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 : 3565404 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 : ['2645908'] with mtr_portfolio_ids : ['21129082'] and first list_photo_ids : [] new path : /proc/3565404/ 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 , BFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 1 ; length of list_pids : 1 ; length of list_args : 1 time to download the photos : 0.2972087860107422 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 Sun Mar 9 01:20:29 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 9926 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-09 01:20:33.856238: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-09 01:20:33.895111: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-09 01:20:33.897938: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f3a08000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-09 01:20:33.897982: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-09 01:20:33.908001: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-09 01:20:34.175971: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x30e33320 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-09 01:20:34.176055: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-09 01:20:34.177138: 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 2025-03-09 01:20:34.177983: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-09 01:20:34.182791: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-09 01:20:34.191851: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-09 01:20:34.193169: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-09 01:20:34.215202: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-09 01:20:34.218457: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-09 01:20:34.256017: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-09 01:20:34.257838: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-09 01:20:34.257987: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-09 01:20:34.259132: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-09 01:20:34.259159: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-09 01:20:34.259169: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-09 01:20:34.261251: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9188 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. 2025-03-09 01:20:34.612047: 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 2025-03-09 01:20:34.612149: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-09 01:20:34.612169: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-09 01:20:34.612187: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-09 01:20:34.612204: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-09 01:20:34.612221: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-09 01:20:34.612238: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-09 01:20:34.612254: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-09 01:20:34.613550: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-09 01:20:34.614825: 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 2025-03-09 01:20:34.614911: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-09 01:20:34.614933: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-09 01:20:34.614950: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-09 01:20:34.614966: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-09 01:20:34.614982: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-09 01:20:34.614998: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-09 01:20:34.615015: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-09 01:20:34.616257: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-09 01:20:34.616292: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-09 01:20:34.616302: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-09 01:20:34.616310: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-09 01:20:34.617616: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9188 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 : [] 2025-03-09 01:20:44.429756: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-09 01:20:44.647213: 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 : 1 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 36.00000 max: 199.00000 molded_images shape: (1, 640, 640, 3) min: -82.21172 max: 82.76016 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: -117.40313 max: 149.18984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 664 time to create 1 rle with old method : 0.0010933876037597656 length of segment : 39 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 2145 time to create 1 rle with old method : 0.0033135414123535156 length of segment : 84 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0005230903625488281 length of segment : 28 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 674 time to create 1 rle with old method : 0.0010895729064941406 length of segment : 34 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0005428791046142578 length of segment : 15 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0008218288421630859 length of segment : 28 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 487 time to create 1 rle with old method : 0.0008122920989990234 length of segment : 23 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.00036978721618652344 length of segment : 12 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.11797 max: 150.96328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 0.00010347366333007812 nb_pixel_total : 743 time to create 1 rle with old method : 0.0010578632354736328 length of segment : 35 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0007829666137695312 length of segment : 68 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0008754730224609375 length of segment : 34 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002644062042236328 length of segment : 14 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002799034118652344 length of segment : 12 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 1442 time to create 1 rle with old method : 0.0018553733825683594 length of segment : 73 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0005426406860351562 length of segment : 16 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 54 time to create 1 rle with old method : 0.00011849403381347656 length of segment : 8 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.00022792816162109375 length of segment : 12 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 1564 time to create 1 rle with old method : 0.0019457340240478516 length of segment : 65 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 1471 time to create 1 rle with old method : 0.0019466876983642578 length of segment : 71 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0008232593536376953 length of segment : 36 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005879402160644531 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.28203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007607936859130859 length of segment : 34 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0004048347473144531 length of segment : 16 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0005180835723876953 length of segment : 13 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.0005738735198974609 length of segment : 23 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 905 time to create 1 rle with old method : 0.0017960071563720703 length of segment : 52 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0003502368927001953 length of segment : 13 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.0015201568603515625 length of segment : 52 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0013318061828613281 length of segment : 47 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.00057220458984375 length of segment : 26 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1714 time to create 1 rle with old method : 0.0022346973419189453 length of segment : 51 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0003104209899902344 length of segment : 12 time for calcul the mask position with numpy : 0.00013113021850585938 nb_pixel_total : 351 time to create 1 rle with old method : 0.0007693767547607422 length of segment : 34 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004515647888183594 length of segment : 19 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 487 time to create 1 rle with old method : 0.0006740093231201172 length of segment : 26 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.00072479248046875 length of segment : 28 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1411 time to create 1 rle with old method : 0.0018873214721679688 length of segment : 49 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 576 time to create 1 rle with old method : 0.0008947849273681641 length of segment : 34 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0005719661712646484 length of segment : 34 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.000301361083984375 length of segment : 14 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1654 time to create 1 rle with old method : 0.0021533966064453125 length of segment : 52 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.49688 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007736682891845703 length of segment : 25 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 951 time to create 1 rle with old method : 0.0017504692077636719 length of segment : 34 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 1254 time to create 1 rle with old method : 0.0023026466369628906 length of segment : 42 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 689 time to create 1 rle with old method : 0.0013222694396972656 length of segment : 29 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 1666 time to create 1 rle with old method : 0.002953767776489258 length of segment : 51 time for calcul the mask position with numpy : 0.0001583099365234375 nb_pixel_total : 3517 time to create 1 rle with old method : 0.0060307979583740234 length of segment : 77 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0012042522430419922 length of segment : 34 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0005824565887451172 length of segment : 32 time for calcul the mask position with numpy : 0.00013494491577148438 nb_pixel_total : 3548 time to create 1 rle with old method : 0.0061342716217041016 length of segment : 77 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 1085 time to create 1 rle with old method : 0.001964092254638672 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.94609 max: 150.98281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 0.00018644332885742188 nb_pixel_total : 4124 time to create 1 rle with old method : 0.00816488265991211 length of segment : 134 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 1697 time to create 1 rle with old method : 0.0021855831146240234 length of segment : 69 time for calcul the mask position with numpy : 0.0002315044403076172 nb_pixel_total : 8719 time to create 1 rle with old method : 0.010764360427856445 length of segment : 136 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006036758422851562 length of segment : 54 time for calcul the mask position with numpy : 0.0002713203430175781 nb_pixel_total : 6530 time to create 1 rle with old method : 0.008399486541748047 length of segment : 168 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1231 time to create 1 rle with old method : 0.0015294551849365234 length of segment : 41 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.000370025634765625 length of segment : 25 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1356 time to create 1 rle with old method : 0.0017344951629638672 length of segment : 42 time for calcul the mask position with numpy : 0.00010538101196289062 nb_pixel_total : 3855 time to create 1 rle with old method : 0.0046253204345703125 length of segment : 74 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0007066726684570312 length of segment : 27 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005381107330322266 length of segment : 63 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0003440380096435547 length of segment : 23 time for calcul the mask position with numpy : 0.0002014636993408203 nb_pixel_total : 6597 time to create 1 rle with old method : 0.008051395416259766 length of segment : 141 time for calcul the mask position with numpy : 0.0001246929168701172 nb_pixel_total : 3772 time to create 1 rle with old method : 0.004378557205200195 length of segment : 72 Processing 1 images image shape: (400, 160, 3) min: 4.00000 max: 244.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.75234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.00049591064453125 length of segment : 26 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00043010711669921875 length of segment : 29 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 366 time to create 1 rle with old method : 0.0005030632019042969 length of segment : 28 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002665519714355469 length of segment : 22 time for calcul the mask position with numpy : 0.00016570091247558594 nb_pixel_total : 5961 time to create 1 rle with old method : 0.007080793380737305 length of segment : 121 time for calcul the mask position with numpy : 0.00022649765014648438 nb_pixel_total : 8365 time to create 1 rle with old method : 0.010178565979003906 length of segment : 242 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.23516 max: 150.94375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00037598609924316406 nb_pixel_total : 21272 time to create 1 rle with old method : 0.02454090118408203 length of segment : 261 time for calcul the mask position with numpy : 9.846687316894531e-05 nb_pixel_total : 1289 time to create 1 rle with old method : 0.0019383430480957031 length of segment : 68 time for calcul the mask position with numpy : 0.0001976490020751953 nb_pixel_total : 4895 time to create 1 rle with old method : 0.006111860275268555 length of segment : 218 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 865 time to create 1 rle with old method : 0.0010213851928710938 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.55938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00041103363037109375 length of segment : 25 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1741 time to create 1 rle with old method : 0.002195596694946289 length of segment : 63 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0009047985076904297 length of segment : 30 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0005445480346679688 length of segment : 40 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.00030493736267089844 length of segment : 29 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004677772521972656 length of segment : 28 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00031828880310058594 length of segment : 13 time for calcul the mask position with numpy : 0.0001277923583984375 nb_pixel_total : 2711 time to create 1 rle with old method : 0.00339508056640625 length of segment : 103 time for calcul the mask position with numpy : 0.0001201629638671875 nb_pixel_total : 3217 time to create 1 rle with old method : 0.003941774368286133 length of segment : 87 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.50469 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009288787841796875 length of segment : 28 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.0003123283386230469 length of segment : 22 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.0001270771026611328 length of segment : 7 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 802 time to create 1 rle with old method : 0.0010776519775390625 length of segment : 38 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.00047206878662109375 length of segment : 29 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 1445 time to create 1 rle with old method : 0.0018286705017089844 length of segment : 46 time for calcul the mask position with numpy : 0.00010561943054199219 nb_pixel_total : 429 time to create 1 rle with old method : 0.0008356571197509766 length of segment : 36 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00032448768615722656 length of segment : 21 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005755424499511719 length of segment : 25 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 482 time to create 1 rle with old method : 0.0006799697875976562 length of segment : 28 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002675056457519531 length of segment : 15 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.00018143653869628906 length of segment : 20 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 2146 time to create 1 rle with old method : 0.0027053356170654297 length of segment : 64 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 2447 time to create 1 rle with old method : 0.003211498260498047 length of segment : 131 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 252 time to create 1 rle with old method : 0.0004162788391113281 length of segment : 25 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.0009605884552001953 length of segment : 28 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001785755157470703 length of segment : 13 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 684 time to create 1 rle with old method : 0.0009953975677490234 length of segment : 28 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004284381866455078 length of segment : 18 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1216 time to create 1 rle with old method : 0.0019350051879882812 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 13.