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 : 1269041 load datou : 4234 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2628344'] with mtr_portfolio_ids : ['20966465'] and first list_photo_ids : [] new path : /proc/1269041/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.28261256217956543 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 Mon Mar 3 09:20:27 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 : 10814 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-03 09:20:30.394430: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-03 09:20:30.423166: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-03 09:20:30.425531: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fa8dc000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-03 09:20:30.425604: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-03 09:20:30.430136: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-03 09:20:30.676138: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x261ec6d0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-03 09:20:30.676201: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-03 09:20:30.677536: 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 2025-03-03 09:20:30.678019: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-03 09:20:30.681543: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-03 09:20:30.684810: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-03 09:20:30.685419: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-03 09:20:30.688842: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-03 09:20:30.690023: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-03 09:20:30.694966: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-03 09:20:30.696587: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-03 09:20:30.696693: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-03 09:20:30.697479: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-03 09:20:30.697496: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-03 09:20:30.697506: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-03 09:20:30.698926: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10023 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. 2025-03-03 09:20:30.962370: 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 2025-03-03 09:20:30.963113: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-03 09:20:30.963144: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-03 09:20:30.963167: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-03 09:20:30.963188: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-03 09:20:30.963209: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-03 09:20:30.963229: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-03 09:20:30.963252: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-03 09:20:30.964935: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-03 09:20:30.966845: 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 2025-03-03 09:20:30.966877: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-03 09:20:30.966892: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-03 09:20:30.966922: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-03 09:20:30.966937: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-03 09:20:30.966951: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-03 09:20:30.966965: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-03 09:20:30.966979: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-03 09:20:30.968176: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-03 09:20:30.968215: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-03 09:20:30.968223: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-03 09:20:30.968231: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-03 09:20:30.969476: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10023 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 : [] 2025-03-03 09:20:39.084675: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-03 09:20:39.302363: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 2 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 32.00000 max: 214.00000 molded_images shape: (1, 640, 640, 3) min: -88.91875 max: 104.62344 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: 254.00000 molded_images shape: (1, 640, 640, 3) min: -118.37578 max: 133.53750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 0.0001385211944580078 nb_pixel_total : 3935 time to create 1 rle with old method : 0.00493931770324707 length of segment : 155 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 1471 time to create 1 rle with old method : 0.0017879009246826172 length of segment : 115 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0009386539459228516 length of segment : 31 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.0004150867462158203 length of segment : 22 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1496 time to create 1 rle with old method : 0.001956939697265625 length of segment : 123 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1444 time to create 1 rle with old method : 0.001817941665649414 length of segment : 110 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.87578 max: 137.69766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1587 time to create 1 rle with old method : 0.0021562576293945312 length of segment : 39 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.00025463104248046875 length of segment : 18 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1172 time to create 1 rle with old method : 0.001623392105102539 length of segment : 44 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1427 time to create 1 rle with old method : 0.0018877983093261719 length of segment : 41 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.00029087066650390625 length of segment : 21 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00019431114196777344 length of segment : 11 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.73906 max: 138.89687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006601810455322266 length of segment : 22 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005025863647460938 length of segment : 21 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 432 time to create 1 rle with old method : 0.0006203651428222656 length of segment : 29 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0007586479187011719 length of segment : 48 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0006258487701416016 length of segment : 29 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005934238433837891 length of segment : 28 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.0010411739349365234 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.49297 max: 150.87734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.0003883838653564453 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.17266 max: 145.28750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00041675567626953125 nb_pixel_total : 11980 time to create 1 rle with old method : 0.015058517456054688 length of segment : 455 Processing 1 images image shape: (400, 160, 3) min: 65.00000 max: 138.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 27.00234 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: 14.00000 max: 247.00000 molded_images shape: (1, 640, 640, 3) min: -97.90313 max: 133.06484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 946 time to create 1 rle with old method : 0.0012767314910888672 length of segment : 85 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1759 time to create 1 rle with old method : 0.002262115478515625 length of segment : 47 time for calcul the mask position with numpy : 0.0001850128173828125 nb_pixel_total : 4133 time to create 1 rle with old method : 0.005475282669067383 length of segment : 130 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 823 time to create 1 rle with old method : 0.0015630722045898438 length of segment : 76 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 503 time to create 1 rle with old method : 0.0007464885711669922 length of segment : 24 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 1252 time to create 1 rle with old method : 0.0017554759979248047 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: -112.83672 max: 150.08828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004756450653076172 length of segment : 102 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 2251 time to create 1 rle with old method : 0.0028765201568603516 length of segment : 68 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 3255 time to create 1 rle with old method : 0.0041656494140625 length of segment : 57 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 825 time to create 1 rle with old method : 0.0011823177337646484 length of segment : 26 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 971 time to create 1 rle with old method : 0.0013031959533691406 length of segment : 75 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 3644 time to create 1 rle with old method : 0.004421710968017578 length of segment : 66 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0003008842468261719 length of segment : 20 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1297 time to create 1 rle with old method : 0.0017082691192626953 length of segment : 95 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 3598 time to create 1 rle with old method : 0.0045015811920166016 length of segment : 67 Processing 1 images image shape: (400, 400, 3) min: 8.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -105.21953 max: 150.60391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 867 time to create 1 rle with old method : 0.0011491775512695312 length of segment : 36 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004825592041015625 length of segment : 38 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1698 time to create 1 rle with old method : 0.002231121063232422 length of segment : 38 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003287792205810547 length of segment : 20 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.00067901611328125 length of segment : 16 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1207 time to create 1 rle with old method : 0.001560211181640625 length of segment : 48 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.0008046627044677734 length of segment : 32 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1511 time to create 1 rle with old method : 0.0019731521606445312 length of segment : 42 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1600 time to create 1 rle with old method : 0.002069711685180664 length of segment : 51 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.000949859619140625 length of segment : 27 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1237 time to create 1 rle with old method : 0.0015475749969482422 length of segment : 48 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0011467933654785156 length of segment : 47 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 2483 time to create 1 rle with old method : 0.003433704376220703 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 27.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -84.45781 max: 141.50234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 693 time to create 1 rle with old method : 0.0008709430694580078 length of segment : 42 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003845691680908203 length of segment : 13 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001571178436279297 length of segment : 14 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1595 time to create 1 rle with old method : 0.002038717269897461 length of segment : 39 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0004723072052001953 length of segment : 16 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1103 time to create 1 rle with old method : 0.0014801025390625 length of segment : 36 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 2250 time to create 1 rle with old method : 0.002938985824584961 length of segment : 87 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003960132598876953 length of segment : 16 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0008063316345214844 length of segment : 48 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.0010695457458496094 length of segment : 20 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004553794860839844 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 31.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -84.70781 max: 150.44375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.00061798095703125 length of segment : 13 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.0008015632629394531 length of segment : 29 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 579 time to create 1 rle with old method : 0.0007910728454589844 length of segment : 31 time for calcul the mask position with numpy : 0.0002167224884033203 nb_pixel_total : 817 time to create 1 rle with old method : 0.001329183578491211 length of segment : 116 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 2326 time to create 1 rle with old method : 0.002966642379760742 length of segment : 45 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 1443 time to create 1 rle with old method : 0.0019516944885253906 length of segment : 39 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002911090850830078 length of segment : 20 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00029540061950683594 length of segment : 18 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002789497375488281 length of segment : 12 time for calcul the mask position with numpy : 9.560585021972656e-05 nb_pixel_total : 2911 time to create 1 rle with old method : 0.0038497447967529297 length of segment : 85 time for calcul the mask position with numpy : 8.940696716308594e-05 nb_pixel_total : 696 time to create 1 rle with old method : 0.0014345645904541016 length of segment : 39 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0009129047393798828 length of segment : 26 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 2465 time to create 1 rle with old method : 0.003904104232788086 length of segment : 81 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0004334449768066406 length of segment : 31 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 847 time to create 1 rle with old method : 0.0013337135314941406 length of segment : 40 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 2201 time to create 1 rle with old method : 0.0030324459075927734 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 20.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.04766 max: 151.01797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 0.00013113021850585938 nb_pixel_total : 1424 time to create 1 rle with old method : 0.002310514450073242 length of segment : 57 time for calcul the mask position with numpy : 0.0001785755157470703 nb_pixel_total : 880 time to create 1 rle with old method : 0.0018463134765625 length of segment : 102 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0006093978881835938 length of segment : 22 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004513263702392578 length of segment : 59 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 1445 time to create 1 rle with old method : 0.0021257400512695312 length of segment : 59 time for calcul the mask position with numpy : 0.00013136863708496094 nb_pixel_total : 3093 time to create 1 rle with old method : 0.005465507507324219 length of segment : 97 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 550 time to create 1 rle with old method : 0.0009102821350097656 length of segment : 66 Processing 1 images image shape: (400, 160, 3) min: 41.00000 max: 239.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 117.89141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.00033926963806152344 length of segment : 15 Processing 1 images image shape: (400, 400, 3) min: 22.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -96.62578 max: 150.43203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0005190372467041016 length of segment : 35 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 727 time to create 1 rle with old method : 0.0010612010955810547 length of segment : 18 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002841949462890625 length of segment : 22 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0008244514465332031 length of segment : 29 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 690 time to create 1 rle with old method : 0.0009427070617675781 length of segment : 39 time for calcul the mask position with numpy : 0.00011205673217773438 nb_pixel_total : 3239 time to create 1 rle with old method : 0.004016399383544922 length of segment : 98 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 1075 time to create 1 rle with old method : 0.0013916492462158203 length of segment : 44 time for calcul the mask position with numpy : 0.00017261505126953125 nb_pixel_total : 4173 time to create 1 rle with old method : 0.005100250244140625 length of segment : 132 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 3195 time to create 1 rle with old method : 0.0039594173431396484 length of segment : 98 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 951 time to create 1 rle with old method : 0.0012323856353759766 length of segment : 40 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 529 time to create 1 rle with old method : 0.0007376670837402344 length of segment : 49 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0007302761077880859 length of segment : 39 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0005235671997070312 length of segment : 24 time for calcul the mask position with numpy : 0.00012993812561035156 nb_pixel_total : 3845 time to create 1 rle with old method : 0.0047872066497802734 length of segment : 152 Processing 1 images image shape: (400, 400, 3) min: 18.