python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 20 -a ' -a 3318 ' -s datou_3318 -M 0 -S 0 -U 95,95,120 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 : 55244 load datou : 3318 # 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 ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 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 : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( 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 ? [ (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 ? 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 ? 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 ? 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 ? 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)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load pdts add pdt : 5275 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 : 3318, datou_cur_ids : ['2601861'] with mtr_portfolio_ids : ['20699449'] and first list_photo_ids : [] new path : /proc/55244/ 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 ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 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 : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, crop_condition, rle_unique_nms_with_priority, ventilate_hashtags_in_portfolio, final, blur_detection, brightness, velours_tree, send_mail_cod, split_time_score over limit max, limiting to limit_max 40 list_input_json : [] origin We have 1 , BFBFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 12 ; length of list_pids : 12 ; length of list_args : 12 time to download the photos : 2.743220090866089 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 : 10 step1:mask_detect Fri Feb 21 00:30:30 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 : 2741 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-21 00:30:36.428216: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-21 00:30:36.471272: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-21 00:30:36.476480: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fb8b8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-21 00:30:36.476522: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-21 00:30:36.487066: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-21 00:30:36.914943: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x341fcfa0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-21 00:30:36.914997: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-21 00:30:36.917399: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-21 00:30:36.922272: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-21 00:30:37.020324: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-21 00:30:37.079146: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-21 00:30:37.089566: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-21 00:30:37.197855: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-21 00:30:37.211532: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-21 00:30:37.390366: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-21 00:30:37.392778: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-21 00:30:37.397579: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-21 00:30:37.399383: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-21 00:30:37.399415: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-21 00:30:37.399427: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-21 00:30:37.402478: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2136 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-02-21 00:30:38.167771: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-21 00:30:38.168017: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-21 00:30:38.168108: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-21 00:30:38.168165: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-21 00:30:38.168203: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-21 00:30:38.168237: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-21 00:30:38.168280: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-21 00:30:38.168328: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-21 00:30:38.170348: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-21 00:30:38.171851: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-21 00:30:38.171908: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-21 00:30:38.171934: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-21 00:30:38.171958: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-21 00:30:38.171981: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-21 00:30:38.172005: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-21 00:30:38.172028: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-21 00:30:38.172052: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-21 00:30:38.174311: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-21 00:30:38.174369: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-21 00:30:38.174395: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-21 00:30:38.174412: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-21 00:30:38.176190: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2136 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-21 00:30:51.905943: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-21 00:30:52.253356: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-21 00:30:54.105640: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.105743: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.128412: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.128460: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.252715: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.252782: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.355810: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.355860: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.468014: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.468066: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-21 00:30:54.477227: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.09G (1167982592 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.477272: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-02-21 00:30:54.492359: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.493576: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.553582: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.554155: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.558209: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.558761: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.574563: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.575162: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.579539: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.580093: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.595759: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.596280: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.600405: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.600913: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.688202: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.689108: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.690136: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.691089: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.708472: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.709001: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.746935: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.747874: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.748583: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.749101: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.781437: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.782378: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.783083: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.783605: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.823508: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.824530: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.830404: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.831103: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.843655: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.844451: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.848887: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.849924: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.850970: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.851793: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.862222: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.862984: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.863756: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.864497: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.865038: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.865567: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.915875: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.915941: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-02-21 00:30:54.916908: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.917838: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.924962: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.925636: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.933947: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.934622: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.957381: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.958385: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.959250: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.960115: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.964641: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.965503: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.966346: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.967210: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.969473: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.978864: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.979446: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.988429: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.988970: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.989512: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.990027: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.990551: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-21 00:30:54.991080: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 1.59G (1704853504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 12 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 94 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 75 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 67 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 83 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 41 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 37 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 36 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 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: 3264.00000 nb d'objets trouves : 38 Detection mask done ! Trying to reset tf kernel 56079 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1988 tf kernel not reseted sub process len(results) : 12 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 12 len(list_Values) 0 process is alive 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 : 3183 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2847 Catched exception ! Connect or reconnect ! 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 ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] time for calcul the mask position with numpy : 0.24986743927001953 nb_pixel_total : 62238 time to create 1 rle with old method : 0.09727668762207031 length of segment : 419 time for calcul the mask position with numpy : 0.027846574783325195 nb_pixel_total : 4853 time to create 1 rle with old method : 0.008130550384521484 length of segment : 93 time for calcul the mask position with numpy : 0.046282291412353516 nb_pixel_total : 7789 time to create 1 rle with old method : 0.01290583610534668 length of segment : 111 time for calcul the mask position with numpy : 0.11658167839050293 nb_pixel_total : 17663 time to create 1 rle with old method : 0.030128002166748047 length of segment : 217 time for calcul the mask position with numpy : 0.08947253227233887 nb_pixel_total : 19667 time to create 1 rle with old method : 0.02675342559814453 length of segment : 315 time for calcul the mask position with numpy : 0.17783880233764648 nb_pixel_total : 26409 time to create 1 rle with old method : 0.033060550689697266 length of segment : 337 time for calcul the mask position with numpy : 0.05095052719116211 nb_pixel_total : 17837 time to create 1 rle with old method : 0.024192333221435547 length of segment : 176 time for calcul the mask position with numpy : 0.029155492782592773 nb_pixel_total : 6102 time to create 1 rle with old method : 0.007512807846069336 length of segment : 102 time for calcul the mask position with numpy : 0.30047082901000977 nb_pixel_total : 77153 time to create 1 rle with old method : 0.11018109321594238 length of segment : 304 time for calcul the mask position with numpy : 0.6420149803161621 nb_pixel_total : 232776 time to create 1 rle with new method : 0.024411439895629883 length of segment : 908 time for calcul the mask position with numpy : 0.02518773078918457 nb_pixel_total : 5688 time to create 1 rle with old method : 0.010530471801757812 length of segment : 84 time for calcul the mask position with numpy : 0.03425025939941406 nb_pixel_total : 13498 time to create 1 rle with old method : 0.020772695541381836 length of segment : 160 time for calcul the mask position with numpy : 0.06020808219909668 nb_pixel_total : 17369 time to create 1 rle with old method : 0.028396129608154297 length of segment : 187 time for calcul the mask position with numpy : 0.0444791316986084 nb_pixel_total : 8791 time to create 1 rle with old method : 0.015211105346679688 length of segment : 107 time for calcul the mask position with numpy : 0.17212939262390137 nb_pixel_total : 31538 time to create 1 rle with old method : 0.04247474670410156 length of segment : 214 time for calcul the mask position with numpy : 0.058713674545288086 nb_pixel_total : 9278 time to create 1 rle with old method : 0.015184640884399414 length of segment : 119 time for calcul the mask position with numpy : 0.17899656295776367 nb_pixel_total : 47139 time to create 1 rle with old method : 0.06023001670837402 length of segment : 330 time for calcul the mask position with numpy : 0.07315874099731445 nb_pixel_total : 22421 time to create 1 rle with old method : 0.02708148956298828 length of segment : 443 time for calcul the mask position with numpy : 0.062177181243896484 nb_pixel_total : 21626 time to create 1 rle with old method : 0.029201745986938477 length of segment : 133 time for calcul the mask position with numpy : 0.11931920051574707 nb_pixel_total : 33036 time to create 1 rle with old method : 0.04235029220581055 length of segment : 259 time for calcul the mask position with numpy : 0.06184554100036621 nb_pixel_total : 27807 time to create 1 rle with old method : 0.049814701080322266 length of segment : 163 time for calcul the mask position with numpy : 0.10111570358276367 nb_pixel_total : 30520 time to create 1 rle with old method : 0.043305158615112305 length of segment : 207 time for calcul the mask position with numpy : 0.06918215751647949 nb_pixel_total : 11530 time to create 1 rle with old method : 0.019248008728027344 length of segment : 272 time for calcul the mask position with numpy : 0.3174440860748291 nb_pixel_total : 82383 time to create 1 rle with old method : 0.09475111961364746 length of segment : 445 time for calcul the mask position with numpy : 0.019417762756347656 nb_pixel_total : 9371 time to create 1 rle with old method : 0.013014078140258789 length of segment : 94 time for calcul the mask position with numpy : 0.29732489585876465 nb_pixel_total : 88745 time to create 1 rle with old method : 0.10127854347229004 length of segment : 480 time for calcul the mask position with numpy : 0.08715605735778809 nb_pixel_total : 25554 time to create 1 rle with old method : 0.03134751319885254 length of segment : 211 time for calcul the mask position with numpy : 0.07092404365539551 nb_pixel_total : 16988 time to create 1 rle with old method : 0.02287769317626953 length of segment : 250 time for calcul the mask position with numpy : 0.10866141319274902 nb_pixel_total : 30407 time to create 1 rle with old method : 0.03509831428527832 length of segment : 351 time for calcul the mask position with numpy : 0.030789852142333984 nb_pixel_total : 12062 time to create 1 rle with old method : 0.01910400390625 length of segment : 102 time for calcul the mask position with numpy : 0.0987238883972168 nb_pixel_total : 20692 time to create 1 rle with old method : 0.031617164611816406 length of segment : 257 time for calcul the mask position with numpy : 0.231292724609375 nb_pixel_total : 111303 time to create 1 rle with old method : 0.12757015228271484 length of segment : 371 time for calcul the mask position with numpy : 0.033273935317993164 nb_pixel_total : 9929 time to create 1 rle with old method : 0.015275716781616211 length of segment : 89 time for calcul the mask position with numpy : 0.07027459144592285 nb_pixel_total : 21845 time to create 1 rle with old method : 0.0302579402923584 length of segment : 135 time for calcul the mask position with numpy : 0.048323631286621094 nb_pixel_total : 15087 time to create 1 rle with old method : 0.022128582000732422 length of segment : 133 time for calcul the mask position with numpy : 0.14988207817077637 nb_pixel_total : 111000 time to create 1 rle with old method : 0.12535786628723145 length of segment : 478 time for calcul the mask position with numpy : 0.03586459159851074 nb_pixel_total : 18672 time to create 1 rle with old method : 0.023260831832885742 length of segment : 136 time for calcul the mask position with numpy : 0.17397093772888184 nb_pixel_total : 35287 time to create 1 rle with old method : 0.041385650634765625 length of segment : 315 time for calcul the mask position with numpy : 0.021418333053588867 nb_pixel_total : 5436 time to create 1 rle with old method : 0.008043289184570312 length of segment : 75 time for calcul the mask position with numpy : 0.010429620742797852 nb_pixel_total : 12214 time to create 1 rle with old method : 0.015720844268798828 length of segment : 161 time for calcul the mask position with numpy : 0.026472806930541992 nb_pixel_total : 9041 time to create 1 rle with old method : 0.013431549072265625 length of segment : 114 time for calcul the mask position with numpy : 0.03988361358642578 nb_pixel_total : 16642 time to create 1 rle with old method : 0.02182936668395996 length of segment : 196 time for calcul the mask position with numpy : 0.03674793243408203 nb_pixel_total : 11615 time to create 1 rle with old method : 0.01772618293762207 length of segment : 149 time for calcul the mask position with numpy : 0.07460975646972656 nb_pixel_total : 19119 time to create 1 rle with old method : 0.0275418758392334 length of segment : 231 time for calcul the mask position with numpy : 0.10362672805786133 nb_pixel_total : 30209 time to create 1 rle with old method : 0.035685062408447266 length of segment : 333 time for calcul the mask position with numpy : 0.012093067169189453 nb_pixel_total : 6067 time to create 1 rle with old method : 0.011567831039428711 length of segment : 94 time for calcul the mask position with numpy : 0.00395965576171875 nb_pixel_total : 23438 time to create 1 rle with old method : 0.02839970588684082 length of segment : 133 time for calcul the mask position with numpy : 0.06934785842895508 nb_pixel_total : 39384 time to create 1 rle with old method : 0.046875 length of segment : 190 time for calcul the mask position with numpy : 0.06574583053588867 nb_pixel_total : 24960 time to create 1 rle with old method : 0.03207206726074219 length of segment : 235 time for calcul the mask position with numpy : 0.028598308563232422 nb_pixel_total : 8730 time to create 1 rle with old method : 0.014140844345092773 length of segment : 94 time for calcul the mask position with numpy : 0.03708386421203613 nb_pixel_total : 15179 time to create 1 rle with old method : 0.01937270164489746 length of segment : 135 time for calcul the mask position with numpy : 0.07235288619995117 nb_pixel_total : 18551 time to create 1 rle with old method : 0.03265070915222168 length of segment : 255 time for calcul the mask position with numpy : 0.2782926559448242 nb_pixel_total : 74755 time to create 1 rle with old method : 0.08294391632080078 length of segment : 419 time for calcul the mask position with numpy : 0.17869353294372559 nb_pixel_total : 58321 time to create 1 rle with old method : 0.06348156929016113 length of segment : 398 time for calcul the mask position with numpy : 0.21587491035461426 nb_pixel_total : 87150 time to create 1 rle with old method : 0.11588573455810547 length of segment : 516 time for calcul the mask position with numpy : 0.06019449234008789 nb_pixel_total : 26395 time to create 1 rle with old method : 0.03208804130554199 length of segment : 186 time for calcul the mask position with numpy : 0.032219648361206055 nb_pixel_total : 8187 time to create 1 rle with old method : 0.01342916488647461 length of segment : 90 time for calcul the mask position with numpy : 0.12519526481628418 nb_pixel_total : 47593 time to create 1 rle with old method : 0.054834842681884766 length of segment : 449 time for calcul the mask position with numpy : 0.030474424362182617 nb_pixel_total : 24378 time to create 1 rle with old method : 0.031132936477661133 length of segment : 227 time for calcul the mask position with numpy : 0.12151813507080078 nb_pixel_total : 51126 time to create 1 rle with old method : 0.06293368339538574 length of segment : 282 time for calcul the mask position with numpy : 0.08574676513671875 nb_pixel_total : 29664 time to create 1 rle with old method : 0.04246044158935547 length of segment : 306 time for calcul the mask position with numpy : 0.03330421447753906 nb_pixel_total : 19765 time to create 1 rle with old method : 0.03020620346069336 length of segment : 192 time for calcul the mask position with numpy : 0.05765724182128906 nb_pixel_total : 20501 time to create 1 rle with old method : 0.02254176139831543 length of segment : 138 time for calcul the mask position with numpy : 0.03307318687438965 nb_pixel_total : 16692 time to create 1 rle with old method : 0.02594161033630371 length of segment : 204 time for calcul the mask position with numpy : 0.04758501052856445 nb_pixel_total : 28544 time to create 1 rle with old method : 0.0357663631439209 length of segment : 220 time for calcul the mask position with numpy : 0.06779050827026367 nb_pixel_total : 29926 time to create 1 rle with old method : 0.0370025634765625 length of segment : 202 time for calcul the mask position with numpy : 0.031571388244628906 nb_pixel_total : 12649 time to create 1 rle with old method : 0.0185244083404541 length of segment : 157 time for calcul the mask position with numpy : 0.02077031135559082 nb_pixel_total : 2769 time to create 1 rle with old method : 0.005768299102783203 length of segment : 113 time for calcul the mask position with numpy : 0.05317878723144531 nb_pixel_total : 34981 time to create 1 rle with old method : 0.04429292678833008 length of segment : 245 time for calcul the mask position with numpy : 0.028070449829101562 nb_pixel_total : 10857 time to create 1 rle with old method : 0.015625476837158203 length of segment : 104 time for calcul the mask position with numpy : 0.019862651824951172 nb_pixel_total : 26813 time to create 1 rle with old method : 0.031245946884155273 length of segment : 215 time for calcul the mask position with numpy : 0.002576589584350586 nb_pixel_total : 9498 time to create 1 rle with old method : 0.010568857192993164 length of segment : 116 time for calcul the mask position with numpy : 0.00040984153747558594 nb_pixel_total : 13145 time to create 1 rle with old method : 0.016729354858398438 length of segment : 156 time for calcul the mask position with numpy : 0.032379150390625 nb_pixel_total : 12679 time to create 1 rle with old method : 0.018230438232421875 length of segment : 168 time for calcul the mask position with numpy : 0.033960819244384766 nb_pixel_total : 16612 time to create 1 rle with old method : 0.022533893585205078 length of segment : 164 time for calcul the mask position with numpy : 0.008673429489135742 nb_pixel_total : 18714 time to create 1 rle with old method : 0.025821447372436523 length of segment : 145 time for calcul the mask position with numpy : 0.012669563293457031 nb_pixel_total : 7623 time to create 1 rle with old method : 0.00890970230102539 length of segment : 104 time for calcul the mask position with numpy : 0.021713733673095703 nb_pixel_total : 10837 time to create 1 rle with old method : 0.012314558029174805 length of segment : 126 time for calcul the mask position with numpy : 0.019788503646850586 nb_pixel_total : 8015 time to create 1 rle with old method : 0.00958704948425293 length of segment : 111 time for calcul the mask position with numpy : 0.0029129981994628906 nb_pixel_total : 16018 time to create 1 rle with old method : 0.019856691360473633 length of segment : 221 time for calcul the mask position with numpy : 0.05255317687988281 nb_pixel_total : 20211 time to create 1 rle with old method : 0.026921987533569336 length of segment : 171 time for calcul the mask position with numpy : 0.03411126136779785 nb_pixel_total : 20672 time to create 1 rle with old method : 0.02299809455871582 length of segment : 139 time for calcul the mask position with numpy : 0.009152650833129883 nb_pixel_total : 4915 time to create 1 rle with old method : 0.005918025970458984 length of segment : 100 time for calcul the mask position with numpy : 0.041146039962768555 nb_pixel_total : 11824 time to create 1 rle with old method : 0.01785421371459961 length of segment : 146 time for calcul the mask position with numpy : 0.05384469032287598 nb_pixel_total : 22139 time to create 1 rle with old method : 0.028949975967407227 length of segment : 254 time for calcul the mask position with numpy : 0.09246063232421875 nb_pixel_total : 39676 time to create 1 rle with old method : 0.04738426208496094 length of segment : 235 time for calcul the mask position with numpy : 0.1884326934814453 nb_pixel_total : 105739 time to create 1 rle with old method : 0.11339926719665527 length of segment : 533 time for calcul the mask position with numpy : 0.06981897354125977 nb_pixel_total : 62357 time to create 1 rle with old method : 0.07346868515014648 length of segment : 294 time for calcul the mask position with numpy : 0.027323007583618164 nb_pixel_total : 6876 time to create 1 rle with old method : 0.010739803314208984 length of segment : 120 time for calcul the mask position with numpy : 0.165724515914917 nb_pixel_total : 63325 time to create 1 rle with old method : 0.08169102668762207 length of segment : 390 time for calcul the mask position with numpy : 0.021060705184936523 nb_pixel_total : 18307 time to create 1 rle with old method : 0.027181386947631836 length of segment : 199 time for calcul the mask position with numpy : 0.02182459831237793 nb_pixel_total : 21653 time to create 1 rle with old method : 0.028420209884643555 length of segment : 196 time for calcul the mask position with numpy : 0.009103059768676758 nb_pixel_total : 9861 time to create 1 rle with old method : 0.013777017593383789 length of segment : 119 time for calcul the mask position with numpy : 0.05591988563537598 nb_pixel_total : 9498 time to create 1 rle with old method : 0.015829801559448242 length of segment : 243 time for calcul the mask position with numpy : 0.027014970779418945 nb_pixel_total : 11402 time to create 1 rle with old method : 0.01739335060119629 length of segment : 179 time for calcul the mask position with numpy : 0.04288649559020996 nb_pixel_total : 14098 time to create 1 rle with old method : 0.020548343658447266 length of segment : 167 time for calcul the mask position with numpy : 0.007927417755126953 nb_pixel_total : 14539 time to create 1 rle with old method : 0.022723913192749023 length of segment : 245 time for calcul the mask position with numpy : 0.07110095024108887 nb_pixel_total : 37172 time to create 1 rle with old method : 0.040077924728393555 length of segment : 254 time for calcul the mask position with numpy : 0.029930591583251953 nb_pixel_total : 21023 time to create 1 rle with old method : 0.024517297744750977 length of segment : 172 time for calcul the mask position with numpy : 0.05985522270202637 nb_pixel_total : 41065 time to create 1 rle with old method : 0.04446840286254883 length of segment : 285 time for calcul the mask position with numpy : 0.005361080169677734 nb_pixel_total : 7772 time to create 1 rle with old method : 0.009917497634887695 length of segment : 123 time for calcul the mask position with numpy : 0.05592608451843262 nb_pixel_total : 19599 time to create 1 rle with old method : 0.027492523193359375 length of segment : 275 time for calcul the mask position with numpy : 0.01591348648071289 nb_pixel_total : 15365 time to create 1 rle with old method : 0.021707534790039062 length of segment : 147 time for calcul the mask position with numpy : 0.030996084213256836 nb_pixel_total : 21547 time to create 1 rle with old method : 0.03340482711791992 length of segment : 224 time for calcul the mask position with numpy : 0.022081613540649414 nb_pixel_total : 5973 time to create 1 rle with old method : 0.014304637908935547 length of segment : 115 time for calcul the mask position with numpy : 0.026508808135986328 nb_pixel_total : 7492 time to create 1 rle with old method : 0.013898849487304688 length of segment : 94 time for calcul the mask position with numpy : 0.032678842544555664 nb_pixel_total : 10768 time to create 1 rle with old method : 0.014081478118896484 length of segment : 154 time for calcul the mask position with numpy : 0.03478074073791504 nb_pixel_total : 32804 time to create 1 rle with old method : 0.04016613960266113 length of segment : 327 time for calcul the mask position with numpy : 0.057366371154785156 nb_pixel_total : 34539 time to create 1 rle with old method : 0.041036128997802734 length of segment : 254 time for calcul the mask position with numpy : 0.02346014976501465 nb_pixel_total : 26410 time to create 1 rle with old method : 0.03650808334350586 length of segment : 204 time for calcul the mask position with numpy : 0.03482198715209961 nb_pixel_total : 19950 time to create 1 rle with old method : 0.026015758514404297 length of segment : 170 time for calcul the mask position with numpy : 0.03387331962585449 nb_pixel_total : 14494 time to create 1 rle with old method : 0.020488262176513672 length of segment : 114 time for calcul the mask position with numpy : 0.02518486976623535 nb_pixel_total : 29344 time to create 1 rle with old method : 0.04441571235656738 length of segment : 206 time for calcul the mask position with numpy : 0.0028510093688964844 nb_pixel_total : 20461 time to create 1 rle with old method : 0.02243804931640625 length of segment : 181 time for calcul the mask position with numpy : 0.007226705551147461 nb_pixel_total : 8255 time to create 1 rle with old method : 0.011077642440795898 length of segment : 114 time for calcul the mask position with numpy : 0.014714241027832031 nb_pixel_total : 34345 time to create 1 rle with old method : 0.03978323936462402 length of segment : 390 time for calcul the mask position with numpy : 0.009661197662353516 nb_pixel_total : 9530 time to create 1 rle with old method : 0.01441335678100586 length of segment : 108 time for calcul the mask position with numpy : 0.05517292022705078 nb_pixel_total : 16359 time to create 1 rle with old method : 0.02126908302307129 length of segment : 146 time for calcul the mask position with numpy : 0.0068302154541015625 nb_pixel_total : 21935 time to create 1 rle with old method : 0.025589466094970703 length of segment : 184 time for calcul the mask position with numpy : 0.004133701324462891 nb_pixel_total : 72168 time to create 1 rle with old method : 0.07759928703308105 length of segment : 306 time for calcul the mask position with numpy : 0.10016584396362305 nb_pixel_total : 32359 time to create 1 rle with old method : 0.039629220962524414 length of segment : 191 time for calcul the mask position with numpy : 0.10479354858398438 nb_pixel_total : 33734 time to create 1 rle with old method : 0.045296669006347656 length of segment : 445 time for calcul the mask position with numpy : 0.03069782257080078 nb_pixel_total : 64680 time to create 1 rle with old method : 0.07416653633117676 length of segment : 419 time for calcul the mask position with numpy : 0.04743480682373047 nb_pixel_total : 11682 time to create 1 rle with old method : 0.01656961441040039 length of segment : 105 time for calcul the mask position with numpy : 0.0831904411315918 nb_pixel_total : 28280 time to create 1 rle with old method : 0.03377246856689453 length of segment : 196 time for calcul the mask position with numpy : 0.01851201057434082 nb_pixel_total : 19595 time to create 1 rle with old method : 0.026928186416625977 length of segment : 258 time for calcul the mask position with numpy : 0.12585878372192383 nb_pixel_total : 83444 time to create 1 rle with old method : 0.09403443336486816 length of segment : 333 time for calcul the mask position with numpy : 0.015575647354125977 nb_pixel_total : 61467 time to create 1 rle with old method : 0.06999063491821289 length of segment : 294 time for calcul the mask position with numpy : 0.12265896797180176 nb_pixel_total : 54393 time to create 1 rle with old method : 0.06358122825622559 length of segment : 448 time for calcul the mask position with numpy : 0.08095955848693848 nb_pixel_total : 29513 time to create 1 rle with old method : 0.04667782783508301 length of segment : 316 time for calcul the mask position with numpy : 0.02567887306213379 nb_pixel_total : 66523 time to create 1 rle with old method : 0.07552933692932129 length of segment : 484 time for calcul the mask position with numpy : 0.021024227142333984 nb_pixel_total : 33190 time to create 1 rle with old method : 0.04274749755859375 length of segment : 178 time for calcul the mask position with numpy : 0.015411376953125 nb_pixel_total : 40310 time to create 1 rle with old method : 0.04943990707397461 length of segment : 357 time for calcul the mask position with numpy : 0.0008070468902587891 nb_pixel_total : 10019 time to create 1 rle with old method : 0.01147150993347168 length of segment : 137 time for calcul the mask position with numpy : 0.0006906986236572266 nb_pixel_total : 8856 time to create 1 rle with old method : 0.010376453399658203 length of segment : 107 time for calcul the mask position with numpy : 0.006691455841064453 nb_pixel_total : 89826 time to create 1 rle with old method : 0.13011908531188965 length of segment : 369 time for calcul the mask position with numpy : 0.026934146881103516 nb_pixel_total : 12264 time to create 1 rle with old method : 0.019780635833740234 length of segment : 156 time for calcul the mask position with numpy : 0.004800558090209961 nb_pixel_total : 25370 time to create 1 rle with old method : 0.030410289764404297 length of segment : 195 time for calcul the mask position with numpy : 0.0016727447509765625 nb_pixel_total : 20472 time to create 1 rle with old method : 0.02708911895751953 length of segment : 165 time for calcul the mask position with numpy : 0.009832620620727539 nb_pixel_total : 18681 time to create 1 rle with old method : 0.025426387786865234 length of segment : 181 time for calcul the mask position with numpy : 0.0019752979278564453 nb_pixel_total : 10969 time to create 1 rle with old method : 0.01308894157409668 length of segment : 120 time for calcul the mask position with numpy : 0.017203569412231445 nb_pixel_total : 10776 time to create 1 rle with old method : 0.016323328018188477 length of segment : 177 time for calcul the mask position with numpy : 0.018761396408081055 nb_pixel_total : 6115 time to create 1 rle with old method : 0.010815620422363281 length of segment : 77 time for calcul the mask position with numpy : 0.005399465560913086 nb_pixel_total : 11701 time to create 1 rle with old method : 0.014875411987304688 length of segment : 135 time for calcul the mask position with numpy : 0.16439294815063477 nb_pixel_total : 91021 time to create 1 rle with old method : 0.10468554496765137 length of segment : 390 time for calcul the mask position with numpy : 0.002100229263305664 nb_pixel_total : 26573 time to create 1 rle with old method : 0.02891373634338379 length of segment : 315 time for calcul the mask position with numpy : 0.013366222381591797 nb_pixel_total : 6323 time to create 1 rle with old method : 0.011482954025268555 length of segment : 103 time for calcul the mask position with numpy : 0.03132987022399902 nb_pixel_total : 39072 time to create 1 rle with old method : 0.04495048522949219 length of segment : 177 time for calcul the mask position with numpy : 0.03247833251953125 nb_pixel_total : 36849 time to create 1 rle with old method : 0.0458829402923584 length of segment : 283 time for calcul the mask position with numpy : 0.004119157791137695 nb_pixel_total : 12169 time to create 1 rle with old method : 0.015418291091918945 length of segment : 194 time for calcul the mask position with numpy : 0.007911920547485352 nb_pixel_total : 13456 time to create 1 rle with old method : 0.01696038246154785 length of segment : 253 time for calcul the mask position with numpy : 0.13306879997253418 nb_pixel_total : 30106 time to create 1 rle with old method : 0.037894487380981445 length of segment : 370 time for calcul the mask position with numpy : 0.005231618881225586 nb_pixel_total : 10541 time to create 1 rle with old method : 0.013268232345581055 length of segment : 146 time for calcul the mask position with numpy : 0.00203704833984375 nb_pixel_total : 10622 time to create 1 rle with old method : 0.012043237686157227 length of segment : 111 time for calcul the mask position with numpy : 0.008461475372314453 nb_pixel_total : 13751 time to create 1 rle with old method : 0.019516706466674805 length of segment : 122 time for calcul the mask position with numpy : 0.005427837371826172 nb_pixel_total : 37955 time to create 1 rle with old method : 0.04384469985961914 length of segment : 252 time for calcul the mask position with numpy : 0.2485034465789795 nb_pixel_total : 129501 time to create 1 rle with old method : 0.14403796195983887 length of segment : 511 time for calcul the mask position with numpy : 0.2407393455505371 nb_pixel_total : 85759 time to create 1 rle with old method : 0.09582257270812988 length of segment : 283 time for calcul the mask position with numpy : 1.0034687519073486 nb_pixel_total : 751102 time to create 1 rle with new method : 0.08602285385131836 length of segment : 666 time for calcul the mask position with numpy : 0.030440807342529297 nb_pixel_total : 28123 time to create 1 rle with old method : 0.03579115867614746 length of segment : 158 time for calcul the