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -100.34844 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 1708 time to create 1 rle with old method : 0.002130746841430664 length of segment : 77 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1098 time to create 1 rle with old method : 0.0013589859008789062 length of segment : 64 time for calcul the mask position with numpy : 9.465217590332031e-05 nb_pixel_total : 1889 time to create 1 rle with old method : 0.002474546432495117 length of segment : 48 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 830 time to create 1 rle with old method : 0.001260519027709961 length of segment : 31 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 538 time to create 1 rle with old method : 0.000759124755859375 length of segment : 25 time for calcul the mask position with numpy : 0.0001671314239501953 nb_pixel_total : 5153 time to create 1 rle with old method : 0.006445407867431641 length of segment : 98 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0009026527404785156 length of segment : 19 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.00036787986755371094 length of segment : 34 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0004057884216308594 length of segment : 25 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 2259 time to create 1 rle with old method : 0.002962350845336914 length of segment : 40 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1048 time to create 1 rle with old method : 0.0014221668243408203 length of segment : 31 time for calcul the mask position with numpy : 0.00016379356384277344 nb_pixel_total : 4729 time to create 1 rle with old method : 0.005861997604370117 length of segment : 90 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0010485649108886719 length of segment : 48 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0006685256958007812 length of segment : 31 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00043010711669921875 length of segment : 34 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0003159046173095703 length of segment : 16 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 1165 time to create 1 rle with old method : 0.0015606880187988281 length of segment : 37 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1068 time to create 1 rle with old method : 0.0013585090637207031 length of segment : 45 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003399848937988281 length of segment : 15 time for calcul the mask position with numpy : 0.0001456737518310547 nb_pixel_total : 5026 time to create 1 rle with old method : 0.0066525936126708984 length of segment : 96 time for calcul the mask position with numpy : 0.00010371208190917969 nb_pixel_total : 899 time to create 1 rle with old method : 0.0017371177673339844 length of segment : 64 time for calcul the mask position with numpy : 0.00019288063049316406 nb_pixel_total : 4778 time to create 1 rle with old method : 0.00826883316040039 length of segment : 97 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.64922 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 : 8.96453857421875e-05 nb_pixel_total : 792 time to create 1 rle with old method : 0.0010395050048828125 length of segment : 43 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 858 time to create 1 rle with old method : 0.0011196136474609375 length of segment : 43 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006830692291259766 length of segment : 26 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00021910667419433594 length of segment : 9 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0003063678741455078 length of segment : 21 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1249 time to create 1 rle with old method : 0.0015742778778076172 length of segment : 66 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.00029158592224121094 length of segment : 16 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006589889526367188 length of segment : 34 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 50 time to create 1 rle with old method : 0.00010418891906738281 length of segment : 11 length of segment : 0 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 2036 time to create 1 rle with old method : 0.0025386810302734375 length of segment : 62 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -94.47344 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 : 0.00010442733764648438 nb_pixel_total : 1551 time to create 1 rle with old method : 0.0020542144775390625 length of segment : 42 time for calcul the mask position with numpy : 0.00012087821960449219 nb_pixel_total : 4110 time to create 1 rle with old method : 0.0051670074462890625 length of segment : 72 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0005445480346679688 length of segment : 25 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1975 time to create 1 rle with old method : 0.0026230812072753906 length of segment : 48 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 1249 time to create 1 rle with old method : 0.001743316650390625 length of segment : 65 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 893 time to create 1 rle with old method : 0.0012118816375732422 length of segment : 45 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.00047326087951660156 length of segment : 21 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1552 time to create 1 rle with old method : 0.0020253658294677734 length of segment : 46 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00044345855712890625 length of segment : 17 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0005674362182617188 length of segment : 24 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 480 time to create 1 rle with old method : 0.0008308887481689453 length of segment : 25 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002770423889160156 length of segment : 31 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0018661022186279297 length of segment : 99 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0007116794586181641 length of segment : 28 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0007417201995849609 length of segment : 19 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0007576942443847656 length of segment : 32 Processing 1 images image shape: (400, 160, 3) min: 8.00000 max: 240.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 123.07656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0010159015655517578 length of segment : 89 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 2171 time to create 1 rle with old method : 0.0030508041381835938 length of segment : 80 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 2300 time to create 1 rle with old method : 0.0030040740966796875 length of segment : 39 time for calcul the mask position with numpy : 0.00016880035400390625 nb_pixel_total : 5306 time to create 1 rle with old method : 0.007002115249633789 length of segment : 122 time for calcul the mask position with numpy : 0.00015306472778320312 nb_pixel_total : 5043 time to create 1 rle with old method : 0.006050825119018555 length of segment : 118 time for calcul the mask position with numpy : 0.00014734268188476562 nb_pixel_total : 5011 time to create 1 rle with old method : 0.006186485290527344 length of segment : 112 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.46563 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 : 5.555152893066406e-05 nb_pixel_total : 1195 time to create 1 rle with old method : 0.0015959739685058594 length of segment : 47 time for calcul the mask position with numpy : 0.00016021728515625 nb_pixel_total : 2834 time to create 1 rle with old method : 0.004193782806396484 length of segment : 93 time for calcul the mask position with numpy : 0.00012636184692382812 nb_pixel_total : 5667 time to create 1 rle with old method : 0.007347822189331055 length of segment : 164 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.0006308555603027344 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 3.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -107.21172 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 27 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0007021427154541016 length of segment : 30 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.00040340423583984375 length of segment : 18 time for calcul the mask position with numpy : 0.00012564659118652344 nb_pixel_total : 4099 time to create 1 rle with old method : 0.005347251892089844 length of segment : 112 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1960 time to create 1 rle with old method : 0.0025992393493652344 length of segment : 70 time for calcul the mask position with numpy : 0.0002574920654296875 nb_pixel_total : 10158 time to create 1 rle with old method : 0.012802839279174805 length of segment : 171 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0006916522979736328 length of segment : 90 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0007083415985107422 length of segment : 24 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1209 time to create 1 rle with old method : 0.0016036033630371094 length of segment : 40 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.00066375732421875 length of segment : 20 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003974437713623047 length of segment : 22 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0014171600341796875 length of segment : 37 time for calcul the mask position with numpy : 0.0002751350402832031 nb_pixel_total : 8585 time to create 1 rle with old method : 0.01371312141418457 length of segment : 221 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0006551742553710938 length of segment : 31 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 825 time to create 1 rle with old method : 0.0017528533935546875 length of segment : 35 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003650188446044922 length of segment : 24 time for calcul the mask position with numpy : 0.0002148151397705078 nb_pixel_total : 4995 time to create 1 rle with old method : 0.008288145065307617 length of segment : 52 time for calcul the mask position with numpy : 0.00012445449829101562 nb_pixel_total : 1592 time to create 1 rle with old method : 0.002924203872680664 length of segment : 54 time for calcul the mask position with numpy : 0.00024390220642089844 nb_pixel_total : 1325 time to create 1 rle with old method : 0.002604246139526367 length of segment : 99 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.000469207763671875 length of segment : 19 time for calcul the mask position with numpy : 0.000370025634765625 nb_pixel_total : 9327 time to create 1 rle with old method : 0.01452779769897461 length of segment : 229 time for calcul the mask position with numpy : 0.00015211105346679688 nb_pixel_total : 732 time to create 1 rle with old method : 0.00109100341796875 length of segment : 30 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 805 time to create 1 rle with old method : 0.0012359619140625 length of segment : 50 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0005114078521728516 length of segment : 18 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 482 time to create 1 rle with old method : 0.0010199546813964844 length of segment : 28 time for calcul the mask position with numpy : 0.00019407272338867188 nb_pixel_total : 5364 time to create 1 rle with old method : 0.008267641067504883 length of segment : 158 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 781 time to create 1 rle with old method : 0.001116037368774414 length of segment : 36 time for calcul the mask position with numpy : 0.00013518333435058594 nb_pixel_total : 6208 time to create 1 rle with old method : 0.007899761199951172 length of segment : 107 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -107.62578 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.00033926963806152344 length of segment : 22 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 838 time to create 1 rle with old method : 0.0010662078857421875 length of segment : 32 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1186 time to create 1 rle with old method : 0.0014023780822753906 length of segment : 63 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0003254413604736328 length of segment : 17 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2197 time to create 1 rle with old method : 0.002665281295776367 length of segment : 71 time for calcul the mask position with numpy : 0.00013709068298339844 nb_pixel_total : 6475 time to create 1 rle with old method : 0.007327556610107422 length of segment : 105 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005054473876953125 length of segment : 18 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.00044727325439453125 length of segment : 23 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0008068084716796875 length of segment : 23 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 490 time to create 1 rle with old method : 0.0006763935089111328 length of segment : 37 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1362 time to create 1 rle with old method : 0.0017309188842773438 length of segment : 46 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 2016 time to create 1 rle with old method : 0.0024576187133789062 length of segment : 55 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 959 time to create 1 rle with old method : 0.0013611316680908203 length of segment : 33 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 2351 time to create 1 rle with old method : 0.0027647018432617188 length of segment : 74 time for calcul the mask position with numpy : 0.00016260147094726562 nb_pixel_total : 8221 time to create 1 rle with old method : 0.009067296981811523 length of segment : 105 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 2596 time to create 1 rle with old method : 0.002953052520751953 length of segment : 59 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1747 time to create 1 rle with old method : 0.0031228065490722656 length of segment : 47 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1092 time to create 1 rle with old method : 0.0014638900756835938 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -97.29375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 0.0001068115234375 nb_pixel_total : 383 time to create 1 rle with old method : 0.000553131103515625 length of segment : 29 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1185 time to create 1 rle with old method : 0.0015561580657958984 length of segment : 57 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 922 time to create 1 rle with old method : 0.0011591911315917969 length of segment : 63 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 491 time to create 1 rle with old method : 0.0006284713745117188 length of segment : 36 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1937 time to create 1 rle with old method : 0.0023136138916015625 length of segment : 46 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 16 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002942085266113281 length of segment : 14 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003306865692138672 length of segment : 18 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 852 time to create 1 rle with old method : 0.001085519790649414 length of segment : 43 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 629 time to create 1 rle with old method : 0.0008456707000732422 length of segment : 36 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 1264 time to create 1 rle with old method : 0.0015878677368164062 length of segment : 53 time for calcul the mask position with numpy : 0.00017833709716796875 nb_pixel_total : 6851 time to create 1 rle with old method : 0.008122920989990234 length of segment : 114 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.00022125244140625 length of segment : 10 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0008134841918945312 length of segment : 31 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.0001437664031982422 length of segment : 17 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 2632 time to create 1 rle with old method : 0.003233671188354492 length of segment : 59 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 697 time to create 1 rle with old method : 0.0009307861328125 length of segment : 62 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 1875 time to create 1 rle with old method : 0.0022809505462646484 length of segment : 47 time for calcul the mask position with numpy : 0.00017547607421875 nb_pixel_total : 6750 time to create 1 rle with old method : 0.00807952880859375 length of segment : 116 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.00033402442932128906 length of segment : 20 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1226 time to create 1 rle with old method : 0.0015354156494140625 length of segment : 56 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 669 time to create 1 rle with old method : 0.0008232593536376953 length of segment : 35 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.0005667209625244141 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.52422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.0006990432739257812 length of segment : 40 time for calcul the mask position with numpy : 0.00011396408081054688 nb_pixel_total : 4691 time to create 1 rle with old method : 0.005355119705200195 length of segment : 146 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.00043201446533203125 length of segment : 29 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 4995 time to create 1 rle with old method : 0.0059566497802734375 length of segment : 72 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 750 time to create 1 rle with old method : 0.0009644031524658203 length of segment : 25 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.00046563148498535156 length of segment : 13 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003426074981689453 length of segment : 16 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 3742 time to create 1 rle with old method : 0.004438877105712891 length of segment : 99 time for calcul the mask position with numpy : 0.00010752677917480469 nb_pixel_total : 4415 time to create 1 rle with old method : 0.005026340484619141 length of segment : 79 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 815 time to create 1 rle with old method : 0.001035451889038086 length of segment : 34 time for calcul the mask position with numpy : 0.00012564659118652344 nb_pixel_total : 5670 time to create 1 rle with old method : 0.006675243377685547 length of segment : 91 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.00021505355834960938 length of segment : 15 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 3908 time to create 1 rle with old method : 0.005554676055908203 length of segment : 61 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 917 time to create 1 rle with old method : 0.0010657310485839844 length of segment : 74 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006837844848632812 length of segment : 42 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 2522 time to create 1 rle with old method : 0.00351715087890625 length of segment : 77 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006303787231445312 length of segment : 27 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.0009810924530029297 length of segment : 30 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.0008323192596435547 length of segment : 42 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1303 time to create 1 rle with old method : 0.0017740726470947266 length of segment : 43 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.00047659873962402344 length of segment : 32 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1056 time to create 1 rle with old method : 0.0011992454528808594 length of segment : 82 Processing 1 images image shape: (400, 400, 3) min: 27.