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.44609 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 9.989738464355469e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.0003676414489746094 length of segment : 7 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 30 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1627 time to create 1 rle with old method : 0.0021715164184570312 length of segment : 44 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.00020813941955566406 length of segment : 15 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 969 time to create 1 rle with old method : 0.0013003349304199219 length of segment : 39 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0008766651153564453 length of segment : 16 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0007021427154541016 length of segment : 23 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007097721099853516 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 24.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -80.69609 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 : 4.1484832763671875e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005662441253662109 length of segment : 34 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1831 time to create 1 rle with old method : 0.0022068023681640625 length of segment : 66 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1317 time to create 1 rle with old method : 0.001737356185913086 length of segment : 81 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 3051 time to create 1 rle with old method : 0.003753662109375 length of segment : 122 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0010912418365478516 length of segment : 41 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 861 time to create 1 rle with old method : 0.001188516616821289 length of segment : 30 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 1168 time to create 1 rle with old method : 0.001638174057006836 length of segment : 72 Processing 1 images image shape: (400, 400, 3) min: 38.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -74.03594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 624 time to create 1 rle with old method : 0.0008425712585449219 length of segment : 25 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0006842613220214844 length of segment : 21 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0007083415985107422 length of segment : 20 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.000484466552734375 length of segment : 13 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.0003235340118408203 length of segment : 18 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0004999637603759766 length of segment : 30 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 633 time to create 1 rle with old method : 0.0011284351348876953 length of segment : 29 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0006034374237060547 length of segment : 19 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 752 time to create 1 rle with old method : 0.0014147758483886719 length of segment : 36 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0004508495330810547 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.63750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 912 time to create 1 rle with old method : 0.0012316703796386719 length of segment : 37 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006339550018310547 length of segment : 28 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0005402565002441406 length of segment : 10 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00032830238342285156 length of segment : 15 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 63 time to create 1 rle with old method : 0.0001900196075439453 length of segment : 8 time for calcul the mask position with numpy : 0.0007112026214599609 nb_pixel_total : 30568 time to create 1 rle with old method : 0.054886579513549805 length of segment : 577 time for calcul the mask position with numpy : 0.000476837158203125 nb_pixel_total : 16056 time to create 1 rle with old method : 0.0194246768951416 length of segment : 477 Processing 1 images image shape: (400, 400, 3) min: 50.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -67.49688 max: 128.87969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 585 time to create 1 rle with old method : 0.0014538764953613281 length of segment : 30 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004210472106933594 length of segment : 33 Processing 1 images image shape: (400, 160, 3) min: 31.00000 max: 223.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 104.78984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 2022 time to create 1 rle with old method : 0.0024836063385009766 length of segment : 62 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1196 time to create 1 rle with old method : 0.0015742778778076172 length of segment : 46 Processing 1 images image shape: (240, 400, 3) min: 61.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.04141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 3516 time to create 1 rle with old method : 0.004642963409423828 length of segment : 34 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.0008096694946289062 length of segment : 25 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 922 time to create 1 rle with old method : 0.0012485980987548828 length of segment : 26 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 3149 time to create 1 rle with old method : 0.00392460823059082 length of segment : 69 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2845 time to create 1 rle with old method : 0.003407716751098633 length of segment : 70 Processing 1 images image shape: (240, 400, 3) min: 72.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (240, 400, 3) min: 25.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1084 time to create 1 rle with old method : 0.0013797283172607422 length of segment : 52 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1541 time to create 1 rle with old method : 0.002032756805419922 length of segment : 61 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0004398822784423828 length of segment : 22 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.00033354759216308594 length of segment : 20 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00023293495178222656 length of segment : 19 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.000232696533203125 length of segment : 17 time for calcul the mask position with numpy : 0.0003447532653808594 nb_pixel_total : 23400 time to create 1 rle with old method : 0.02881789207458496 length of segment : 142 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 769 time to create 1 rle with old method : 0.0009827613830566406 length of segment : 61 Processing 1 images image shape: (240, 400, 3) min: 48.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0008208751678466797 length of segment : 42 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1807 time to create 1 rle with old method : 0.003209829330444336 length of segment : 55 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 3673 time to create 1 rle with old method : 0.006577014923095703 length of segment : 65 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.001247406005859375 length of segment : 23 Processing 1 images image shape: (240, 400, 3) min: 59.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 1375 time to create 1 rle with old method : 0.0019152164459228516 length of segment : 35 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00033092498779296875 length of segment : 24 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1147 time to create 1 rle with old method : 0.001508474349975586 length of segment : 52 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 939 time to create 1 rle with old method : 0.0013225078582763672 length of segment : 24 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 2480 time to create 1 rle with old method : 0.003618955612182617 length of segment : 68 Processing 1 images image shape: (240, 400, 3) min: 58.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.45156 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 : 787 time to create 1 rle with old method : 0.0012896060943603516 length of segment : 57 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 2385 time to create 1 rle with old method : 0.0031647682189941406 length of segment : 47 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1023 time to create 1 rle with old method : 0.001422882080078125 length of segment : 62 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1513 time to create 1 rle with old method : 0.0018742084503173828 length of segment : 64 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0017664432525634766 length of segment : 75 Processing 1 images image shape: (240, 160, 3) min: 85.00000 max: 251.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 125.39785 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 35.00000 max: 213.00000 molded_images shape: (1, 640, 640, 3) min: -80.33672 max: 96.37734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.34063 max: 150.76406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1561 time to create 1 rle with old method : 0.0023522377014160156 length of segment : 110 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1543 time to create 1 rle with old method : 0.0024836063385009766 length of segment : 36 time for calcul the mask position with numpy : 0.00018405914306640625 nb_pixel_total : 4897 time to create 1 rle with old method : 0.0076296329498291016 length of segment : 179 time for calcul the mask position with numpy : 0.00010919570922851562 nb_pixel_total : 1625 time to create 1 rle with old method : 0.0022046566009521484 length of segment : 116 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0002574920654296875 length of segment : 12 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 1545 time to create 1 rle with old method : 0.0025517940521240234 length of segment : 49 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 1578 time to create 1 rle with old method : 0.0025217533111572266 length of segment : 115 Processing 1 images image shape: (400, 400, 3) min: 15.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -95.65313 max: 144.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 538 time to create 1 rle with old method : 0.0008139610290527344 length of segment : 33 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.0004413127899169922 length of segment : 16 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 1886 time to create 1 rle with old method : 0.003637075424194336 length of segment : 62 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1039 time to create 1 rle with old method : 0.0022313594818115234 length of segment : 31 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0004963874816894531 length of segment : 20 time for calcul the mask position with numpy : 0.00010180473327636719 nb_pixel_total : 2120 time to create 1 rle with old method : 0.004324674606323242 length of segment : 79 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 681 time to create 1 rle with old method : 0.0016026496887207031 length of segment : 40 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0003407001495361328 length of segment : 17 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 561 time to create 1 rle with old method : 0.0011124610900878906 length of segment : 34 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1074 time to create 1 rle with old method : 0.0020363330841064453 length of segment : 34 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 2015 time to create 1 rle with old method : 0.0037796497344970703 length of segment : 77 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0006964206695556641 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 9.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -98.61797 max: 148.54531 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 : 768 time to create 1 rle with old method : 0.0010228157043457031 length of segment : 30 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005371570587158203 length of segment : 25 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 590 time to create 1 rle with old method : 0.0008285045623779297 length of segment : 32 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0005922317504882812 length of segment : 43 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0005838871002197266 length of segment : 33 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1397 time to create 1 rle with old method : 0.0021238327026367188 length of segment : 35 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0004189014434814453 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -100.78984 max: 149.64687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003628730773925781 length of segment : 24 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1928 time to create 1 rle with old method : 0.002476215362548828 length of segment : 61 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 432 time to create 1 rle with old method : 0.0006463527679443359 length of segment : 27 time for calcul the mask position with numpy : 0.000148773193359375 nb_pixel_total : 628 time to create 1 rle with old method : 0.0010356903076171875 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 25.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -90.24688 max: 150.94375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 3512 time to create 1 rle with old method : 0.004872798919677734 length of segment : 86 time for calcul the mask position with numpy : 0.0003314018249511719 nb_pixel_total : 3920 time to create 1 rle with old method : 0.00466609001159668 length of segment : 118 time for calcul the mask position with numpy : 0.0003209114074707031 nb_pixel_total : 5411 time to create 1 rle with old method : 0.006631374359130859 length of segment : 266 Processing 1 images image shape: (400, 160, 3) min: 32.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.65078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.37188 max: 150.54922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.000762939453125 length of segment : 31 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1434 time to create 1 rle with old method : 0.0021092891693115234 length of segment : 73 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.0007815361022949219 length of segment : 27 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1566 time to create 1 rle with old method : 0.0020368099212646484 length of segment : 46 time for calcul the mask position with numpy : 0.0001976490020751953 nb_pixel_total : 6282 time to create 1 rle with old method : 0.008273601531982422 length of segment : 289 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1077 time to create 1 rle with old method : 0.001489877700805664 length of segment : 65 Processing 1 images image shape: (400, 400, 3) min: 4.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.35625 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 3069 time to create 1 rle with old method : 0.0038213729858398438 length of segment : 95 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 849 time to create 1 rle with old method : 0.0011353492736816406 length of segment : 27 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 586 time to create 1 rle with old method : 0.0008189678192138672 length of segment : 49 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 3536 time to create 1 rle with old method : 0.004315853118896484 length of segment : 64 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00027298927307128906 length of segment : 17 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 681 time to create 1 rle with old method : 0.0010418891906738281 length of segment : 34 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.00025916099548339844 length of segment : 16 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 709 time to create 1 rle with old method : 0.0009610652923583984 length of segment : 34 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2517 time to create 1 rle with old method : 0.003500699996948242 length of segment : 68 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 1089 time to create 1 rle with old method : 0.0015594959259033203 length of segment : 41 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 1083 time to create 1 rle with old method : 0.0015358924865722656 length of segment : 43 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 858 time to create 1 rle with old method : 0.001186370849609375 length of segment : 28 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 3625 time to create 1 rle with old method : 0.004377603530883789 length of segment : 64 Processing 1 images image shape: (400, 400, 3) min: 18.