mask position with numpy : 0.025524377822875977 nb_pixel_total : 19240 time to create 1 rle with old method : 0.025916337966918945 length of segment : 167 time for calcul the mask position with numpy : 0.04879045486450195 nb_pixel_total : 11618 time to create 1 rle with old method : 0.017618179321289062 length of segment : 202 time for calcul the mask position with numpy : 0.019425153732299805 nb_pixel_total : 19345 time to create 1 rle with old method : 0.02724480628967285 length of segment : 180 time for calcul the mask position with numpy : 0.02549004554748535 nb_pixel_total : 19826 time to create 1 rle with old method : 0.02772212028503418 length of segment : 205 time for calcul the mask position with numpy : 0.05621838569641113 nb_pixel_total : 24140 time to create 1 rle with old method : 0.030302047729492188 length of segment : 242 time for calcul the mask position with numpy : 0.023388147354125977 nb_pixel_total : 12776 time to create 1 rle with old method : 0.020220518112182617 length of segment : 136 time for calcul the mask position with numpy : 0.11679482460021973 nb_pixel_total : 48255 time to create 1 rle with old method : 0.05384469032287598 length of segment : 358 time for calcul the mask position with numpy : 0.014941215515136719 nb_pixel_total : 49493 time to create 1 rle with old method : 0.05875515937805176 length of segment : 334 time for calcul the mask position with numpy : 0.02669072151184082 nb_pixel_total : 15567 time to create 1 rle with old method : 0.02183675765991211 length of segment : 139 time for calcul the mask position with numpy : 0.017033815383911133 nb_pixel_total : 6102 time to create 1 rle with old method : 0.012006759643554688 length of segment : 89 time for calcul the mask position with numpy : 0.023958921432495117 nb_pixel_total : 10172 time to create 1 rle with old method : 0.016403913497924805 length of segment : 128 time for calcul the mask position with numpy : 0.16517972946166992 nb_pixel_total : 76571 time to create 1 rle with old method : 0.11346936225891113 length of segment : 443 time for calcul the mask position with numpy : 0.07810235023498535 nb_pixel_total : 22622 time to create 1 rle with old method : 0.027325868606567383 length of segment : 188 time for calcul the mask position with numpy : 0.0927119255065918 nb_pixel_total : 53805 time to create 1 rle with old method : 0.059513092041015625 length of segment : 290 time for calcul the mask position with numpy : 0.001912832260131836 nb_pixel_total : 5714 time to create 1 rle with old method : 0.0067996978759765625 length of segment : 70 time for calcul the mask position with numpy : 0.2124936580657959 nb_pixel_total : 261287 time to create 1 rle with new method : 0.01559591293334961 length of segment : 538 time for calcul the mask position with numpy : 0.023210525512695312 nb_pixel_total : 9343 time to create 1 rle with old method : 0.01312875747680664 length of segment : 98 time for calcul the mask position with numpy : 0.009205102920532227 nb_pixel_total : 13470 time to create 1 rle with old method : 0.016731739044189453 length of segment : 155 time for calcul the mask position with numpy : 0.012096405029296875 nb_pixel_total : 8370 time to create 1 rle with old method : 0.011603116989135742 length of segment : 138 time for calcul the mask position with numpy : 0.004103660583496094 nb_pixel_total : 7920 time to create 1 rle with old method : 0.010190010070800781 length of segment : 137 time for calcul the mask position with numpy : 0.05766916275024414 nb_pixel_total : 30775 time to create 1 rle with old method : 0.03585481643676758 length of segment : 254 time for calcul the mask position with numpy : 0.0042421817779541016 nb_pixel_total : 5453 time to create 1 rle with old method : 0.008199691772460938 length of segment : 81 time for calcul the mask position with numpy : 0.0038759708404541016 nb_pixel_total : 2623 time to create 1 rle with old method : 0.0053615570068359375 length of segment : 59 time for calcul the mask position with numpy : 0.10207080841064453 nb_pixel_total : 51732 time to create 1 rle with old method : 0.0577847957611084 length of segment : 289 time for calcul the mask position with numpy : 0.012035608291625977 nb_pixel_total : 19931 time to create 1 rle with old method : 0.021597623825073242 length of segment : 169 time for calcul the mask position with numpy : 0.0004591941833496094 nb_pixel_total : 5997 time to create 1 rle with old method : 0.0068051815032958984 length of segment : 81 time for calcul the mask position with numpy : 0.01764392852783203 nb_pixel_total : 11801 time to create 1 rle with old method : 0.01854872703552246 length of segment : 181 time for calcul the mask position with numpy : 0.01568746566772461 nb_pixel_total : 7486 time to create 1 rle with old method : 0.012349843978881836 length of segment : 96 time for calcul the mask position with numpy : 0.008716344833374023 nb_pixel_total : 5703 time to create 1 rle with old method : 0.010738372802734375 length of segment : 101 time for calcul the mask position with numpy : 0.025899648666381836 nb_pixel_total : 33437 time to create 1 rle with old method : 0.038055419921875 length of segment : 262 time for calcul the mask position with numpy : 0.00018262863159179688 nb_pixel_total : 5424 time to create 1 rle with old method : 0.00632166862487793 length of segment : 81 time for calcul the mask position with numpy : 0.00022339820861816406 nb_pixel_total : 4949 time to create 1 rle with old method : 0.005814790725708008 length of segment : 68 time for calcul the mask position with numpy : 0.00016760826110839844 nb_pixel_total : 2759 time to create 1 rle with old method : 0.003314971923828125 length of segment : 54 time for calcul the mask position with numpy : 0.029196977615356445 nb_pixel_total : 72253 time to create 1 rle with old method : 0.08223557472229004 length of segment : 304 time for calcul the mask position with numpy : 0.0051729679107666016 nb_pixel_total : 26617 time to create 1 rle with old method : 0.029141902923583984 length of segment : 192 time for calcul the mask position with numpy : 0.0028314590454101562 nb_pixel_total : 10465 time to create 1 rle with old method : 0.01270914077758789 length of segment : 185 time for calcul the mask position with numpy : 0.05160665512084961 nb_pixel_total : 40866 time to create 1 rle with old method : 0.04905843734741211 length of segment : 147 time for calcul the mask position with numpy : 0.1349658966064453 nb_pixel_total : 178705 time to create 1 rle with new method : 0.174940824508667 length of segment : 516 time for calcul the mask position with numpy : 0.007642507553100586 nb_pixel_total : 10680 time to create 1 rle with old method : 0.015104532241821289 length of segment : 105 time for calcul the mask position with numpy : 0.02100062370300293 nb_pixel_total : 81573 time to create 1 rle with old method : 0.09046792984008789 length of segment : 214 time for calcul the mask position with numpy : 0.010718822479248047 nb_pixel_total : 12138 time to create 1 rle with old method : 0.016684532165527344 length of segment : 274 time for calcul the mask position with numpy : 0.0004322528839111328 nb_pixel_total : 3677 time to create 1 rle with old method : 0.0044324398040771484 length of segment : 97 time for calcul the mask position with numpy : 0.0011343955993652344 nb_pixel_total : 14962 time to create 1 rle with old method : 0.016480445861816406 length of segment : 214 time for calcul the mask position with numpy : 0.0011944770812988281 nb_pixel_total : 16325 time to create 1 rle with old method : 0.018175363540649414 length of segment : 180 time for calcul the mask position with numpy : 0.025320053100585938 nb_pixel_total : 15980 time to create 1 rle with old method : 0.021701812744140625 length of segment : 248 time for calcul the mask position with numpy : 0.012561559677124023 nb_pixel_total : 15115 time to create 1 rle with old method : 0.020185232162475586 length of segment : 143 time for calcul the mask position with numpy : 0.0009832382202148438 nb_pixel_total : 11398 time to create 1 rle with old method : 0.013320207595825195 length of segment : 161 time for calcul the mask position with numpy : 0.033792972564697266 nb_pixel_total : 35373 time to create 1 rle with old method : 0.043877601623535156 length of segment : 222 time for calcul the mask position with numpy : 0.0009431838989257812 nb_pixel_total : 10585 time to create 1 rle with old method : 0.012859106063842773 length of segment : 128 time for calcul the mask position with numpy : 0.002536296844482422 nb_pixel_total : 50691 time to create 1 rle with old method : 0.0641031265258789 length of segment : 323 time for calcul the mask position with numpy : 0.010061502456665039 nb_pixel_total : 18542 time to create 1 rle with old method : 0.02412700653076172 length of segment : 162 time for calcul the mask position with numpy : 0.0011684894561767578 nb_pixel_total : 11798 time to create 1 rle with old method : 0.018413305282592773 length of segment : 107 time for calcul the mask position with numpy : 0.0014202594757080078 nb_pixel_total : 17109 time to create 1 rle with old method : 0.022830724716186523 length of segment : 149 time for calcul the mask position with numpy : 0.007253408432006836 nb_pixel_total : 21871 time to create 1 rle with old method : 0.028486013412475586 length of segment : 155 time for calcul the mask position with numpy : 0.0017392635345458984 nb_pixel_total : 19029 time to create 1 rle with old method : 0.022250890731811523 length of segment : 207 time for calcul the mask position with numpy : 0.019601106643676758 nb_pixel_total : 16294 time to create 1 rle with old method : 0.022639751434326172 length of segment : 195 time for calcul the mask position with numpy : 0.005309343338012695 nb_pixel_total : 11327 time to create 1 rle with old method : 0.01454305648803711 length of segment : 104 time for calcul the mask position with numpy : 0.011837482452392578 nb_pixel_total : 23490 time to create 1 rle with old method : 0.030939340591430664 length of segment : 289 time for calcul the mask position with numpy : 0.021807432174682617 nb_pixel_total : 12727 time to create 1 rle with old method : 0.01895761489868164 length of segment : 117 time for calcul the mask position with numpy : 0.0006084442138671875 nb_pixel_total : 3034 time to create 1 rle with old method : 0.0036613941192626953 length of segment : 51 time for calcul the mask position with numpy : 0.0045909881591796875 nb_pixel_total : 48756 time to create 1 rle with old method : 0.05425071716308594 length of segment : 328 time for calcul the mask position with numpy : 0.0013933181762695312 nb_pixel_total : 22859 time to create 1 rle with old method : 0.025303125381469727 length of segment : 246 time for calcul the mask position with numpy : 0.07836008071899414 nb_pixel_total : 84066 time to create 1 rle with old method : 0.09337282180786133 length of segment : 478 time for calcul the mask position with numpy : 0.009229183197021484 nb_pixel_total : 15372 time to create 1 rle with old method : 0.02713489532470703 length of segment : 148 time for calcul the mask position with numpy : 0.0020678043365478516 nb_pixel_total : 25518 time to create 1 rle with old method : 0.040075063705444336 length of segment : 423 time for calcul the mask position with numpy : 0.008744955062866211 nb_pixel_total : 10942 time to create 1 rle with old method : 0.012269973754882812 length of segment : 74 time for calcul the mask position with numpy : 0.00042247772216796875 nb_pixel_total : 3897 time to create 1 rle with old method : 0.004231929779052734 length of segment : 66 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 2073 time to create 1 rle with old method : 0.0023956298828125 length of segment : 65 time for calcul the mask position with numpy : 0.0019655227661132812 nb_pixel_total : 20419 time to create 1 rle with old method : 0.022552013397216797 length of segment : 207 time for calcul the mask position with numpy : 0.0003266334533691406 nb_pixel_total : 9635 time to create 1 rle with old method : 0.01092839241027832 length of segment : 191 time for calcul the mask position with numpy : 0.0017828941345214844 nb_pixel_total : 18381 time to create 1 rle with old method : 0.020197629928588867 length of segment : 259 time for calcul the mask position with numpy : 0.0027828216552734375 nb_pixel_total : 11718 time to create 1 rle with old method : 0.013625621795654297 length of segment : 133 time for calcul the mask position with numpy : 0.03296494483947754 nb_pixel_total : 14013 time to create 1 rle with old method : 0.02061009407043457 length of segment : 152 time for calcul the mask position with numpy : 0.042345285415649414 nb_pixel_total : 9027 time to create 1 rle with old method : 0.014513015747070312 length of segment : 179 time for calcul the mask position with numpy : 0.02138495445251465 nb_pixel_total : 10739 time to create 1 rle with old method : 0.017261743545532227 length of segment : 107 time for calcul the mask position with numpy : 0.060277700424194336 nb_pixel_total : 67504 time to create 1 rle with old method : 0.07754039764404297 length of segment : 236 time for calcul the mask position with numpy : 0.04530692100524902 nb_pixel_total : 106167 time to create 1 rle with old method : 0.12008833885192871 length of segment : 390 time for calcul the mask position with numpy : 0.0007183551788330078 nb_pixel_total : 7684 time to create 1 rle with old method : 0.008969306945800781 length of segment : 150 time for calcul the mask position with numpy : 0.011791706085205078 nb_pixel_total : 29023 time to create 1 rle with old method : 0.03615236282348633 length of segment : 221 time for calcul the mask position with numpy : 0.0027184486389160156 nb_pixel_total : 19888 time to create 1 rle with old method : 0.026586055755615234 length of segment : 178 time for calcul the mask position with numpy : 0.012820720672607422 nb_pixel_total : 7168 time to create 1 rle with old method : 0.008700847625732422 length of segment : 132 time for calcul the mask position with numpy : 0.0019047260284423828 nb_pixel_total : 10978 time to create 1 rle with old method : 0.013405323028564453 length of segment : 174 time for calcul the mask position with numpy : 0.013668060302734375 nb_pixel_total : 157015 time to create 1 rle with new method : 0.009551525115966797 length of segment : 672 time for calcul the mask position with numpy : 0.0024709701538085938 nb_pixel_total : 12340 time to create 1 rle with old method : 0.01422429084777832 length of segment : 148 time for calcul the mask position with numpy : 0.0010924339294433594 nb_pixel_total : 5868 time to create 1 rle with old method : 0.006925344467163086 length of segment : 85 time for calcul the mask position with numpy : 0.02257704734802246 nb_pixel_total : 15985 time to create 1 rle with old method : 0.02236175537109375 length of segment : 132 time for calcul the mask position with numpy : 0.024968624114990234 nb_pixel_total : 29555 time to create 1 rle with old method : 0.03472900390625 length of segment : 355 time for calcul the mask position with numpy : 0.026100873947143555 nb_pixel_total : 15207 time to create 1 rle with old method : 0.020321369171142578 length of segment : 186 time for calcul the mask position with numpy : 0.0037937164306640625 nb_pixel_total : 45835 time to create 1 rle with old method : 0.050132036209106445 length of segment : 329 time for calcul the mask position with numpy : 0.017720460891723633 nb_pixel_total : 62933 time to create 1 rle with old method : 0.06986212730407715 length of segment : 400 time for calcul the mask position with numpy : 0.004564762115478516 nb_pixel_total : 16110 time to create 1 rle with old method : 0.02020096778869629 length of segment : 157 time for calcul the mask position with numpy : 0.0016069412231445312 nb_pixel_total : 13587 time to create 1 rle with old method : 0.015321493148803711 length of segment : 208 time for calcul the mask position with numpy : 0.0009326934814453125 nb_pixel_total : 9777 time to create 1 rle with old method : 0.011223316192626953 length of segment : 122 time for calcul the mask position with numpy : 0.008266448974609375 nb_pixel_total : 73007 time to create 1 rle with old method : 0.07924294471740723 length of segment : 408 time for calcul the mask position with numpy : 0.011014699935913086 nb_pixel_total : 97242 time to create 1 rle with old method : 0.12157702445983887 length of segment : 272 time for calcul the mask position with numpy : 0.0022974014282226562 nb_pixel_total : 31544 time to create 1 rle with old method : 0.04412698745727539 length of segment : 237 time for calcul the mask position with numpy : 0.0050427913665771484 nb_pixel_total : 51845 time to create 1 rle with old method : 0.06452703475952148 length of segment : 435 time for calcul the mask position with numpy : 0.0018627643585205078 nb_pixel_total : 14205 time to create 1 rle with old method : 0.01828145980834961 length of segment : 202 time for calcul the mask position with numpy : 0.016644001007080078 nb_pixel_total : 32137 time to create 1 rle with old method : 0.04006552696228027 length of segment : 190 time for calcul the mask position with numpy : 0.0037589073181152344 nb_pixel_total : 6918 time to create 1 rle with old method : 0.011426210403442383 length of segment : 85 time for calcul the mask position with numpy : 0.0022690296173095703 nb_pixel_total : 25862 time to create 1 rle with old method : 0.03998422622680664 length of segment : 201 time for calcul the mask position with numpy : 0.00020837783813476562 nb_pixel_total : 4615 time to create 1 rle with old method : 0.005409955978393555 length of segment : 79 time for calcul the mask position with numpy : 0.005994081497192383 nb_pixel_total : 19798 time to create 1 rle with old method : 0.022403717041015625 length of segment : 188 time for calcul the mask position with numpy : 0.011029958724975586 nb_pixel_total : 15688 time to create 1 rle with old method : 0.024805545806884766 length of segment : 202 time for calcul the mask position with numpy : 0.002126932144165039 nb_pixel_total : 25864 time to create 1 rle with old method : 0.030066490173339844 length of segment : 183 time for calcul the mask position with numpy : 0.0005586147308349609 nb_pixel_total : 6860 time to create 1 rle with old method : 0.008274555206298828 length of segment : 141 time for calcul the mask position with numpy : 0.014136552810668945 nb_pixel_total : 4675 time to create 1 rle with old method : 0.009894371032714844 length of segment : 73 time for calcul the mask position with numpy : 0.0023660659790039062 nb_pixel_total : 27718 time to create 1 rle with old method : 0.03144192695617676 length of segment : 213 time for calcul the mask position with numpy : 0.0022110939025878906 nb_pixel_total : 11267 time to create 1 rle with old method : 0.013090133666992188 length of segment : 193 time for calcul the mask position with numpy : 0.005401134490966797 nb_pixel_total : 19533 time to create 1 rle with old method : 0.0240328311920166 length of segment : 158 time for calcul the mask position with numpy : 0.0069882869720458984 nb_pixel_total : 54401 time to create 1 rle with old method : 0.059531211853027344 length of segment : 414 time for calcul the mask position with numpy : 0.0011212825775146484 nb_pixel_total : 18160 time to create 1 rle with old method : 0.020344018936157227 length of segment : 115 time for calcul the mask position with numpy : 0.01985335350036621 nb_pixel_total : 29051 time to create 1 rle with old method : 0.03377652168273926 length of segment : 194 time for calcul the mask position with