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -88.01641 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 : 6.413459777832031e-05 nb_pixel_total : 981 time to create 1 rle with old method : 0.0012562274932861328 length of segment : 42 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 1192 time to create 1 rle with old method : 0.0015053749084472656 length of segment : 45 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004382133483886719 length of segment : 26 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 2682 time to create 1 rle with old method : 0.003196239471435547 length of segment : 73 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.00044226646423339844 length of segment : 28 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 805 time to create 1 rle with old method : 0.0011773109436035156 length of segment : 27 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0006711483001708984 length of segment : 33 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.0004649162292480469 length of segment : 11 time for calcul the mask position with numpy : 0.00012946128845214844 nb_pixel_total : 1161 time to create 1 rle with old method : 0.0015494823455810547 length of segment : 83 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 1076 time to create 1 rle with old method : 0.0013148784637451172 length of segment : 41 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 813 time to create 1 rle with old method : 0.0011022090911865234 length of segment : 27 Processing 1 images image shape: (400, 160, 3) min: 24.00000 max: 227.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 102.18203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0005269050598144531 length of segment : 14 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0006895065307617188 length of segment : 47 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 3799 time to create 1 rle with old method : 0.006627798080444336 length of segment : 88 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 3569 time to create 1 rle with old method : 0.005013942718505859 length of segment : 89 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: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 9.751319885253906e-05 nb_pixel_total : 4843 time to create 1 rle with old method : 0.0057103633880615234 length of segment : 147 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 : 10 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1193 time to create 1 rle with old method : 0.0015225410461425781 length of segment : 37 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 39 time to create 1 rle with old method : 7.915496826171875e-05 length of segment : 16 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00014066696166992188 length of segment : 6 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.00026345252990722656 length of segment : 17 time for calcul the mask position with numpy : 9.894371032714844e-05 nb_pixel_total : 3752 time to create 1 rle with old method : 0.0045871734619140625 length of segment : 104 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.0001735687255859375 length of segment : 16 time for calcul the mask position with numpy : 8.559226989746094e-05 nb_pixel_total : 1817 time to create 1 rle with old method : 0.0023355484008789062 length of segment : 129 time for calcul the mask position with numpy : 0.0007207393646240234 nb_pixel_total : 63195 time to create 1 rle with old method : 0.07277894020080566 length of segment : 239 time for calcul the mask position with numpy : 0.00012922286987304688 nb_pixel_total : 1004 time to create 1 rle with old method : 0.0015034675598144531 length of segment : 57 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001735687255859375 length of segment : 11 Processing 1 images image shape: (240, 400, 3) min: 27.00000 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 : 10 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.00017333030700683594 length of segment : 10 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1571 time to create 1 rle with old method : 0.0019750595092773438 length of segment : 57 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0005114078521728516 length of segment : 19 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1164 time to create 1 rle with old method : 0.0016334056854248047 length of segment : 29 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 3513 time to create 1 rle with old method : 0.004509687423706055 length of segment : 34 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0006797313690185547 length of segment : 88 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 611 time to create 1 rle with old method : 0.0008754730224609375 length of segment : 30 time for calcul the mask position with numpy : 0.0003895759582519531 nb_pixel_total : 27396 time to create 1 rle with old method : 0.033258676528930664 length of segment : 164 time for calcul the mask position with numpy : 9.775161743164062e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006186962127685547 length of segment : 96 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 3780 time to create 1 rle with old method : 0.0045833587646484375 length of segment : 87 Processing 1 images image shape: (240, 400, 3) min: 23.00000 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 : 22 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0016644001007080078 length of segment : 47 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 1645 time to create 1 rle with old method : 0.002170562744140625 length of segment : 43 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003173351287841797 length of segment : 14 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0007646083831787109 length of segment : 24 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0008072853088378906 length of segment : 27 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006406307220458984 length of segment : 29 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0007102489471435547 length of segment : 32 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.0010828971862792969 length of segment : 40 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005826950073242188 length of segment : 31 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0005037784576416016 length of segment : 22 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0005939006805419922 length of segment : 25 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1137 time to create 1 rle with old method : 0.0016179084777832031 length of segment : 39 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005667209625244141 length of segment : 30 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 769 time to create 1 rle with old method : 0.0010178089141845703 length of segment : 47 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1487 time to create 1 rle with old method : 0.0019414424896240234 length of segment : 42 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1239 time to create 1 rle with old method : 0.0016961097717285156 length of segment : 34 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0009715557098388672 length of segment : 36 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1504 time to create 1 rle with old method : 0.0020139217376708984 length of segment : 41 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0009140968322753906 length of segment : 31 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1512 time to create 1 rle with old method : 0.001882791519165039 length of segment : 54 time for calcul the mask position with numpy : 0.00011539459228515625 nb_pixel_total : 5677 time to create 1 rle with old method : 0.006697416305541992 length of segment : 78 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.00046563148498535156 length of segment : 17 Processing 1 images image shape: (240, 400, 3) min: 38.00000 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 : 19 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 3055 time to create 1 rle with old method : 0.0038094520568847656 length of segment : 67 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.00069427490234375 length of segment : 38 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0011403560638427734 length of segment : 45 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1558 time to create 1 rle with old method : 0.002161264419555664 length of segment : 38 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 644 time to create 1 rle with old method : 0.0008866786956787109 length of segment : 31 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 653 time to create 1 rle with old method : 0.0008180141448974609 length of segment : 49 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0003733634948730469 length of segment : 28 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 2206 time to create 1 rle with old method : 0.0027930736541748047 length of segment : 56 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 773 time to create 1 rle with old method : 0.0011065006256103516 length of segment : 29 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1216 time to create 1 rle with old method : 0.0015993118286132812 length of segment : 42 time for calcul the mask position with numpy : 0.0001430511474609375 nb_pixel_total : 4819 time to create 1 rle with old method : 0.006024837493896484 length of segment : 114 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005626678466796875 length of segment : 32 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 776 time to create 1 rle with old method : 0.0011258125305175781 length of segment : 38 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.0006921291351318359 length of segment : 29 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.0002493858337402344 length of segment : 18 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.0010602474212646484 length of segment : 35 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 966 time to create 1 rle with old method : 0.0012333393096923828 length of segment : 53 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 708 time to create 1 rle with old method : 0.0009312629699707031 length of segment : 44 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.0008935928344726562 length of segment : 28 Processing 1 images image shape: (240, 400, 3) min: 17.00000 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 : 18 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 3340 time to create 1 rle with old method : 0.003954172134399414 length of segment : 90 time for calcul the mask position with numpy : 0.00012421607971191406 nb_pixel_total : 2910 time to create 1 rle with old method : 0.0037512779235839844 length of segment : 98 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 558 time to create 1 rle with old method : 0.000736236572265625 length of segment : 35 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 31 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 2390 time to create 1 rle with old method : 0.0029120445251464844 length of segment : 93 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0004038810729980469 length of segment : 11 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 611 time to create 1 rle with old method : 0.0008146762847900391 length of segment : 24 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0006363391876220703 length of segment : 28 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 677 time to create 1 rle with old method : 0.0009124279022216797 length of segment : 32 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00022268295288085938 length of segment : 14 time for calcul the mask position with numpy : 0.00013828277587890625 nb_pixel_total : 2707 time to create 1 rle with old method : 0.004304647445678711 length of segment : 52 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0007302761077880859 length of segment : 24 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0009839534759521484 length of segment : 45 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0014095306396484375 length of segment : 26 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 735 time to create 1 rle with old method : 0.0009322166442871094 length of segment : 48 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.000263214111328125 length of segment : 24 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005731582641601562 length of segment : 25 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 1662 time to create 1 rle with old method : 0.0022001266479492188 length of segment : 52 Processing 1 images image shape: (240, 160, 3) min: 66.00000 max: 173.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 59.29914 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003662109375 length of segment : 36 Detection mask done ! Trying to reset tf kernel 3566003 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 3838 tf kernel not reseted sub process len(results) : 349 len(list_Values) 349 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 349 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 : 9127 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 421 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 17270 save missing photos in datou_result : time spend for datou_step_exec : 27.983738899230957 time spend to save output : 19.25072693824768 total time spend for step 1 : 47.23446583747864 step2:brightness Sun Mar 9 01:21:17 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 toutes les photos sont déjà traitées, on saute les calculs 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 : 1 time used for this insertion : 0.012022733688354492 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.21182823181152344 save missing photos in datou_result : time spend for datou_step_exec : 0.06202220916748047 time spend to save output : 0.22843480110168457 total time spend for step 2 : 0.29045701026916504 step3:blur_detection Sun Mar 9 01:21:17 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 toutes les photos sont déjà traitées, on saute les calculs 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 : 1 time used for this insertion : 0.01006317138671875 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.008671998977661133 save missing photos in datou_result : time spend for datou_step_exec : 0.021095752716064453 time spend to save output : 0.02376270294189453 total time spend for step 3 : 0.044858455657958984 step4:rle_unique_nms_with_priority Sun Mar 9 01:21:17 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 421 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 417 nb_hashtags : 7 time to prepare the origin masks : 11.602338552474976 time for calcul the mask position with numpy : 0.16725707054138184 nb_pixel_total : 3161960 time to create 1 rle with new method : 0.44420957565307617 time for calcul the mask position with numpy : 0.016205549240112305 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003371238708496094 time for calcul the mask position with numpy : 0.015603065490722656 nb_pixel_total : 689 time to create 1 rle with old method : 0.0008394718170166016 time for calcul the mask position with numpy : 0.01599431037902832 nb_pixel_total : 127 time to create 1 rle with old method : 0.000194549560546875 time for calcul the mask position with numpy : 0.01578235626220703 nb_pixel_total : 905 time to create 1 rle with old method : 0.001176595687866211 time for calcul the mask position with numpy : 0.01580357551574707 nb_pixel_total : 280 time to create 1 rle with old method : 0.00044417381286621094 time for calcul the mask position with numpy : 0.01904916763305664 nb_pixel_total : 1231 time to create 1 rle with old method : 0.0014524459838867188 time for calcul the mask position with numpy : 0.01593327522277832 nb_pixel_total : 75 time to create 1 rle with old method : 0.00020694732666015625 time for calcul the mask position with numpy : 0.015914201736450195 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002243518829345703 time for calcul the mask position with numpy : 0.01660323143005371 nb_pixel_total : 605 time to create 1 rle with old method : 0.0008871555328369141 time for calcul the mask position with numpy : 