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -93.07891 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 570 time to create 1 rle with old method : 0.0008077621459960938 length of segment : 28 time for calcul the mask position with numpy : 8.559226989746094e-05 nb_pixel_total : 1253 time to create 1 rle with old method : 0.0016498565673828125 length of segment : 51 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 892 time to create 1 rle with old method : 0.0012066364288330078 length of segment : 38 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0003032684326171875 length of segment : 19 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1878 time to create 1 rle with old method : 0.0024275779724121094 length of segment : 36 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.0011169910430908203 length of segment : 37 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.0013494491577148438 length of segment : 34 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00044798851013183594 length of segment : 22 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0004851818084716797 length of segment : 23 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0005087852478027344 length of segment : 26 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.00045943260192871094 length of segment : 15 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006434917449951172 length of segment : 28 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0006563663482666016 length of segment : 25 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0005621910095214844 length of segment : 20 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 2789 time to create 1 rle with old method : 0.0035893917083740234 length of segment : 64 Processing 1 images image shape: (400, 400, 3) min: 39.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -72.89922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 726 time to create 1 rle with old method : 0.0009427070617675781 length of segment : 39 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1485 time to create 1 rle with old method : 0.0019519329071044922 length of segment : 51 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00038695335388183594 length of segment : 23 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.0001666545867919922 length of segment : 12 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1358 time to create 1 rle with old method : 0.001798868179321289 length of segment : 58 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004889965057373047 length of segment : 17 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0003197193145751953 length of segment : 11 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.00030994415283203125 length of segment : 11 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.00030684471130371094 length of segment : 22 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1839 time to create 1 rle with old method : 0.0024023056030273438 length of segment : 38 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1416 time to create 1 rle with old method : 0.0018911361694335938 length of segment : 31 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1656 time to create 1 rle with old method : 0.0022830963134765625 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 33.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -80.73516 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005273818969726562 length of segment : 31 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.00029277801513671875 length of segment : 14 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1865 time to create 1 rle with old method : 0.0024499893188476562 length of segment : 50 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 871 time to create 1 rle with old method : 0.00115966796875 length of segment : 39 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00034356117248535156 length of segment : 20 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 2381 time to create 1 rle with old method : 0.003134489059448242 length of segment : 50 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0007472038269042969 length of segment : 26 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2715 time to create 1 rle with old method : 0.004796743392944336 length of segment : 50 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 592 time to create 1 rle with old method : 0.0010280609130859375 length of segment : 17 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0006957054138183594 length of segment : 26 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 2827 time to create 1 rle with old method : 0.004888296127319336 length of segment : 54 time for calcul the mask position with numpy : 0.00010824203491210938 nb_pixel_total : 3143 time to create 1 rle with old method : 0.0040814876556396484 length of segment : 106 Processing 1 images image shape: (400, 400, 3) min: 31.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -90.02813 max: 150.41641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0003771781921386719 nb_pixel_total : 2662 time to create 1 rle with old method : 0.003316164016723633 length of segment : 194 Processing 1 images image shape: (400, 160, 3) min: 55.00000 max: 180.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 72.11172 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: 8.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -104.56719 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0004994869232177734 length of segment : 35 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 607 time to create 1 rle with old method : 0.0010495185852050781 length of segment : 35 time for calcul the mask position with numpy : 0.00022339820861816406 nb_pixel_total : 3023 time to create 1 rle with old method : 0.004556417465209961 length of segment : 99 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00024509429931640625 length of segment : 16 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.00106048583984375 length of segment : 44 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003085136413574219 length of segment : 29 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 874 time to create 1 rle with old method : 0.0011622905731201172 length of segment : 38 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 774 time to create 1 rle with old method : 0.001153707504272461 length of segment : 22 time for calcul the mask position with numpy : 0.00012612342834472656 nb_pixel_total : 4932 time to create 1 rle with old method : 0.0061435699462890625 length of segment : 144 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 343 time to create 1 rle with old method : 0.0005016326904296875 length of segment : 25 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 922 time to create 1 rle with old method : 0.0011789798736572266 length of segment : 40 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0007843971252441406 length of segment : 24 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0005946159362792969 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 13.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -102.88750 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 : 4.649162292480469e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005528926849365234 length of segment : 30 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.00021529197692871094 length of segment : 15 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0006256103515625 length of segment : 24 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0010595321655273438 length of segment : 40 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 700 time to create 1 rle with old method : 0.0014750957489013672 length of segment : 28 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 648 time to create 1 rle with old method : 0.0008704662322998047 length of segment : 42 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 779 time to create 1 rle with old method : 0.0011022090911865234 length of segment : 49 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1480 time to create 1 rle with old method : 0.002017974853515625 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 20.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -92.30938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 2232 time to create 1 rle with old method : 0.0028095245361328125 length of segment : 66 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 863 time to create 1 rle with old method : 0.0015938282012939453 length of segment : 63 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1040 time to create 1 rle with old method : 0.0019562244415283203 length of segment : 77 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0004467964172363281 length of segment : 48 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.00045037269592285156 length of segment : 12 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0005218982696533203 length of segment : 11 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 801 time to create 1 rle with old method : 0.0015380382537841797 length of segment : 31 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0007765293121337891 length of segment : 38 time for calcul the mask position with numpy : 0.00011587142944335938 nb_pixel_total : 2695 time to create 1 rle with old method : 0.005154848098754883 length of segment : 70 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1533 time to create 1 rle with old method : 0.0027284622192382812 length of segment : 47 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 954 time to create 1 rle with old method : 0.0018458366394042969 length of segment : 34 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.00029587745666503906 length of segment : 16 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007526874542236328 length of segment : 27 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 735 time to create 1 rle with old method : 0.001230478286743164 length of segment : 27 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 988 time to create 1 rle with old method : 0.0014050006866455078 length of segment : 51 Processing 1 images image shape: (400, 400, 3) min: 32.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -80.07109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.0006964206695556641 length of segment : 26 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0005815029144287109 length of segment : 23 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 2027 time to create 1 rle with old method : 0.0029997825622558594 length of segment : 36 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0003063678741455078 length of segment : 18 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0005788803100585938 length of segment : 44 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0004382133483886719 length of segment : 18 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.00044083595275878906 length of segment : 29 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0006656646728515625 length of segment : 16 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00031685829162597656 length of segment : 16 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 389 time to create 1 rle with old method : 0.0006372928619384766 length of segment : 13 time for calcul the mask position with numpy : 0.0001461505889892578 nb_pixel_total : 5693 time to create 1 rle with old method : 0.0073375701904296875 length of segment : 112 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.00018262863159179688 length of segment : 11 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 1827 time to create 1 rle with old method : 0.002405405044555664 length of segment : 84 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1322 time to create 1 rle with old method : 0.0019447803497314453 length of segment : 47 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0005550384521484375 length of segment : 20 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 1947 time to create 1 rle with old method : 0.002605438232421875 length of segment : 71 Processing 1 images image shape: (400, 400, 3) min: 43.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -68.52422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0007159709930419922 length of segment : 27 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001354217529296875 length of segment : 12 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1660 time to create 1 rle with old method : 0.002286672592163086 length of segment : 43 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005528926849365234 length of segment : 35 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009016990661621094 length of segment : 33 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 613 time to create 1 rle with old method : 0.0011081695556640625 length of segment : 48 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0004215240478515625 length of segment : 11 time for calcul the mask position with numpy : 0.0003750324249267578 nb_pixel_total : 1698 time to create 1 rle with old method : 0.002331972122192383 length of segment : 125 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0007317066192626953 length of segment : 24 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0007205009460449219 length of segment : 16 time for calcul the mask position with numpy : 0.0004367828369140625 nb_pixel_total : 4728 time to create 1 rle with old method : 0.006432533264160156 length of segment : 257 Processing 1 images image shape: (400, 400, 3) min: 43.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -62.55938 max: 142.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0008561611175537109 length of segment : 32 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004222393035888672 length of segment : 28 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0009758472442626953 length of segment : 18 Processing 1 images image shape: (400, 160, 3) min: 61.00000 max: 184.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 67.17031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (240, 400, 3) min: 49.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.08437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003910064697265625 length of segment : 21 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 941 time to create 1 rle with old method : 0.0012483596801757812 length of segment : 28 time for calcul the mask position with numpy : 0.00011324882507324219 nb_pixel_total : 3146 time to create 1 rle with old method : 0.006028890609741211 length of segment : 32 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 2248 time to create 1 rle with old method : 0.0029120445251464844 length of segment : 97 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 3244 time to create 1 rle with old method : 0.003997087478637695 length of segment : 76 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 3042 time to create 1 rle with old method : 0.0038824081420898438 length of segment : 88 Processing 1 images image shape: (240, 400, 3) min: 55.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (240, 400, 3) min: 18.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2120 time to create 1 rle with old method : 0.0027196407318115234 length of segment : 89 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 668 time to create 1 rle with old method : 0.0009129047393798828 length of segment : 39 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0005331039428710938 length of segment : 22 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 511 time to create 1 rle with old method : 0.0006899833679199219 length of segment : 39 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001926422119140625 length of segment : 25 time for calcul the mask position with numpy : 0.0007224082946777344 nb_pixel_total : 73784 time to create 1 rle with old method : 0.11175060272216797 length of segment : 238 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1078 time to create 1 rle with old method : 0.0014507770538330078 length of segment : 47 Processing 1 images image shape: (240, 400, 3) min: 57.