numpy : 0.0008118152618408203 nb_pixel_total : 21552 time to create 1 rle with old method : 0.02451610565185547 length of segment : 254 time for calcul the mask position with numpy : 0.0006134510040283203 nb_pixel_total : 4751 time to create 1 rle with old method : 0.0059757232666015625 length of segment : 79 time for calcul the mask position with numpy : 0.0008795261383056641 nb_pixel_total : 10874 time to create 1 rle with old method : 0.012993097305297852 length of segment : 120 time for calcul the mask position with numpy : 0.004202127456665039 nb_pixel_total : 11675 time to create 1 rle with old method : 0.013975381851196289 length of segment : 195 time for calcul the mask position with numpy : 0.0019304752349853516 nb_pixel_total : 12422 time to create 1 rle with old method : 0.01683831214904785 length of segment : 164 time for calcul the mask position with numpy : 0.006735086441040039 nb_pixel_total : 13257 time to create 1 rle with old method : 0.017191648483276367 length of segment : 293 time for calcul the mask position with numpy : 0.04072451591491699 nb_pixel_total : 26643 time to create 1 rle with old method : 0.04282402992248535 length of segment : 711 time for calcul the mask position with numpy : 0.00034999847412109375 nb_pixel_total : 2456 time to create 1 rle with old method : 0.003979921340942383 length of segment : 96 time for calcul the mask position with numpy : 0.0017549991607666016 nb_pixel_total : 13099 time to create 1 rle with old method : 0.017342090606689453 length of segment : 136 time for calcul the mask position with numpy : 0.005895376205444336 nb_pixel_total : 23998 time to create 1 rle with old method : 0.029953956604003906 length of segment : 306 time for calcul the mask position with numpy : 0.0031740665435791016 nb_pixel_total : 40964 time to create 1 rle with old method : 0.04695558547973633 length of segment : 209 time for calcul the mask position with numpy : 0.004492282867431641 nb_pixel_total : 14067 time to create 1 rle with old method : 0.01632094383239746 length of segment : 98 time for calcul the mask position with numpy : 0.00020313262939453125 nb_pixel_total : 4537 time to create 1 rle with old method : 0.005210399627685547 length of segment : 128 time for calcul the mask position with numpy : 0.00031828880310058594 nb_pixel_total : 9034 time to create 1 rle with old method : 0.010105609893798828 length of segment : 244 time for calcul the mask position with numpy : 0.0005962848663330078 nb_pixel_total : 5786 time to create 1 rle with old method : 0.006723165512084961 length of segment : 70 time for calcul the mask position with numpy : 0.00020456314086914062 nb_pixel_total : 3019 time to create 1 rle with old method : 0.003690004348754883 length of segment : 59 time for calcul the mask position with numpy : 0.0013513565063476562 nb_pixel_total : 15749 time to create 1 rle with old method : 0.0177915096282959 length of segment : 141 time for calcul the mask position with numpy : 0.0025577545166015625 nb_pixel_total : 10300 time to create 1 rle with old method : 0.011522054672241211 length of segment : 243 time for calcul the mask position with numpy : 0.001100301742553711 nb_pixel_total : 13310 time to create 1 rle with old method : 0.015540838241577148 length of segment : 128 time for calcul the mask position with numpy : 0.0005464553833007812 nb_pixel_total : 5550 time to create 1 rle with old method : 0.0064852237701416016 length of segment : 72 time for calcul the mask position with numpy : 0.0008113384246826172 nb_pixel_total : 16799 time to create 1 rle with old method : 0.01934814453125 length of segment : 242 time for calcul the mask position with numpy : 0.0332186222076416 nb_pixel_total : 49912 time to create 1 rle with old method : 0.05825400352478027 length of segment : 333 time for calcul the mask position with numpy : 0.00022935867309570312 nb_pixel_total : 4939 time to create 1 rle with old method : 0.005655050277709961 length of segment : 68 time for calcul the mask position with numpy : 0.0023589134216308594 nb_pixel_total : 9316 time to create 1 rle with old method : 0.011063814163208008 length of segment : 147 time for calcul the mask position with numpy : 0.024332046508789062 nb_pixel_total : 193307 time to create 1 rle with new method : 0.011480093002319336 length of segment : 477 time for calcul the mask position with numpy : 0.0011758804321289062 nb_pixel_total : 18784 time to create 1 rle with old method : 0.022928476333618164 length of segment : 135 time for calcul the mask position with numpy : 0.0019421577453613281 nb_pixel_total : 10650 time to create 1 rle with old method : 0.014837980270385742 length of segment : 146 time for calcul the mask position with numpy : 0.0031218528747558594 nb_pixel_total : 29028 time to create 1 rle with old method : 0.05326128005981445 length of segment : 215 time for calcul the mask position with numpy : 0.0003402233123779297 nb_pixel_total : 5625 time to create 1 rle with old method : 0.0065157413482666016 length of segment : 87 time for calcul the mask position with numpy : 0.01574397087097168 nb_pixel_total : 70546 time to create 1 rle with old method : 0.07889199256896973 length of segment : 422 time for calcul the mask position with numpy : 0.0028989315032958984 nb_pixel_total : 25422 time to create 1 rle with old method : 0.027382850646972656 length of segment : 194 time for calcul the mask position with numpy : 0.0037386417388916016 nb_pixel_total : 22873 time to create 1 rle with old method : 0.025059938430786133 length of segment : 208 time for calcul the mask position with numpy : 0.0023717880249023438 nb_pixel_total : 10851 time to create 1 rle with old method : 0.01162266731262207 length of segment : 120 time for calcul the mask position with numpy : 0.0064945220947265625 nb_pixel_total : 24552 time to create 1 rle with old method : 0.02924513816833496 length of segment : 229 time for calcul the mask position with numpy : 0.009286165237426758 nb_pixel_total : 74169 time to create 1 rle with old method : 0.0782928466796875 length of segment : 289 time for calcul the mask position with numpy : 0.004751920700073242 nb_pixel_total : 29896 time to create 1 rle with old method : 0.03099989891052246 length of segment : 252 time for calcul the mask position with numpy : 0.0023946762084960938 nb_pixel_total : 20740 time to create 1 rle with old method : 0.022114276885986328 length of segment : 193 time for calcul the mask position with numpy : 0.0035758018493652344 nb_pixel_total : 24256 time to create 1 rle with old method : 0.026140689849853516 length of segment : 199 time for calcul the mask position with numpy : 0.0023789405822753906 nb_pixel_total : 19062 time to create 1 rle with old method : 0.021603822708129883 length of segment : 146 time for calcul the mask position with numpy : 0.0030248165130615234 nb_pixel_total : 36621 time to create 1 rle with old method : 0.039348602294921875 length of segment : 236 time for calcul the mask position with numpy : 0.0026438236236572266 nb_pixel_total : 17826 time to create 1 rle with old method : 0.019379377365112305 length of segment : 202 time for calcul the mask position with numpy : 0.003688812255859375 nb_pixel_total : 28008 time to create 1 rle with old method : 0.029926300048828125 length of segment : 249 time for calcul the mask position with numpy : 0.004090547561645508 nb_pixel_total : 19561 time to create 1 rle with old method : 0.021615028381347656 length of segment : 199 time for calcul the mask position with numpy : 0.0014095306396484375 nb_pixel_total : 14346 time to create 1 rle with old method : 0.022785663604736328 length of segment : 171 time for calcul the mask position with numpy : 0.0028753280639648438 nb_pixel_total : 14500 time to create 1 rle with old method : 0.02277827262878418 length of segment : 200 time for calcul the mask position with numpy : 0.003955364227294922 nb_pixel_total : 35902 time to create 1 rle with old method : 0.038698673248291016 length of segment : 263 time for calcul the mask position with numpy : 0.0005011558532714844 nb_pixel_total : 3487 time to create 1 rle with old method : 0.00415492057800293 length of segment : 90 time for calcul the mask position with numpy : 0.0003113746643066406 nb_pixel_total : 5703 time to create 1 rle with old method : 0.006390571594238281 length of segment : 109 time for calcul the mask position with numpy : 0.0018994808197021484 nb_pixel_total : 31218 time to create 1 rle with old method : 0.033657073974609375 length of segment : 288 time for calcul the mask position with numpy : 0.0006814002990722656 nb_pixel_total : 19215 time to create 1 rle with old method : 0.02295708656311035 length of segment : 162 time for calcul the mask position with numpy : 0.0018534660339355469 nb_pixel_total : 13022 time to create 1 rle with old method : 0.014706611633300781 length of segment : 116 time for calcul the mask position with numpy : 0.0010607242584228516 nb_pixel_total : 5127 time to create 1 rle with old method : 0.005778312683105469 length of segment : 79 time for calcul the mask position with numpy : 0.0005593299865722656 nb_pixel_total : 10523 time to create 1 rle with old method : 0.01164698600769043 length of segment : 128 time for calcul the mask position with numpy : 0.006843090057373047 nb_pixel_total : 62660 time to create 1 rle with old method : 0.06694436073303223 length of segment : 425 time for calcul the mask position with numpy : 0.016433238983154297 nb_pixel_total : 155328 time to create 1 rle with new method : 0.011045455932617188 length of segment : 630 time for calcul the mask position with numpy : 0.002405405044555664 nb_pixel_total : 21539 time to create 1 rle with old method : 0.023370742797851562 length of segment : 155 time for calcul the mask position with numpy : 0.001056671142578125 nb_pixel_total : 15905 time to create 1 rle with old method : 0.017557621002197266 length of segment : 164 time for calcul the mask position with numpy : 0.0032656192779541016 nb_pixel_total : 30639 time to create 1 rle with old method : 0.034630775451660156 length of segment : 195 time for calcul the mask position with numpy : 0.0020744800567626953 nb_pixel_total : 14690 time to create 1 rle with old method : 0.016426801681518555 length of segment : 159 time for calcul the mask position with numpy : 0.0019364356994628906 nb_pixel_total : 14040 time to create 1 rle with old method : 0.015630483627319336 length of segment : 209 time for calcul the mask position with numpy : 0.004694223403930664 nb_pixel_total : 30515 time to create 1 rle with old method : 0.03381752967834473 length of segment : 240 time for calcul the mask position with numpy : 0.0035419464111328125 nb_pixel_total : 38868 time to create 1 rle with old method : 0.04240775108337402 length of segment : 264 time for calcul the mask position with numpy : 0.0024678707122802734 nb_pixel_total : 26610 time to create 1 rle with old method : 0.028644323348999023 length of segment : 341 time for calcul the mask position with numpy : 0.0048675537109375 nb_pixel_total : 8025 time to create 1 rle with old method : 0.011589765548706055 length of segment : 133 time for calcul the mask position with numpy : 0.011044979095458984 nb_pixel_total : 65583 time to create 1 rle with old method : 0.07316398620605469 length of segment : 393 time for calcul the mask position with numpy : 0.0012354850769042969 nb_pixel_total : 8961 time to create 1 rle with old method : 0.009971857070922852 length of segment : 116 time for calcul the mask position with numpy : 0.0018725395202636719 nb_pixel_total : 22540 time to create 1 rle with old method : 0.029160022735595703 length of segment : 209 time for calcul the mask position with numpy : 0.0037407875061035156 nb_pixel_total : 68941 time to create 1 rle with old method : 0.07340002059936523 length of segment : 276 time for calcul the mask position with numpy : 0.00244140625 nb_pixel_total : 30576 time to create 1 rle with old method : 0.0333709716796875 length of segment : 366 time for calcul the mask position with numpy : 0.011135101318359375 nb_pixel_total : 139684 time to create 1 rle with old method : 0.15257954597473145 length of segment : 364 time for calcul the mask position with numpy : 0.006415843963623047 nb_pixel_total : 98325 time to create 1 rle with old method : 0.10762906074523926 length of segment : 282 time for calcul the mask position with numpy : 0.00658106803894043 nb_pixel_total : 68182 time to create 1 rle with old method : 0.07290220260620117 length of segment : 444 time for calcul the mask position with numpy : 0.0010418891906738281 nb_pixel_total : 11343 time to create 1 rle with old method : 0.012146949768066406 length of segment : 140 time for calcul the mask position with numpy : 0.002258777618408203 nb_pixel_total : 36091 time to create 1 rle with old method : 0.03860163688659668 length of segment : 170 time for calcul the mask position with numpy : 0.0017192363739013672 nb_pixel_total : 16731 time to create 1 rle with old method : 0.01802825927734375 length of segment : 366 time for calcul the mask position with numpy : 0.0020296573638916016 nb_pixel_total : 28938 time to create 1 rle with old method : 0.030896663665771484 length of segment : 426 time for calcul the mask position with numpy : 0.0075037479400634766 nb_pixel_total : 141753 time to create 1 rle with old method : 0.15047430992126465 length of segment : 351 time for calcul the mask position with numpy : 0.0005650520324707031 nb_pixel_total : 8708 time to create 1 rle with old method : 0.010003805160522461 length of segment : 88 time for calcul the mask position with numpy : 0.002678394317626953 nb_pixel_total : 26660 time to create 1 rle with old method : 0.029455900192260742 length of segment : 372 time for calcul the mask position with numpy : 0.0028378963470458984 nb_pixel_total : 28080 time to create 1 rle with old method : 0.030861377716064453 length of segment : 212 time for calcul the mask position with numpy : 0.0004825592041015625 nb_pixel_total : 5114 time to create 1 rle with old method : 0.0056493282318115234 length of segment : 90 time for calcul the mask position with numpy : 0.0002884864807128906 nb_pixel_total : 8120 time to create 1 rle with old method : 0.00902414321899414 length of segment : 94 time for calcul the mask position with numpy : 0.008871793746948242 nb_pixel_total : 130071 time to create 1 rle with old method : 0.13681268692016602 length of segment : 465 time for calcul the mask position with numpy : 0.0021467208862304688 nb_pixel_total : 32077 time to create 1 rle with old method : 0.035005807876586914 length of segment : 165 time for calcul the mask position with numpy : 0.0011518001556396484 nb_pixel_total : 14086 time to create 1 rle with old method : 0.015562295913696289 length of segment : 204 time for calcul the mask position with numpy : 0.0019261837005615234 nb_pixel_total : 23193 time to create 1 rle with old method : 0.02610039710998535 length of segment : 236 time for calcul the mask position with numpy : 0.0023834705352783203 nb_pixel_total : 9828 time to create 1 rle with old method : 0.011738777160644531 length of segment : 286 time for calcul the mask position with numpy : 0.005330801010131836 nb_pixel_total : 56779 time to create 1 rle with old method : 0.060935020446777344 length of segment : 382 time for calcul the mask position with numpy : 0.0008935928344726562 nb_pixel_total : 30345 time to create 1 rle with old method : 0.03306841850280762 length of segment : 330 time for calcul the mask position with numpy : 0.004216670989990234 nb_pixel_total : 60929 time to create 1 rle with old method : 0.06662130355834961 length of segment : 203 time for calcul the mask position with numpy : 0.0007023811340332031 nb_pixel_total : 12263 time to create 1 rle with old method : 0.013596773147583008 length of segment : 205 time for calcul the mask position with numpy : 0.0056705474853515625 nb_pixel_total : 58383 time to create 1 rle with old method : 0.06361079216003418 length of segment : 320 time for calcul the mask position with numpy : 0.0008175373077392578 nb_pixel_total : 8860 time to create 1 rle with old method : 0.010025501251220703 length of segment : 203 time for calcul the mask position with numpy : 0.0010600090026855469 nb_pixel_total : 15262 time to create 1 rle with old method : 0.0171356201171875 length of segment : 193 time for calcul the mask position with numpy : 0.0032520294189453125 nb_pixel_total : 31783 time to create 1 rle with old method : 0.035961151123046875 length of segment : 271 time for calcul the mask position with numpy : 0.0011560916900634766 nb_pixel_total : 16812 time to create 1 rle with old method : 0.01867198944091797 length of segment : 159 time for calcul the mask position with numpy : 0.0014450550079345703 nb_pixel_total : 18770 time to create 1 rle with old method : 0.0210421085357666 length of segment : 283 time for calcul the mask position with numpy : 0.004079580307006836 nb_pixel_total : 78316 time to create 1 rle with old method : 0.08528280258178711 length of segment : 293 time for calcul the mask position with numpy : 0.0019559860229492188 nb_pixel_total : 18101 time to create 1 rle with old method : 0.021033048629760742 length of segment : 227 time for calcul the mask position with numpy : 0.0029878616333007812 nb_pixel_total : 49811 time to create 1 rle with old method : 0.05308103561401367 length of segment : 342 time for calcul the mask position with numpy : 0.0007534027099609375 nb_pixel_total : 11660 time to create 1 rle with old method : 0.012741804122924805 length of segment : 140 time for calcul the mask position with numpy : 0.002211332321166992 nb_pixel_total : 36570 time to create 1 rle with old method : 0.03918719291687012 length of segment : 292 time for calcul the mask position with numpy : 0.002878904342651367 nb_pixel_total : 59739 time to create 1 rle with old method : 0.06479763984680176 length of segment : 254 time for calcul the mask position with numpy : 0.002342700958251953 nb_pixel_total : 29266 time to create 1 rle with old method : 0.03163337707519531 length of segment : 417 time for calcul the mask position with numpy : 0.0024263858795166016 nb_pixel_total : 26118 time to create 1 rle with old method : 0.028657913208007812 length of segment : 271 time for calcul the mask position with numpy : 0.0005276203155517578 nb_pixel_total : 12311 time to create 1 rle with old method : 0.013768196105957031 length of segment : 121 time for calcul the mask position with numpy : 0.0008015632629394531 nb_pixel_total : 12053 time to create 1 rle with old method : 0.013639450073242188 length of segment : 110 time for calcul the mask position with numpy : 0.0013890266418457031 nb_pixel_total : 22638 time to create 1 rle with old method : 0.0267333984375 length of segment : 219 time for calcul the mask position with numpy : 0.001071929931640625 nb_pixel_total : 20170 time to create 1 rle with old method : 0.03044724464416504 length of segment : 188 time for calcul the mask position with numpy : 0.0006434917449951172 nb_pixel_total : 13183 time to create 1 rle with old method : 0.014526128768920898 length of segment : 146 time for calcul the mask position with numpy : 0.0008082389831542969 nb_pixel_total : 14919 time to create 1 rle with old method : 0.019678115844726562 length of segment : 213 time for calcul the mask position with numpy : 0.001402139663696289 nb_pixel_total : 28870 time to create 1 rle with old method : 0.0320131778717041 length of segment : 243 time for calcul the mask position with numpy : 0.0028486251831054688 nb_pixel_total : 94920 time to create 1 rle with old method : 0.09984230995178223 