0.017935514450073242 nb_pixel_total : 54 time to create 1 rle with old method : 0.00013494491577148438 time for calcul the mask position with numpy : 0.016781330108642578 nb_pixel_total : 2145 time to create 1 rle with old method : 0.002729177474975586 time for calcul the mask position with numpy : 0.01848149299621582 nb_pixel_total : 6530 time to create 1 rle with old method : 0.008767127990722656 time for calcul the mask position with numpy : 0.01593494415283203 nb_pixel_total : 528 time to create 1 rle with old method : 0.0008654594421386719 time for calcul the mask position with numpy : 0.01566028594970703 nb_pixel_total : 102 time to create 1 rle with old method : 0.0003299713134765625 time for calcul the mask position with numpy : 0.0156404972076416 nb_pixel_total : 1666 time to create 1 rle with old method : 0.0019698143005371094 time for calcul the mask position with numpy : 0.015748023986816406 nb_pixel_total : 460 time to create 1 rle with old method : 0.0005955696105957031 time for calcul the mask position with numpy : 0.01566624641418457 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002715587615966797 time for calcul the mask position with numpy : 0.015544414520263672 nb_pixel_total : 390 time to create 1 rle with old method : 0.0005323886871337891 time for calcul the mask position with numpy : 0.015587329864501953 nb_pixel_total : 674 time to create 1 rle with old method : 0.0008854866027832031 time for calcul the mask position with numpy : 0.015552997589111328 nb_pixel_total : 530 time to create 1 rle with old method : 0.0006608963012695312 time for calcul the mask position with numpy : 0.01560664176940918 nb_pixel_total : 261 time to create 1 rle with old method : 0.00032806396484375 time for calcul the mask position with numpy : 0.015593767166137695 nb_pixel_total : 280 time to create 1 rle with old method : 0.0004870891571044922 time for calcul the mask position with numpy : 0.015702009201049805 nb_pixel_total : 9371 time to create 1 rle with old method : 0.010711193084716797 time for calcul the mask position with numpy : 0.0157468318939209 nb_pixel_total : 743 time to create 1 rle with old method : 0.0009427070617675781 time for calcul the mask position with numpy : 0.01571035385131836 nb_pixel_total : 104 time to create 1 rle with old method : 0.0002906322479248047 time for calcul the mask position with numpy : 0.015612125396728516 nb_pixel_total : 1714 time to create 1 rle with old method : 0.0020585060119628906 time for calcul the mask position with numpy : 0.015576362609863281 nb_pixel_total : 18 time to create 1 rle with old method : 8.225440979003906e-05 time for calcul the mask position with numpy : 0.01528310775756836 nb_pixel_total : 1411 time to create 1 rle with old method : 0.0016865730285644531 time for calcul the mask position with numpy : 0.015115976333618164 nb_pixel_total : 951 time to create 1 rle with old method : 0.0011222362518310547 time for calcul the mask position with numpy : 0.015187740325927734 nb_pixel_total : 1254 time to create 1 rle with old method : 0.0014770030975341797 time for calcul the mask position with numpy : 0.015584945678710938 nb_pixel_total : 33 time to create 1 rle with old method : 9.322166442871094e-05 time for calcul the mask position with numpy : 0.01789379119873047 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004589557647705078 time for calcul the mask position with numpy : 0.01569080352783203 nb_pixel_total : 512 time to create 1 rle with old method : 0.0006155967712402344 time for calcul the mask position with numpy : 0.015311717987060547 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004756450653076172 time for calcul the mask position with numpy : 0.015645265579223633 nb_pixel_total : 1356 time to create 1 rle with old method : 0.0016124248504638672 time for calcul the mask position with numpy : 0.015778064727783203 nb_pixel_total : 9 time to create 1 rle with old method : 8.392333984375e-05 time for calcul the mask position with numpy : 0.01574993133544922 nb_pixel_total : 1085 time to create 1 rle with old method : 0.0013384819030761719 time for calcul the mask position with numpy : 0.015581607818603516 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002357959747314453 time for calcul the mask position with numpy : 0.01534724235534668 nb_pixel_total : 160 time to create 1 rle with old method : 0.00023126602172851562 time for calcul the mask position with numpy : 0.015347003936767578 nb_pixel_total : 4124 time to create 1 rle with old method : 0.004667997360229492 time for calcul the mask position with numpy : 0.015486955642700195 nb_pixel_total : 8719 time to create 1 rle with old method : 0.009862661361694336 time for calcul the mask position with numpy : 0.015571832656860352 nb_pixel_total : 589 time to create 1 rle with old method : 0.0007102489471435547 time for calcul the mask position with numpy : 0.01587963104248047 nb_pixel_total : 19 time to create 1 rle with old method : 0.00012683868408203125 time for calcul the mask position with numpy : 0.01609325408935547 nb_pixel_total : 3855 time to create 1 rle with old method : 0.0044744014739990234 time for calcul the mask position with numpy : 0.015211343765258789 nb_pixel_total : 285 time to create 1 rle with old method : 0.00036025047302246094 time for calcul the mask position with numpy : 0.015166997909545898 nb_pixel_total : 576 time to create 1 rle with old method : 0.0007166862487792969 time for calcul the mask position with numpy : 0.015017509460449219 nb_pixel_total : 35 time to create 1 rle with old method : 8.726119995117188e-05 time for calcul the mask position with numpy : 0.0150299072265625 nb_pixel_total : 295 time to create 1 rle with old method : 0.00035309791564941406 time for calcul the mask position with numpy : 0.016047000885009766 nb_pixel_total : 487 time to create 1 rle with old method : 0.0005638599395751953 time for calcul the mask position with numpy : 0.014962434768676758 nb_pixel_total : 1564 time to create 1 rle with old method : 0.0017650127410888672 time for calcul the mask position with numpy : 0.014965534210205078 nb_pixel_total : 487 time to create 1 rle with old method : 0.0005860328674316406 time for calcul the mask position with numpy : 0.01502537727355957 nb_pixel_total : 903 time to create 1 rle with old method : 0.0010275840759277344 time for calcul the mask position with numpy : 0.015005111694335938 nb_pixel_total : 169 time to create 1 rle with old method : 0.00020599365234375 time for calcul the mask position with numpy : 0.015010356903076172 nb_pixel_total : 399 time to create 1 rle with old method : 0.000469207763671875 time for calcul the mask position with numpy : 0.01500391960144043 nb_pixel_total : 656 time to create 1 rle with old method : 0.0007610321044921875 time for calcul the mask position with numpy : 0.014966487884521484 nb_pixel_total : 200 time to create 1 rle with old method : 0.00023365020751953125 time for calcul the mask position with numpy : 0.014905214309692383 nb_pixel_total : 291 time to create 1 rle with old method : 0.0003504753112792969 time for calcul the mask position with numpy : 0.014892578125 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006089210510253906 time for calcul the mask position with numpy : 0.014965534210205078 nb_pixel_total : 94 time to create 1 rle with old method : 0.0001595020294189453 time for calcul the mask position with numpy : 0.014924287796020508 nb_pixel_total : 1442 time to create 1 rle with old method : 0.002168416976928711 time for calcul the mask position with numpy : 0.014971494674682617 nb_pixel_total : 3517 time to create 1 rle with old method : 0.0039827823638916016 time for calcul the mask position with numpy : 0.014918088912963867 nb_pixel_total : 94 time to create 1 rle with old method : 0.00017905235290527344 time for calcul the mask position with numpy : 0.01506948471069336 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002467632293701172 time for calcul the mask position with numpy : 0.014989614486694336 nb_pixel_total : 55 time to create 1 rle with old method : 0.00011491775512695312 time for calcul the mask position with numpy : 0.015001535415649414 nb_pixel_total : 329 time to create 1 rle with old method : 0.0003898143768310547 time for calcul the mask position with numpy : 0.015073299407958984 nb_pixel_total : 1697 time to create 1 rle with old method : 0.0019428730010986328 time for calcul the mask position with numpy : 0.015156984329223633 nb_pixel_total : 329 time to create 1 rle with old method : 0.0003895759582519531 time for calcul the mask position with numpy : 0.015178918838500977 nb_pixel_total : 20 time to create 1 rle with old method : 6.175041198730469e-05 time for calcul the mask position with numpy : 0.015125274658203125 nb_pixel_total : 366 time to create 1 rle with old method : 0.0004425048828125 time for calcul the mask position with numpy : 0.015119791030883789 nb_pixel_total : 639 time to create 1 rle with old method : 0.0007367134094238281 time for calcul the mask position with numpy : 0.015158653259277344 nb_pixel_total : 3 time to create 1 rle with old method : 2.7418136596679688e-05 time for calcul the mask position with numpy : 0.015082836151123047 nb_pixel_total : 357 time to create 1 rle with old method : 0.00043463706970214844 time for calcul the mask position with numpy : 0.015166282653808594 nb_pixel_total : 133 time to create 1 rle with old method : 0.00020313262939453125 time for calcul the mask position with numpy : 0.015095949172973633 nb_pixel_total : 664 time to create 1 rle with old method : 0.0008041858673095703 time for calcul the mask position with numpy : 0.015197515487670898 nb_pixel_total : 8 time to create 1 rle with old method : 4.673004150390625e-05 time for calcul the mask position with numpy : 0.015128612518310547 nb_pixel_total : 510 time to create 1 rle with old method : 0.0006053447723388672 time for calcul the mask position with numpy : 0.015617132186889648 nb_pixel_total : 301 time to create 1 rle with old method : 0.0003867149353027344 time for calcul the mask position with numpy : 0.015704870223999023 nb_pixel_total : 59 time to create 1 rle with old method : 9.393692016601562e-05 time for calcul the mask position with numpy : 0.01566791534423828 nb_pixel_total : 54 time to create 1 rle with old method : 0.0001385211944580078 time for calcul the mask position with numpy : 0.015213251113891602 nb_pixel_total : 8 time to create 1 rle with old method : 4.839897155761719e-05 time for calcul the mask position with numpy : 0.015238761901855469 nb_pixel_total : 177 time to create 1 rle with old method : 0.00022125244140625 time for calcul the mask position with numpy : 0.015107154846191406 nb_pixel_total : 1552 time to create 1 rle with old method : 0.0018091201782226562 time for calcul the mask position with numpy : 0.015163660049438477 nb_pixel_total : 606 time to create 1 rle with old method : 0.0007419586181640625 time for calcul the mask position with numpy : 0.015134572982788086 nb_pixel_total : 656 time to create 1 rle with old method : 0.0008246898651123047 time for calcul the mask position with numpy : 0.015120267868041992 nb_pixel_total : 304 time to create 1 rle with old method : 0.0003619194030761719 time for calcul the mask position with numpy : 0.015152215957641602 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004277229309082031 time for calcul the mask position with numpy : 0.01508021354675293 nb_pixel_total : 291 time to create 1 rle with old method : 0.00034165382385253906 time for calcul the mask position with numpy : 0.015068769454956055 nb_pixel_total : 13 time to create 1 rle with old method : 5.0067901611328125e-05 time for calcul the mask position with numpy : 0.014996528625488281 nb_pixel_total : 1072 time to create 1 rle with old method : 0.0013127326965332031 time for calcul the mask position with numpy : 0.015186548233032227 nb_pixel_total : 486 time to create 1 rle with old method : 0.0005919933319091797 time for calcul the mask position with numpy : 0.015360593795776367 nb_pixel_total : 13 time to create 1 rle with old method : 6.461143493652344e-05 time for calcul the mask position with numpy : 0.016618967056274414 nb_pixel_total : 190 time to create 1 rle with old method : 0.00027632713317871094 time for calcul the mask position with numpy : 0.0175626277923584 nb_pixel_total : 792 time to create 1 rle with old method : 0.0009984970092773438 time for calcul the mask position with numpy : 0.015358686447143555 nb_pixel_total : 22 time to create 1 rle with old method : 7.62939453125e-05 time for calcul the mask position with numpy : 0.015337228775024414 nb_pixel_total : 71 time to create 1 rle with old method : 0.00016832351684570312 time for calcul the mask position with numpy : 0.015323400497436523 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003178119659423828 time for calcul the mask position with numpy : 0.015399694442749023 nb_pixel_total : 54 time to create 1 rle with old method : 0.0001442432403564453 time for calcul the mask position with numpy : 0.015404701232910156 nb_pixel_total : 19 time to create 1 rle with old method : 7.462501525878906e-05 time for calcul the mask position with numpy : 0.015233993530273438 nb_pixel_total : 5153 time to create 1 rle with old method : 0.005881309509277344 time for calcul the mask position with numpy : 0.015114545822143555 nb_pixel_total : 60 time to create 1 rle with old method : 0.00016164779663085938 time for calcul the mask position with numpy : 0.01503610610961914 nb_pixel_total : 301 time to create 1 rle with old method : 0.00038123130798339844 time for calcul the mask position with numpy : 0.01536870002746582 nb_pixel_total : 17 time to create 1 rle with old method : 6.556510925292969e-05 time for calcul the mask position with numpy : 0.015730619430541992 nb_pixel_total : 218 time to create 1 rle with old method : 0.0004417896270751953 time for calcul the mask position with numpy : 0.015105724334716797 nb_pixel_total : 37 time to create 1 rle with old method : 9.965896606445312e-05 time for calcul the mask position with numpy : 0.01521611213684082 nb_pixel_total : 221 time to create 1 rle with old method : 0.00026726722717285156 time for calcul the mask position with numpy : 0.015137910842895508 nb_pixel_total : 296 time to create 1 rle with old method : 0.00035572052001953125 time for calcul the mask position with numpy : 0.015053510665893555 nb_pixel_total : 213 time to create 1 rle with old method : 0.00027823448181152344 time for calcul the mask position with numpy : 0.015125274658203125 nb_pixel_total : 14 time to create 1 rle with old method : 4.792213439941406e-05 time for calcul the mask position with numpy : 0.01505136489868164 nb_pixel_total : 1975 time to create 1 rle with old method : 0.0028357505798339844 time for calcul the mask position with numpy : 0.01819896697998047 nb_pixel_total : 21 time to create 1 rle with old method : 0.00010251998901367188 time for calcul the mask position with numpy : 0.01501607894897461 nb_pixel_total : 5306 time to create 1 rle with old method : 0.005948543548583984 time for calcul the mask position with numpy : 0.015109777450561523 nb_pixel_total : 53 time to create 1 rle with old method : 0.00012373924255371094 time for calcul the mask position with numpy : 0.015045166015625 nb_pixel_total : 610 time to create 1 rle with old method : 0.0007584095001220703 time for calcul the mask position with numpy : 0.015517950057983398 nb_pixel_total : 159 time to create 1 rle with old method : 0.00021767616271972656 time for calcul the mask position with numpy : 0.014999866485595703 nb_pixel_total : 184 time to create 1 rle with old method : 0.0002315044403076172 time for calcul the mask position with numpy : 0.01497960090637207 nb_pixel_total : 666 time to create 1 rle with old method : 0.0007910728454589844 time for calcul the mask position with numpy : 0.01508188247680664 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001461505889892578 time for calcul the mask position with numpy : 0.015004396438598633 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007112026214599609 time for calcul the mask position with numpy : 0.015158653259277344 nb_pixel_total : 166 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.015027999877929688 nb_pixel_total : 10 time to create 1 rle with old method : 5.793571472167969e-05 time for calcul the mask position with numpy : 0.015066862106323242 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003402233123779297 time for calcul the mask position with numpy : 0.015085697174072266 nb_pixel_total : 74 time to create 1 rle with old method : 9.298324584960938e-05 time for calcul the mask position with numpy : 0.016770362854003906 nb_pixel_total : 1087 time to create 1 rle with old method : 0.001516580581665039 time for calcul the mask position with numpy : 0.015424489974975586 nb_pixel_total : 1098 time to create 1 rle with old method : 0.001386880874633789 time for calcul the mask position with numpy : 0.015841245651245117 nb_pixel_total : 213 time to create 1 rle with old method : 0.0002601146697998047 time for calcul the mask position with numpy : 0.015931367874145508 nb_pixel_total : 7 time to create 1 rle with old method : 3.4809112548828125e-05 time for calcul the mask position with numpy : 0.015248775482177734 nb_pixel_total : 59 time to create 1 rle with old method : 0.0001087188720703125 time for calcul the mask position with numpy : 0.015403270721435547 nb_pixel_total : 10 time to create 1 rle with old method : 8.130073547363281e-05 time for calcul the mask position with numpy : 0.015479087829589844 nb_pixel_total : 252 time to create 1 rle with old method : 0.00045990943908691406 time for calcul the mask position with numpy : 0.01725459098815918 nb_pixel_total : 192 time to create 1 rle with old method : 0.0003504753112792969 time for calcul the mask position with numpy : 0.017410993576049805 nb_pixel_total : 549 time to create 1 rle with old method : 0.0009267330169677734 time for calcul the mask position with numpy : 0.017380237579345703 nb_pixel_total : 8 time to create 1 rle with old method : 9.608268737792969e-05 time for calcul the mask position with numpy : 0.01740741729736328 nb_pixel_total : 1445 time to create 1 rle with old method : 0.002420663833618164 time for calcul the mask position with numpy : 0.016921281814575195 nb_pixel_total : 2252 time to create 1 rle with old method : 0.002540111541748047 time for calcul the mask position with numpy : 0.015234947204589844 nb_pixel_total : 49 time to create 1 rle with old method : 0.0001652240753173828 time for calcul the mask position with numpy : 0.015319108963012695 nb_pixel_total : 387 time to create 1 rle with old method : 0.0005092620849609375 time for calcul the mask position with numpy : 0.01525115966796875 nb_pixel_total : 4110 time to create 1 rle with old method : 0.004706382751464844 time for calcul the mask position with numpy : 0.01519322395324707 nb_pixel_total : 2132 time to create 1 rle with old method : 0.0025887489318847656 time for calcul the mask position with numpy : 0.015071392059326172 nb_pixel_total : 42 time to create 1 rle with old method : 0.0001850128173828125 time for calcul the mask position with numpy : 0.020761489868164062 nb_pixel_total : 23638 time to create 1 rle with old method : 0.02916121482849121 time for calcul the mask position with numpy : 0.01771688461303711 nb_pixel_total : 47 time to create 1 rle with old method : 0.0001735687255859375 time for calcul the mask position with numpy : 0.019087553024291992 nb_pixel_total : 204 time to create 1 rle with old method : 0.00037026405334472656 time for calcul the mask position with numpy : 0.015678882598876953 nb_pixel_total : 11 time to create 1 rle with old method : 5.221366882324219e-05 time for calcul the mask position with numpy : 0.01690053939819336 nb_pixel_total : 112 time to create 1 rle with old method : 0.00016951560974121094 time for calcul the mask position with numpy : 0.01525568962097168 nb_pixel_total : 15 time to create 1 rle with old method : 6.079673767089844e-05 time for calcul the mask position with numpy : 0.015258550643920898 nb_pixel_total : 2146 time to create 1 rle with old method : 0.0024924278259277344 time for calcul the mask position with numpy : 0.017255067825317383 nb_pixel_total : 705 time to create 1 rle with old method : 0.0010542869567871094 time for calcul the mask position with numpy : 0.015642404556274414 nb_pixel_total : 11 time to create 1 rle with old method : 4.172325134277344e-05 time for calcul the mask position with numpy : 0.015305519104003906 nb_pixel_total : 331 time to create 1 rle with old method : 0.00040602684020996094 time for calcul the mask position with numpy : 0.016780614852905273 nb_pixel_total : 814 time to create 1 rle with old method : 0.0012853145599365234 time for calcul the mask position with numpy : 0.01594090461730957 nb_pixel_total : 44 time to create 1 rle with old method : 0.00012087821960449219 time for calcul the mask position with numpy : 0.015068769454956055 nb_pixel_total : 1 time to create 1 rle with old method : 4.649162292480469e-05 time for calcul the mask position with numpy : 0.016831398010253906 nb_pixel_total : 528 time to create 1 rle with old method : 0.0006496906280517578 time for calcul the mask position with numpy : 0.015406370162963867 nb_pixel_total : 31 time to create 1 rle with old method : 8.869171142578125e-05 time for calcul the mask position with numpy : 0.015395402908325195 nb_pixel_total : 25 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.01541280746459961 nb_pixel_total : 508 time to create 1 rle with old method : 0.0006268024444580078 time for calcul the mask position with numpy : 0.015292882919311523 nb_pixel_total : 1708 time to create 1 rle with old method : 0.001971721649169922 time for calcul the mask position with numpy : 0.017997026443481445 nb_pixel_total : 17 time to create 1 rle with old method : 8.273124694824219e-05 time for calcul the mask position with numpy : 0.01710796356201172 nb_pixel_total : 261 time to create 1 rle with old method : 0.000408172607421875 time for calcul the mask position with numpy : 0.015753507614135742 nb_pixel_total : 559 time to create 1 rle with old method : 0.0008358955383300781 time for calcul the mask position with numpy : 0.015668392181396484 nb_pixel_total : 2711 time to create 1 rle with old method : 0.003183603286743164 time for calcul the mask position with numpy : 0.015630006790161133 nb_pixel_total : 1249 time to create 1 rle with old method : 0.001577138900756836 time for calcul the mask position with numpy : 0.015558481216430664 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005183219909667969 time for calcul the mask position with numpy : 0.015617609024047852 nb_pixel_total : 79 time to create 1 rle with old method : 0.00021004676818847656 time for calcul the mask position with numpy : 0.015568971633911133 nb_pixel_total : 802 time to create 1 rle with old method : 0.0009846687316894531 time for calcul the mask position with numpy : 0.01575303077697754 nb_pixel_total : 6 time to create 1 rle with old method : 6.127357482910156e-05 time for calcul the mask position with numpy : 0.015738487243652344 nb_pixel_total : 381 time to create 1 rle with old method : 0.00054168701171875 time for calcul the mask position with numpy : 0.015834808349609375 nb_pixel_total : 335 time to create 1 rle with old method : 0.0005335807800292969 time for calcul the mask position with numpy : 0.017322063446044922 nb_pixel_total : 1068 time to create 1 rle with old method : 0.0015759468078613281 time for calcul the mask position with numpy : 0.016258955001831055 nb_pixel_total : 740 time to create 1 rle with old method : 0.000949859619140625 time for calcul the mask position with numpy : 0.01578545570373535 nb_pixel_total : 104 time to create 1 rle with old method : 0.0002522468566894531 time for calcul the mask position with numpy : 0.01568126678466797 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002961158752441406 time for calcul the mask position with numpy : 0.015744924545288086 nb_pixel_total : 2447 time to create 1 rle with old method : 0.0029134750366210938 time for calcul the mask position with numpy : 0.015695571899414062 nb_pixel_total : 2064 time to create 1 rle with old method : 0.0024297237396240234 time for calcul the mask position with numpy : 0.01576542854309082 nb_pixel_total : 73 time to create 1 rle with old method : 0.0002617835998535156 time for calcul the mask position with numpy : 0.015908002853393555 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005731582641601562 time for calcul the mask position with numpy : 0.015781879425048828 nb_pixel_total : 1741 time to create 1 rle with old method : 0.002025127410888672 time for calcul the mask position with numpy : 0.015733957290649414 nb_pixel_total : 437 time to create 1 rle with old method : 0.0009377002716064453 time for calcul the mask position with numpy : 0.017647743225097656 nb_pixel_total : 353 time to create 1 rle with old method : 0.0006499290466308594 time for calcul the mask position with numpy : 0.017574071884155273 nb_pixel_total : 4729 time to create 1 rle with old method : 0.008049964904785156 time for calcul the mask position with numpy : 0.018125057220458984 nb_pixel_total : 1948 time to create 1 rle with old method : 0.0034308433532714844 time for calcul the mask position with numpy : 0.017432212829589844 nb_pixel_total : 429 time to create 1 rle with old method : 0.0006279945373535156 time for calcul the mask position with numpy : 0.015675067901611328 nb_pixel_total : 456 time to create 1 rle with old method : 0.0005905628204345703 time for calcul the mask position with numpy : 0.015729427337646484 nb_pixel_total : 26 time to create 1 rle with old method : 0.00010204315185546875 time for calcul the mask position with numpy : 0.015527486801147461 nb_pixel_total : 47 time to create 1 rle with old method : 0.0001327991485595703 time for calcul the mask position with numpy : 0.015512943267822266 nb_pixel_total : 164 time to create 1 rle with old method : 0.0002810955047607422 time for calcul the mask position with numpy : 0.015513181686401367 nb_pixel_total : 29 time to create 1 rle with old method : 7.343292236328125e-05 time for calcul the mask position with numpy : 0.01558995246887207 nb_pixel_total : 3 time to create 1 rle with old method : 4.673004150390625e-05 time for calcul the mask position with numpy : 0.015569925308227539 nb_pixel_total : 1248 time to create 1 rle with old method : 0.0015003681182861328 time for calcul the mask position with numpy : 0.015558004379272461 nb_pixel_total : 13 time to create 1 rle with old method : 0.000141143798828125 time for calcul the mask position with numpy : 0.015460491180419922 nb_pixel_total : 858 time to create 1 rle with old method : 0.0010592937469482422 time for calcul the mask position with numpy : 0.015093326568603516 nb_pixel_total : 796 time to create 1 rle with old method : 0.0009572505950927734 time for calcul the mask position with numpy : 0.015101909637451172 nb_pixel_total : 704 time to create 1 rle with old method : 0.0008325576782226562 time for calcul the mask position with numpy : 0.015166282653808594 nb_pixel_total : 2029 time to create 1 rle with old method : 0.002313375473022461 time for calcul the mask position with numpy : 0.015291690826416016 nb_pixel_total : 29 time to create 1 rle with old method : 0.00012564659118652344 time for calcul the mask position with numpy : 0.015332698822021484 nb_pixel_total : 328 time to create 1 rle with old method : 0.00038933753967285156 time for calcul the mask position with numpy : 0.016224145889282227 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002715587615966797 time for calcul the mask position with numpy : 0.015379190444946289 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003657341003417969 time for calcul the mask position with numpy : 0.015398502349853516 nb_pixel_total : 893 time to create 1 rle with old method : 0.0010411739349365234 time for calcul the mask position with numpy : 0.015407800674438477 nb_pixel_total : 1551 time to create 1 rle with old method : 0.0017852783203125 time for calcul the mask position with numpy : 0.015412330627441406 nb_pixel_total : 2300 time to create 1 rle with old method : 0.002607107162475586 time for calcul the mask position with numpy : 0.01747441291809082 nb_pixel_total : 482 time to create 1 rle with old method : 0.0005619525909423828 time for calcul the mask position with numpy : 0.01553797721862793 nb_pixel_total : 56 time to create 1 rle with old method : 0.00014400482177734375 time for calcul the mask position with numpy : 0.01572585105895996 nb_pixel_total : 72 time to create 1 rle with old method : 0.0001533031463623047 time for calcul the mask position with numpy : 0.01549839973449707 nb_pixel_total : 33 time to create 1 rle with old method : 0.00010919570922851562 time for calcul the mask position with numpy : 0.015311002731323242 nb_pixel_total : 1072 time to create 1 rle with old method : 0.001318216323852539 time for calcul the mask position with numpy : 0.01663947105407715 nb_pixel_total : 464 time to create 1 rle with old method : 0.0009677410125732422 time for calcul the mask position with numpy : 0.01722860336303711 nb_pixel_total : 501 time to create 1 rle with old method : 0.0006251335144042969 time for calcul the mask position with numpy : 0.015360593795776367 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002722740173339844 time for calcul the mask position with numpy : 0.015416145324707031 nb_pixel_total : 493 time to create 1 rle with old method : 0.0006191730499267578 time for calcul the mask position with numpy : 0.015444517135620117 nb_pixel_total : 111 time to create 1 rle with old method : 0.00015234947204589844 time for calcul the mask position with numpy : 0.015376806259155273 nb_pixel_total : 2 time to create 1 rle with old method : 3.0279159545898438e-05 time for calcul the mask position with numpy : 0.015431642532348633 nb_pixel_total : 6 time to create 1 rle with old method : 4.57763671875e-05 time for calcul the mask position with numpy : 0.015398025512695312 nb_pixel_total : 288 time to create 1 rle with old method : 0.0003762245178222656 time for calcul the mask position with numpy : 0.016304492950439453 nb_pixel_total : 290 time to create 1 rle with old method : 0.00036072731018066406 time for calcul the mask position with numpy : 0.015275239944458008 nb_pixel_total : 127 time to create 1 rle with old method : 0.00017833709716796875 time for calcul the mask position with numpy : 0.015288591384887695 nb_pixel_total : 1161 time to create 1 rle with old method : 0.0013680458068847656 time for calcul the mask position with numpy : 0.015323400497436523 nb_pixel_total : 79 time to create 1 rle with old method : 0.00014448165893554688 time for calcul the mask position with numpy : 0.01537632942199707 nb_pixel_total : 3799 time to create 1 rle with old method : 0.004405975341796875 time for calcul the mask position with numpy : 0.017388343811035156 nb_pixel_total : 8051 time to create 1 rle with old method : 0.012813091278076172 time for calcul the mask position with numpy : 0.015236139297485352 nb_pixel_total : 73 time to create 1 rle with old method : 0.00015926361083984375 time for calcul the mask position with numpy : 0.0172426700592041 nb_pixel_total : 1355 time to create 1 rle with old method : 0.0026407241821289062 time for calcul the mask position with numpy : 0.018235445022583008 nb_pixel_total : 3742 time to create 1 rle with old method : 0.004752159118652344 time for calcul the mask position with numpy : 0.015187263488769531 nb_pixel_total : 1185 time to create 1 rle with old method : 0.0013835430145263672 time for calcul the mask position with numpy : 0.015267372131347656 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003292560577392578 time for calcul the mask position with numpy : 0.015324592590332031 nb_pixel_total : 2880 time to create 1 rle with old method : 0.003381490707397461 time for calcul the mask position with numpy : 0.015141725540161133 nb_pixel_total : 226 time to create 1 rle with old method : 0.0002989768981933594 time for calcul the mask position with numpy : 0.015173196792602539 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003452301025390625 time for calcul the mask position with numpy : 0.01516866683959961 nb_pixel_total : 543 time to create 1 rle with old method : 0.0006582736968994141 time for calcul the mask position with numpy : 0.015302658081054688 nb_pixel_total : 330 time to create 1 rle with old method : 0.0006482601165771484 time for calcul the mask position with numpy : 0.017373323440551758 nb_pixel_total : 411 time to create 1 rle with old method : 0.0007116794586181641 time for calcul the mask position with numpy : 0.01757216453552246 nb_pixel_total : 177 time to create 1 rle with old method : 0.00032639503479003906 time for calcul the mask position with numpy : 0.017502307891845703 nb_pixel_total : 235 time to create 1 rle with old method : 0.0004394054412841797 time for calcul the mask position with numpy : 0.017322778701782227 nb_pixel_total : 85 time to create 1 rle with old method : 0.0001761913299560547 time for calcul the mask position with numpy : 0.017096519470214844 nb_pixel_total : 587 time to create 1 rle with old method : 0.0007157325744628906 time for calcul the mask position with numpy : 0.015330791473388672 nb_pixel_total : 5670 time to create 1 rle with old method : 0.006327629089355469 time for calcul the mask position with numpy : 0.015397787094116211 nb_pixel_total : 669 time to create 1 rle with old method : 0.0007967948913574219 time for calcul the mask position with numpy : 0.015200376510620117 nb_pixel_total : 2632 time to create 1 rle with old method : 0.003020763397216797 time for calcul the mask position with numpy : 0.015310287475585938 nb_pixel_total : 229 time to create 1 rle with old method : 0.0002944469451904297 time for calcul the mask position with numpy : 0.015201330184936523 nb_pixel_total : 500 time to create 1 rle with old method : 0.0005869865417480469 time for calcul the mask position with numpy : 0.015199422836303711 nb_pixel_total : 383 time to create 1 rle with old method : 0.0004649162292480469 time for calcul the mask position with numpy : 0.015289783477783203 nb_pixel_total : 1960 time to create 1 rle with old method : 0.002248525619506836 time for calcul the mask position with numpy : 0.01533055305480957 nb_pixel_total : 490 time to create 1 rle with old method : 0.0005972385406494141 time for calcul the mask position with numpy : 0.015264749526977539 nb_pixel_total : 332 time to create 1 rle with old method : 0.00038743019104003906 time for calcul the mask position with numpy : 0.015241384506225586 nb_pixel_total : 383 time to create 1 rle with old method : 0.00047516822814941406 time for calcul the mask position with numpy : 0.015246152877807617 nb_pixel_total : 4691 time to create 1 rle with old method : 0.005437374114990234 time for calcul the mask position with numpy : 0.01529550552368164 nb_pixel_total : 193 time to create 1 rle with old method : 0.00025463104248046875 time for calcul the mask position with numpy : 0.015328645706176758 nb_pixel_total : 211 time to create 1 rle with old method : 0.00028777122497558594 time for calcul the mask position with numpy : 0.017246246337890625 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003840923309326172 time for calcul the mask position with numpy : 0.015664339065551758 nb_pixel_total : 328 time to create 1 rle with old method : 0.0003998279571533203 time for calcul the mask position with numpy : 0.01775217056274414 nb_pixel_total : 852 time to create 1 rle with old method : 0.001245737075805664 time for calcul the mask position with numpy : 0.018164634704589844 nb_pixel_total : 143 time to create 1 rle with old method : 0.00019931793212890625 time for calcul the mask position with numpy : 0.015052080154418945 nb_pixel_total : 1226 time to create 1 rle with old method : 0.0017750263214111328 time for calcul the mask position with numpy : 0.015288829803466797 nb_pixel_total : 5 time to create 1 rle with old method : 4.220008850097656e-05 time for