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1974 time to create 1 rle with old method : 0.002413511276245117 length of segment : 58 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 673 time to create 1 rle with old method : 0.0009276866912841797 length of segment : 32 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 165 time to create 1 rle with old method : 0.000293731689453125 length of segment : 15 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006475448608398438 length of segment : 24 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0003979206085205078 length of segment : 22 Processing 1 images image shape: (240, 400, 3) min: 46.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1443 time to create 1 rle with old method : 0.0025818347930908203 length of segment : 53 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1306 time to create 1 rle with old method : 0.0025124549865722656 length of segment : 39 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0004658699035644531 length of segment : 26 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0008893013000488281 length of segment : 17 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 1056 time to create 1 rle with old method : 0.0024242401123046875 length of segment : 56 Processing 1 images image shape: (240, 400, 3) min: 52.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.48672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 3500 time to create 1 rle with old method : 0.004831552505493164 length of segment : 64 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 683 time to create 1 rle with old method : 0.0009148120880126953 length of segment : 62 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1380 time to create 1 rle with old method : 0.001752614974975586 length of segment : 59 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1411 time to create 1 rle with old method : 0.0017745494842529297 length of segment : 63 Processing 1 images image shape: (240, 160, 3) min: 94.00000 max: 206.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 79.80102 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0010750293731689453 length of segment : 45 Detection mask done ! Trying to reset tf kernel 1269839 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5525 tf kernel not reseted sub process len(results) : 347 len(list_Values) 347 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 347 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 : 10814 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 347 chid ids of type : 4228 Number RLEs to save : 17461 save missing photos in datou_result : time spend for datou_step_exec : 27.667256355285645 time spend to save output : 1.190375566482544 total time spend for step 1 : 28.85763192176819 step2:brightness Mon Mar 3 09:20:56 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/1740990027_1269041_1340594502_a27a50ff7be5a0ad58895c042edb0c96.jpg treat image : temp/1740990027_1269041_1340592503_357959e384256c06c6b582bcda30093d.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 2 time used for this insertion : 0.01195383071899414 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.010687112808227539 save missing photos in datou_result : time spend for datou_step_exec : 0.8191988468170166 time spend to save output : 0.02758622169494629 total time spend for step 2 : 0.8467850685119629 step3:blur_detection Mon Mar 3 09:20:57 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/1740990027_1269041_1340594502_a27a50ff7be5a0ad58895c042edb0c96.jpg resize: (1440, 2560) 1340594502 -6.308313052053489 treat image : temp/1740990027_1269041_1340592503_357959e384256c06c6b582bcda30093d.jpg resize: (1440, 2560) 1340592503 -6.837232459615305 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 2 time used for this insertion : 0.0126190185546875 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.01113128662109375 save missing photos in datou_result : time spend for datou_step_exec : 3.6628260612487793 time spend to save output : 0.02827930450439453 total time spend for step 3 : 3.691105365753174 step4:rle_unique_nms_with_priority Mon Mar 3 09:21:00 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 347 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 161 nb_hashtags : 7 time to prepare the origin masks : 1.7550914287567139 time for calcul the mask position with numpy : 0.4354667663574219 nb_pixel_total : 3486970 time to create 1 rle with new method : 0.4080088138580322 time for calcul the mask position with numpy : 0.014729976654052734 nb_pixel_total : 348 time to create 1 rle with old method : 0.00042557716369628906 time for calcul the mask position with numpy : 0.014911651611328125 nb_pixel_total : 11980 time to create 1 rle with old method : 0.014547109603881836 time for calcul the mask position with numpy : 0.015501022338867188 nb_pixel_total : 152 time to create 1 rle with old method : 0.00021696090698242188 time for calcul the mask position with numpy : 0.015453100204467773 nb_pixel_total : 587 time to create 1 rle with old method : 0.0007386207580566406 time for calcul the mask position with numpy : 0.018176555633544922 nb_pixel_total : 721 time to create 1 rle with old method : 0.0008652210235595703 time for calcul the mask position with numpy : 0.014801502227783203 nb_pixel_total : 432 time to create 1 rle with old method : 0.0005247592926025391 time for calcul the mask position with numpy : 0.01659560203552246 nb_pixel_total : 100 time to create 1 rle with old method : 0.00014281272888183594 time for calcul the mask position with numpy : 0.01553964614868164 nb_pixel_total : 1587 time to create 1 rle with old method : 0.0019333362579345703 time for calcul the mask position with numpy : 0.0158693790435791 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005667209625244141 time for calcul the mask position with numpy : 0.015574932098388672 nb_pixel_total : 451 time to create 1 rle with old method : 0.000568389892578125 time for calcul the mask position with numpy : 0.015288114547729492 nb_pixel_total : 10 time to create 1 rle with old method : 3.457069396972656e-05 time for calcul the mask position with numpy : 0.015986204147338867 nb_pixel_total : 266 time to create 1 rle with old method : 0.0003437995910644531 time for calcul the mask position with numpy : 0.015309572219848633 nb_pixel_total : 1172 time to create 1 rle with old method : 0.001432657241821289 time for calcul the mask position with numpy : 0.015521764755249023 nb_pixel_total : 95 time to create 1 rle with old method : 0.00017333030700683594 time for calcul the mask position with numpy : 0.015334367752075195 nb_pixel_total : 35 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.015128612518310547 nb_pixel_total : 1471 time to create 1 rle with old method : 0.001626729965209961 time for calcul the mask position with numpy : 0.014772176742553711 nb_pixel_total : 3935 time to create 1 rle with old method : 0.004546165466308594 time for calcul the mask position with numpy : 0.014966487884521484 nb_pixel_total : 1427 time to create 1 rle with old method : 0.0017430782318115234 time for calcul the mask position with numpy : 0.015003204345703125 nb_pixel_total : 548 time to create 1 rle with old method : 0.000690460205078125 time for calcul the mask position with numpy : 0.015256166458129883 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002815723419189453 time for calcul the mask position with numpy : 0.015608549118041992 nb_pixel_total : 221 time to create 1 rle with old method : 0.0002968311309814453 time for calcul the mask position with numpy : 0.015136957168579102 nb_pixel_total : 579 time to create 1 rle with old method : 0.000698089599609375 time for calcul the mask position with numpy : 0.014714717864990234 nb_pixel_total : 80 time to create 1 rle with old method : 0.00015497207641601562 time for calcul the mask position with numpy : 0.01569390296936035 nb_pixel_total : 880 time to create 1 rle with old method : 0.001018524169921875 time for calcul the mask position with numpy : 0.015837907791137695 nb_pixel_total : 202 time to create 1 rle with old method : 0.00023603439331054688 time for calcul the mask position with numpy : 0.014801979064941406 nb_pixel_total : 35 time to create 1 rle with old method : 8.606910705566406e-05 time for calcul the mask position with numpy : 0.016198396682739258 nb_pixel_total : 1698 time to create 1 rle with old method : 0.002638101577758789 time for calcul the mask position with numpy : 0.015213727951049805 nb_pixel_total : 16 time to create 1 rle with old method : 5.6743621826171875e-05 time for calcul the mask position with numpy : 0.015155553817749023 nb_pixel_total : 237 time to create 1 rle with old method : 0.00031375885009765625 time for calcul the mask position with numpy : 0.015171527862548828 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004119873046875 time for calcul the mask position with numpy : 0.014940023422241211 nb_pixel_total : 390 time to create 1 rle with old method : 0.0006010532379150391 time for calcul the mask position with numpy : 0.015254735946655273 nb_pixel_total : 353 time to create 1 rle with old method : 0.0004818439483642578 time for calcul the mask position with numpy : 0.015064239501953125 nb_pixel_total : 90 time to create 1 rle with old method : 0.000125885009765625 time for calcul the mask position with numpy : 0.014809370040893555 nb_pixel_total : 546 time to create 1 rle with old method : 0.0007781982421875 time for calcul the mask position with numpy : 0.015189886093139648 nb_pixel_total : 1595 time to create 1 rle with old method : 0.0019097328186035156 time for calcul the mask position with numpy : 0.014939546585083008 nb_pixel_total : 159 time to create 1 rle with old method : 0.00021505355834960938 time for calcul the mask position with numpy : 0.01511836051940918 nb_pixel_total : 1600 time to create 1 rle with old method : 0.0019867420196533203 time for calcul the mask position with numpy : 0.014980792999267578 nb_pixel_total : 324 time to create 1 rle with old method : 0.00038909912109375 time for calcul the mask position with numpy : 0.015044450759887695 nb_pixel_total : 2911 time to create 1 rle with old method : 0.0034477710723876953 time for calcul the mask position with numpy : 0.014715194702148438 nb_pixel_total : 312 time to create 1 rle with old method : 0.00036787986755371094 time for calcul the mask position with numpy : 0.014882802963256836 nb_pixel_total : 69 time to create 1 rle with old method : 0.00011110305786132812 time for calcul the mask position with numpy : 0.015245199203491211 nb_pixel_total : 825 time to create 1 rle with old method : 0.0010006427764892578 time for calcul the mask position with numpy : 0.01548910140991211 nb_pixel_total : 299 time to create 1 rle with old method : 0.000537872314453125 time for calcul the mask position with numpy : 0.0156400203704834 nb_pixel_total : 358 time to create 1 rle with old method : 0.0004715919494628906 time for calcul the mask position with numpy : 0.014705896377563477 nb_pixel_total : 971 time to create 1 rle with old method : 0.0011756420135498047 time for calcul the mask position with numpy : 0.014434337615966797 nb_pixel_total : 594 time to create 1 rle with old method : 0.0006682872772216797 time for calcul the mask position with numpy : 0.015117883682250977 nb_pixel_total : 867 time to create 1 rle with old method : 0.0010333061218261719 time for calcul the mask position with numpy : 0.014663934707641602 nb_pixel_total : 443 time to create 1 rle with old method : 0.0004954338073730469 time for calcul the mask position with numpy : 0.014640092849731445 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002892017364501953 time for calcul the mask position with numpy : 0.014652013778686523 nb_pixel_total : 578 time to create 1 rle with old method : 0.0006718635559082031 time for calcul the mask position with numpy : 0.014422416687011719 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002467632293701172 time for calcul the mask position with numpy : 0.014914989471435547 nb_pixel_total : 1443 time to create 1 rle with old method : 0.0017788410186767578 time for calcul the mask position with numpy : 0.014864921569824219 nb_pixel_total : 2483 time to create 1 rle with old method : 0.003049135208129883 time for calcul the mask position with numpy : 0.014872074127197266 nb_pixel_total : 847 time to create 1 rle with old method : 0.0010755062103271484 time for calcul the mask position with numpy : 0.014960527420043945 nb_pixel_total : 191 time to create 1 rle with old method : 0.00028133392333984375 time for calcul the mask position with numpy : 0.014991283416748047 nb_pixel_total : 2250 time to create 1 rle with old method : 0.002718210220336914 time for calcul the mask position with numpy : 0.015289783477783203 nb_pixel_total : 1103 time to create 1 rle with old method : 0.001321554183959961 time for calcul the mask position with numpy : 0.015181303024291992 nb_pixel_total : 817 time to create 1 rle with old method : 0.0011332035064697266 time for calcul the mask position with numpy : 0.0162966251373291 nb_pixel_total : 65 time to create 1 rle with old method : 0.00017309188842773438 time for calcul the mask position with numpy : 0.02932262420654297 nb_pixel_total : 1207 time to create 1 rle with old method : 0.002300262451171875 time for calcul the mask position with numpy : 0.017731904983520508 nb_pixel_total : 696 time to create 1 rle with old method : 0.0011181831359863281 time for calcul the mask position with numpy : 0.01551055908203125 nb_pixel_total : 2251 time to create 1 rle with old method : 0.0027039051055908203 time for calcul the mask position with numpy : 0.015167474746704102 nb_pixel_total : 4015 time to create 1 rle with old method : 0.0047533512115478516 time for calcul the mask position with numpy : 0.015665054321289062 nb_pixel_total : 3093 time to create 1 rle with old method : 0.004061460494995117 time for calcul the mask position with numpy : 0.015651226043701172 nb_pixel_total : 2326 time to create 1 rle with old method : 0.002800464630126953 time for calcul the mask position with numpy : 0.015668869018554688 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004456043243408203 time for calcul the mask position with numpy : 0.015457630157470703 nb_pixel_total : 437 time to create 1 rle with old method : 0.0008165836334228516 time for calcul the mask position with numpy : 0.015364408493041992 nb_pixel_total : 417 time to create 1 rle with old method : 0.0005884170532226562 time for calcul the mask position with numpy : 0.018137693405151367 nb_pixel_total : 3255 time to create 1 rle with old method : 0.003902912139892578 time for calcul the mask position with numpy : 0.015615463256835938 nb_pixel_total : 946 time to create 1 rle with old method : 0.0011949539184570312 time for calcul the mask position with numpy : 0.01493978500366211 nb_pixel_total : 298 time to create 1 rle with old method : 0.00040459632873535156 time for calcul the mask position with numpy : 0.015434503555297852 nb_pixel_total : 16 time to create 1 rle with old method : 5.269050598144531e-05 time for calcul the mask position with numpy : 0.014704465866088867 nb_pixel_total : 117 time to create 1 rle with old method : 0.0001583099365234375 time for calcul the mask position with numpy : 0.01474618911743164 nb_pixel_total : 29 time to create 1 rle with old method : 7.748603820800781e-05 time for calcul the mask position with numpy : 0.01613593101501465 nb_pixel_total : 66 time to create 1 rle with old method : 0.00010251998901367188 time for calcul the mask position with numpy : 0.015640735626220703 nb_pixel_total : 1424 time to create 1 rle with old method : 0.0016622543334960938 time for calcul the mask position with numpy : 0.01538395881652832 nb_pixel_total : 688 time to create 1 rle with old method : 0.0008947849273681641 time for calcul the mask position with numpy : 0.015976428985595703 nb_pixel_total : 195 time to create 1 rle with old method : 0.00024819374084472656 time for calcul the mask position with numpy : 0.015369415283203125 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005102157592773438 time for calcul the mask position with numpy : 0.015274286270141602 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005164146423339844 time for calcul the mask position with numpy : 0.015187978744506836 nb_pixel_total : 1759 time to create 1 rle with old method : 0.0026977062225341797 time for calcul the mask position with numpy : 0.016264677047729492 nb_pixel_total : 693 time to create 1 rle with old method : 0.0008435249328613281 time for calcul the mask position with numpy : 0.015417098999023438 nb_pixel_total : 1252 time to create 1 rle with old method : 0.0016286373138427734 time for calcul the mask position with numpy : 0.015061616897583008 nb_pixel_total : 578 time to create 1 rle with old method : 0.0009012222290039062 time for calcul the mask position with numpy : 0.015602588653564453 nb_pixel_total : 293 time to create 1 rle with old method : 0.00040030479431152344 time for calcul the mask position with numpy : 0.015526533126831055 nb_pixel_total : 180 time to create 1 rle with old method : 0.0003781318664550781 time for calcul the mask position with numpy : 0.01639556884765625 nb_pixel_total : 633 time to create 1 rle with old method : 0.0010819435119628906 