length of segment : 422 time for calcul the mask position with numpy : 0.0010254383087158203 nb_pixel_total : 25215 time to create 1 rle with old method : 0.027549028396606445 length of segment : 123 time for calcul the mask position with numpy : 0.0020966529846191406 nb_pixel_total : 42905 time to create 1 rle with old method : 0.04540133476257324 length of segment : 255 time for calcul the mask position with numpy : 0.004924774169921875 nb_pixel_total : 121889 time to create 1 rle with old method : 0.12516570091247559 length of segment : 600 time for calcul the mask position with numpy : 0.0010485649108886719 nb_pixel_total : 23638 time to create 1 rle with old method : 0.024599313735961914 length of segment : 209 time for calcul the mask position with numpy : 0.003190279006958008 nb_pixel_total : 103883 time to create 1 rle with old method : 0.11218047142028809 length of segment : 381 time for calcul the mask position with numpy : 0.0007619857788085938 nb_pixel_total : 12814 time to create 1 rle with old method : 0.014380216598510742 length of segment : 189 time for calcul the mask position with numpy : 0.015568971633911133 nb_pixel_total : 246971 time to create 1 rle with new method : 0.03803300857543945 length of segment : 670 time for calcul the mask position with numpy : 0.024561405181884766 nb_pixel_total : 464816 time to create 1 rle with new method : 0.09925961494445801 length of segment : 958 time for calcul the mask position with numpy : 0.0009100437164306641 nb_pixel_total : 22182 time to create 1 rle with old method : 0.024366378784179688 length of segment : 355 time for calcul the mask position with numpy : 0.0036764144897460938 nb_pixel_total : 109214 time to create 1 rle with old method : 0.11951780319213867 length of segment : 306 time for calcul the mask position with numpy : 0.0035479068756103516 nb_pixel_total : 65654 time to create 1 rle with old method : 0.07218551635742188 length of segment : 494 time for calcul the mask position with numpy : 0.0010340213775634766 nb_pixel_total : 14785 time to create 1 rle with old method : 0.016872167587280273 length of segment : 244 time for calcul the mask position with numpy : 0.0053217411041259766 nb_pixel_total : 172766 time to create 1 rle with new method : 0.009793996810913086 length of segment : 639 time for calcul the mask position with numpy : 0.014434099197387695 nb_pixel_total : 588110 time to create 1 rle with new method : 0.03683352470397949 length of segment : 687 time for calcul the mask position with numpy : 0.0006880760192871094 nb_pixel_total : 12713 time to create 1 rle with old method : 0.01429438591003418 length of segment : 121 time for calcul the mask position with numpy : 0.003873586654663086 nb_pixel_total : 89842 time to create 1 rle with old method : 0.0992128849029541 length of segment : 349 time for calcul the mask position with numpy : 0.0039713382720947266 nb_pixel_total : 23137 time to create 1 rle with old method : 0.027797937393188477 length of segment : 289 time for calcul the mask position with numpy : 0.002640247344970703 nb_pixel_total : 68642 time to create 1 rle with old method : 0.07536172866821289 length of segment : 296 time for calcul the mask position with numpy : 0.0015304088592529297 nb_pixel_total : 34870 time to create 1 rle with old method : 0.03947043418884277 length of segment : 320 time for calcul the mask position with numpy : 0.0003223419189453125 nb_pixel_total : 4856 time to create 1 rle with old method : 0.005641937255859375 length of segment : 94 time for calcul the mask position with numpy : 0.0009043216705322266 nb_pixel_total : 22197 time to create 1 rle with old method : 0.02559208869934082 length of segment : 109 time for calcul the mask position with numpy : 0.009622335433959961 nb_pixel_total : 201215 time to create 1 rle with new method : 0.016773462295532227 length of segment : 729 time for calcul the mask position with numpy : 0.0007956027984619141 nb_pixel_total : 7442 time to create 1 rle with old method : 0.010233879089355469 length of segment : 163 time for calcul the mask position with numpy : 0.0006225109100341797 nb_pixel_total : 9518 time to create 1 rle with old method : 0.011337041854858398 length of segment : 139 time for calcul the mask position with numpy : 0.0007336139678955078 nb_pixel_total : 21049 time to create 1 rle with old method : 0.023940324783325195 length of segment : 120 time for calcul the mask position with numpy : 0.00038623809814453125 nb_pixel_total : 17882 time to create 1 rle with old method : 0.020371675491333008 length of segment : 176 time for calcul the mask position with numpy : 0.0010979175567626953 nb_pixel_total : 15550 time to create 1 rle with old method : 0.01772284507751465 length of segment : 240 time for calcul the mask position with numpy : 0.0057561397552490234 nb_pixel_total : 183540 time to create 1 rle with new method : 0.007181644439697266 length of segment : 378 time for calcul the mask position with numpy : 0.01288604736328125 nb_pixel_total : 436318 time to create 1 rle with new method : 0.03996992111206055 length of segment : 649 time for calcul the mask position with numpy : 0.0033910274505615234 nb_pixel_total : 72835 time to create 1 rle with old method : 0.1031961441040039 length of segment : 402 time for calcul the mask position with numpy : 0.006871461868286133 nb_pixel_total : 159377 time to create 1 rle with new method : 0.014465093612670898 length of segment : 572 time for calcul the mask position with numpy : 0.00034117698669433594 nb_pixel_total : 4934 time to create 1 rle with old method : 0.0060884952545166016 length of segment : 111 time for calcul the mask position with numpy : 0.0048618316650390625 nb_pixel_total : 122903 time to create 1 rle with old method : 0.1618821620941162 length of segment : 282 time for calcul the mask position with numpy : 0.0023276805877685547 nb_pixel_total : 40027 time to create 1 rle with old method : 0.04570484161376953 length of segment : 356 time for calcul the mask position with numpy : 0.005499124526977539 nb_pixel_total : 173310 time to create 1 rle with new method : 0.008011817932128906 length of segment : 574 time for calcul the mask position with numpy : 0.0003147125244140625 nb_pixel_total : 11336 time to create 1 rle with old method : 0.012746810913085938 length of segment : 131 time for calcul the mask position with numpy : 0.0055391788482666016 nb_pixel_total : 181346 time to create 1 rle with new method : 0.007924556732177734 length of segment : 598 time for calcul the mask position with numpy : 0.004509449005126953 nb_pixel_total : 123003 time to create 1 rle with old method : 0.15707898139953613 length of segment : 287 time for calcul the mask position with numpy : 0.00668644905090332 nb_pixel_total : 263487 time to create 1 rle with new method : 0.015691280364990234 length of segment : 638 time for calcul the mask position with numpy : 0.006946086883544922 nb_pixel_total : 263939 time to create 1 rle with new method : 0.009710550308227539 length of segment : 532 time for calcul the mask position with numpy : 0.0021021366119384766 nb_pixel_total : 51365 time to create 1 rle with old method : 0.05464673042297363 length of segment : 288 time for calcul the mask position with numpy : 0.0002593994140625 nb_pixel_total : 9209 time to create 1 rle with old method : 0.010233163833618164 length of segment : 92 time for calcul the mask position with numpy : 0.0019609928131103516 nb_pixel_total : 58335 time to create 1 rle with old method : 0.0632321834564209 length of segment : 305 time for calcul the mask position with numpy : 0.002048492431640625 nb_pixel_total : 46630 time to create 1 rle with old method : 0.05192065238952637 length of segment : 255 time for calcul the mask position with numpy : 0.005101919174194336 nb_pixel_total : 138917 time to create 1 rle with old method : 0.17012596130371094 length of segment : 442 time for calcul the mask position with numpy : 0.00284576416015625 nb_pixel_total : 76166 time to create 1 rle with old method : 0.10190868377685547 length of segment : 471 time for calcul the mask position with numpy : 0.0057604312896728516 nb_pixel_total : 101916 time to create 1 rle with old method : 0.15493988990783691 length of segment : 514 time for calcul the mask position with numpy : 0.0010287761688232422 nb_pixel_total : 20595 time to create 1 rle with old method : 0.028220176696777344 length of segment : 211 time for calcul the mask position with numpy : 0.008933544158935547 nb_pixel_total : 179187 time to create 1 rle with new method : 0.012532472610473633 length of segment : 994 time for calcul the mask position with numpy : 0.0024602413177490234 nb_pixel_total : 64031 time to create 1 rle with old method : 0.06927323341369629 length of segment : 249 time for calcul the mask position with numpy : 0.006388187408447266 nb_pixel_total : 184949 time to create 1 rle with new method : 0.011522531509399414 length of segment : 544 time for calcul the mask position with numpy : 0.003693819046020508 nb_pixel_total : 130956 time to create 1 rle with old method : 0.14765620231628418 length of segment : 547 time for calcul the mask position with numpy : 0.0013744831085205078 nb_pixel_total : 28761 time to create 1 rle with old method : 0.03955721855163574 length of segment : 282 time for calcul the mask position with numpy : 0.0011258125305175781 nb_pixel_total : 32093 time to create 1 rle with old method : 0.03584480285644531 length of segment : 161 time for calcul the mask position with numpy : 0.0018444061279296875 nb_pixel_total : 40272 time to create 1 rle with old method : 0.047493934631347656 length of segment : 321 time for calcul the mask position with numpy : 0.0009036064147949219 nb_pixel_total : 28266 time to create 1 rle with old method : 0.0314326286315918 length of segment : 229 time for calcul the mask position with numpy : 0.0035948753356933594 nb_pixel_total : 39998 time to create 1 rle with old method : 0.04416775703430176 length of segment : 520 time for calcul the mask position with numpy : 0.0019228458404541016 nb_pixel_total : 59322 time to create 1 rle with old method : 0.06608057022094727 length of segment : 300 time for calcul the mask position with numpy : 0.0010118484497070312 nb_pixel_total : 18256 time to create 1 rle with old method : 0.020959138870239258 length of segment : 178 time for calcul the mask position with numpy : 0.005127906799316406 nb_pixel_total : 129455 time to create 1 rle with old method : 0.1465151309967041 length of segment : 519 time for calcul the mask position with numpy : 0.002771139144897461 nb_pixel_total : 99284 time to create 1 rle with old method : 0.11075901985168457 length of segment : 439 time for calcul the mask position with numpy : 0.0006551742553710938 nb_pixel_total : 16398 time to create 1 rle with old method : 0.017976760864257812 length of segment : 173 time for calcul the mask position with numpy : 0.002025604248046875 nb_pixel_total : 57017 time to create 1 rle with old method : 0.06245565414428711 length of segment : 334 time for calcul the mask position with numpy : 0.0033578872680664062 nb_pixel_total : 46557 time to create 1 rle with old method : 0.05227184295654297 length of segment : 409 time for calcul the mask position with numpy : 0.029160737991333008 nb_pixel_total : 820621 time to create 1 rle with new method : 0.0994572639465332 length of segment : 1136 time for calcul the mask position with numpy : 0.0011031627655029297 nb_pixel_total : 43961 time to create 1 rle with old method : 0.049227237701416016 length of segment : 185 time for calcul the mask position with numpy : 0.003188610076904297 nb_pixel_total : 90224 time to create 1 rle with old method : 0.0990912914276123 length of segment : 399 time for calcul the mask position with numpy : 0.0008544921875 nb_pixel_total : 11550 time to create 1 rle with old method : 0.013359785079956055 length of segment : 167 time for calcul the mask position with numpy : 0.0011131763458251953 nb_pixel_total : 19868 time to create 1 rle with old method : 0.024506092071533203 length of segment : 191 time for calcul the mask position with numpy : 0.005391120910644531 nb_pixel_total : 117964 time to create 1 rle with old method : 0.13010692596435547 length of segment : 625 time for calcul the mask position with numpy : 0.021669864654541016 nb_pixel_total : 629457 time to create 1 rle with new method : 0.22127938270568848 length of segment : 1050 time for calcul the mask position with numpy : 0.0012750625610351562 nb_pixel_total : 33816 time to create 1 rle with old method : 0.03728318214416504 length of segment : 301 time for calcul the mask position with numpy : 0.00034737586975097656 nb_pixel_total : 7232 time to create 1 rle with old method : 0.008546113967895508 length of segment : 162 time for calcul the mask position with numpy : 0.0003204345703125 nb_pixel_total : 12418 time to create 1 rle with old method : 0.014081954956054688 length of segment : 120 time for calcul the mask position with numpy : 0.0060253143310546875 nb_pixel_total : 220582 time to create 1 rle with new method : 0.012473344802856445 length of segment : 468 time for calcul the mask position with numpy : 0.0024878978729248047 nb_pixel_total : 42785 time to create 1 rle with old method : 0.04692983627319336 length of segment : 405 time for calcul the mask position with numpy : 0.0006580352783203125 nb_pixel_total : 19240 time to create 1 rle with old method : 0.021256208419799805 length of segment : 194 time for calcul the mask position with numpy : 0.0017514228820800781 nb_pixel_total : 44165 time to create 1 rle with old method : 0.04865741729736328 length of segment : 255 time for calcul the mask position with numpy : 0.00016832351684570312 nb_pixel_total : 5355 time to create 1 rle with old method : 0.006296873092651367 length of segment : 92 time for calcul the mask position with numpy : 0.0012531280517578125 nb_pixel_total : 37744 time to create 1 rle with old method : 0.042168617248535156 length of segment : 217 time for calcul the mask position with numpy : 0.0011372566223144531 nb_pixel_total : 46790 time to create 1 rle with old method : 0.05346846580505371 length of segment : 428 time for calcul the mask position with numpy : 0.0017538070678710938 nb_pixel_total : 46678 time to create 1 rle with old method : 0.0509030818939209 length of segment : 284 time for calcul the mask position with numpy : 0.0013689994812011719 nb_pixel_total : 39550 time to create 1 rle with old method : 0.04334664344787598 length of segment : 181 time for calcul the mask position with numpy : 0.001535177230834961 nb_pixel_total : 42150 time to create 1 rle with old method : 0.046692609786987305 length of segment : 447 time spent for convertir_results : 49.90970730781555 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 470 chid ids of type : 3594 Number RLEs to save : 115712 save missing photos in datou_result : time spend for datou_step_exec : 244.782559633255 time spend to save output : 20.68847393989563 total time spend for step 1 : 265.47103357315063 step2:crop_condition Fri Feb 21 00:34:55 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 Loading chi in step crop with photo_hashtag_type : 3594 Loading chi in step crop for list_pids : 12 ! batch 1 Loaded 470 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ begin to crop the class : papier param for this class : {'min_score': 0.7} filtre for class : papier hashtag_id of this class : 492668766 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 345 About to insert : list_path_to_insert length 345 new photo from crops ! About to upload 345 photos upload in portfolio : 3736932 init cache_photo without model_param we have 345 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740094558_55244 we have uploaded 345 photos in the portfolio 3736932 time of upload the photos Elapsed time : 116.58340501785278 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.7} filtre for class : carton hashtag_id of this class : 492774966 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 73 About to insert : list_path_to_insert length 73 new photo from crops ! About to upload 73 photos upload in portfolio : 3736932 init cache_photo without model_param we have 73 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740094702_55244 we have uploaded 73 photos in the portfolio 3736932 time of upload the photos Elapsed time : 25.514407873153687 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.7} filtre for class : metal hashtag_id of this class : 492628673 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 3736932 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740094729_55244 we have uploaded 4 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.36812424659729 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.7} filtre for class : pet_clair hashtag_id of this class : 2107755846 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 27 About to insert : list_path_to_insert length 27 new photo from crops ! About to upload 27 photos upload in portfolio : 3736932 init cache_photo without model_param we have 27 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740094744_55244 we have uploaded 27 photos in the portfolio 3736932 time of upload the photos Elapsed time : 8.15471339225769 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.7} filtre for class : autre hashtag_id of this class : 494826614 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! About to upload 13 photos upload in portfolio : 3736932 init cache_photo without model_param we have 13 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740094756_55244 we have uploaded 13 photos in the portfolio 3736932 time of upload the photos Elapsed time : 4.278475046157837 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.7} filtre for class : pehd hashtag_id of this class : 628944319 we have both polygon and rles Next one ! we have both polygon and rles 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 : 3736932 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740094763_55244 we have uploaded 2 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.028752088546753 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.7} filtre for class : pet_fonce hashtag_id of this class : 2107755900 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 6 About to insert : list_path_to_insert length 6 new photo from crops ! About to upload 6 photos upload in portfolio : 3736932 init cache_photo without model_param we have 6 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740094767_55244 we have uploaded 6 photos in the portfolio 3736932 time of upload the photos Elapsed time : 2.5300440788269043 we have finished the crop for the class : pet_fonce delete rles from all chi we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles we have 0 chi objets contains the rles Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1338685154, 1338685152, 1338685150, 1338685147, 1338647445, 1338647408, 1338647395, 1338647392, 1338647390, 1338647353, 1338647351, 1338647350] Looping around the photos to save general results len do output : 470 /1338697758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338697999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338698999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1338699046Didn'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 ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685154', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685152', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685150', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685147', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647445', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647408', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647395', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647392', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647390', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647353', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647351', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647350', None, None, None, None, None, '2601861') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1422 time used for this insertion : 0.6499433517456055 save_final save missing photos in datou_result : time spend for datou_step_exec : 273.76159024238586 time spend to save output : 0.6603922843933105 total time spend for step 2 : 274.4219825267792 step3:rle_unique_nms_with_priority Fri Feb 21 00:39:30 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 expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 470 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 48 nb_hashtags : 6 time to prepare the origin masks : 4.125774621963501 time for calcul the mask position with numpy : 0.3660297393798828 nb_pixel_total : 5517384 time to create 1 rle with new method : 0.6995866298675537 time for calcul the mask position with numpy : 0.028199434280395508 nb_pixel_total : 6102 time to create 1 rle with old method : 0.006988525390625 time for calcul the mask position with numpy : 0.02866220474243164 nb_pixel_total : 13498 time to create 1 rle with old method : 0.0152130126953125 time for calcul the mask position with numpy : 0.028378725051879883 nb_pixel_total : 30155 time to create 1 rle with old method : 0.03371167182922363 time for calcul the mask position with numpy : 0.029232025146484375 nb_pixel_total : 25554 time to create 1 rle with old method : 0.029002666473388672 time for calcul the mask position with numpy : 0.028762340545654297 nb_pixel_total : 31538 time to create 1 rle with old method : 0.03517031669616699 time for calcul the mask position with numpy : 0.028911352157592773 nb_pixel_total : 17369 time to create 1 rle with old method : 0.020689725875854492 time for calcul the mask position with numpy : 0.028568267822265625 nb_pixel_total : 26409 time to create 1 rle with old method : 0.029732465744018555 time for calcul the mask position with numpy : 0.029202938079833984 nb_pixel_total : 111000 time to create 1 rle with old method : 0.11814045906066895 time for calcul the mask position with numpy : 0.028954505920410156 nb_pixel_total : 23438 time to create 1 rle with old method : 0.025522232055664062 time for calcul the mask position with numpy : 0.02815532684326172 nb_pixel_total : 19667 time to create 1 rle with old method : 0.02045297622680664 time for calcul the mask position with numpy : 0.027534008026123047 nb_pixel_total : 22421 time to create 1 rle with old method : 0.024990558624267578 time for calcul the mask position with numpy : 0.028235435485839844 nb_pixel_total : 15087 time to create 1 rle with old method : 0.015508174896240234 time for calcul the mask position with numpy : 0.02659749984741211 nb_pixel_total : 17663 time to create 1 rle with old method : 0.018123149871826172 time for calcul the mask position with numpy : 0.02702188491821289 nb_pixel_total : 77153 time to create 1 rle with old method : 0.08011555671691895 time for calcul the mask position with numpy : 0.027445077896118164 nb_pixel_total : 82383 time to create 1 rle with old method : 0.086944580078125 time for calcul the mask position with numpy : 0.028729915618896484 nb_pixel_total : 16642 time to create 1 rle with old method : 0.02574443817138672 time for calcul the mask position with numpy : 0.031070947647094727 nb_pixel_total : 19119 time to create 1 rle with old method : 0.020189523696899414 time for calcul the mask position with numpy : 0.028996944427490234 nb_pixel_total : 33036 time to create 1 rle with old method : 0.03862309455871582 time for calcul the mask position with numpy : 0.029226064682006836 nb_pixel_total : 9041 time to create 1 rle with old method : 0.010260581970214844 time for calcul the mask position with numpy : 0.028072834014892578 nb_pixel_total : 16988 time to create 1 rle with old method : 0.01931166648864746 time for calcul the mask position with numpy : 0.030387401580810547 nb_pixel_total : 111303 time to create 1 rle with old method : 0.12302350997924805 time for calcul the mask position with numpy : 0.028220415115356445 nb_pixel_total : 21845 time to create 1 rle with old method : 0.024224281311035156 time for calcul the mask position with numpy : 0.029022693634033203 nb_pixel_total : 27807 time to create 1 rle with old method : 0.03178715705871582 time for calcul the mask position with numpy : 0.028214454650878906 nb_pixel_total : 11530 time to create 1 rle with old method : 0.014475107192993164 time for calcul the mask position with numpy : 0.028395652770996094 nb_pixel_total : 88745 time to create 1 rle with old method : 0.09430170059204102 time for calcul the mask position with numpy : 0.027864456176757812 nb_pixel_total : 12062 time to create 1 rle with old method : 0.012576818466186523 time for calcul the mask position with numpy : 0.028549909591674805 nb_pixel_total : 62238 time to create 1 rle with old method : 0.07042431831359863 time for calcul the mask position with numpy : 0.029327392578125 nb_pixel_total : 232776 time to create 1 rle with new method : 0.4059581756591797 time for calcul the mask position with numpy : 0.028023242950439453 nb_pixel_total : 35287 time to create 1 rle with old method : 0.03697013854980469 time for calcul the mask position with numpy : 0.0286867618560791 nb_pixel_total : 11615 time to create 1 rle with old method : 0.012227296829223633 time for calcul the mask position with numpy : 0.02867412567138672 nb_pixel_total : 8791 time to create 1 rle with old method : 0.009577274322509766 time for calcul the mask position with numpy : 0.02781200408935547 nb_pixel_total : 17837 time to create 1 rle with old method : 0.019220352172851562 time for calcul the mask position with numpy : 0.02806854248046875 nb_pixel_total : 47139 time to create 1 rle with old method : 0.048758506774902344 time for calcul the mask position with numpy : 0.027988672256469727 nb_pixel_total : 28167 time to create 1 rle with old method : 0.030084609985351562 time for calcul the mask position with numpy : 0.0276031494140625 nb_pixel_total : 4853 time to create 1 rle with old method : 0.004983663558959961 time for calcul the mask position with numpy : 0.02692270278930664 nb_pixel_total : 7789 time to create 1 rle with old method : 0.008559226989746094 time for calcul the mask position with numpy : 0.027087688446044922 nb_pixel_total : 5436 time to create 1 rle with old method : 0.0056095123291015625 time for calcul the mask position with numpy : 0.02651071548461914 nb_pixel_total : 30520 time to create 1 rle with old method : 0.030514955520629883 time for calcul the mask position with numpy : 0.028011322021484375 nb_pixel_total : 9371 time to create 1 rle with old method : 0.009979724884033203 time for calcul the mask position with numpy : 0.026737213134765625 nb_pixel_total : 9278 time to create 1 rle with old method : 0.010004997253417969 time for calcul the mask position with numpy : 0.027505874633789062 nb_pixel_total : 6067 time to create 1 rle with old method : 0.006611347198486328 time for calcul the mask position with numpy : 0.02697277069091797 nb_pixel_total : 18672 time to create 1 rle with old method : 0.019983530044555664 time for calcul the mask position with numpy : 0.028182268142700195 nb_pixel_total : 21626 time to create 1 rle with old method : 0.023177385330200195 time for calcul the mask position with numpy : 0.027707338333129883 nb_pixel_total : 20692 time to create 1 rle with old method : 0.021273374557495117 time for calcul the mask position with numpy : 0.02765488624572754 nb_pixel_total : 39384 time to create 1 rle with old method : 0.039693355560302734 time for calcul the mask position with numpy : 0.02686285972595215 nb_pixel_total : 12146 time to create 1 rle with old method : 0.012859582901000977 time for calcul the mask position with numpy : 0.027743816375732422 nb_pixel_total : 9929 time to create 1 rle with old method : 0.01084756851196289 time for calcul the mask position with numpy : 0.027696609497070312 nb_pixel_total : 5688 time to create 1 rle with old method : 0.006270170211791992 create new chi : 4.303892374038696 time to delete rle : 0.017253637313842773 batch 1 Loaded 97 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 24396 TO DO : save crop sub photo not yet done ! save time : 3.061657667160034 nb_obj : 64 nb_hashtags : 5 time to prepare the origin masks : 4.154240131378174 time for calcul the mask position with numpy : 0.7766902446746826 nb_pixel_total : 5495616 time to create 1 rle with new method : 0.6963706016540527 time for calcul the mask position with numpy : 0.02909231185913086 nb_pixel_total : 29926 time to create 1 rle with old method : 0.03759932518005371 time for calcul the mask position with numpy : 0.03017711639404297 nb_pixel_total : 32804 time to create 1 rle with old method : 0.03683137893676758 time for calcul the mask position with numpy : 0.029448747634887695 nb_pixel_total : 4915 time to create 1 rle with old method : 0.005594968795776367 time for calcul the mask position with numpy : 0.029083251953125 nb_pixel_total : 41065 time to create 1 rle with old method : 0.06452131271362305 time for calcul the mask position with numpy : 0.034032344818115234 nb_pixel_total : 34981 time to create 1 rle with old method : 0.04812788963317871 time for calcul the mask position with numpy : 0.029273271560668945 nb_pixel_total : 51126 time to create 1 rle with old method : 0.0557246208190918 time for calcul the mask position with numpy : 0.029610633850097656 nb_pixel_total : 8015 time to create 1 rle with old method : 0.008630990982055664 time for calcul the mask position with numpy : 0.028846025466918945 nb_pixel_total : 12649 time to create 1 rle with old method : 0.013572931289672852 time for calcul the mask position with numpy : 0.0293428897857666 nb_pixel_total : 11402 time to create 1 rle with old method : 0.012546777725219727 time for calcul the mask position with numpy : 0.028519392013549805 nb_pixel_total : 9498 time to create 1 rle with old method : 0.011325359344482422 time for calcul the mask position with numpy : 0.029349327087402344 nb_pixel_total : 19599 time to create 1 rle with old method : 0.022328853607177734 time for calcul the mask position with numpy : 0.028918743133544922 nb_pixel_total : 24960 time to create 1 rle with old method : 0.026634693145751953 time for calcul the mask position with numpy : 0.02992844581604004 nb_pixel_total : 20269 time to create 1 rle with old method : 0.026132583618164062 time for calcul the mask position with numpy : 0.029153108596801758 nb_pixel_total : 16612 time to create 1 rle with old method : 0.017705440521240234 time for calcul the mask position with numpy : 0.029320716857910156 nb_pixel_total : 26410 time to create 1 rle with old method : 0.02780747413635254 time for calcul the mask position with numpy : 0.02829599380493164 nb_pixel_total : 18307 time to create 1 rle with old method : 0.0209653377532959 time for calcul the mask position with numpy : 0.028566598892211914 nb_pixel_total : 20501 time to create 1 rle with old method : 0.026440858840942383 time for calcul the mask position with numpy : 0.03199195861816406 nb_pixel_total : 10837 time to create 1 rle with old method : 0.01670360565185547 time for calcul the mask position with numpy : 0.030128955841064453 nb_pixel_total : 4352 time to create 1 rle with old method : 0.005089759826660156 time for calcul the mask position with numpy : 0.028867006301879883 nb_pixel_total : 10768 time to create 1 rle with old method : 0.012092113494873047 time for calcul the mask position with numpy : 0.028746366500854492 nb_pixel_total : 20672 time to create 1 rle with old method : 0.02325129508972168 time for calcul the mask position with numpy : 0.02873373031616211 nb_pixel_total : 9861 time to create 1 rle with old method : 0.011005640029907227 time for calcul the mask position with numpy : 0.029415369033813477 nb_pixel_total : 28544 time to create 1 rle with old method : 0.03251051902770996 time for calcul the mask position with numpy : 0.02921605110168457 nb_pixel_total : 37172 time to create 1 rle with old method : 0.04625821113586426 time for calcul the mask position with numpy : 0.030281543731689453 nb_pixel_total : 87150 time to create 1 rle with old method : 0.09516072273254395 time for calcul the mask position with numpy : 0.035162925720214844 nb_pixel_total : 29664 time to create 1 rle with old method : 0.03421616554260254 time for calcul the mask position with numpy : 0.029196977615356445 nb_pixel_total : 16692 time to create 1 rle with old method : 0.01816415786743164 time for calcul the mask position with numpy : 0.029272079467773438 nb_pixel_total : 15179 time to create 1 rle with old method : 0.016580581665039062 time for calcul the mask position with numpy : 0.028917551040649414 nb_pixel_total : 26813 time to create 1 rle with old method : 0.028816938400268555 time for calcul the mask position with numpy : 0.02919459342956543 nb_pixel_total : 12679 time to create 1 rle with old method : 0.014365434646606445 time for calcul the mask position with numpy : 0.029263973236083984 nb_pixel_total : 14865 time to create 1 rle with old method : 0.016907930374145508 time for calcul the mask position with numpy : 0.029115676879882812 nb_pixel_total : 8730 time to create 1 rle with old method : 0.01020956039428711 time for calcul the mask position with numpy : 0.028949499130249023 nb_pixel_total : 7492 time to create 1 rle with old method : 0.00858616828918457 time for calcul the mask position with numpy : 0.02892017364501953 nb_pixel_total : 8187 time to create 1 rle with old method : 0.009127616882324219 time for calcul the mask position with numpy : 0.029024600982666016 nb_pixel_total : 19950 time to create 1 rle with old method : 0.02196192741394043 time for calcul the mask position with numpy : 0.029069900512695312 nb_pixel_total : 6876 time to create 1 rle with old method : 0.008087873458862305 time for calcul the mask position with numpy : 0.028675079345703125 nb_pixel_total : 11824 time to create 1 rle with old method : 0.013225793838500977 time for calcul the mask position with numpy : 0.029015064239501953 nb_pixel_total : 18551 time to create 1 rle with old method : 0.0206754207611084 time for calcul the mask position with numpy : 0.02893805503845215 nb_pixel_total : 7772 time to create 1 rle with old method : 0.008788824081420898 time for calcul the mask position with numpy : 0.029038667678833008 nb_pixel_total : 34539 time to create 1 rle with old method : 0.037427663803100586 time for calcul the mask position with numpy : 0.029149532318115234 nb_pixel_total : 14539 time to create 1 rle with old method : 0.01577591896057129 time for calcul the mask position with numpy : 0.02915644645690918 nb_pixel_total : 39676 time to create 1 rle with old method : 0.04293251037597656 time for calcul the mask position with numpy : 0.028855085372924805 nb_pixel_total : 105739 time to create 1 rle with old method : 0.11111211776733398 time for calcul the mask position with numpy : 0.02864360809326172 nb_pixel_total : 9498 time to create 1 rle with old method : 0.010576009750366211 time for calcul the mask position with numpy : 0.030466079711914062 nb_pixel_total : 58321 time to create 1 rle with old method : 0.0633859634399414 time for calcul the mask position with numpy : 0.029426097869873047 nb_pixel_total : 15778 time to create 1 rle with old method : 0.017165660858154297 time for calcul the mask position with numpy : 0.028656005859375 nb_pixel_total : 21023 time to create 1 rle with old method : 0.02273416519165039 time for calcul the mask position with numpy : 0.02871561050415039 nb_pixel_total : 18714 time to create 1 rle with old method : 0.02002549171447754 time for calcul the mask position with numpy : 0.028419971466064453 nb_pixel_total : 74755 time to create 1 rle with old method : 0.07750797271728516 time for calcul the mask position with numpy : 0.02869725227355957 nb_pixel_total : 62357 time to create 1 rle with old method : 0.06707406044006348 time for calcul the mask position with numpy : 0.028278589248657227 nb_pixel_total : 63325 time to create 1 rle with old method : 0.06803536415100098 time for calcul the mask position with numpy : 0.02838277816772461 nb_pixel_total : 24378 time to create 1 rle with old method : 0.026645898818969727 time for calcul the mask position with numpy : 0.028067827224731445 nb_pixel_total : 14098 time to create 1 rle with old method : 0.01566028594970703 time for calcul the mask position with numpy : 0.028483152389526367 nb_pixel_total : 47593 time to create 1 rle with old method : 0.054735422134399414 time for calcul the mask position with numpy : 0.029244184494018555 nb_pixel_total : 14494 time to create 1 rle with old method : 0.015323638916015625 time for calcul the mask position with numpy : 0.028586626052856445 nb_pixel_total : 7623 time to create 1 rle with old method : 0.009458303451538086 time for calcul the mask position with numpy : 0.028771162033081055 nb_pixel_total : 2769 time to create 1 rle with old method : 0.003138303756713867 time for calcul the mask position with numpy : 0.028374910354614258 nb_pixel_total : 22139 time to create 1 rle with old method : 0.024025440216064453 time for calcul the mask position with numpy : 0.028327226638793945 nb_pixel_total : 20211 time to create 1 rle with old method : 0.022295236587524414 time for calcul the mask position with numpy : 0.0288698673248291 nb_pixel_total : 26395 time to create 1 rle with old method : 0.029783248901367188 time for calcul the mask position with numpy : 0.028555631637573242 nb_pixel_total : 19765 time to create 1 rle with old method : 0.023004531860351562 time for calcul the mask position with numpy : 0.029300928115844727 nb_pixel_total : 11706 time to create 1 rle with old method : 0.01333308219909668 time for calcul the mask position with numpy : 0.028402090072631836 nb_pixel_total : 21547 time to create 1 rle with old method : 0.02275371551513672 time for calcul the mask position with numpy : 0.02935647964477539 nb_pixel_total : 5973 time to create 1 rle with old method : 0.006741762161254883 create new chi : 5.136261701583862 time to delete rle : 0.006088733673095703 batch 1 Loaded 129 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 28653 TO DO : save crop sub photo not yet done ! save time : 3.0131688117980957 nb_obj : 44 nb_hashtags : 2 time to prepare the origin masks : 3.996825695037842 time for calcul the mask position with numpy : 0.930600643157959 nb_pixel_total : 5777019 time to create 1 rle with new method : 0.9629042148590088 time for calcul the mask position with numpy : 0.029597759246826172 nb_pixel_total : 39072 time to create 1 rle with old method : 0.042871713638305664 time for calcul the mask position with numpy : 0.029734134674072266 nb_pixel_total : 10622 time to create 1 rle with old method : 0.012264490127563477 time for calcul the mask position with numpy : 0.029077529907226562 nb_pixel_total : 11701 time to create 1 rle with old method : 0.012905597686767578 time for calcul the mask position with numpy : 0.03291654586791992 nb_pixel_total : 13751 time to create 1 rle with old method : 0.016857624053955078 time for calcul the mask position with numpy : 0.031664371490478516 nb_pixel_total : 8255 time to create 1 rle with old method : 