calcul the mask position with numpy : 0.015772104263305664 nb_pixel_total : 1303 time to create 1 rle with old method : 0.0015392303466796875 time for calcul the mask position with numpy : 0.01523447036743164 nb_pixel_total : 8221 time to create 1 rle with old method : 0.00934600830078125 time for calcul the mask position with numpy : 0.015358686447143555 nb_pixel_total : 534 time to create 1 rle with old method : 0.000659942626953125 time for calcul the mask position with numpy : 0.015179872512817383 nb_pixel_total : 524 time to create 1 rle with old method : 0.0006544589996337891 time for calcul the mask position with numpy : 0.01536417007446289 nb_pixel_total : 825 time to create 1 rle with old method : 0.0009760856628417969 time for calcul the mask position with numpy : 0.015258550643920898 nb_pixel_total : 990 time to create 1 rle with old method : 0.0011703968048095703 time for calcul the mask position with numpy : 0.017254352569580078 nb_pixel_total : 8 time to create 1 rle with old method : 6.0558319091796875e-05 time for calcul the mask position with numpy : 0.01631760597229004 nb_pixel_total : 377 time to create 1 rle with old method : 0.00045943260192871094 time for calcul the mask position with numpy : 0.015100240707397461 nb_pixel_total : 248 time to create 1 rle with old method : 0.00032138824462890625 time for calcul the mask position with numpy : 0.015583992004394531 nb_pixel_total : 478 time to create 1 rle with old method : 0.0006723403930664062 time for calcul the mask position with numpy : 0.015317201614379883 nb_pixel_total : 128 time to create 1 rle with old method : 0.00020456314086914062 time for calcul the mask position with numpy : 0.015567779541015625 nb_pixel_total : 983 time to create 1 rle with old method : 0.001195669174194336 time for calcul the mask position with numpy : 0.015410661697387695 nb_pixel_total : 4995 time to create 1 rle with old method : 0.005658626556396484 time for calcul the mask position with numpy : 0.015055656433105469 nb_pixel_total : 593 time to create 1 rle with old method : 0.0007321834564208984 time for calcul the mask position with numpy : 0.01480245590209961 nb_pixel_total : 272 time to create 1 rle with old method : 0.0004267692565917969 time for calcul the mask position with numpy : 0.015436649322509766 nb_pixel_total : 12 time to create 1 rle with old method : 0.00010848045349121094 time for calcul the mask position with numpy : 0.015012741088867188 nb_pixel_total : 2834 time to create 1 rle with old method : 0.0032625198364257812 time for calcul the mask position with numpy : 0.015393733978271484 nb_pixel_total : 95 time to create 1 rle with old method : 0.00014781951904296875 time for calcul the mask position with numpy : 0.015354156494140625 nb_pixel_total : 10158 time to create 1 rle with old method : 0.011396408081054688 time for calcul the mask position with numpy : 0.01528167724609375 nb_pixel_total : 113 time to create 1 rle with old method : 0.00024700164794921875 time for calcul the mask position with numpy : 0.015296220779418945 nb_pixel_total : 307 time to create 1 rle with old method : 0.0004284381866455078 time for calcul the mask position with numpy : 0.015067338943481445 nb_pixel_total : 628 time to create 1 rle with old method : 0.0007467269897460938 time for calcul the mask position with numpy : 0.015370607376098633 nb_pixel_total : 637 time to create 1 rle with old method : 0.0007674694061279297 time for calcul the mask position with numpy : 0.014826774597167969 nb_pixel_total : 202 time to create 1 rle with old method : 0.00028324127197265625 time for calcul the mask position with numpy : 0.015597820281982422 nb_pixel_total : 311 time to create 1 rle with old method : 0.00039315223693847656 time for calcul the mask position with numpy : 0.015593290328979492 nb_pixel_total : 1937 time to create 1 rle with old method : 0.0023772716522216797 time for calcul the mask position with numpy : 0.015824556350708008 nb_pixel_total : 1209 time to create 1 rle with old method : 0.0014681816101074219 time for calcul the mask position with numpy : 0.01707625389099121 nb_pixel_total : 2682 time to create 1 rle with old method : 0.003308534622192383 time for calcul the mask position with numpy : 0.015376567840576172 nb_pixel_total : 6475 time to create 1 rle with old method : 0.0076901912689208984 time for calcul the mask position with numpy : 0.0158383846282959 nb_pixel_total : 23 time to create 1 rle with old method : 0.00011444091796875 time for calcul the mask position with numpy : 0.015318870544433594 nb_pixel_total : 1805 time to create 1 rle with old method : 0.00206756591796875 time for calcul the mask position with numpy : 0.015221118927001953 nb_pixel_total : 1592 time to create 1 rle with old method : 0.00182342529296875 time for calcul the mask position with numpy : 0.015201807022094727 nb_pixel_total : 922 time to create 1 rle with old method : 0.0010845661163330078 time for calcul the mask position with numpy : 0.015282392501831055 nb_pixel_total : 486 time to create 1 rle with old method : 0.0005908012390136719 time for calcul the mask position with numpy : 0.015512704849243164 nb_pixel_total : 642 time to create 1 rle with old method : 0.0008480548858642578 time for calcul the mask position with numpy : 0.015341997146606445 nb_pixel_total : 1362 time to create 1 rle with old method : 0.0015652179718017578 time for calcul the mask position with numpy : 0.01537322998046875 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002682209014892578 time for calcul the mask position with numpy : 0.015297889709472656 nb_pixel_total : 2289 time to create 1 rle with old method : 0.002785205841064453 time for calcul the mask position with numpy : 0.015618085861206055 nb_pixel_total : 2016 time to create 1 rle with old method : 0.0023920536041259766 time for calcul the mask position with numpy : 0.015518426895141602 nb_pixel_total : 4099 time to create 1 rle with old method : 0.004782676696777344 time for calcul the mask position with numpy : 0.016002893447875977 nb_pixel_total : 6788 time to create 1 rle with old method : 0.007870674133300781 time for calcul the mask position with numpy : 0.015595436096191406 nb_pixel_total : 34 time to create 1 rle with old method : 8.630752563476562e-05 time for calcul the mask position with numpy : 0.015636444091796875 nb_pixel_total : 1264 time to create 1 rle with old method : 0.0015211105346679688 time for calcul the mask position with numpy : 0.015506744384765625 nb_pixel_total : 491 time to create 1 rle with old method : 0.0006730556488037109 time for calcul the mask position with numpy : 0.015511751174926758 nb_pixel_total : 468 time to create 1 rle with old method : 0.0005872249603271484 time for calcul the mask position with numpy : 0.015560626983642578 nb_pixel_total : 815 time to create 1 rle with old method : 0.0009827613830566406 time for calcul the mask position with numpy : 0.01559758186340332 nb_pixel_total : 26 time to create 1 rle with old method : 0.0001347064971923828 time for calcul the mask position with numpy : 0.015722274780273438 nb_pixel_total : 805 time to create 1 rle with old method : 0.0009799003601074219 time for calcul the mask position with numpy : 0.01568889617919922 nb_pixel_total : 2197 time to create 1 rle with old method : 0.002628803253173828 time for calcul the mask position with numpy : 0.015929698944091797 nb_pixel_total : 1192 time to create 1 rle with old method : 0.0014338493347167969 time for calcul the mask position with numpy : 0.01573967933654785 nb_pixel_total : 98 time to create 1 rle with old method : 0.0002593994140625 time for calcul the mask position with numpy : 0.016822338104248047 nb_pixel_total : 6851 time to create 1 rle with old method : 0.014962196350097656 time for calcul the mask position with numpy : 0.015332221984863281 nb_pixel_total : 7 time to create 1 rle with old method : 5.602836608886719e-05 time for calcul the mask position with numpy : 0.015210866928100586 nb_pixel_total : 838 time to create 1 rle with old method : 0.0009725093841552734 time for calcul the mask position with numpy : 0.01509714126586914 nb_pixel_total : 2522 time to create 1 rle with old method : 0.002833843231201172 time for calcul the mask position with numpy : 0.015094757080078125 nb_pixel_total : 5667 time to create 1 rle with old method : 0.0064237117767333984 time for calcul the mask position with numpy : 0.01495218276977539 nb_pixel_total : 1186 time to create 1 rle with old method : 0.001352548599243164 time for calcul the mask position with numpy : 0.015272855758666992 nb_pixel_total : 239 time to create 1 rle with old method : 0.000293731689453125 time for calcul the mask position with numpy : 0.016704559326171875 nb_pixel_total : 629 time to create 1 rle with old method : 0.0007622241973876953 time for calcul the mask position with numpy : 0.015445232391357422 nb_pixel_total : 2351 time to create 1 rle with old method : 0.0027451515197753906 time for calcul the mask position with numpy : 0.015574932098388672 nb_pixel_total : 309 time to create 1 rle with old method : 0.0005059242248535156 time for calcul the mask position with numpy : 0.015406370162963867 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002238750457763672 time for calcul the mask position with numpy : 0.015246868133544922 nb_pixel_total : 917 time to create 1 rle with old method : 0.0010783672332763672 time for calcul the mask position with numpy : 0.015273571014404297 nb_pixel_total : 4415 time to create 1 rle with old method : 0.005008697509765625 time for calcul the mask position with numpy : 0.015322208404541016 nb_pixel_total : 325 time to create 1 rle with old method : 0.000408172607421875 time for calcul the mask position with numpy : 0.015305757522583008 nb_pixel_total : 92 time to create 1 rle with old method : 0.00016736984252929688 time for calcul the mask position with numpy : 0.01530313491821289 nb_pixel_total : 3908 time to create 1 rle with old method : 0.004483699798583984 time for calcul the mask position with numpy : 0.017095088958740234 nb_pixel_total : 4995 time to create 1 rle with old method : 0.00563812255859375 time for calcul the mask position with numpy : 0.015302419662475586 nb_pixel_total : 1195 time to create 1 rle with old method : 0.001367807388305664 time for calcul the mask position with numpy : 0.015132904052734375 nb_pixel_total : 1243 time to create 1 rle with old method : 0.0014586448669433594 time for calcul the mask position with numpy : 0.015031099319458008 nb_pixel_total : 697 time to create 1 rle with old method : 0.0008826255798339844 time for calcul the mask position with numpy : 0.0153350830078125 nb_pixel_total : 308 time to create 1 rle with old method : 0.0004799365997314453 time for calcul the mask position with numpy : 0.015399694442749023 nb_pixel_total : 959 time to create 1 rle with old method : 0.0011646747589111328 time for calcul the mask position with numpy : 0.017975568771362305 nb_pixel_total : 764 time to create 1 rle with old method : 0.0009562969207763672 time for calcul the mask position with numpy : 0.015243053436279297 nb_pixel_total : 750 time to create 1 rle with old method : 0.0008847713470458984 time for calcul the mask position with numpy : 0.015372514724731445 nb_pixel_total : 236 time to create 1 rle with old method : 0.00030303001403808594 time for calcul the mask position with numpy : 0.015214204788208008 nb_pixel_total : 95 time to create 1 rle with old method : 0.00013899803161621094 time for calcul the mask position with numpy : 0.015286922454833984 nb_pixel_total : 525 time to create 1 rle with old method : 0.0006742477416992188 time for calcul the mask position with numpy : 0.015407323837280273 nb_pixel_total : 1164 time to create 1 rle with old method : 0.0013556480407714844 time for calcul the mask position with numpy : 0.015397310256958008 nb_pixel_total : 78 time to create 1 rle with old method : 0.00013947486877441406 time for calcul the mask position with numpy : 0.015387535095214844 nb_pixel_total : 611 time to create 1 rle with old method : 0.000732421875 time for calcul the mask position with numpy : 0.015231132507324219 nb_pixel_total : 73 time to create 1 rle with old method : 0.00010919570922851562 time for calcul the mask position with numpy : 0.015481710433959961 nb_pixel_total : 1239 time to create 1 rle with old method : 0.0014781951904296875 time for calcul the mask position with numpy : 0.015419244766235352 nb_pixel_total : 3780 time to create 1 rle with old method : 0.004388332366943359 time for calcul the mask position with numpy : 0.015408754348754883 nb_pixel_total : 2910 time to create 1 rle with old method : 0.003412961959838867 time for calcul the mask position with numpy : 0.01780533790588379 nb_pixel_total : 3513 time to create 1 rle with old method : 0.004168033599853516 time for calcul the mask position with numpy : 0.015159368515014648 nb_pixel_total : 954 time to create 1 rle with old method : 0.001203775405883789 time for calcul the mask position with numpy : 0.015160083770751953 nb_pixel_total : 1115 time to create 1 rle with old method : 0.0013370513916015625 time for calcul the mask position with numpy : 0.01595592498779297 nb_pixel_total : 62053 time to create 1 rle with old method : 0.06891155242919922 time for calcul the mask position with numpy : 0.015284538269042969 nb_pixel_total : 491 time to create 1 rle with old method : 0.0009090900421142578 time for calcul the mask position with numpy : 0.015048503875732422 nb_pixel_total : 410 time to create 1 rle with old method : 0.0004820823669433594 time for calcul the mask position with numpy : 0.015293598175048828 nb_pixel_total : 1193 time to create 1 rle with old method : 0.0014014244079589844 time for calcul the mask position with numpy : 0.01527714729309082 nb_pixel_total : 773 time to create 1 rle with old method : 0.0009324550628662109 time for calcul the mask position with numpy : 0.01785111427307129 nb_pixel_total : 1504 time to create 1 rle with old method : 0.0017600059509277344 time for calcul the mask position with numpy : 0.015540599822998047 nb_pixel_total : 152 time to create 1 rle with old method : 0.0002143383026123047 time for calcul the mask position with numpy : 0.016002178192138672 nb_pixel_total : 643 time to create 1 rle with old method : 0.0008013248443603516 time for calcul the mask position with numpy : 0.015546560287475586 nb_pixel_total : 462 time to create 1 rle with old method : 0.0005745887756347656 time for calcul the mask position with numpy : 0.015741825103759766 nb_pixel_total : 4843 time to create 1 rle with old method : 0.0055086612701416016 time for calcul the mask position with numpy : 0.015598058700561523 nb_pixel_total : 26884 time to create 1 rle with old method : 0.03230929374694824 time for calcul the mask position with numpy : 0.015316009521484375 nb_pixel_total : 103 time to create 1 rle with old method : 0.00016808509826660156 time for calcul the mask position with numpy : 0.015340328216552734 nb_pixel_total : 483 time to create 1 rle with old method : 0.0006499290466308594 time for calcul the mask position with numpy : 0.015307426452636719 nb_pixel_total : 178 time to create 1 rle with old method : 0.00023102760314941406 time for calcul the mask position with numpy : 0.015787124633789062 nb_pixel_total : 489 time to create 1 rle with old method : 0.0008118152618408203 time for calcul the mask position with numpy : 0.016386747360229492 nb_pixel_total : 677 time to create 1 rle with old method : 0.0008347034454345703 time for calcul the mask position with numpy : 0.015601396560668945 nb_pixel_total : 99 time to create 1 rle with old method : 0.00017595291137695312 time for calcul the mask position with numpy : 0.015796422958374023 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002808570861816406 time for calcul the mask position with numpy : 0.015694379806518555 nb_pixel_total : 130 time to create 1 rle with old method : 0.00019311904907226562 time for calcul the mask position with numpy : 0.015561819076538086 nb_pixel_total : 3752 time to create 1 rle with old method : 0.004335165023803711 time for calcul the mask position with numpy : 0.015474319458007812 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0012180805206298828 time for calcul the mask position with numpy : 0.015527009963989258 nb_pixel_total : 393 time to create 1 rle with old method : 0.0005154609680175781 time for calcul the mask position with numpy : 0.015498638153076172 nb_pixel_total : 645 time to create 1 rle with old method : 0.000804901123046875 time for calcul the mask position with numpy : 0.017487287521362305 nb_pixel_total : 7 time to create 1 rle with old method : 6.532669067382812e-05 time for calcul the mask position with numpy : 0.017699003219604492 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005464553833007812 time for calcul the mask position with numpy : 0.015643596649169922 nb_pixel_total : 1645 time to create 1 rle with old method : 0.0020198822021484375 time for calcul the mask position with numpy : 0.017606258392333984 nb_pixel_total : 637 time to create 1 rle with old method : 0.0007696151733398438 time for calcul the mask position with numpy : 0.015569210052490234 nb_pixel_total : 496 time to create 1 rle with old method : 0.0006563663482666016 time for calcul the mask position with numpy : 0.015818357467651367 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006089210510253906 time for calcul the mask position with numpy : 0.015809297561645508 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007085800170898438 time for calcul the mask position with numpy : 0.015548467636108398 nb_pixel_total : 39 time to create 1 rle with old method : 0.00010347366333007812 time for calcul the mask position with numpy : 0.01581096649169922 nb_pixel_total : 5677 time to create 1 rle with old method : 0.006490945816040039 time for calcul the mask position with numpy : 0.015586137771606445 nb_pixel_total : 702 time to create 1 rle with old method : 0.0008549690246582031 time for calcul the mask position with numpy : 0.015350341796875 nb_pixel_total : 5 time to