time for calcul the mask position with numpy : 0.01610851287841797 nb_pixel_total : 525 time to create 1 rle with old method : 0.0011477470397949219 time for calcul the mask position with numpy : 0.019511938095092773 nb_pixel_total : 30096 time to create 1 rle with old method : 0.044217824935913086 time for calcul the mask position with numpy : 0.014836788177490234 nb_pixel_total : 128 time to create 1 rle with old method : 0.00016236305236816406 time for calcul the mask position with numpy : 0.014828920364379883 nb_pixel_total : 507 time to create 1 rle with old method : 0.000606536865234375 time for calcul the mask position with numpy : 0.014868021011352539 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002307891845703125 time for calcul the mask position with numpy : 0.01493525505065918 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002262592315673828 time for calcul the mask position with numpy : 0.014909505844116211 nb_pixel_total : 402 time to create 1 rle with old method : 0.00046896934509277344 time for calcul the mask position with numpy : 0.014933109283447266 nb_pixel_total : 156 time to create 1 rle with old method : 0.00019073486328125 time for calcul the mask position with numpy : 0.015799760818481445 nb_pixel_total : 690 time to create 1 rle with old method : 0.0010042190551757812 time for calcul the mask position with numpy : 0.015115499496459961 nb_pixel_total : 291 time to create 1 rle with old method : 0.0003516674041748047 time for calcul the mask position with numpy : 0.014968395233154297 nb_pixel_total : 528 time to create 1 rle with old method : 0.0006203651428222656 time for calcul the mask position with numpy : 0.014877796173095703 nb_pixel_total : 1075 time to create 1 rle with old method : 0.0012221336364746094 time for calcul the mask position with numpy : 0.014873504638671875 nb_pixel_total : 752 time to create 1 rle with old method : 0.0008792877197265625 time for calcul the mask position with numpy : 0.015311717987060547 nb_pixel_total : 191 time to create 1 rle with old method : 0.00038886070251464844 time for calcul the mask position with numpy : 0.01516103744506836 nb_pixel_total : 4173 time to create 1 rle with old method : 0.004683971405029297 time for calcul the mask position with numpy : 0.014944076538085938 nb_pixel_total : 18 time to create 1 rle with old method : 3.409385681152344e-05 time for calcul the mask position with numpy : 0.014947175979614258 nb_pixel_total : 2022 time to create 1 rle with old method : 0.002315998077392578 time for calcul the mask position with numpy : 0.015029191970825195 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003426074981689453 time for calcul the mask position with numpy : 0.014919281005859375 nb_pixel_total : 559 time to create 1 rle with old method : 0.0006580352783203125 time for calcul the mask position with numpy : 0.014925241470336914 nb_pixel_total : 358 time to create 1 rle with old method : 0.0004410743713378906 time for calcul the mask position with numpy : 0.014843225479125977 nb_pixel_total : 1196 time to create 1 rle with old method : 0.0013713836669921875 time for calcul the mask position with numpy : 0.014849424362182617 nb_pixel_total : 377 time to create 1 rle with old method : 0.0004467964172363281 time for calcul the mask position with numpy : 0.014762401580810547 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0014615058898925781 time for calcul the mask position with numpy : 0.01487421989440918 nb_pixel_total : 40 time to create 1 rle with old method : 0.00014209747314453125 time for calcul the mask position with numpy : 0.014914989471435547 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005209445953369141 time for calcul the mask position with numpy : 0.014925241470336914 nb_pixel_total : 301 time to create 1 rle with old method : 0.00035858154296875 time for calcul the mask position with numpy : 0.014829397201538086 nb_pixel_total : 3239 time to create 1 rle with old method : 0.0037703514099121094 time for calcul the mask position with numpy : 0.014946460723876953 nb_pixel_total : 27 time to create 1 rle with old method : 0.00011706352233886719 time for calcul the mask position with numpy : 0.014885902404785156 nb_pixel_total : 1627 time to create 1 rle with old method : 0.0018811225891113281 time for calcul the mask position with numpy : 0.014828205108642578 nb_pixel_total : 330 time to create 1 rle with old method : 0.00042819976806640625 time for calcul the mask position with numpy : 0.014904260635375977 nb_pixel_total : 806 time to create 1 rle with old method : 0.0009369850158691406 time for calcul the mask position with numpy : 0.01489877700805664 nb_pixel_total : 727 time to create 1 rle with old method : 0.0008771419525146484 time for calcul the mask position with numpy : 0.014912843704223633 nb_pixel_total : 8 time to create 1 rle with old method : 3.600120544433594e-05 time for calcul the mask position with numpy : 0.014683961868286133 nb_pixel_total : 224 time to create 1 rle with old method : 0.0002734661102294922 time for calcul the mask position with numpy : 0.01495504379272461 nb_pixel_total : 1831 time to create 1 rle with old method : 0.002051115036010742 time for calcul the mask position with numpy : 0.014911174774169922 nb_pixel_total : 3051 time to create 1 rle with old method : 0.0035538673400878906 time for calcul the mask position with numpy : 0.014972925186157227 nb_pixel_total : 497 time to create 1 rle with old method : 0.0005877017974853516 time for calcul the mask position with numpy : 0.014986515045166016 nb_pixel_total : 585 time to create 1 rle with old method : 0.0007526874542236328 time for calcul the mask position with numpy : 0.015052318572998047 nb_pixel_total : 861 time to create 1 rle with old method : 0.0010709762573242188 time for calcul the mask position with numpy : 0.015392780303955078 nb_pixel_total : 912 time to create 1 rle with old method : 0.0013544559478759766 time for calcul the mask position with numpy : 0.015428781509399414 nb_pixel_total : 969 time to create 1 rle with old method : 0.0011105537414550781 time for calcul the mask position with numpy : 0.01566791534423828 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004107952117919922 time for calcul the mask position with numpy : 0.015048027038574219 nb_pixel_total : 264 time to create 1 rle with old method : 0.0003170967102050781 time for calcul the mask position with numpy : 0.014936447143554688 nb_pixel_total : 450 time to create 1 rle with old method : 0.000537872314453125 time for calcul the mask position with numpy : 0.014679670333862305 nb_pixel_total : 624 time to create 1 rle with old method : 0.0007500648498535156 time for calcul the mask position with numpy : 0.015011072158813477 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007016658782958984 time for calcul the mask position with numpy : 0.014978885650634766 nb_pixel_total : 63 time to create 1 rle with old method : 9.918212890625e-05 time for calcul the mask position with numpy : 0.014861583709716797 nb_pixel_total : 3516 time to create 1 rle with old method : 0.00400996208190918 time for calcul the mask position with numpy : 0.015155553817749023 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002682209014892578 time for calcul the mask position with numpy : 0.015167236328125 nb_pixel_total : 2385 time to create 1 rle with old method : 0.002869129180908203 time for calcul the mask position with numpy : 0.015192985534667969 nb_pixel_total : 23400 time to create 1 rle with old method : 0.026707172393798828 time for calcul the mask position with numpy : 0.014893293380737305 nb_pixel_total : 531 time to create 1 rle with old method : 0.0006415843963623047 time for calcul the mask position with numpy : 0.014924764633178711 nb_pixel_total : 54 time to create 1 rle with old method : 0.00010895729064941406 time for calcul the mask position with numpy : 0.01489877700805664 nb_pixel_total : 3673 time to create 1 rle with old method : 0.004300832748413086 time for calcul the mask position with numpy : 0.014937639236450195 nb_pixel_total : 1023 time to create 1 rle with old method : 0.0011944770812988281 time for calcul the mask position with numpy : 0.014867782592773438 nb_pixel_total : 769 time to create 1 rle with old method : 0.0008885860443115234 time for calcul the mask position with numpy : 0.014766931533813477 nb_pixel_total : 939 time to create 1 rle with old method : 0.0010356903076171875 time for calcul the mask position with numpy : 0.01468801498413086 nb_pixel_total : 1807 time to create 1 rle with old method : 0.0019330978393554688 time for calcul the mask position with numpy : 0.014907121658325195 nb_pixel_total : 1084 time to create 1 rle with old method : 0.001255035400390625 time for calcul the mask position with numpy : 0.014985799789428711 nb_pixel_total : 1147 time to create 1 rle with old method : 0.0014257431030273438 time for calcul the mask position with numpy : 0.01493072509765625 nb_pixel_total : 636 time to create 1 rle with old method : 0.0007205009460449219 time for calcul the mask position with numpy : 0.014922380447387695 nb_pixel_total : 426 time to create 1 rle with old method : 0.00048542022705078125 time for calcul the mask position with numpy : 0.01476740837097168 nb_pixel_total : 154 time to create 1 rle with old method : 0.0001709461212158203 time for calcul the mask position with numpy : 0.014945745468139648 nb_pixel_total : 209 time to create 1 rle with old method : 0.00026917457580566406 time for calcul the mask position with numpy : 0.014991998672485352 nb_pixel_total : 1513 time to create 1 rle with old method : 0.0017626285552978516 time for calcul the mask position with numpy : 0.014887571334838867 nb_pixel_total : 1541 time to create 1 rle with old method : 0.0017919540405273438 time for calcul the mask position with numpy : 0.014826536178588867 nb_pixel_total : 60 time to create 1 rle with old method : 0.00011301040649414062 time for calcul the mask position with numpy : 0.015062093734741211 nb_pixel_total : 3149 time to create 1 rle with old method : 0.0037565231323242188 time for calcul the mask position with numpy : 0.015017032623291016 nb_pixel_total : 787 time to create 1 rle with old method : 0.0009377002716064453 time for calcul the mask position with numpy : 0.014675378799438477 nb_pixel_total : 153 time to create 1 rle with old method : 0.00019621849060058594 time for calcul the mask position with numpy : 0.014907360076904297 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003070831298828125 time for calcul the mask position with numpy : 0.01485133171081543 nb_pixel_total : 1375 time to create 1 rle with old method : 0.0016696453094482422 time for calcul the mask position with numpy : 0.015195369720458984 nb_pixel_total : 1815 time to create 1 rle with old method : 0.002264261245727539 time for calcul the mask position with numpy : 0.014617681503295898 nb_pixel_total : 922 time to create 1 rle with old method : 0.0010828971862792969 create new chi : 3.580097198486328 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 : 0.01129770278930664 batch 1 Loaded 162 chid ids of type : 4230 Number RLEs to save : 15959 TO DO : save crop sub photo not yet done ! save time : 0.9464340209960938 nb_obj : 186 nb_hashtags : 6 time to prepare the origin masks : 4.74190616607666 time for calcul the mask position with numpy : 0.13744544982910156 nb_pixel_total : 3439367 time to create 1 rle with new method : 0.17708611488342285 time for calcul the mask position with numpy : 0.011466503143310547 nb_pixel_total : 1928 time to create 1 rle with old method : 0.0022890567779541016 time for calcul the mask position with numpy : 0.011632442474365234 nb_pixel_total : 234 time to create 1 rle with old method : 0.00028896331787109375 time for calcul the mask position with numpy : 0.011423826217651367 nb_pixel_total : 95 time to create 1 rle with old method : 0.00013327598571777344 time for calcul the mask position with numpy : 0.011308431625366211 nb_pixel_total : 460 time to create 1 rle with old method : 0.0007932186126708984 time for calcul the mask position with numpy : 0.01186227798461914 nb_pixel_total : 153 time to create 1 rle with old method : 0.00028204917907714844 time for calcul the mask position with numpy : 0.01198124885559082 nb_pixel_total : 305 time to create 1 rle with old method : 0.0005466938018798828 time for calcul the mask position with numpy : 0.01984095573425293 nb_pixel_total : 1495 time to create 1 rle with old method : 0.002672433853149414 time for calcul the mask position with numpy : 0.020098447799682617 nb_pixel_total : 378 time to create 1 rle with old method : 0.0006496906280517578 time for calcul the mask position with numpy : 0.018769502639770508 nb_pixel_total : 538 time to create 1 rle with old method : 0.0006346702575683594 time for calcul the mask position with numpy : 0.018149614334106445 nb_pixel_total : 768 time to create 1 rle with old method : 0.0009026527404785156 time for calcul the mask position with numpy : 0.012835264205932617 nb_pixel_total : 1886 time to create 1 rle with old method : 0.002438068389892578 time for calcul the mask position with numpy : 0.010958194732666016 nb_pixel_total : 590 time to create 1 rle with old method : 0.0006926059722900391 time for calcul the mask position with numpy : 0.011288642883300781 nb_pixel_total : 1545 time to create 1 rle with old method : 0.0016400814056396484 time for calcul the mask position with numpy : 0.010967016220092773 nb_pixel_total : 2120 time to create 1 rle with old method : 0.002450704574584961 time for calcul the mask position with numpy : 0.012041807174682617 nb_pixel_total : 30 time to create 1 rle with old method : 6.341934204101562e-05 time for calcul the mask position with numpy : 0.010799169540405273 nb_pixel_total : 681 time to create 1 rle with old method : 0.0008397102355957031 time for calcul the mask position with numpy : 0.010784149169921875 nb_pixel_total : 453 time to create 1 rle with old method : 0.00054168701171875 time for calcul the mask position with numpy : 0.011850118637084961 nb_pixel_total : 66 time to create 1 rle with old method : 0.000125885009765625 time for calcul the mask position with numpy : 0.011133432388305664 nb_pixel_total : 101 time to create 1 rle with old method : 0.00016808509826660156 time for calcul the mask position with numpy : 0.010935544967651367 nb_pixel_total : 1561 time to create 1 rle with old method : 0.0018279552459716797 time for calcul the mask position with numpy : 0.011461973190307617 nb_pixel_total : 4897 time to create 1 rle with old method : 0.005618572235107422 time for calcul the mask position with numpy : 0.01162266731262207 nb_pixel_total : 3920 time to create 1 rle with old method : 0.0054662227630615234 time for calcul the mask position with numpy : 0.011766433715820312 nb_pixel_total : 57 time to create 1 rle with old method : 0.000118255615234375 time for calcul the mask position with numpy : 0.011907577514648438 nb_pixel_total : 1039 time to create 1 rle with old method : 0.0013461112976074219 time for calcul the mask position with numpy : 0.011332035064697266 nb_pixel_total : 432 time to create 1 rle with old method : 0.0004968643188476562 time for calcul the mask position with numpy : 0.017942428588867188 nb_pixel_total : 455 time to create 1 rle with old method : 0.0005550384521484375 time for calcul the mask position with numpy : 0.0180666446685791 nb_pixel_total : 628 time to create 1 rle with old method : 0.0007936954498291016 time for calcul the mask position with numpy : 0.017871856689453125 nb_pixel_total : 205 time to create 1 rle with old method : 0.00025653839111328125 time for calcul the mask position with numpy : 0.017910480499267578 nb_pixel_total : 3512 time to create 1 rle with old method : 0.004065275192260742 time for calcul the mask position with numpy : 0.017863988876342773 nb_pixel_total : 1543 time to create 1 rle with old method : 0.0020515918731689453 time for calcul the mask position with numpy : 0.02031111717224121 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003063678741455078 time for calcul the mask position with numpy : 0.01829242706298828 nb_pixel_total : 1397 time to create 1 rle with old method : 0.001651763916015625 time for calcul the mask position with numpy : 0.017828702926635742 nb_pixel_total : 275 time to create 1 rle with old method : 0.00032258033752441406 time for calcul the mask position with numpy : 0.0173187255859375 nb_pixel_total : 6 time to create 1 rle with old method : 2.9325485229492188e-05 time for calcul the mask position with numpy : 0.0178835391998291 nb_pixel_total : 246 time to create 1 rle with old method : 0.00032329559326171875 time for calcul the mask position with numpy : 0.018053770065307617 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003266334533691406 time for calcul the mask position with numpy : 0.017721891403198242 nb_pixel_total : 1878 time to create 1 rle with old method : 0.002226591110229492 time for calcul the mask position with numpy : 0.01207876205444336 nb_pixel_total : 197 time to create 1 rle with old method : 0.00025343894958496094 time for calcul the mask position