0.008950233459472656 time for calcul the mask position with numpy : 0.029613971710205078 nb_pixel_total : 19595 time to create 1 rle with old method : 0.023386240005493164 time for calcul the mask position with numpy : 0.029859542846679688 nb_pixel_total : 33190 time to create 1 rle with old method : 0.03602886199951172 time for calcul the mask position with numpy : 0.03024888038635254 nb_pixel_total : 29344 time to create 1 rle with old method : 0.03323221206665039 time for calcul the mask position with numpy : 0.030435800552368164 nb_pixel_total : 66523 time to create 1 rle with old method : 0.07628607749938965 time for calcul the mask position with numpy : 0.02977132797241211 nb_pixel_total : 61467 time to create 1 rle with old method : 0.0662539005279541 time for calcul the mask position with numpy : 0.030173063278198242 nb_pixel_total : 87574 time to create 1 rle with old method : 0.09450101852416992 time for calcul the mask position with numpy : 0.028306007385253906 nb_pixel_total : 21935 time to create 1 rle with old method : 0.022919654846191406 time for calcul the mask position with numpy : 0.02846217155456543 nb_pixel_total : 40310 time to create 1 rle with old method : 0.04251837730407715 time for calcul the mask position with numpy : 0.02776503562927246 nb_pixel_total : 25370 time to create 1 rle with old method : 0.027049541473388672 time for calcul the mask position with numpy : 0.02838921546936035 nb_pixel_total : 18266 time to create 1 rle with old method : 0.019701004028320312 time for calcul the mask position with numpy : 0.028070449829101562 nb_pixel_total : 10411 time to create 1 rle with old method : 0.011379718780517578 time for calcul the mask position with numpy : 0.028604984283447266 nb_pixel_total : 83444 time to create 1 rle with old method : 0.08868813514709473 time for calcul the mask position with numpy : 0.0281679630279541 nb_pixel_total : 9530 time to create 1 rle with old method : 0.010637283325195312 time for calcul the mask position with numpy : 0.02813100814819336 nb_pixel_total : 10776 time to create 1 rle with old method : 0.01201176643371582 time for calcul the mask position with numpy : 0.028368234634399414 nb_pixel_total : 6533 time to create 1 rle with old method : 0.00714874267578125 time for calcul the mask position with numpy : 0.028891801834106445 nb_pixel_total : 36849 time to create 1 rle with old method : 0.0453493595123291 time for calcul the mask position with numpy : 0.028866052627563477 nb_pixel_total : 12264 time to create 1 rle with old method : 0.013684511184692383 time for calcul the mask position with numpy : 0.029334545135498047 nb_pixel_total : 64680 time to create 1 rle with old method : 0.06977987289428711 time for calcul the mask position with numpy : 0.029046297073364258 nb_pixel_total : 11694 time to create 1 rle with old method : 0.01318812370300293 time for calcul the mask position with numpy : 0.0352022647857666 nb_pixel_total : 34345 time to create 1 rle with old method : 0.03710603713989258 time for calcul the mask position with numpy : 0.029847383499145508 nb_pixel_total : 20461 time to create 1 rle with old method : 0.023868799209594727 time for calcul the mask position with numpy : 0.028403759002685547 nb_pixel_total : 13456 time to create 1 rle with old method : 0.014256477355957031 time for calcul the mask position with numpy : 0.028696537017822266 nb_pixel_total : 26573 time to create 1 rle with old method : 0.028765201568603516 time for calcul the mask position with numpy : 0.028897523880004883 nb_pixel_total : 8856 time to create 1 rle with old method : 0.009827375411987305 time for calcul the mask position with numpy : 0.028809547424316406 nb_pixel_total : 20472 time to create 1 rle with old method : 0.02241826057434082 time for calcul the mask position with numpy : 0.028936386108398438 nb_pixel_total : 72168 time to create 1 rle with old method : 0.07705140113830566 time for calcul the mask position with numpy : 0.028883934020996094 nb_pixel_total : 54393 time to create 1 rle with old method : 0.05759167671203613 time for calcul the mask position with numpy : 0.029123306274414062 nb_pixel_total : 91021 time to create 1 rle with old method : 0.09659814834594727 time for calcul the mask position with numpy : 0.028933048248291016 nb_pixel_total : 29513 time to create 1 rle with old method : 0.031731367111206055 time for calcul the mask position with numpy : 0.028377771377563477 nb_pixel_total : 33734 time to create 1 rle with old method : 0.036185264587402344 time for calcul the mask position with numpy : 0.028461217880249023 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002796649932861328 time for calcul the mask position with numpy : 0.027762651443481445 nb_pixel_total : 3702 time to create 1 rle with old method : 0.004018545150756836 time for calcul the mask position with numpy : 0.027268648147583008 nb_pixel_total : 32359 time to create 1 rle with old method : 0.03424334526062012 time for calcul the mask position with numpy : 0.028354167938232422 nb_pixel_total : 28280 time to create 1 rle with old method : 0.030497074127197266 time for calcul the mask position with numpy : 0.028545618057250977 nb_pixel_total : 6115 time to create 1 rle with old method : 0.007271766662597656 time for calcul the mask position with numpy : 0.029155731201171875 nb_pixel_total : 30106 time to create 1 rle with old method : 0.038872718811035156 time for calcul the mask position with numpy : 0.02917623519897461 nb_pixel_total : 16359 time to create 1 rle with old method : 0.017943620681762695 time for calcul the mask position with numpy : 0.03241086006164551 nb_pixel_total : 11682 time to create 1 rle with old method : 0.012839794158935547 time for calcul the mask position with numpy : 0.028977155685424805 nb_pixel_total : 6323 time to create 1 rle with old method : 0.007363319396972656 create new chi : 4.617603540420532 time to delete rle : 0.0031485557556152344 batch 1 Loaded 89 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 21610 TO DO : save crop sub photo not yet done ! save time : 1.7686057090759277 nb_obj : 42 nb_hashtags : 4 time to prepare the origin masks : 4.438523054122925 time for calcul the mask position with numpy : 0.6603305339813232 nb_pixel_total : 4847966 time to create 1 rle with new method : 0.889153003692627 time for calcul the mask position with numpy : 0.02999567985534668 nb_pixel_total : 261287 time to create 1 rle with new method : 0.7502593994140625 time for calcul the mask position with numpy : 0.028949260711669922 nb_pixel_total : 12776 time to create 1 rle with old method : 0.013878345489501953 time for calcul the mask position with numpy : 0.028795957565307617 nb_pixel_total : 19240 time to create 1 rle with old method : 0.021331787109375 time for calcul the mask position with numpy : 0.028895854949951172 nb_pixel_total : 19345 time to create 1 rle with old method : 0.020532608032226562 time for calcul the mask position with numpy : 0.028980016708374023 nb_pixel_total : 19931 time to create 1 rle with old method : 0.021525859832763672 time for calcul the mask position with numpy : 0.02897930145263672 nb_pixel_total : 129501 time to create 1 rle with old method : 0.13656139373779297 time for calcul the mask position with numpy : 0.028437376022338867 nb_pixel_total : 7920 time to create 1 rle with old method : 0.008691549301147461 time for calcul the mask position with numpy : 0.028467178344726562 nb_pixel_total : 9343 time to create 1 rle with old method : 0.01069784164428711 time for calcul the mask position with numpy : 0.028910160064697266 nb_pixel_total : 40866 time to create 1 rle with old method : 0.043221473693847656 time for calcul the mask position with numpy : 0.028643131256103516 nb_pixel_total : 48255 time to create 1 rle with old method : 0.05141925811767578 time for calcul the mask position with numpy : 0.028640270233154297 nb_pixel_total : 24140 time to create 1 rle with old method : 0.026019573211669922 time for calcul the mask position with numpy : 0.02797102928161621 nb_pixel_total : 76571 time to create 1 rle with old method : 0.08085441589355469 time for calcul the mask position with numpy : 0.028035879135131836 nb_pixel_total : 10465 time to create 1 rle with old method : 0.011540889739990234 time for calcul the mask position with numpy : 0.028716564178466797 nb_pixel_total : 11801 time to create 1 rle with old method : 0.013204574584960938 time for calcul the mask position with numpy : 0.028942346572875977 nb_pixel_total : 28123 time to create 1 rle with old method : 0.030695438385009766 time for calcul the mask position with numpy : 0.02884078025817871 nb_pixel_total : 13470 time to create 1 rle with old method : 0.014878034591674805 time for calcul the mask position with numpy : 0.028841257095336914 nb_pixel_total : 22622 time to create 1 rle with old method : 0.026029586791992188 time for calcul the mask position with numpy : 0.029143333435058594 nb_pixel_total : 72253 time to create 1 rle with old method : 0.07714653015136719 time for calcul the mask position with numpy : 0.02878260612487793 nb_pixel_total : 51732 time to create 1 rle with old method : 0.05528116226196289 time for calcul the mask position with numpy : 0.02834486961364746 nb_pixel_total : 6102 time to create 1 rle with old method : 0.006796598434448242 time for calcul the mask position with numpy : 0.02825188636779785 nb_pixel_total : 10172 time to create 1 rle with old method : 0.011299848556518555 time for calcul the mask position with numpy : 0.02881336212158203 nb_pixel_total : 85759 time to create 1 rle with old method : 0.09113717079162598 time for calcul the mask position with numpy : 0.02915358543395996 nb_pixel_total : 178705 time to create 1 rle with new method : 0.6188509464263916 time for calcul the mask position with numpy : 0.03274846076965332 nb_pixel_total : 7486 time to create 1 rle with old method : 0.01204228401184082 time for calcul the mask position with numpy : 0.03260540962219238 nb_pixel_total : 26617 time to create 1 rle with old method : 0.029503583908081055 time for calcul the mask position with numpy : 0.03641223907470703 nb_pixel_total : 15567 time to create 1 rle with old method : 0.017319202423095703 time for calcul the mask position with numpy : 0.03745412826538086 nb_pixel_total : 751102 time to create 1 rle with new method : 0.5322644710540771 time for calcul the mask position with numpy : 0.02886509895324707 nb_pixel_total : 5205 time to create 1 rle with old method : 0.005690336227416992 time for calcul the mask position with numpy : 0.02925562858581543 nb_pixel_total : 11618 time to create 1 rle with old method : 0.012472152709960938 time for calcul the mask position with numpy : 0.028786659240722656 nb_pixel_total : 33437 time to create 1 rle with old method : 0.03628134727478027 time for calcul the mask position with numpy : 0.029194355010986328 nb_pixel_total : 19826 time to create 1 rle with old method : 0.02145552635192871 time for calcul the mask position with numpy : 0.029234647750854492 nb_pixel_total : 30775 time to create 1 rle with old method : 0.03316640853881836 time for calcul the mask position with numpy : 0.02917170524597168 nb_pixel_total : 5703 time to create 1 rle with old method : 0.006398439407348633 time for calcul the mask position with numpy : 0.028894662857055664 nb_pixel_total : 8370 time to create 1 rle with old method : 0.009826421737670898 time for calcul the mask position with numpy : 0.028951644897460938 nb_pixel_total : 48790 time to create 1 rle with old method : 0.05333733558654785 time for calcul the mask position with numpy : 0.02901768684387207 nb_pixel_total : 53805 time to create 1 rle with old method : 0.058266639709472656 time for calcul the mask position with numpy : 0.02868056297302246 nb_pixel_total : 2623 time to create 1 rle with old method : 0.002985715866088867 time for calcul the mask position with numpy : 0.028761625289916992 nb_pixel_total : 5372 time to create 1 rle with old method : 0.006145954132080078 time for calcul the mask position with numpy : 0.029172897338867188 nb_pixel_total : 4949 time to create 1 rle with old method : 0.005626201629638672 time for calcul the mask position with numpy : 0.028838157653808594 nb_pixel_total : 2753 time to create 1 rle with old method : 0.003224611282348633 time for calcul the mask position with numpy : 0.028963804244995117 nb_pixel_total : 2183 time to create 1 rle with old method : 0.0025534629821777344 time for calcul the mask position with numpy : 0.0287168025970459 nb_pixel_total : 5714 time to create 1 rle with old method : 0.006401538848876953 create new chi : 5.8851447105407715 time to delete rle : 0.004410743713378906 batch 1 Loaded 85 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 19935 TO DO : save crop sub photo not yet done ! save time : 2.570781946182251 nb_obj : 32 nb_hashtags : 5 time to prepare the origin masks : 3.475308418273926 time for calcul the mask position with numpy : 0.6820361614227295 nb_pixel_total : 6382613 time to create 1 rle with new method : 0.9838252067565918 time for calcul the mask position with numpy : 0.03037095069885254 nb_pixel_total : 81573 time to create 1 rle with old method : 0.08773255348205566 time for calcul the mask position with numpy : 0.029172420501708984 nb_pixel_total : 12138 time to create 1 rle with old method : 0.013509511947631836 time for calcul the mask position with numpy : 0.029257535934448242 nb_pixel_total : 10680 time to create 1 rle with old method : 0.011716604232788086 time for calcul the mask position with numpy : 0.02912282943725586 nb_pixel_total : 15980 time to create 1 rle with old method : 0.01721024513244629 time for calcul the mask position with numpy : 0.029034137725830078 nb_pixel_total : 10942 time to create 1 rle with old method : 0.012050867080688477 time for calcul the mask position with numpy : 0.029374122619628906 nb_pixel_total : 18542 time to create 1 rle with old method : 0.023495912551879883 time for calcul the mask position with numpy : 0.029376506805419922 nb_pixel_total : 35373 time to create 1 rle with old method : 0.038710832595825195 time for calcul the mask position with numpy : 0.03097367286682129 nb_pixel_total : 84066 time to create 1 rle with old method : 0.09058976173400879 time for calcul the mask position with numpy : 0.028978824615478516 nb_pixel_total : 12727 time to create 1 rle with old method : 0.014499902725219727 time for calcul the mask position with numpy : 0.029245615005493164 nb_pixel_total : 16294 time to create 1 rle with old method : 0.017896175384521484 time for calcul the mask position with numpy : 0.02920699119567871 nb_pixel_total : 15372 time to create 1 rle with old method : 0.01749873161315918 time for calcul the mask position with numpy : 0.029453277587890625 nb_pixel_total : 15115 time to create 1 rle with old method : 0.016641855239868164 time for calcul the mask position with numpy : 0.03026866912841797 nb_pixel_total : 23490 time to create 1 rle with old method : 0.025928497314453125 time for calcul the mask position with numpy : 0.03000497817993164 nb_pixel_total : 21871 time to create 1 rle with old method : 0.03561687469482422 time for calcul the mask position with numpy : 0.029558897018432617 nb_pixel_total : 3897 time to create 1 rle with old method : 0.004316091537475586 time for calcul the mask position with numpy : 0.03258681297302246 nb_pixel_total : 19029 time to create 1 rle with old method : 0.020479917526245117 time for calcul the mask position with numpy : 0.029244661331176758 nb_pixel_total : 7899 time to create 1 rle with old method : 0.009101152420043945 time for calcul the mask position with numpy : 0.02935624122619629 nb_pixel_total : 50625 time to create 1 rle with old method : 0.05477595329284668 time for calcul the mask position with numpy : 0.02905559539794922 nb_pixel_total : 10585 time to create 1 rle with old method : 0.011722087860107422 time for calcul the mask position with numpy : 0.02919626235961914 nb_pixel_total : 22859 time to create 1 rle with old method : 0.0314023494720459 time for calcul the mask position with numpy : 0.03530693054199219 nb_pixel_total : 20419 time to create 1 rle with old method : 0.05264449119567871 time for calcul the mask position with numpy : 0.09198784828186035 nb_pixel_total : 11398 time to create 1 rle with old method : 0.02535223960876465 time for calcul the mask position with numpy : 0.0451664924621582 nb_pixel_total : 3677 time to create 1 rle with old method : 0.005898952484130859 time for calcul the mask position with numpy : 0.037819623947143555 nb_pixel_total : 14455 time to create 1 rle with old method : 0.022870779037475586 time for calcul the mask position with numpy : 0.03652834892272949 nb_pixel_total : 16325 time to create 1 rle with old method : 0.02510523796081543 time for calcul the mask position with numpy : 0.03666186332702637 nb_pixel_total : 19901 time to create 1 rle with old method : 0.0314631462097168 time for calcul the mask position with numpy : 0.03782987594604492 nb_pixel_total : 17109 time to create 1 rle with old method : 0.032470703125 time for calcul the mask position with numpy : 0.07160568237304688 nb_pixel_total : 48756 time to create 1 rle with old method : 0.09483790397644043 time for calcul the mask position with numpy : 0.0393674373626709 nb_pixel_total : 11798 time to create 1 rle with old method : 0.02488994598388672 time for calcul the mask position with numpy : 0.03780055046081543 nb_pixel_total : 3034 time to create 1 rle with old method : 0.005864858627319336 time for calcul the mask position with numpy : 0.04092144966125488 nb_pixel_total : 11327 time to create 1 rle with old method : 0.021650075912475586 time for calcul the mask position with numpy : 0.05042672157287598 nb_pixel_total : 371 time to create 1 rle with old method : 0.0007448196411132812 create new chi : 3.763566493988037 time to delete rle : 0.00421452522277832 batch 1 Loaded 65 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++Number RLEs to save : 13733 TO DO : save crop sub photo not yet done ! save time : 1.4408187866210938 nb_obj : 67 nb_hashtags : 6 time to prepare the origin masks : 4.631327390670776 time for calcul the mask position with numpy : 1.242311954498291 nb_pixel_total : 5472462 time to create 1 rle with new method : 1.3233368396759033 time for calcul the mask position with numpy : 0.03662467002868652 nb_pixel_total : 14067 time to create 1 rle with old method : 0.01716136932373047 time for calcul the mask position with numpy : 0.030583620071411133 nb_pixel_total : 23998 time to create 1 rle with old method : 0.028113365173339844 time for calcul the mask position with numpy : 0.0309598445892334 nb_pixel_total : 13257 time to create 1 rle with old method : 0.014684915542602539 time for calcul the mask position with numpy : 0.029405832290649414 nb_pixel_total : 32137 time to create 1 rle with old method : 0.046950340270996094 time for calcul the mask position with numpy : 0.03071761131286621 nb_pixel_total : 29051 time to create 1 rle with old method : 0.03348588943481445 time for calcul the mask position with numpy : 0.029562950134277344 nb_pixel_total : 15688 time to create 1 rle with old method : 0.017122983932495117 time for calcul the mask position with numpy : 0.02932882308959961 nb_pixel_total : 14015 time to create 1 rle with old method : 0.017186641693115234 time for calcul the mask position with numpy : 0.02906942367553711 nb_pixel_total : 49912 time to create 1 rle with old method : 0.05411028861999512 time for calcul the mask position with numpy : 0.02905893325805664 nb_pixel_total : 15985 time to create 1 rle with old method : 0.017595529556274414 time for