811 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266812 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266814 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266817 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266075 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266077 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266078 order by id desc limit 1 Qualite : 0.1826699120141101 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20266080_05-02-2025_17_35_10.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266080 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`=20266080 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266082 order by id desc limit 1 Qualite : 0.17244981350823854 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20266084_05-02-2025_17_22_39.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266084 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`=20266084 AND mptpi.`type`=4230 To do Qualite : 0.20283218631561806 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20266086_05-02-2025_17_23_33.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266086 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`=20266086 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266819 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266821 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266823 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266825 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266827 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266830 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266832 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266834 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266836 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266838 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266840 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266842 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266844 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266846 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266848 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266849 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266850 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266851 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266852 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266853 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266854 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266855 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266856 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266857 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266858 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20266859 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268377 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268394 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268395 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268396 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268397 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268398 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268400 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268402 order by id desc limit 1 Qualite : 0.20653110844289468 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20268404_05-02-2025_18_24_18.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268404 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`=20268404 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20268407 order by id desc limit 1 NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'05022025': {'nb_upload': 13, 'nb_taggue_class': 13, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1334990972, 1334990941, 1334990938, 1334990936, 1334990932] Looping around the photos to save general results len do output : 1 /20268404Didn'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, '2553113') ('4234', '20268404', '1334990972', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990941', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990938', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990936', None, None, None, None, None, '2553113') ('4234', None, None, None, None, None, None, None, '2553113') ('4234', '20268404', '1334990932', None, None, None, None, None, '2553113') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.013485908508300781 save_final save missing photos in datou_result : time spend for datou_step_exec : 67.95851349830627 time spend to save output : 0.013704776763916016 total time spend for step 11 : 67.97221827507019 caffe_path_current : About to save ! 2 After save, about to update current ! update_current_state 55.00user 36.09system 5:05.67elapsed 29%CPU (0avgtext+0avgdata 2402092maxresident)k 465488inputs+17848outputs (193major+2298096minor)pagefaults 0swaps