create 1 rle with old method : 3.981590270996094e-05 time for calcul the mask position with numpy : 0.015155792236328125 nb_pixel_total : 3340 time to create 1 rle with old method : 0.003826141357421875 time for calcul the mask position with numpy : 0.016516685485839844 nb_pixel_total : 1817 time to create 1 rle with old method : 0.0023233890533447266 time for calcul the mask position with numpy : 0.015345096588134766 nb_pixel_total : 2390 time to create 1 rle with old method : 0.002737283706665039 time for calcul the mask position with numpy : 0.017273664474487305 nb_pixel_total : 323 time to create 1 rle with old method : 0.0011508464813232422 time for calcul the mask position with numpy : 0.01538395881652832 nb_pixel_total : 1512 time to create 1 rle with old method : 0.001781463623046875 time for calcul the mask position with numpy : 0.015285253524780273 nb_pixel_total : 644 time to create 1 rle with old method : 0.0007631778717041016 time for calcul the mask position with numpy : 0.015460729598999023 nb_pixel_total : 424 time to create 1 rle with old method : 0.0005207061767578125 time for calcul the mask position with numpy : 0.015469074249267578 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007865428924560547 time for calcul the mask position with numpy : 0.015518903732299805 nb_pixel_total : 465 time to create 1 rle with old method : 0.0005586147308349609 time for calcul the mask position with numpy : 0.015460491180419922 nb_pixel_total : 1487 time to create 1 rle with old method : 0.0017118453979492188 time for calcul the mask position with numpy : 0.015508651733398438 nb_pixel_total : 3055 time to create 1 rle with old method : 0.0034275054931640625 time for calcul the mask position with numpy : 0.015294313430786133 nb_pixel_total : 2697 time to create 1 rle with old method : 0.003068208694458008 time for calcul the mask position with numpy : 0.01522970199584961 nb_pixel_total : 431 time to create 1 rle with old method : 0.0005371570587158203 time for calcul the mask position with numpy : 0.01532888412475586 nb_pixel_total : 834 time to create 1 rle with old method : 0.0009758472442626953 time for calcul the mask position with numpy : 0.015098333358764648 nb_pixel_total : 965 time to create 1 rle with old method : 0.001127004623413086 time for calcul the mask position with numpy : 0.01961660385131836 nb_pixel_total : 551 time to create 1 rle with old method : 0.0007045269012451172 time for calcul the mask position with numpy : 0.01721048355102539 nb_pixel_total : 187 time to create 1 rle with old method : 0.0004112720489501953 time for calcul the mask position with numpy : 0.019903182983398438 nb_pixel_total : 181 time to create 1 rle with old method : 0.0003211498260498047 time for calcul the mask position with numpy : 0.017308712005615234 nb_pixel_total : 2206 time to create 1 rle with old method : 0.0025243759155273438 time for calcul the mask position with numpy : 0.01535487174987793 nb_pixel_total : 653 time to create 1 rle with old method : 0.0007722377777099609 time for calcul the mask position with numpy : 0.015333175659179688 nb_pixel_total : 1689 time to create 1 rle with old method : 0.0019578933715820312 time for calcul the mask position with numpy : 0.015307903289794922 nb_pixel_total : 12 time to create 1 rle with old method : 7.557868957519531e-05 time for calcul the mask position with numpy : 0.015709638595581055 nb_pixel_total : 611 time to create 1 rle with old method : 0.0007560253143310547 time for calcul the mask position with numpy : 0.015735387802124023 nb_pixel_total : 776 time to create 1 rle with old method : 0.0009353160858154297 time for calcul the mask position with numpy : 0.01577305793762207 nb_pixel_total : 1571 time to create 1 rle with old method : 0.001821756362915039 time for calcul the mask position with numpy : 0.015810251235961914 nb_pixel_total : 9 time to create 1 rle with old method : 0.0001068115234375 time for calcul the mask position with numpy : 0.015612363815307617 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003330707550048828 time for calcul the mask position with numpy : 0.01624274253845215 nb_pixel_total : 4813 time to create 1 rle with old method : 0.0055959224700927734 time for calcul the mask position with numpy : 0.015180110931396484 nb_pixel_total : 1558 time to create 1 rle with old method : 0.0018100738525390625 time for calcul the mask position with numpy : 0.015346050262451172 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0016067028045654297 time for calcul the mask position with numpy : 0.015307426452636719 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004942417144775391 time for calcul the mask position with numpy : 0.015204906463623047 nb_pixel_total : 769 time to create 1 rle with old method : 0.0009348392486572266 time for calcul the mask position with numpy : 0.016945600509643555 nb_pixel_total : 1216 time to create 1 rle with old method : 0.0017194747924804688 time for calcul the mask position with numpy : 0.015334606170654297 nb_pixel_total : 7 time to create 1 rle with old method : 4.839897155761719e-05 time for calcul the mask position with numpy : 0.018090009689331055 nb_pixel_total : 735 time to create 1 rle with old method : 0.001535654067993164 time for calcul the mask position with numpy : 0.030962228775024414 nb_pixel_total : 751 time to create 1 rle with old method : 0.0010061264038085938 time for calcul the mask position with numpy : 0.015849828720092773 nb_pixel_total : 326 time to create 1 rle with old method : 0.0005290508270263672 time for calcul the mask position with numpy : 0.015545129776000977 nb_pixel_total : 708 time to create 1 rle with old method : 0.0014269351959228516 time for calcul the mask position with numpy : 0.031285762786865234 nb_pixel_total : 835 time to create 1 rle with old method : 0.0010104179382324219 time for calcul the mask position with numpy : 0.015592575073242188 nb_pixel_total : 264 time to create 1 rle with old method : 0.0004074573516845703 time for calcul the mask position with numpy : 0.015961647033691406 nb_pixel_total : 228 time to create 1 rle with old method : 0.0005409717559814453 create new chi : 7.893236398696899 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 : 0.01449728012084961 batch 1 Loaded 459 chid ids of type : 4230 Number RLEs to save : 34935 TO DO : save crop sub photo not yet done ! save time : 20.92187809944153 map_output_result : {1341264129: (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 [1341264129] Looping around the photos to save general results len do output : 1 /1341264129.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, '2645908') ('4234', '21129082', '1341264129', None, None, None, None, None, '2645908') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.01567864418029785 save_final save missing photos in datou_result : time spend for datou_step_exec : 42.354352951049805 time spend to save output : 0.2562394142150879 total time spend for step 4 : 42.61059236526489 step5:crop_condition Sun Mar 9 01:22:00 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 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 : 1 ! batch 1 Loaded 459 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 232 About to insert : list_path_to_insert length 232 new photo from crops ! About to upload 232 photos upload in portfolio : 4869462 init cache_photo without model_param we have 232 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741479726_3565404 we have uploaded 232 photos in the portfolio 4869462 time of upload the photos Elapsed time : 78.81188559532166 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 50 About to insert : list_path_to_insert length 50 new photo from crops ! About to upload 50 photos upload in portfolio : 4869462 init cache_photo without model_param we have 50 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741479806_3565404 we have uploaded 50 photos in the portfolio 4869462 time of upload the photos Elapsed time : 14.438076257705688 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 26 About to insert : list_path_to_insert length 26 new photo from crops ! About to upload 26 photos upload in portfolio : 4869462 init cache_photo without model_param we have 26 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741479821_3565404 we have uploaded 26 photos in the portfolio 4869462 time of upload the photos Elapsed time : 9.510415315628052 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 ! map_result returned by crop_photo_return_map_crop : length : 19 About to insert : list_path_to_insert length 19 new photo from crops ! About to upload 19 photos upload in portfolio : 4869462 init cache_photo without model_param we have 19 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741479831_3565404 we have uploaded 19 photos in the portfolio 4869462 time of upload the photos Elapsed time : 7.147500038146973 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741479839_3565404 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9243640899658203 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 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/1741479840_3565404 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.869450569152832 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 [1341264129] Looping around the photos to save general results len do output : 331 /1342094910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342094999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095136Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095151Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095233Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095241Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095243Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095244Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095245Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095246Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095248Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095311Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095320Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095321Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342095367Didn'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, '2645908') ('4234', '21129082', '1341264129', None, None, None, None, None, '2645908') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 994 time used for this insertion : 0.13730382919311523 save_final save missing photos in datou_result : time spend for datou_step_exec : 122.87905144691467 time spend to save output : 0.14735627174377441 total time spend for step 5 : 123.02640771865845 step6:thcl Sun Mar 9 01:24:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure 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 : 0.01685476303100586 time to convert the images to numpy array : 0.10231304168701172 time to import caffe and check if the image exist : 0.04378867149353027 time to convert the images to numpy array : 0.09721207618713379 time to import caffe and check if the image exist : 0.03296923637390137 time to convert the images to numpy array : 0.10962939262390137 time to import caffe and check if the image exist : 0.028498411178588867 time to convert the images to numpy array : 0.11520123481750488 time to import caffe and check if the image exist : 0.02563929557800293 time to convert the images to numpy array : 0.1250319480895996 time to import caffe and check if the image exist : 0.024988889694213867 time to convert the images to numpy array : 0.12870287895202637 time to import caffe and check if the image exist : 0.03454256057739258 time to convert the images to numpy array : 0.12432122230529785 time to import caffe and check if the image exist : 0.028774738311767578 time to convert the images to numpy array : 0.12917423248291016 time to import caffe and check if the image exist : 0.048058271408081055 time to convert the images to numpy array : 0.11272788047790527 time to import caffe and check if the image exist : 0.017710208892822266 time to convert the images to numpy array : 0.14498162269592285 total time to convert the images to numpy array : 0.6432757377624512 list photo_ids error: [] list photo_ids correct : [1342095340, 1342095341, 1342095343, 1342095344, 1342095345, 1342095346, 1342095347, 1342095348, 1342095349, 1342095350, 1342095351, 1342095352, 1342095353, 1342095355, 1342095356, 1342095357, 1342095358, 1342095359, 1342095360, 1342095361, 1342095362, 1342095363, 1342095364, 1342095366, 1342095367, 1342095106, 1342095107, 1342095108, 1342095109, 1342095110, 1342095111, 1342095112, 1342095113, 1342095114, 1342095115, 1342095116, 1342095117, 1342095118, 1342095119, 1342095120, 1342095121, 1342095122, 1342095123, 1342095124, 1342095125, 1342095126, 1342095127, 1342095128, 1342095129, 1342095130, 1342095131, 1342095132, 1342095133, 1342095134, 1342095136, 1342095138, 1342095140, 1342095142, 1342095143, 1342095071, 1342095072, 1342095073, 1342095074, 1342095075, 1342095076, 1342095077, 1342095078, 1342095079, 1342095080, 1342095081, 1342095082, 1342095083, 1342095084, 1342095085, 1342095086, 1342095087, 1342095088, 1342095090, 1342095091, 1342095092, 1342095093, 1342095094, 1342095095, 1342095096, 1342095097, 1342095098, 1342095099, 1342095100, 1342095101, 1342095102, 1342095103, 1342095104, 1342095105, 1342095035, 1342095036, 1342095037, 1342095038, 1342095039, 1342095040, 1342095041, 1342095042, 1342095043, 1342095044, 1342095045, 1342095046, 1342095047, 1342095048, 1342095049, 1342095050, 1342095051, 1342095052, 1342095053, 1342095054, 1342095055, 1342095056, 1342095057, 1342095060, 1342095061, 1342095062, 1342095063, 1342095064, 1342095065, 1342095066, 1342095067, 1342095068, 1342095069, 1342095070, 1342094977, 1342094979, 1342094981, 1342094983, 1342094985, 1342094987, 1342094991, 1342094993, 1342094995, 1342094997, 1342094999, 1342095001, 1342095003, 1342095005, 1342095007, 1342095009, 1342095011, 1342095013, 1342095014, 1342095016, 1342095018, 1342095020, 1342095021, 1342095022, 1342095025, 1342095026, 1342095027, 1342095028, 1342095029, 1342095030, 1342095031, 1342095032, 1342095033, 1342095034, 1342094910, 1342094914, 1342094917, 1342094920, 1342094923, 1342094926, 1342094929, 1342094932, 1342094935, 1342094938, 1342094942, 1342094944, 1342094948, 1342094950, 1342094954, 1342094956, 1342094959, 1342094960, 1342094961, 1342094962, 1342094963, 1342094964, 1342094965, 1342094966, 1342094967, 1342094968, 1342094969, 1342094970, 1342094971, 1342094972, 1342094973, 1342094974, 1342094975, 1342094976, 1342095181, 1342095182, 1342095183, 1342095184, 1342095185, 1342095186, 1342095188, 1342095190, 1342095191, 1342095192, 1342095193, 1342095194, 1342095195, 1342095196, 1342095199, 1342095202, 1342095205, 1342095206, 1342095207, 1342095208, 1342095209, 1342095210, 1342095211, 1342095212, 1342095213, 1342095214, 1342095215, 1342095216, 1342095233, 1342095237, 1342095241, 1342095243, 1342095244, 1342095245, 1342095144, 1342095145, 1342095146, 1342095147, 1342095148, 1342095149, 1342095150, 1342095151, 1342095152, 1342095153, 1342095154, 1342095155, 1342095158, 1342095159, 1342095160, 1342095161, 1342095162, 1342095163, 1342095164, 1342095166, 1342095167, 1342095168, 1342095169, 1342095170, 1342095171, 1342095172, 1342095173, 1342095174, 1342095175, 1342095176, 1342095177, 1342095178, 1342095179, 1342095180, 1342095246, 1342095247, 1342095248, 1342095249, 1342095250, 1342095251, 1342095252, 1342095253, 1342095254, 1342095255, 1342095256, 1342095257, 1342095258, 1342095259, 1342095260, 1342095261, 1342095262, 1342095263, 1342095264, 1342095265, 1342095266, 1342095267, 1342095268, 1342095269, 1342095270, 1342095271, 1342095272, 1342095273, 1342095275, 1342095276, 1342095277, 1342095278, 1342095279, 1342095280, 1342095281, 1342095282, 1342095283, 1342095284, 1342095285, 1342095286, 1342095287, 1342095288, 1342095289, 1342095290, 1342095311, 1342095313, 1342095316, 1342095318, 1342095319, 1342095320, 1342095321, 1342095322, 1342095324, 1342095325, 1342095326, 1342095327, 1342095328, 1342095329, 1342095330, 1342095331, 1342095332, 1342095333, 1342095334, 1342095335, 1342095336, 1342095337, 1342095338, 1342095339] number of photos to traite : 331 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 : 9926 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 : 9707 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 1.6654760837554932 time used to do the prediction : 1.3420360088348389 save descriptor for thcl : 3237 time to traite the descriptors : 2.038381576538086 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1342095340 To insert : 1342095341 To insert : 1342095343 To insert : 1342095344 To insert : 1342095345 To insert : 1342095346 To insert : 1342095347 To insert : 1342095348 To insert : 1342095349 To insert : 1342095350 To insert : 1342095351 To insert : 1342095352 To insert : 1342095353 To insert : 1342095355 To insert : 1342095356 To insert : 1342095357 To insert : 1342095358 To insert : 1342095359 To insert : 1342095360 To insert : 1342095361 To insert : 1342095362 To insert : 1342095363 To insert : 1342095364 To insert : 1342095366 To insert : 1342095367 To insert : 1342095106 To insert : 1342095107 To insert : 1342095108 To insert : 1342095109 To insert : 1342095110 To insert : 1342095111 To insert : 1342095112 To insert : 1342095113 To insert : 1342095114 To insert : 1342095115 To insert : 1342095116 To insert : 1342095117 To insert : 1342095118 To insert : 1342095119 To insert : 1342095120 To insert : 1342095121 To insert : 1342095122 To insert : 1342095123 To insert : 1342095124 To insert : 1342095125 To insert : 1342095126 To insert : 1342095127 To insert : 1342095128 To insert : 1342095129 To insert : 1342095130 To insert : 1342095131 To insert : 1342095132 To insert : 1342095133 To insert : 1342095134 To insert : 1342095136 To insert : 1342095138 To insert : 1342095140 To insert : 1342095142 To insert : 1342095143 To insert : 1342095071 To insert : 1342095072 To insert : 1342095073 To insert : 1342095074 To insert : 1342095075 To insert : 1342095076 To insert : 1342095077 To insert : 1342095078 To insert : 1342095079 To insert : 1342095080 To insert : 1342095081 To insert : 1342095082 To insert : 1342095083 To insert : 1342095084 To insert : 1342095085 To insert : 1342095086 To insert : 1342095087 To insert : 1342095088 To insert : 1342095090 To insert : 1342095091 To insert : 1342095092 To insert : 1342095093 To insert : 1342095094 To insert : 1342095095 To insert : 1342095096 To insert : 1342095097 To insert : 1342095098 To insert : 1342095099 To insert : 1342095100 To insert : 1342095101 To insert : 1342095102 To insert : 1342095103 To insert : 1342095104 To insert : 1342095105 To insert : 1342095035 To insert : 1342095036 To insert : 1342095037 To insert : 1342095038 To insert : 1342095039 To insert : 1342095040 To insert : 1342095041 To insert : 1342095042 To insert : 1342095043 To insert : 1342095044 To insert : 1342095045 To insert : 1342095046 To insert : 1342095047 To insert : 1342095048 To insert : 1342095049 To insert : 1342095050 To insert : 1342095051 To insert : 1342095052 To insert : 1342095053 To insert : 1342095054 To insert : 1342095055 To insert : 1342095056 To insert : 1342095057 To insert : 1342095060 To insert : 1342095061 To insert : 1342095062 To insert : 1342095063 To insert : 1342095064 To insert : 1342095065 To insert : 1342095066 To insert : 1342095067 To insert : 1342095068 To insert : 1342095069 To insert : 1342095070 To insert : 1342094977 To insert : 1342094979 To insert : 1342094981 To insert : 1342094983 To insert : 1342094985 To insert : 1342094987 To insert : 1342094991 To insert : 1342094993 To insert : 1342094995 To insert : 1342094997 To insert : 1342094999 To insert : 1342095001 To insert : 1342095003 To insert : 1342095005 To insert : 1342095007 To insert : 1342095009 To insert : 1342095011 To insert : 1342095013 To insert : 1342095014 To insert : 1342095016 To insert : 1342095018 To insert : 1342095020 To insert : 1342095021 To insert : 1342095022 To insert : 1342095025 To insert : 1342095026 To insert : 1342095027 To insert : 1342095028 To insert : 1342095029 To insert : 1342095030 To insert : 1342095031 To insert : 1342095032 To insert : 1342095033 To insert : 1342095034 To insert : 1342094910 To insert : 1342094914 To insert : 1342094917 To insert : 1342094920 To insert : 1342094923 To insert : 1342094926 To insert : 1342094929 To insert : 1342094932 To insert : 1342094935 To insert : 1342094938 To insert : 1342094942 To insert : 1342094944 To insert : 1342094948 To insert : 1342094950 To insert : 1342094954 To insert : 1342094956 To insert : 1342094959 To insert : 1342094960 To insert : 1342094961 To insert : 1342094962 To insert : 1342094963 To insert : 1342094964 To insert : 1342094965 To insert : 1342094966 To insert : 1342094967 To insert : 1342094968 To insert : 1342094969 To insert : 1342094970 To insert : 1342094971 To insert : 1342094972 To insert : 1342094973 To insert : 1342094974 To insert : 1342094975 To insert : 1342094976 To insert : 1342095181 To insert : 1342095182 To insert : 1342095183 To insert : 1342095184 To insert : 1342095185 To insert : 1342095186 To insert : 1342095188 To insert : 1342095190 To insert : 1342095191 To insert : 1342095192 To insert : 1342095193 To insert : 1342095194 To insert : 1342095195 To insert : 1342095196 To insert : 1342095199 To insert : 1342095202 To insert : 1342095205 To insert : 1342095206 To insert : 1342095207 To insert : 1342095208 To insert : 1342095209 To insert : 1342095210 To insert : 1342095211 To insert : 1342095212 To insert : 1342095213 To insert : 1342095214 To insert : 1342095215 To insert : 1342095216 To insert : 1342095233 To insert : 1342095237 To insert : 1342095241 To insert : 1342095243 To insert : 1342095244 To insert : 1342095245 To insert : 1342095144 To insert : 1342095145 To insert : 1342095146 To insert : 1342095147 To insert : 1342095148 To insert : 1342095149 To insert : 1342095150 To insert : 1342095151 To insert : 1342095152 To insert : 1342095153 To insert : 1342095154 To insert : 1342095155 To insert : 1342095158 To insert : 1342095159 To insert : 1342095160 To insert : 1342095161 To insert : 1342095162 To insert : 1342095163 To insert : 1342095164 To insert : 1342095166 To insert : 1342095167 To insert : 1342095168 To insert : 1342095169 To insert : 1342095170 To insert : 1342095171 To insert : 1342095172 To insert : 1342095173 To insert : 1342095174 To insert : 1342095175 To insert : 1342095176 To insert : 1342095177 To insert : 1342095178 To insert : 1342095179 To insert : 1342095180 To insert : 1342095246 To insert : 1342095247 To insert : 1342095248 To insert : 1342095249 To insert : 1342095250 To insert : 1342095251 To insert : 1342095252 To insert : 1342095253 To insert : 1342095254 To insert : 1342095255 To insert : 1342095256 To insert : 1342095257 To insert : 1342095258 To insert : 1342095259 To insert : 1342095260 To insert : 1342095261 To insert : 1342095262 To insert : 1342095263 To insert : 1342095264 To insert : 1342095265 To insert : 1342095266 To insert : 1342095267 To insert : 1342095268 To insert : 1342095269 To insert : 1342095270 To insert : 1342095271 To insert : 1342095272 To insert : 1342095273 To insert : 1342095275 To insert : 1342095276 To insert : 1342095277 To insert : 1342095278 To insert : 1342095279 To insert : 1342095280 To insert : 1342095281 To insert : 1342095282 To insert : 1342095283 To insert : 1342095284 To insert : 1342095285 To insert : 1342095286 To insert : 1342095287 To insert : 1342095288 To insert : 1342095289 To insert : 1342095290 To insert : 1342095311 To insert : 1342095313 To insert : 1342095316 To insert : 1342095318 To insert : 1342095319 To insert : 1342095320 To insert : 1342095321 To insert : 1342095322 To insert : 1342095324 To insert : 1342095325 To insert : 1342095326 To insert : 1342095327 To insert : 1342095328 To insert : 1342095329 To insert : 1342095330 To insert : 1342095331 To insert : 1342095332 To insert : 1342095333 To insert : 1342095334 To insert : 1342095335 To insert : 1342095336 To insert : 1342095337 To insert : 1342095338 To insert : 1342095339 time to insert the descriptors : 64.76595997810364 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 : 478 time used for this insertion : 0.03458714485168457 save missing photos in datou_result : time spend for datou_step_exec : 75.19356489181519 time spend to save output : 0.1066751480102539 total time spend for step 6 : 75.30024003982544 step7:ventilate_hashtags_in_portfolio Sun Mar 9 01:25:18 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 : 21129082 get user id for portfolio 21129082 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`=21129082 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('refus','mal_croppe','autre','carton','pehd','pet_clair','pet_fonce','environnement','PET_clair','PET_fonce','Film_plastique','PEHD','Papier','metal','flou','Tetrapak','Carton','papier')) 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`=21129082 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('refus','mal_croppe','autre','carton','pehd','pet_clair','pet_fonce','environnement','PET_clair','PET_fonce','Film_plastique','PEHD','Papier','metal','flou','Tetrapak','Carton','papier')) 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`=21129082 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('refus','mal_croppe','autre','carton','pehd','pet_clair','pet_fonce','environnement','PET_clair','PET_fonce','Film_plastique','PEHD','Papier','metal','flou','Tetrapak','Carton','papier')) 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`=21129082 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('refus','mal_croppe','autre','carton','pehd','pet_clair','pet_fonce','environnement','PET_clair','PET_fonce','Film_plastique','PEHD','Papier','metal','flou','Tetrapak','Carton','papier')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/21195236,21195237,21195238,21195252,21195247,21195244,21195245,21195243,21195246,21195253,21195249,21195250,21195251?tags=refus,mal_croppe,autre,carton,pehd,pet_clair,pet_fonce,environnement,film_plastique,papier,metal,flou,tetrapak&datou_id_consolidate=4235&port_consolidate=21129082 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1341264129] Looping around the photos to save general results len do output : 1 /21129082. 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, '2645908') ('4234', '21129082', '1341264129', None, None, None, None, None, '2645908') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.014261722564697266 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.8962106704711914 time spend to save output : 0.014559745788574219 total time spend for step 7 : 2.9107704162597656 step8:final Sun Mar 9 01:25:21 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 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 : {1341264129: ('0.7011115930113234',)} new output for save of step final : {1341264129: ('0.7011115930113234',)} [1341264129] Looping around the photos to save general results len do output : 1 /1341264129.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, '2645908') ('4234', '21129082', '1341264129', None, None, None, None, None, '2645908') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.022423505783081055 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11564993858337402 time spend to save output : 0.022675275802612305 total time spend for step 8 : 0.13832521438598633 step9:velours_tree Sun Mar 9 01:25:21 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 list_portfolios : 21195236,21195237,21195238,21195252,21195247,21195244,21195245,21195243,21195246,21195253,21195249,21195250,21195251 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=21195236 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=21195237 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=21195238 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=21195252 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=21195247 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=21195244 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=21195245 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=21195243 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=21195246 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=21195253 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=21195249 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=21195250 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=21195251 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 331 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [4 1 4 1 1 5 4 5 4 4 1 1 1 0 2 1 4 5 1 2 0 1 1 0 1 1 5 4 4 0 2 1 1 1 1 1 0 1 0 4 2 2 5 2 0 1 1 1 0 5 2 4 1 0 0 0 4 1 1 0 3 5 0 0 1 1 4 5 3 3 1 1 4 0 0 3 3 5 4 2 4 5 0 2 2 0 1 3 5 1 4 1 0 1 1 1 0 1 1 1 1 0 1 4 1 2 2 1 1 2 4 5 5 0 5 3 3 2 1 5 0 4 1 1 2 0 0 1 1 5 5 0 0 1 1 0 1 3 1 2 4 4 4 1 0 5 2 4 4 3 0 1 1 0 3 1 2 2 5 2 1 2 4 4 2 2 1 4 1 1 1 1 1 2 2 1 3 1 4 3 2 0 0 4 4 5 5 2 4 4 5 2 5 1 1 1 1 1 0 0 1 5 1 4 2 1 0 0 5 0 1 1 4 4 4 5 1 0 1 5 0 1 5 5 4 2 1 1 1 5 1 2 4 5 4 5 4 2 2 1 1 1 1 0 5 4 1 1 2 4 1 5 2 2 2 1 2 2 4 5 5 3 3 2 1 3 1 3 2 4 0 2 2 2 4 4 2 2 4 5 2 1 5 4 4 1 4 1 4 3 1 0 0 5 4 4 5 3 5 3 1 5 4 4 4 5 4 4 4 2 4 0 0 4 4 4 4 4 1 1 5 4 1 2 1 0 5 4 1 0 0] Elapsed time: 0.06964612007141113 graph_id used : 82263 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/21195236,21195237,21195238,21195252,21195247,21195244,21195245,21195243,21195246,21195253,21195249,21195250,21195251?tags=refus,mal_croppe,autre,carton,pehd,pet_clair,pet_fonce,environnement,film_plastique,papier,metal,flou,tetrapak&datou_id_consolidate=4235&port_consolidate=21129082&tree_id=82263 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1341264129] Looping around the photos to save general results len do output : 1 /21129082Didn'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, '2645908') ('4234', '21129082', '1341264129', None, None, None, None, None, '2645908') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.012743949890136719 save_final save missing photos in datou_result : time spend for datou_step_exec : 24.170753002166748 time spend to save output : 0.013063907623291016 total time spend for step 9 : 24.18381690979004 step10:send_mail_cod Sun Mar 9 01:25:45 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 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_P21129082_09-03-2025_01_25_45.pdf 21195218 imagette211952181741479945 21195219 imagette211952191741479945 21195220 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette211952201741479945 21195234 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette211952341741479946 21195229 change filename to text .change filename to text .imagette211952291741479947 21195226 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette211952261741479947 21195227 change filename to text .change filename to text .imagette211952271741479948 21195228 imagette211952281741479948 21195235 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette211952351741479948 21195231 imagette211952311741479949 21195232 imagette211952321741479949 21195233 imagette211952331741479949 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21129082 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21195236,21195237,21195238,21195252,21195247,21195244,21195245,21195243,21195246,21195253,21195249,21195250,21195251?tags=refus,mal_croppe,autre,carton,pehd,pet_clair,pet_fonce,environnement,film_plastique,papier,metal,flou,tetrapak&datou_id_consolidate=4235&port_consolidate=21129082&tree_id=82263 your option no_mail is active, we will not send the real mail to your client args[1341264129] : ((1341264129, -7.904586257885839, 492609224), (1341264129, 0.3059564170588973, 2107752395), '0.7011115930113234') We are sending mail with results at cod@fotonower.com refus_total : 0.7011115930113234 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=21129082 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_P21129082_09-03-2025_01_25_45.pdf results_Qualipapia_P21129082_09-03-2025_01_25_45.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21129082_09-03-2025_01_25_45.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','21129082','results_Qualipapia_P21129082_09-03-2025_01_25_45.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21129082_09-03-2025_01_25_45.pdf','pdf','','0.16','0.7011115930113234') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1341264129] 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, '2645908') ('4234', '21129082', '1341264129', None, None, None, None, None, '2645908') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.011771440505981445 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.289181709289551 time spend to save output : 0.011929750442504883 total time spend for step 10 : 5.301111459732056 step11:split_time_score Sun Mar 9 01:25:50 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', 1),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 06032025 21129082 Nombre de photos uploadées : 1 / 23040 (0%) 06032025 21129082 Nombre de photos taguées (types de déchets): 0 / 1 (0%) 06032025 21129082 Nombre de photos taguées (volume) : 0 / 1 (0%) elapsed_time : load_data_split_time_score 2.6226043701171875e-06 elapsed_time : order_list_meta_photo_and_scores 8.106231689453125e-06 ? elapsed_time : fill_and_build_computed_from_old_data 0.00021266937255859375 elapsed_time : insert_dashboard_record_day_entry 0.024706602096557617 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129074 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129077 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129080 order by id desc limit 1 Qualite : 0.7011115930113234 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21129082_09-03-2025_01_25_45.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129082 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`=21129082 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129087 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129090 order by id desc limit 1 Qualite : 0.5670981156161365 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21129094_09-03-2025_01_19_53.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129094 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`=21129094 AND mptpi.`type`=4230 To do Qualite : 0.5625054533293146 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21129096_09-03-2025_00_54_50.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129096 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`=21129096 AND mptpi.`type`=4230 To do Qualite : 0.6210181954800649 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21129098_09-03-2025_00_28_43.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129098 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`=21129098 AND mptpi.`type`=4230 To do Qualite : 0.5713952786476819 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21129938_06-03-2025_23_40_53.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21129938 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`=21129938 AND mptpi.`type`=4230 To do Qualite : 0.5061654648684487 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21130688_07-03-2025_00_15_18.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21130688 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`=21130688 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'06032025': {'nb_upload': 1, '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 [1341264129] Looping around the photos to save general results len do output : 1 /21129082Didn'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, '2645908') ('4234', '21129082', '1341264129', None, None, None, None, None, '2645908') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.030742168426513672 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.6632397174835205 time spend to save output : 0.030902385711669922 total time spend for step 11 : 5.69414210319519 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 1 set_done_treatment 56.21user 29.58system 5:32.10elapsed 25%CPU (0avgtext+0avgdata 2493188maxresident)k 2089552inputs+26688outputs (11931major+4680355minor)pagefaults 0swaps