with numpy : 0.010767936706542969 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004458427429199219 time for calcul the mask position with numpy : 0.010783910751342773 nb_pixel_total : 128 time to create 1 rle with old method : 0.0002014636993408203 time for calcul the mask position with numpy : 0.010911226272583008 nb_pixel_total : 592 time to create 1 rle with old method : 0.0007538795471191406 time for calcul the mask position with numpy : 0.010993480682373047 nb_pixel_total : 96 time to create 1 rle with old method : 0.0001404285430908203 time for calcul the mask position with numpy : 0.011319398880004883 nb_pixel_total : 486 time to create 1 rle with old method : 0.0005693435668945312 time for calcul the mask position with numpy : 0.011442899703979492 nb_pixel_total : 3069 time to create 1 rle with old method : 0.003538846969604492 time for calcul the mask position with numpy : 0.010776758193969727 nb_pixel_total : 217 time to create 1 rle with old method : 0.0002651214599609375 time for calcul the mask position with numpy : 0.010983705520629883 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002315044403076172 time for calcul the mask position with numpy : 0.01275777816772461 nb_pixel_total : 1416 time to create 1 rle with old method : 0.0017125606536865234 time for calcul the mask position with numpy : 0.01094508171081543 nb_pixel_total : 76 time to create 1 rle with old method : 0.00014901161193847656 time for calcul the mask position with numpy : 0.010912895202636719 nb_pixel_total : 177 time to create 1 rle with old method : 0.00023126602172851562 time for calcul the mask position with numpy : 0.011033296585083008 nb_pixel_total : 709 time to create 1 rle with old method : 0.0008835792541503906 time for calcul the mask position with numpy : 0.010871171951293945 nb_pixel_total : 6282 time to create 1 rle with old method : 0.0070040225982666016 time for calcul the mask position with numpy : 0.010722637176513672 nb_pixel_total : 3143 time to create 1 rle with old method : 0.003598928451538086 time for calcul the mask position with numpy : 0.011788606643676758 nb_pixel_total : 2662 time to create 1 rle with old method : 0.003082275390625 time for calcul the mask position with numpy : 0.01095724105834961 nb_pixel_total : 344 time to create 1 rle with old method : 0.0003917217254638672 time for calcul the mask position with numpy : 0.010781288146972656 nb_pixel_total : 849 time to create 1 rle with old method : 0.0010433197021484375 time for calcul the mask position with numpy : 0.011115074157714844 nb_pixel_total : 321 time to create 1 rle with old method : 0.00039124488830566406 time for calcul the mask position with numpy : 0.010869264602661133 nb_pixel_total : 18 time to create 1 rle with old method : 8.249282836914062e-05 time for calcul the mask position with numpy : 0.010769128799438477 nb_pixel_total : 892 time to create 1 rle with old method : 0.0010440349578857422 time for calcul the mask position with numpy : 0.011491060256958008 nb_pixel_total : 835 time to create 1 rle with old method : 0.0010249614715576172 time for calcul the mask position with numpy : 0.010967493057250977 nb_pixel_total : 1485 time to create 1 rle with old method : 0.0017387866973876953 time for calcul the mask position with numpy : 0.01121664047241211 nb_pixel_total : 216 time to create 1 rle with old method : 0.0002541542053222656 time for calcul the mask position with numpy : 0.010882139205932617 nb_pixel_total : 681 time to create 1 rle with old method : 0.0008196830749511719 time for calcul the mask position with numpy : 0.010935068130493164 nb_pixel_total : 1865 time to create 1 rle with old method : 0.002187967300415039 time for calcul the mask position with numpy : 0.01068425178527832 nb_pixel_total : 586 time to create 1 rle with old method : 0.0006430149078369141 time for calcul the mask position with numpy : 0.010770082473754883 nb_pixel_total : 1839 time to create 1 rle with old method : 0.0022177696228027344 time for calcul the mask position with numpy : 0.011662483215332031 nb_pixel_total : 14 time to create 1 rle with old method : 6.532669067382812e-05 time for calcul the mask position with numpy : 0.010970830917358398 nb_pixel_total : 2789 time to create 1 rle with old method : 0.003117084503173828 time for calcul the mask position with numpy : 0.010987281799316406 nb_pixel_total : 871 time to create 1 rle with old method : 0.0010259151458740234 time for calcul the mask position with numpy : 0.011803627014160156 nb_pixel_total : 1301 time to create 1 rle with old method : 0.0014965534210205078 time for calcul the mask position with numpy : 0.011068582534790039 nb_pixel_total : 1253 time to create 1 rle with old method : 0.0014281272888183594 time for calcul the mask position with numpy : 0.011446475982666016 nb_pixel_total : 2517 time to create 1 rle with old method : 0.004133701324462891 time for calcul the mask position with numpy : 0.011598825454711914 nb_pixel_total : 532 time to create 1 rle with old method : 0.0009138584136962891 time for calcul the mask position with numpy : 0.011444807052612305 nb_pixel_total : 1089 time to create 1 rle with old method : 0.0018510818481445312 time for calcul the mask position with numpy : 0.011474847793579102 nb_pixel_total : 515 time to create 1 rle with old method : 0.0008869171142578125 time for calcul the mask position with numpy : 0.011447429656982422 nb_pixel_total : 54 time to create 1 rle with old method : 0.00015473365783691406 time for calcul the mask position with numpy : 0.011467218399047852 nb_pixel_total : 255 time to create 1 rle with old method : 0.0004642009735107422 time for calcul the mask position with numpy : 0.010935783386230469 nb_pixel_total : 2 time to create 1 rle with old method : 3.24249267578125e-05 time for calcul the mask position with numpy : 0.010742425918579102 nb_pixel_total : 2381 time to create 1 rle with old method : 0.0026938915252685547 time for calcul the mask position with numpy : 0.010703325271606445 nb_pixel_total : 2715 time to create 1 rle with old method : 0.003065347671508789 time for calcul the mask position with numpy : 0.011012554168701172 nb_pixel_total : 141 time to create 1 rle with old method : 0.000339508056640625 time for calcul the mask position with numpy : 0.012718439102172852 nb_pixel_total : 175 time to create 1 rle with old method : 0.00027561187744140625 time for calcul the mask position with numpy : 0.010908365249633789 nb_pixel_total : 283 time to create 1 rle with old method : 0.00036978721618652344 time for calcul the mask position with numpy : 0.011114120483398438 nb_pixel_total : 382 time to create 1 rle with old method : 0.0004591941833496094 time for calcul the mask position with numpy : 0.010697126388549805 nb_pixel_total : 3536 time to create 1 rle with old method : 0.007082223892211914 time for calcul the mask position with numpy : 0.01088261604309082 nb_pixel_total : 152 time to create 1 rle with old method : 0.00023651123046875 time for calcul the mask position with numpy : 0.011286497116088867 nb_pixel_total : 1434 time to create 1 rle with old method : 0.001689910888671875 time for calcul the mask position with numpy : 0.010968446731567383 nb_pixel_total : 528 time to create 1 rle with old method : 0.0006000995635986328 time for calcul the mask position with numpy : 0.010810613632202148 nb_pixel_total : 1566 time to create 1 rle with old method : 0.0016603469848632812 time for calcul the mask position with numpy : 0.010673046112060547 nb_pixel_total : 726 time to create 1 rle with old method : 0.0007863044738769531 time for calcul the mask position with numpy : 0.011529922485351562 nb_pixel_total : 1077 time to create 1 rle with old method : 0.0013098716735839844 time for calcul the mask position with numpy : 0.010562658309936523 nb_pixel_total : 798 time to create 1 rle with old method : 0.0009236335754394531 time for calcul the mask position with numpy : 0.010814666748046875 nb_pixel_total : 570 time to create 1 rle with old method : 0.0006551742553710938 time for calcul the mask position with numpy : 0.010501384735107422 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002601146697998047 time for calcul the mask position with numpy : 0.010858774185180664 nb_pixel_total : 329 time to create 1 rle with old method : 0.0004513263702392578 time for calcul the mask position with numpy : 0.0112457275390625 nb_pixel_total : 38 time to create 1 rle with old method : 9.989738464355469e-05 time for calcul the mask position with numpy : 0.010721683502197266 nb_pixel_total : 310 time to create 1 rle with old method : 0.0003924369812011719 time for calcul the mask position with numpy : 0.010613203048706055 nb_pixel_total : 140 time to create 1 rle with old method : 0.00017976760864257812 time for calcul the mask position with numpy : 0.010980367660522461 nb_pixel_total : 179 time to create 1 rle with old method : 0.00023818016052246094 time for calcul the mask position with numpy : 0.010869026184082031 nb_pixel_total : 408 time to create 1 rle with old method : 0.0004892349243164062 time for calcul the mask position with numpy : 0.010698556900024414 nb_pixel_total : 700 time to create 1 rle with old method : 0.0008673667907714844 time for calcul the mask position with numpy : 0.011759281158447266 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003256797790527344 time for calcul the mask position with numpy : 0.01091623306274414 nb_pixel_total : 305 time to create 1 rle with old method : 0.0003695487976074219 time for calcul the mask position with numpy : 0.010589838027954102 nb_pixel_total : 164 time to create 1 rle with old method : 0.0001938343048095703 time for calcul the mask position with numpy : 0.010681629180908203 nb_pixel_total : 1040 time to create 1 rle with old method : 0.0012285709381103516 time for calcul the mask position with numpy : 0.01058506965637207 nb_pixel_total : 1824 time to create 1 rle with old method : 0.0021119117736816406 time for calcul the mask position with numpy : 0.01076507568359375 nb_pixel_total : 3214 time to create 1 rle with old method : 0.003908872604370117 time for calcul the mask position with numpy : 0.010632514953613281 nb_pixel_total : 206 time to create 1 rle with old method : 0.0003063678741455078 time for calcul the mask position with numpy : 0.01071023941040039 nb_pixel_total : 386 time to create 1 rle with old method : 0.00046181678771972656 time for calcul the mask position with numpy : 0.010605573654174805 nb_pixel_total : 77 time to create 1 rle with old method : 0.00011110305786132812 time for calcul the mask position with numpy : 0.010436296463012695 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002086162567138672 time for calcul the mask position with numpy : 0.01059579849243164 nb_pixel_total : 197 time to create 1 rle with old method : 0.00024509429931640625 time for calcul the mask position with numpy : 0.010775089263916016 nb_pixel_total : 389 time to create 1 rle with old method : 0.0005006790161132812 time for calcul the mask position with numpy : 0.010466337203979492 nb_pixel_total : 635 time to create 1 rle with old method : 0.0007529258728027344 time for calcul the mask position with numpy : 0.01071310043334961 nb_pixel_total : 52 time to create 1 rle with old method : 0.00010514259338378906 time for calcul the mask position with numpy : 0.010677099227905273 nb_pixel_total : 874 time to create 1 rle with old method : 0.0010144710540771484 time for calcul the mask position with numpy : 0.010656595230102539 nb_pixel_total : 401 time to create 1 rle with old method : 0.00048160552978515625 time for calcul the mask position with numpy : 0.01044154167175293 nb_pixel_total : 594 time to create 1 rle with old method : 0.0006809234619140625 time for calcul the mask position with numpy : 0.011566162109375 nb_pixel_total : 329 time to create 1 rle with old method : 0.0003764629364013672 time for calcul the mask position with numpy : 0.010623931884765625 nb_pixel_total : 2695 time to create 1 rle with old method : 0.0031723976135253906 time for calcul the mask position with numpy : 0.01065683364868164 nb_pixel_total : 4925 time to create 1 rle with old method : 0.0056650638580322266 time for calcul the mask position with numpy : 0.010750770568847656 nb_pixel_total : 607 time to create 1 rle with old method : 0.0007293224334716797 time for calcul the mask position with numpy : 0.010751008987426758 nb_pixel_total : 5693 time to create 1 rle with old method : 0.009548425674438477 time for calcul the mask position with numpy : 0.010627269744873047 nb_pixel_total : 93 time to create 1 rle with old method : 0.00013113021850585938 time for calcul the mask position with numpy : 0.010561227798461914 nb_pixel_total : 1533 time to create 1 rle with old method : 0.0017633438110351562 time for calcul the mask position with numpy : 0.010703086853027344 nb_pixel_total : 1322 time to create 1 rle with old method : 0.0015485286712646484 time for calcul the mask position with numpy : 0.010683774948120117 nb_pixel_total : 1698 time to create 1 rle with old method : 0.0020148754119873047 time for calcul the mask position with numpy : 0.010663509368896484 nb_pixel_total : 450 time to create 1 rle with old method : 0.000537872314453125 time for calcul the mask position with numpy : 0.01055908203125 nb_pixel_total : 2027 time to create 1 rle with old method : 0.0023546218872070312 time for calcul the mask position with numpy : 0.0103607177734375 nb_pixel_total : 364 time to create 1 rle with old method : 0.0004017353057861328 time for calcul the mask position with numpy : 0.0103759765625 nb_pixel_total : 863 time to create 1 rle with old method : 0.001056671142578125 time for calcul the mask position with numpy : 0.010431051254272461 nb_pixel_total : 343 time to create 1 rle with old method : 0.00041556358337402344 time for calcul the mask position with numpy : 0.010847091674804688 nb_pixel_total : 1660 time to create 1 rle with old method : 0.0020105838775634766 time for calcul the mask position with numpy : 0.010684967041015625 nb_pixel_total : 666 time to create 1 rle with old method : 0.0007798671722412109 time for calcul the mask position with numpy : 0.01084589958190918 nb_pixel_total : 211 time to create 1 rle with old method : 0.0002627372741699219 time for calcul the mask position with numpy : 0.012726783752441406 nb_pixel_total : 189 time to create 1 rle with old method : 0.0003027915954589844 time for calcul the mask position with numpy : 0.010804176330566406 nb_pixel_total : 395 time to create 1 rle with old method : 0.000453948974609375 time for calcul the mask position with numpy : 0.010564088821411133 nb_pixel_total : 3023 time to create 1 rle with old method : 0.0035066604614257812 time for calcul the mask position with numpy : 0.010761499404907227 nb_pixel_total : 1480 time to create 1 rle with old method : 0.0017240047454833984 time for calcul the mask position with numpy : 0.012396812438964844 nb_pixel_total : 988 time to create 1 rle with old method : 0.001146078109741211 time for calcul the mask position with numpy : 0.01061558723449707 nb_pixel_total : 349 time to create 1 rle with old method : 0.000396728515625 time for calcul the mask position with numpy : 0.01079869270324707 nb_pixel_total : 774 time to create 1 rle with old method : 0.0009365081787109375 time for calcul the mask position with numpy : 0.010842084884643555 nb_pixel_total : 133 time to create 1 rle with old method : 0.00019288063049316406 time for calcul the mask position with numpy : 0.010434150695800781 nb_pixel_total : 648 time to create 1 rle with old method : 0.0007781982421875 time for calcul the mask position with numpy : 0.0106658935546875 nb_pixel_total : 431 time to create 1 rle with old method : 0.0005331039428710938 time for calcul the mask position with numpy : 0.01076197624206543 nb_pixel_total : 374 time to create 1 rle with old method : 0.0004563331604003906 time for calcul the mask position with numpy : 0.010739564895629883 nb_pixel_total : 954 time to create 1 rle with old method : 0.0011496543884277344 time for calcul the mask position with numpy : 0.010640144348144531 nb_pixel_total : 656 time to create 1 rle with old method : 0.0007824897766113281 time for calcul the mask position with numpy : 0.010613203048706055 nb_pixel_total : 2232 time to create 1 rle with old method : 0.0026464462280273438 time for calcul the mask position with numpy : 0.010659933090209961 nb_pixel_total : 613 time to create 1 rle with old method : 0.0007476806640625 time for calcul the mask position with numpy : 0.010552406311035156 nb_pixel_total : 441 time to create 1 rle with old method : 0.0006067752838134766 time for calcul the mask position with numpy : 0.01071786880493164 nb_pixel_total : 735 time to create 1 rle with old method : 0.0009105205535888672 time for calcul the mask position with numpy : 0.010768651962280273 nb_pixel_total : 303 time to create 1 rle with old method : 0.0003647804260253906 time for calcul the mask position with numpy : 0.010806560516357422 nb_pixel_total : 801 time to create 1 rle with old method : 0.0009908676147460938 time for calcul the mask position with numpy : 0.01091313362121582 nb_pixel_total : 710 time to create 1 rle with old method : 0.0008680820465087891 time for calcul the mask position with numpy : 0.010775089263916016 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006058216094970703 time for calcul the mask position with numpy : 0.010658979415893555 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003223419189453125 time for calcul the mask position with numpy : 0.010506153106689453 nb_pixel_total : 348 time to create 1 rle with old method : 0.00039887428283691406 time for calcul the mask position with numpy : 0.010320663452148438 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002608299255371094 time for calcul the mask position with numpy : 0.010421991348266602 nb_pixel_total : 3146 time to create 1 rle with old method : 0.003620624542236328 time for calcul the mask position with numpy : 0.01050710678100586 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002486705780029297 time for calcul the mask position with numpy : 0.010625123977661133 nb_pixel_total : 200 time to create 1 rle with old method : 0.00026226043701171875 time for calcul the mask position with numpy : 0.010568857192993164 nb_pixel_total : 3500 time to create 1 rle with old method : 0.00562739372253418 time for calcul the mask position with numpy : 0.015543460845947266 nb_pixel_total : 71369 time to create 1 rle with old method : 0.0789487361907959 time for calcul the mask position with numpy : 0.014371395111083984 nb_pixel_total : 1443 time to create 1 rle with old method : 0.00164031982421875 time for calcul the mask position with numpy : 0.014569759368896484 nb_pixel_total : 280 time to create 1 rle with old method : 0.0003306865692138672 time for calcul the mask position with numpy : 0.014723062515258789 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005233287811279297 time for calcul the mask position with numpy : 0.014839410781860352 nb_pixel_total : 673 time to create 1 rle with old method : 0.0007624626159667969 time for calcul the mask position with numpy : 0.014845609664916992 nb_pixel_total : 165 time to create 1 rle with old method : 0.00020432472229003906 time for calcul the mask position with numpy : 0.01479482650756836 nb_pixel_total : 1306 time to create 1 rle with old method : 0.0015344619750976562 time for calcul the mask position with numpy : 0.014485597610473633 nb_pixel_total : 1974 time to create 1 rle with old method : 0.002266407012939453 time for calcul the mask position with numpy : 0.014674186706542969 nb_pixel_total : 668 time to create 1 rle with old method : 0.00077056884765625 time for calcul the mask position with numpy : 0.014534473419189453 nb_pixel_total : 91 time to create 1 rle with old method : 0.00011372566223144531 time for calcul the mask position with numpy : 0.014555692672729492 nb_pixel_total : 511 time to create 1 rle with old method : 0.0005664825439453125 time for calcul the mask position with numpy : 0.014730691909790039 nb_pixel_total : 1056 time to create 1 rle with old method : 0.0012097358703613281 time for calcul the mask position with numpy : 0.014727592468261719 nb_pixel_total : 2120 time to create 1 rle with old method : 0.0024423599243164062 time for calcul the mask position with numpy : 0.014684438705444336 nb_pixel_total : 663 time to create 1 rle with old method : 0.0007660388946533203 time for calcul the mask position with numpy : 0.014610528945922852 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001270771026611328 time for calcul the mask position with numpy : 0.01442861557006836 nb_pixel_total : 1380 time to create 1 rle with old method : 0.0015985965728759766 time for calcul the mask position with numpy : 0.014533758163452148 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0012440681457519531 time for calcul the mask position with numpy : 0.014328718185424805 nb_pixel_total : 2248 time to create 1 rle with old method : 0.0024695396423339844 time for calcul the mask position with numpy : 0.014508485794067383 nb_pixel_total : 54 time to create 1 rle with old method : 0.00011539459228515625 time for calcul the mask position with numpy : 0.014741897583007812 nb_pixel_total : 683 time to create 1 rle with old method : 0.0008051395416259766 time for calcul the mask position with numpy : 0.014606475830078125 nb_pixel_total : 327 time to create 1 rle with old method : 0.00037980079650878906 time for calcul the mask position with numpy : 0.014481544494628906 nb_pixel_total : 356 time to create 1 rle with old method : 0.00039458274841308594 time for calcul the mask position with numpy : 0.014143228530883789 nb_pixel_total : 941 time to create 1 rle with old method : 0.0010707378387451172 time for calcul the mask position with numpy : 0.014280557632446289 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003020763397216797 create new chi : 2.8848135471343994 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 : 0.002095937728881836 batch 1 Loaded 187 chid ids of type : 4230 Number RLEs to save : 17209 TO DO : save crop sub photo not yet done ! save time : 1.2267425060272217 map_output_result : {1340594502: (0.0, 'Should be the crop_list due to order', 0.0), 1340592503: (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 [1340594502, 1340592503] Looping around the photos to save general results len do output : 2 /1340594502.Didn't retrieve data . /1340592503.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, '2628344') ('4234', '20966465', '1340594502', None, None, None, None, None, '2628344') ('4234', None, None, None, None, None, None, None, '2628344') ('4234', '20966465', '1340592503', None, None, None, None, None, '2628344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.014028310775756836 save_final save missing photos in datou_result : time spend for datou_step_exec : 15.866790771484375 time spend to save output : 0.01444864273071289 total time spend for step 4 : 15.881239414215088 step5:crop_condition Mon Mar 3 09:21:16 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 2 ! batch 1 Loaded 349 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 156 About to insert : list_path_to_insert length 156 new photo from crops ! About to upload 156 photos upload in portfolio : 4869462 init cache_photo without model_param we have 156 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740990080_1269041 we have uploaded 156 photos in the portfolio 4869462 time of upload the photos Elapsed time : 37.933366775512695 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 ! map_result returned by crop_photo_return_map_crop : length : 24 About to insert : list_path_to_insert length 24 new photo from crops ! About to upload 24 photos upload in portfolio : 4869462 init cache_photo without model_param we have 24 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740990118_1269041 we have uploaded 24 photos in the portfolio 4869462 time of upload the photos Elapsed time : 6.0027124881744385 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740990125_1269041 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.8061497211456299 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 27 About to insert : list_path_to_insert length 27 new photo from crops ! About to upload 27 photos upload in portfolio : 4869462 init cache_photo without model_param we have 27 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740990126_1269041 we have uploaded 27 photos in the portfolio 4869462 time of upload the photos Elapsed time : 6.334892511367798 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 ! map_result returned by crop_photo_return_map_crop : length : 30 About to insert : list_path_to_insert length 30 new photo from crops ! About to upload 30 photos upload in portfolio : 4869462 init cache_photo without model_param we have 30 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740990133_1269041 we have uploaded 30 photos in the portfolio 4869462 time of upload the photos Elapsed time : 6.650125741958618 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 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740990140_1269041 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.5851187705993652 we have finished the crop for the class : pet_fonce delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1340594502, 1340592503] Looping around the photos to save general results len do output : 240 /1340597732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340597999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340598022Didn'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, '2628344') ('4234', '20966465', '1340594502', None, None, None, None, None, '2628344') ('4234', None, None, None, None, None, None, None, '2628344') ('4234', '20966465', '1340592503', None, None, None, None, None, '2628344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 722 time used for this insertion : 0.04362344741821289 save_final save missing photos in datou_result : time spend for datou_step_exec : 64.19406414031982 time spend to save output : 0.051527976989746094 total time spend for step 5 : 64.24559211730957 step6:thcl Mon Mar 3 09:22:21 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 : 0.008719205856323242 time to convert the images to numpy array : 0.07396817207336426 time to import caffe and check if the image exist : 0.01811385154724121 time to convert the images to numpy array : 0.07153844833374023 time to import caffe and check if the image exist : 0.0238187313079834 time to convert the images to numpy array : 0.06752610206604004 time to import caffe and check if the image exist : 0.017332077026367188 time to convert the images to numpy array : 0.07614398002624512 time to import caffe and check if the image exist : 0.017131567001342773 time to convert the images to numpy array : 0.07925748825073242 time to import caffe and check if the image exist : 0.013786554336547852 time to convert the images to numpy array : 0.08215618133544922 time to import caffe and check if the image exist : 0.01851344108581543 time to convert the images to numpy array : 0.07916069030761719 time to import caffe and check if the image exist : 0.024513959884643555 time to convert the images to numpy array : 0.07625174522399902 time to import caffe and check if the image exist : 0.03242039680480957 time to convert the images to numpy array : 0.06827592849731445 time to import caffe and check if the image exist : 0.023126840591430664 time to convert the images to numpy array : 0.07878947257995605 total time to convert the images to numpy array : 0.33806419372558594 list photo_ids error: [] list photo_ids correct : [1340597732, 1340597733, 1340597734, 1340597735, 1340597736, 1340597737, 1340597738, 1340597739, 1340597740, 1340597741, 1340597742, 1340597744, 1340597745, 1340597746, 1340597747, 1340597748, 1340597749, 1340597750, 1340597751, 1340597752, 1340597753, 1340597754, 1340597755, 1340597756, 1340597757, 1340597759, 1340597761, 1340597762, 1340597763, 1340597764, 1340597765, 1340597766, 1340597767, 1340597768, 1340597769, 1340597770, 1340597771, 1340597772, 1340597773, 1340597774, 1340597775, 1340597776, 1340597777, 1340597778, 1340597779, 1340597780, 1340597781, 1340597782, 1340597883, 1340597884, 1340597885, 1340597886, 1340597887, 1340597888, 1340597889, 1340597890, 1340597891, 1340597892, 1340597893, 1340597894, 1340597897, 1340597898, 1340597899, 1340597900, 1340597901, 1340597902, 1340597903, 1340597904, 1340597905, 1340597906, 1340597907, 1340597908, 1340597858, 1340597859, 1340597860, 1340597861, 1340597862, 1340597863, 1340597864, 1340597865, 1340597866, 1340597867, 1340597868, 1340597869, 1340597870, 1340597871, 1340597872, 1340597873, 1340597874, 1340597875, 1340597876, 1340597877, 1340597878, 1340597879, 1340597880, 1340597882, 1340597834, 1340597835, 1340597836, 1340597837, 1340597838, 1340597839, 1340597840, 1340597841, 1340597842, 1340597843, 1340597844, 1340597845, 1340597846, 1340597847, 1340597848, 1340597849, 1340597850, 1340597851, 1340597852, 1340597853, 1340597854, 1340597855, 1340597856, 1340597857, 1340597936, 1340597937, 1340597938, 1340597939, 1340597940, 1340597941, 1340597942, 1340597943, 1340597944, 1340597945, 1340597946, 1340597947, 1340597948, 1340597949, 1340597950, 1340597953, 1340597954, 1340597991, 1340597992, 1340597993, 1340597994, 1340597995, 1340597996, 1340597997, 1340597783, 1340597784, 1340597785, 1340597786, 1340597787, 1340597788, 1340597789, 1340597790, 1340597791, 1340597792, 1340597793, 1340597794, 1340597795, 1340597796, 1340597797, 1340597798, 1340597799, 1340597800, 1340597801, 1340597802, 1340597803, 1340597804, 1340597805, 1340597806, 1340597807, 1340597808, 1340597809, 1340597810, 1340597811, 1340597812, 1340597814, 1340597815, 1340597816, 1340597817, 1340597818, 1340597819, 1340597820, 1340597821, 1340597822, 1340597823, 1340597824, 1340597825, 1340597828, 1340597829, 1340597830, 1340597831, 1340597832, 1340597833, 1340597910, 1340597911, 1340597912, 1340597913, 1340597914, 1340597915, 1340597916, 1340597917, 1340597918, 1340597919, 1340597920, 1340597921, 1340597922, 1340597923, 1340597926, 1340597927, 1340597928, 1340597929, 1340597930, 1340597931, 1340597932, 1340597933, 1340597934, 1340597935, 1340597998, 1340597999, 1340598000, 1340598001, 1340598002, 1340598003, 1340598004, 1340598005, 1340598006, 1340598007, 1340598008, 1340598009, 1340598010, 1340598011, 1340598012, 1340598013, 1340598014, 1340598015, 1340598016, 1340598017, 1340598018, 1340598019, 1340598020, 1340598022] number of photos to traite : 240 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 : 7037 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_rubbia_refus_2500 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_rubbia_refus_2500 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_rubbia_refus_2500 /data/models_weight/learn_rubbia_refus_2500/caffemodel size_local : 94358479 size in s3 : 94358479 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:16 caffemodel already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt size_local : 32544 size in s3 : 32544 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:15 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:09:52 mean.npy already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/synset_words.txt size_local : 334 size in s3 : 334 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:10:06 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /home/admin/workarea/install/caffe_cuda8_python3/python/:/home/admin/workarea/install/darknet/:/home/admin/workarea/git/Velours/python:/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python:/home/admin/mtr/.credentials:/home/admin/workarea/install/caffe/python:/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools/:/home/admin/workarea/git/fotonowerpip/:/home/admin/workarea/install/segment-anything:/home/admin//workarea/git/pyfvs/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt caffemodel_filename : /data/models_weight/learn_rubbia_refus_2500/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 6818 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 1.4426591396331787 time used to do the prediction : 0.8926985263824463 save descriptor for thcl : 3237 time to traite the descriptors : 1.4499332904815674 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1340597732 To insert : 1340597733 To insert : 1340597734 To insert : 1340597735 To insert : 1340597736 To insert : 1340597737 To insert : 1340597738 To insert : 1340597739 To insert : 1340597740 To insert : 1340597741 To insert : 1340597742 To insert : 1340597744 To insert : 1340597745 To insert : 1340597746 To insert : 1340597747 To insert : 1340597748 To insert : 1340597749 To insert : 1340597750 To insert : 1340597751 To insert : 1340597752 To insert : 1340597753 To insert : 1340597754 To insert : 1340597755 To insert : 1340597756 To insert : 1340597757 To insert : 1340597759 To insert : 1340597761 To insert : 1340597762 To insert : 1340597763 To insert : 1340597764 To insert : 1340597765 To insert : 1340597766 To insert : 1340597767 To insert : 1340597768 To insert : 1340597769 To insert : 1340597770 To insert : 1340597771 To insert : 1340597772 To insert : 1340597773 To insert : 1340597774 To insert : 1340597775 To insert : 1340597776 To insert : 1340597777 To insert : 1340597778 To insert : 1340597779 To insert : 1340597780 To insert : 1340597781 To insert : 1340597782 To insert : 1340597883 To insert : 1340597884 To insert : 1340597885 To insert : 1340597886 To insert : 1340597887 To insert : 1340597888 To insert : 1340597889 To insert : 1340597890 To insert : 1340597891 To insert : 1340597892 To insert : 1340597893 To insert : 1340597894 To insert : 1340597897 To insert : 1340597898 To insert : 1340597899 To insert : 1340597900 To insert : 1340597901 To insert : 1340597902 To insert : 1340597903 To insert : 1340597904 To insert : 1340597905 To insert : 1340597906 To insert : 1340597907 To insert : 1340597908 To insert : 1340597858 To insert : 1340597859 To insert : 1340597860 To insert : 1340597861 To insert : 1340597862 To insert : 1340597863 To insert : 1340597864 To insert : 1340597865 To insert : 1340597866 To insert : 1340597867 To insert : 1340597868 To insert : 1340597869 To insert : 1340597870 To insert : 1340597871 To insert : 1340597872 To insert : 1340597873 To insert : 1340597874 To insert : 1340597875 To insert : 1340597876 To insert : 1340597877 To insert : 1340597878 To insert : 1340597879 To insert : 1340597880 To insert : 1340597882 To insert : 1340597834 To insert : 1340597835 To insert : 1340597836 To insert : 1340597837 To insert : 1340597838 To insert : 1340597839 To insert : 1340597840 To insert : 1340597841 To insert : 1340597842 To insert : 1340597843 To insert : 1340597844 To insert : 1340597845 To insert : 1340597846 To insert : 1340597847 To insert : 1340597848 To insert : 1340597849 To insert : 1340597850 To insert : 1340597851 To insert : 1340597852 To insert : 1340597853 To insert : 1340597854 To insert : 1340597855 To insert : 1340597856 To insert : 1340597857 To insert : 1340597936 To insert : 1340597937 To insert : 1340597938 To insert : 1340597939 To insert : 1340597940 To insert : 1340597941 To insert : 1340597942 To insert : 1340597943 To insert : 1340597944 To insert : 1340597945 To insert : 1340597946 To insert : 1340597947 To insert : 1340597948 To insert : 1340597949 To insert : 1340597950 To insert : 1340597953 To insert : 1340597954 To insert : 1340597991 To insert : 1340597992 To insert : 1340597993 To insert : 1340597994 To insert : 1340597995 To insert : 1340597996 To insert : 1340597997 To insert : 1340597783 To insert : 1340597784 To insert : 1340597785 To insert : 1340597786 To insert : 1340597787 To insert : 1340597788 To insert : 1340597789 To insert : 1340597790 To insert : 1340597791 To insert : 1340597792 To insert : 1340597793 To insert : 1340597794 To insert : 1340597795 To insert : 1340597796 To insert : 1340597797 To insert : 1340597798 To insert : 1340597799 To insert : 1340597800 To insert : 1340597801 To insert : 1340597802 To insert : 1340597803 To insert : 1340597804 To insert : 1340597805 To insert : 1340597806 To insert : 1340597807 To insert : 1340597808 To insert : 1340597809 To insert : 1340597810 To insert : 1340597811 To insert : 1340597812 To insert : 1340597814 To insert : 1340597815 To insert : 1340597816 To insert : 1340597817 To insert : 1340597818 To insert : 1340597819 To insert : 1340597820 To insert : 1340597821 To insert : 1340597822 To insert : 1340597823 To insert : 1340597824 To insert : 1340597825 To insert : 1340597828 To insert : 1340597829 To insert : 1340597830 To insert : 1340597831 To insert : 1340597832 To insert : 1340597833 To insert : 1340597910 To insert : 1340597911 To insert : 1340597912 To insert : 1340597913 To insert : 1340597914 To insert : 1340597915 To insert : 1340597916 To insert : 1340597917 To insert : 1340597918 To insert : 1340597919 To insert : 1340597920 To insert : 1340597921 To insert : 1340597922 To insert : 1340597923 To insert : 1340597926 To insert : 1340597927 To insert : 1340597928 To insert : 1340597929 To insert : 1340597930 To insert : 1340597931 To insert : 1340597932 To insert : 1340597933 To insert : 1340597934 To insert : 1340597935 To insert : 1340597998 To insert : 1340597999 To insert : 1340598000 To insert : 1340598001 To insert : 1340598002 To insert : 1340598003 To insert : 1340598004 To insert : 1340598005 To insert : 1340598006 To insert : 1340598007 To insert : 1340598008 To insert : 1340598009 To insert : 1340598010 To insert : 1340598011 To insert : 1340598012 To insert : 1340598013 To insert : 1340598014 To insert : 1340598015 To insert : 1340598016 To insert : 1340598017 To insert : 1340598018 To insert : 1340598019 To insert : 1340598020 To insert : 1340598022 time to insert the descriptors : 48.774035692214966 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 : 391 time used for this insertion : 0.17603135108947754 save missing photos in datou_result : time spend for datou_step_exec : 56.91870880126953 time spend to save output : 0.22714543342590332 total time spend for step 6 : 57.145854234695435 step7:ventilate_hashtags_in_portfolio Mon Mar 3 09:23:18 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 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 : 20966465 get user id for portfolio 20966465 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`=20966465 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Film_plastique','Tetrapak','pehd','flou','papier','PEHD','autre','Carton','PET_clair','pet_clair','pet_fonce','mal_croppe','PET_fonce','metal','carton','Papier','environnement','refus')) 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`=20966465 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Film_plastique','Tetrapak','pehd','flou','papier','PEHD','autre','Carton','PET_clair','pet_clair','pet_fonce','mal_croppe','PET_fonce','metal','carton','Papier','environnement','refus')) 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`=20966465 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Film_plastique','Tetrapak','pehd','flou','papier','PEHD','autre','Carton','PET_clair','pet_clair','pet_fonce','mal_croppe','PET_fonce','metal','carton','Papier','environnement','refus')) 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`=20966465 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Film_plastique','Tetrapak','pehd','flou','papier','PEHD','autre','Carton','PET_clair','pet_clair','pet_fonce','mal_croppe','PET_fonce','metal','carton','Papier','environnement','refus')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20966922,20966923,20966927,20966925,20966937,20966928,20966936,20966931,20966934,20966933,20966935,20966938,20966939?tags=film_plastique,tetrapak,pehd,flou,papier,autre,carton,pet_clair,pet_fonce,mal_croppe,metal,environnement,refus&datou_id_consolidate=4235&port_consolidate=20966465 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1340594502, 1340592503] Looping around the photos to save general results len do output : 1 /20966465. 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, '2628344') ('4234', '20966465', '1340594502', None, None, None, None, None, '2628344') ('4234', None, None, None, None, None, None, None, '2628344') ('4234', '20966465', '1340592503', None, None, None, None, None, '2628344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.012916088104248047 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.29345440864563 time spend to save output : 0.013282060623168945 total time spend for step 7 : 2.306736469268799 step8:final Mon Mar 3 09:23:20 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 : {1340594502: ('0.8590098130212904',), 1340592503: ('0.8590098130212904',)} new output for save of step final : {1340594502: ('0.8590098130212904',), 1340592503: ('0.8590098130212904',)} [1340594502, 1340592503] Looping around the photos to save general results len do output : 2 /1340594502.Didn't retrieve data . /1340592503.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, '2628344') ('4234', '20966465', '1340594502', None, None, None, None, None, '2628344') ('4234', None, None, None, None, None, None, None, '2628344') ('4234', '20966465', '1340592503', None, None, None, None, None, '2628344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.01213693618774414 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12068867683410645 time spend to save output : 0.012370824813842773 total time spend for step 8 : 0.13305950164794922 step9:velours_tree Mon Mar 3 09:23:20 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 : 20966922,20966923,20966927,20966925,20966937,20966928,20966936,20966931,20966934,20966933,20966935,20966938,20966939 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=20966922 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=20966923 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=20966927 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=20966925 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=20966937 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=20966928 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=20966936 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=20966931 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=20966934 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=20966933 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=20966935 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=20966938 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=20966939 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 240 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [2 0 2 5 0 2 1 1 5 2 2 0 1 0 1 1 0 1 5 1 1 1 1 1 0 0 0 0 1 4 0 0 1 0 0 5 1 0 0 0 0 0 0 2 1 1 0 0 1 0 1 1 0 0 0 1 0 1 0 0 2 1 2 0 1 2 2 3 2 2 2 2 0 2 0 0 2 0 2 2 1 5 1 2 0 2 0 1 1 1 2 5 1 1 2 0 0 1 1 2 0 1 4 1 0 5 0 1 0 0 0 4 3 5 1 5 0 0 0 0 5 1 0 0 1 0 0 3 1 0 0 1 0 0 0 5 1 1 3 0 0 1 0 1 0 0 3 0 0 0 0 1 0 3 3 0 2 2 0 2 0 2 2 1 0 0 0 0 0 2 0 2 2 1 0 0 0 0 0 2 2 2 5 0 5 2 2 1 4 0 1 1 2 5 5 5 5 0 2 1 1 0 2 1 4 5 5 1 2 2 1 2 1 3 3 3 1 0 3 2 2 0 2 1 0 1 2 3 0 2 3 2 1 3 2 1 3 2 2 1] Elapsed time: 0.042853355407714844 graph_id used : 81145 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20966922,20966923,20966927,20966925,20966937,20966928,20966936,20966931,20966934,20966933,20966935,20966938,20966939?tags=film_plastique,tetrapak,pehd,flou,papier,autre,carton,pet_clair,pet_fonce,mal_croppe,metal,environnement,refus&datou_id_consolidate=4235&port_consolidate=20966465&tree_id=81145 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1340594502, 1340592503] Looping around the photos to save general results len do output : 1 /20966465Didn'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, '2628344') ('4234', '20966465', '1340594502', None, None, None, None, None, '2628344') ('4234', None, None, None, None, None, None, None, '2628344') ('4234', '20966465', '1340592503', None, None, None, None, None, '2628344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.012015342712402344 save_final save missing photos in datou_result : time spend for datou_step_exec : 15.348716735839844 time spend to save output : 0.012440204620361328 total time spend for step 9 : 15.361156940460205 step10:send_mail_cod Mon Mar 3 09:23:35 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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_P20966465_03-03-2025_09_23_35.pdf 20966904 imagette209669041740990215 20966905 imagette209669051740990215 20966909 imagette209669091740990216 20966907 imagette209669071740990216 20966919 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette209669191740990216 20966910 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette209669101740990216 20966918 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette209669181740990217 20966913 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette209669131740990218 20966916 change filename to text .imagette209669161740990219 20966915 imagette209669151740990219 20966917 change filename to text .change filename to text .imagette209669171740990219 20966921 imagette209669211740990219 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20966465 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20966922,20966923,20966927,20966925,20966937,20966928,20966936,20966931,20966934,20966933,20966935,20966938,20966939?tags=film_plastique,tetrapak,pehd,flou,papier,autre,carton,pet_clair,pet_fonce,mal_croppe,metal,environnement,refus&datou_id_consolidate=4235&port_consolidate=20966465&tree_id=81145 your option no_mail is active, we will not send the real mail to your client args[1340594502] : ((1340594502, -6.308313052053489, 492609224), (1340594502, 0.25407508972663395, 2107752395), '0.8590098130212904') We are sending mail with results at cod@fotonower.com args[1340592503] : ((1340592503, -6.837232459615305, 492609224), (1340592503, 0.5263693477908093, 2107752395), '0.8590098130212904') We are sending mail with results at cod@fotonower.com refus_total : 0.8590098130212904 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=20966465 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_P20966465_03-03-2025_09_23_35.pdf results_Qualipapia_P20966465_03-03-2025_09_23_35.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20966465_03-03-2025_09_23_35.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','20966465','results_Qualipapia_P20966465_03-03-2025_09_23_35.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20966465_03-03-2025_09_23_35.pdf','pdf','','0.16','0.8590098130212904') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1340594502, 1340592503] 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, '2628344') ('4234', '20966465', '1340594502', None, None, None, None, None, '2628344') ('4234', None, None, None, None, None, None, None, '2628344') ('4234', '20966465', '1340592503', None, None, None, None, None, '2628344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.01277613639831543 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.875041246414185 time spend to save output : 0.012972116470336914 total time spend for step 10 : 4.8880133628845215 step11:split_time_score Mon Mar 3 09:23:40 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 3442, 'mtr_user_id': 31, 'name': 'classifieur_2camions_valcor_021122_v1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'deux_camions,camion_droite,camion_gauche,pas_de_camion', 'svm_portfolios_learning': '7659379,7659034,7657685,7657114', 'photo_hashtag_type': 4458, 'photo_desc_type': 5723, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107760533,2107760534,2107760535,2107760536'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('20', 2),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 03032025 20966465 Nombre de photos uploadées : 2 / 23040 (0%) 03032025 20966465 Nombre de photos taguées (types de déchets): 0 / 2 (0%) 03032025 20966465 Nombre de photos taguées (volume) : 0 / 2 (0%) elapsed_time : load_data_split_time_score 5.4836273193359375e-06 elapsed_time : order_list_meta_photo_and_scores 1.4066696166992188e-05 ?? elapsed_time : fill_and_build_computed_from_old_data 0.0002830028533935547 elapsed_time : insert_dashboard_record_day_entry 0.022680997848510742 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.8306114841852944 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20958332_03-03-2025_02_04_47.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20958332 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`=20958332 AND mptpi.`type`=4230 To do Qualite : 0.7860637886380225 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20958333_03-03-2025_02_00_48.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20958333 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`=20958333 AND mptpi.`type`=4230 To do Qualite : 0.7958290525550784 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20958863_03-03-2025_03_16_23.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20958863 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`=20958863 AND mptpi.`type`=4230 To do Qualite : 0.8149470979188714 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20959629_03-03-2025_03_59_37.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20959629 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`=20959629 AND mptpi.`type`=4230 To do Qualite : 0.7860512433937296 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20961267_03-03-2025_06_04_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20961267 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`=20961267 AND mptpi.`type`=4230 To do Qualite : 0.8094902536487374 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20963097_03-03-2025_07_06_59.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20963097 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`=20963097 AND mptpi.`type`=4230 To do Qualite : 0.8200226721616566 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20965279_03-03-2025_08_03_46.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20965279 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`=20965279 AND mptpi.`type`=4230 To do Qualite : 0.8590098130212904 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20966465_03-03-2025_09_23_35.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20966465 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`=20966465 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'03032025': {'nb_upload': 2, 'nb_taggue_class': 0, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1340594502, 1340592503] Looping around the photos to save general results len do output : 1 /20966465Didn'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, '2628344') ('4234', '20966465', '1340594502', None, None, None, None, None, '2628344') ('4234', None, None, None, None, None, None, None, '2628344') ('4234', '20966465', '1340592503', None, None, None, None, None, '2628344') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.012992620468139648 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.6713976860046387 time spend to save output : 0.013225078582763672 total time spend for step 11 : 0.6846227645874023 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 2 set_done_treatment 48.93user 31.78system 3:17.44elapsed 40%CPU (0avgtext+0avgdata 5453756maxresident)k 696104inputs+16416outputs (133major+4165348minor)pagefaults 0swaps