calcul the mask position with numpy : 0.03149724006652832 nb_pixel_total : 10739 time to create 1 rle with old method : 0.012462854385375977 time for calcul the mask position with numpy : 0.028928756713867188 nb_pixel_total : 9027 time to create 1 rle with old method : 0.01033473014831543 time for calcul the mask position with numpy : 0.02907252311706543 nb_pixel_total : 4675 time to create 1 rle with old method : 0.0053272247314453125 time for calcul the mask position with numpy : 0.029209375381469727 nb_pixel_total : 14013 time to create 1 rle with old method : 0.015909433364868164 time for calcul the mask position with numpy : 0.03270673751831055 nb_pixel_total : 6918 time to create 1 rle with old method : 0.008245706558227539 time for calcul the mask position with numpy : 0.029268264770507812 nb_pixel_total : 7168 time to create 1 rle with old method : 0.00775599479675293 time for calcul the mask position with numpy : 0.029395103454589844 nb_pixel_total : 15207 time to create 1 rle with old method : 0.016949892044067383 time for calcul the mask position with numpy : 0.029939651489257812 nb_pixel_total : 67504 time to create 1 rle with old method : 0.07802152633666992 time for calcul the mask position with numpy : 0.03022599220275879 nb_pixel_total : 16108 time to create 1 rle with old method : 0.017689228057861328 time for calcul the mask position with numpy : 0.030864477157592773 nb_pixel_total : 28551 time to create 1 rle with old method : 0.03218364715576172 time for calcul the mask position with numpy : 0.03152751922607422 nb_pixel_total : 10300 time to create 1 rle with old method : 0.011164188385009766 time for calcul the mask position with numpy : 0.0319821834564209 nb_pixel_total : 106167 time to create 1 rle with old method : 0.11467361450195312 time for calcul the mask position with numpy : 0.029591083526611328 nb_pixel_total : 62933 time to create 1 rle with old method : 0.06936383247375488 time for calcul the mask position with numpy : 0.029733896255493164 nb_pixel_total : 40964 time to create 1 rle with old method : 0.04581856727600098 time for calcul the mask position with numpy : 0.029505491256713867 nb_pixel_total : 11675 time to create 1 rle with old method : 0.012931585311889648 time for calcul the mask position with numpy : 0.02944159507751465 nb_pixel_total : 13099 time to create 1 rle with old method : 0.014862060546875 time for calcul the mask position with numpy : 0.02943897247314453 nb_pixel_total : 18160 time to create 1 rle with old method : 0.019846677780151367 time for calcul the mask position with numpy : 0.029602527618408203 nb_pixel_total : 19798 time to create 1 rle with old method : 0.033165931701660156 time for calcul the mask position with numpy : 0.035659074783325195 nb_pixel_total : 9316 time to create 1 rle with old method : 0.015397071838378906 time for calcul the mask position with numpy : 0.03610086441040039 nb_pixel_total : 10978 time to create 1 rle with old method : 0.01660919189453125 time for calcul the mask position with numpy : 0.029784679412841797 nb_pixel_total : 29023 time to create 1 rle with old method : 0.0342104434967041 time for calcul the mask position with numpy : 0.03283286094665527 nb_pixel_total : 12422 time to create 1 rle with old method : 0.01584029197692871 time for calcul the mask position with numpy : 0.03222799301147461 nb_pixel_total : 15749 time to create 1 rle with old method : 0.017971277236938477 time for calcul the mask position with numpy : 0.03247213363647461 nb_pixel_total : 10874 time to create 1 rle with old method : 0.016780614852905273 time for calcul the mask position with numpy : 0.0341649055480957 nb_pixel_total : 31544 time to create 1 rle with old method : 0.039446115493774414 time for calcul the mask position with numpy : 0.03200697898864746 nb_pixel_total : 73007 time to create 1 rle with old method : 0.08568882942199707 time for calcul the mask position with numpy : 0.031317949295043945 nb_pixel_total : 16726 time to create 1 rle with old method : 0.023143768310546875 time for calcul the mask position with numpy : 0.031407833099365234 nb_pixel_total : 11718 time to create 1 rle with old method : 0.015140056610107422 time for calcul the mask position with numpy : 0.033627986907958984 nb_pixel_total : 157015 time to create 1 rle with new method : 0.718346357345581 time for calcul the mask position with numpy : 0.03007030487060547 nb_pixel_total : 571 time to create 1 rle with old method : 0.0013828277587890625 time for calcul the mask position with numpy : 0.030557870864868164 nb_pixel_total : 19888 time to create 1 rle with old method : 0.0231168270111084 time for calcul the mask position with numpy : 0.03207588195800781 nb_pixel_total : 14205 time to create 1 rle with old method : 0.019159793853759766 time for calcul the mask position with numpy : 0.03184986114501953 nb_pixel_total : 54401 time to create 1 rle with old method : 0.06912612915039062 time for calcul the mask position with numpy : 0.030479907989501953 nb_pixel_total : 97242 time to create 1 rle with old method : 0.11117744445800781 time for calcul the mask position with numpy : 0.029604434967041016 nb_pixel_total : 45835 time to create 1 rle with old method : 0.0529935359954834 time for calcul the mask position with numpy : 0.030083417892456055 nb_pixel_total : 25862 time to create 1 rle with old method : 0.028833389282226562 time for calcul the mask position with numpy : 0.029564380645751953 nb_pixel_total : 4937 time to create 1 rle with old method : 0.0059430599212646484 time for calcul the mask position with numpy : 0.03125739097595215 nb_pixel_total : 18381 time to create 1 rle with old method : 0.022444963455200195 time for calcul the mask position with numpy : 0.031061410903930664 nb_pixel_total : 7682 time to create 1 rle with old method : 0.010027885437011719 time for calcul the mask position with numpy : 0.02965831756591797 nb_pixel_total : 40879 time to create 1 rle with old method : 0.046370506286621094 time for calcul the mask position with numpy : 0.029218196868896484 nb_pixel_total : 7684 time to create 1 rle with old method : 0.008772611618041992 time for calcul the mask position with numpy : 0.02963089942932129 nb_pixel_total : 1566 time to create 1 rle with old method : 0.0019176006317138672 time for calcul the mask position with numpy : 0.030484914779663086 nb_pixel_total : 12340 time to create 1 rle with old method : 0.02065873146057129 time for calcul the mask position with numpy : 0.03363633155822754 nb_pixel_total : 27718 time to create 1 rle with old method : 0.03479433059692383 time for calcul the mask position with numpy : 0.029938220977783203 nb_pixel_total : 5550 time to create 1 rle with old method : 0.006498575210571289 time for calcul the mask position with numpy : 0.029904603958129883 nb_pixel_total : 13587 time to create 1 rle with old method : 0.01586294174194336 time for calcul the mask position with numpy : 0.03012681007385254 nb_pixel_total : 11267 time to create 1 rle with old method : 0.01238870620727539 time for calcul the mask position with numpy : 0.029375076293945312 nb_pixel_total : 21552 time to create 1 rle with old method : 0.02659440040588379 time for calcul the mask position with numpy : 0.03191256523132324 nb_pixel_total : 13310 time to create 1 rle with old method : 0.020444869995117188 time for calcul the mask position with numpy : 0.03278684616088867 nb_pixel_total : 25864 time to create 1 rle with old method : 0.03116154670715332 time for calcul the mask position with numpy : 0.030176162719726562 nb_pixel_total : 6860 time to create 1 rle with old method : 0.007752180099487305 time for calcul the mask position with numpy : 0.03021979331970215 nb_pixel_total : 2456 time to create 1 rle with old method : 0.0036973953247070312 time for calcul the mask position with numpy : 0.030021190643310547 nb_pixel_total : 19452 time to create 1 rle with old method : 0.024444103240966797 time for calcul the mask position with numpy : 0.030063152313232422 nb_pixel_total : 5786 time to create 1 rle with old method : 0.007669925689697266 time for calcul the mask position with numpy : 0.03215670585632324 nb_pixel_total : 9777 time to create 1 rle with old method : 0.012738227844238281 time for calcul the mask position with numpy : 0.03027176856994629 nb_pixel_total : 5868 time to create 1 rle with old method : 0.007032155990600586 time for calcul the mask position with numpy : 0.030772924423217773 nb_pixel_total : 4751 time to create 1 rle with old method : 0.005370616912841797 time for calcul the mask position with numpy : 0.03219413757324219 nb_pixel_total : 3019 time to create 1 rle with old method : 0.003960132598876953 create new chi : 7.126138925552368 time to delete rle : 0.005115032196044922 batch 1 Loaded 135 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 28708 TO DO : save crop sub photo not yet done ! save time : 2.73291015625 nb_obj : 42 nb_hashtags : 5 time to prepare the origin masks : 4.055552959442139 time for calcul the mask position with numpy : 0.24222064018249512 nb_pixel_total : 5725038 time to create 1 rle with new method : 0.36975622177124023 time for calcul the mask position with numpy : 0.03573250770568848 nb_pixel_total : 8961 time to create 1 rle with old method : 0.010203838348388672 time for calcul the mask position with numpy : 0.03026437759399414 nb_pixel_total : 74169 time to create 1 rle with old method : 0.07819819450378418 time for calcul the mask position with numpy : 0.028903961181640625 nb_pixel_total : 20740 time to create 1 rle with old method : 0.02265310287475586 time for calcul the mask position with numpy : 0.029471635818481445 nb_pixel_total : 193307 time to create 1 rle with new method : 0.274280309677124 time for calcul the mask position with numpy : 0.02932906150817871 nb_pixel_total : 25422 time to create 1 rle with old method : 0.027549028396606445 time for calcul the mask position with numpy : 0.0286104679107666 nb_pixel_total : 29028 time to create 1 rle with old method : 0.0350799560546875 time for calcul the mask position with numpy : 0.028900861740112305 nb_pixel_total : 26610 time to create 1 rle with old method : 0.02865004539489746 time for calcul the mask position with numpy : 0.02883315086364746 nb_pixel_total : 24256 time to create 1 rle with old method : 0.02662944793701172 time for calcul the mask position with numpy : 0.02924633026123047 nb_pixel_total : 70546 time to create 1 rle with old method : 0.07526183128356934 time for calcul the mask position with numpy : 0.028890609741210938 nb_pixel_total : 30515 time to create 1 rle with old method : 0.03320670127868652 time for calcul the mask position with numpy : 0.029164791107177734 nb_pixel_total : 18125 time to create 1 rle with old method : 0.020569324493408203 time for calcul the mask position with numpy : 0.02903270721435547 nb_pixel_total : 14346 time to create 1 rle with old method : 0.015781164169311523 time for calcul the mask position with numpy : 0.028578758239746094 nb_pixel_total : 29896 time to create 1 rle with old method : 0.03231954574584961 time for calcul the mask position with numpy : 0.0286867618560791 nb_pixel_total : 35902 time to create 1 rle with old method : 0.038925886154174805 time for calcul the mask position with numpy : 0.029244422912597656 nb_pixel_total : 155328 time to create 1 rle with new method : 1.3058083057403564 time for calcul the mask position with numpy : 0.031229019165039062 nb_pixel_total : 63694 time to create 1 rle with old method : 0.0708305835723877 time for calcul the mask position with numpy : 0.029476404190063477 nb_pixel_total : 62660 time to create 1 rle with old method : 0.06703662872314453 time for calcul the mask position with numpy : 0.02986741065979004 nb_pixel_total : 17826 time to create 1 rle with old method : 0.0284879207611084 time for calcul the mask position with numpy : 0.03287172317504883 nb_pixel_total : 22873 time to create 1 rle with old method : 0.02504587173461914 time for calcul the mask position with numpy : 0.02922511100769043 nb_pixel_total : 31216 time to create 1 rle with old method : 0.03979301452636719 time for calcul the mask position with numpy : 0.02936530113220215 nb_pixel_total : 14500 time to create 1 rle with old method : 0.0156862735748291 time for calcul the mask position with numpy : 0.028965234756469727 nb_pixel_total : 14690 time to create 1 rle with old method : 0.016538619995117188 time for calcul the mask position with numpy : 0.02922677993774414 nb_pixel_total : 14040 time to create 1 rle with old method : 0.015247106552124023 time for calcul the mask position with numpy : 0.02913665771484375 nb_pixel_total : 30639 time to create 1 rle with old method : 0.03355884552001953 time for calcul the mask position with numpy : 0.029062747955322266 nb_pixel_total : 19561 time to create 1 rle with old method : 0.021497249603271484 time for calcul the mask position with numpy : 0.029219388961791992 nb_pixel_total : 13022 time to create 1 rle with old method : 0.014432907104492188 time for calcul the mask position with numpy : 0.029095888137817383 nb_pixel_total : 10851 time to create 1 rle with old method : 0.012029647827148438 time for calcul the mask position with numpy : 0.02899456024169922 nb_pixel_total : 3487 time to create 1 rle with old method : 0.004012107849121094 time for calcul the mask position with numpy : 0.029173851013183594 nb_pixel_total : 38868 time to create 1 rle with old method : 0.04193258285522461 time for calcul the mask position with numpy : 0.029268264770507812 nb_pixel_total : 21539 time to create 1 rle with old method : 0.024068832397460938 time for calcul the mask position with numpy : 0.029275178909301758 nb_pixel_total : 24552 time to create 1 rle with old method : 0.02706170082092285 time for calcul the mask position with numpy : 0.02906179428100586 nb_pixel_total : 36621 time to create 1 rle with old method : 0.039449453353881836 time for calcul the mask position with numpy : 0.029219388961791992 nb_pixel_total : 8025 time to create 1 rle with old method : 0.009179353713989258 time for calcul the mask position with numpy : 0.02941751480102539 nb_pixel_total : 28008 time to create 1 rle with old method : 0.03148460388183594 time for calcul the mask position with numpy : 0.02897477149963379 nb_pixel_total : 5127 time to create 1 rle with old method : 0.005765199661254883 time for calcul the mask position with numpy : 0.029053926467895508 nb_pixel_total : 15905 time to create 1 rle with old method : 0.025294065475463867 time for calcul the mask position with numpy : 0.03328657150268555 nb_pixel_total : 19062 time to create 1 rle with old method : 0.028022050857543945 time for calcul the mask position with numpy : 0.02918839454650879 nb_pixel_total : 5703 time to create 1 rle with old method : 0.008340835571289062 time for calcul the mask position with numpy : 0.0294952392578125 nb_pixel_total : 10650 time to create 1 rle with old method : 0.015633821487426758 time for calcul the mask position with numpy : 0.03063797950744629 nb_pixel_total : 5625 time to create 1 rle with old method : 0.006625175476074219 time for calcul the mask position with numpy : 0.03146028518676758 nb_pixel_total : 18784 time to create 1 rle with old method : 0.021083593368530273 time for calcul the mask position with numpy : 0.031177520751953125 nb_pixel_total : 10523 time to create 1 rle with old method : 0.012091398239135742 create new chi : 4.624436616897583 time to delete rle : 0.004923343658447266 batch 1 Loaded 85 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 20461 TO DO : save crop sub photo not yet done ! save time : 2.195667266845703 nb_obj : 44 nb_hashtags : 5 time to prepare the origin masks : 4.387342691421509 time for calcul the mask position with numpy : 0.5578768253326416 nb_pixel_total : 5414344 time to create 1 rle with new method : 0.8802700042724609 time for calcul the mask position with numpy : 0.0312504768371582 nb_pixel_total : 8708 time to create 1 rle with old method : 0.01071929931640625 time for calcul the mask position with numpy : 0.03197669982910156 nb_pixel_total : 26118 time to create 1 rle with old method : 0.02965545654296875 time for calcul the mask position with numpy : 0.031159400939941406 nb_pixel_total : 59739 time to create 1 rle with old method : 0.0682373046875 time for calcul the mask position with numpy : 0.0317840576171875 nb_pixel_total : 14086 time to create 1 rle with old method : 0.016087770462036133 time for calcul the mask position with numpy : 0.03207087516784668 nb_pixel_total : 28938 time to create 1 rle with old method : 0.03550577163696289 time for calcul the mask position with numpy : 0.033814191818237305 nb_pixel_total : 22540 time to create 1 rle with old method : 0.02675771713256836 time for calcul the mask position with numpy : 0.03070664405822754 nb_pixel_total : 20004 time to create 1 rle with old method : 0.02437591552734375 time for calcul the mask position with numpy : 0.02991342544555664 nb_pixel_total : 56779 time to create 1 rle with old method : 0.0705564022064209 time for calcul the mask position with numpy : 0.030204057693481445 nb_pixel_total : 58383 time to create 1 rle with old method : 0.06996965408325195 time for calcul the mask position with numpy : 0.03501009941101074 nb_pixel_total : 30576 time to create 1 rle with old method : 0.03426814079284668 time for calcul the mask position with numpy : 0.031137466430664062 nb_pixel_total : 141753 time to create 1 rle with old method : 0.15915775299072266 time for calcul the mask position with numpy : 0.03014969825744629 nb_pixel_total : 15262 time to create 1 rle with old method : 0.018557310104370117 time for calcul the mask position with numpy : 0.029517412185668945 nb_pixel_total : 16731 time to create 1 rle with old method : 0.026157379150390625 time for calcul the mask position with numpy : 0.03062725067138672 nb_pixel_total : 11660 time to create 1 rle with old method : 0.013391971588134766 time for calcul the mask position with numpy : 0.030337810516357422 nb_pixel_total : 12263 time to create 1 rle with old method : 0.01394033432006836 time for calcul the mask position with numpy : 0.030590057373046875 nb_pixel_total : 49527 time to create 1 rle with old method : 0.05751991271972656 time for calcul the mask position with numpy : 0.02935171127319336 nb_pixel_total : 23193 time to create 1 rle with old method : 0.024876117706298828 time for calcul the mask position with numpy : 0.02932000160217285 nb_pixel_total : 21204 time to create 1 rle with old method : 0.023075103759765625 time for calcul the mask position with numpy : 0.029295682907104492 nb_pixel_total : 30345 time to create 1 rle with old method : 0.033115386962890625 time for calcul the mask position with numpy : 0.02924656867980957 nb_pixel_total : 68182 time to create 1 rle with old method : 0.07376837730407715 time for calcul the mask position with numpy : 0.029108524322509766 nb_pixel_total : 13183 time to create 1 rle with old method : 0.014653921127319336 time for calcul the mask position with numpy : 0.029284954071044922 nb_pixel_total : 28080 time to create 1 rle with old method : 0.030606508255004883 time for calcul the mask position with numpy : 0.029834985733032227 nb_pixel_total : 130071 time to create 1 rle with old method : 0.1385180950164795 time for calcul the mask position with numpy : 0.030112743377685547 nb_pixel_total : 139684 time to create 1 rle with old method : 0.15247344970703125 time for calcul the mask position with numpy : 0.031138181686401367 nb_pixel_total : 1358 time to create 1 rle with old method : 0.0016474723815917969 time for calcul the mask position with numpy : 0.03339648246765137 nb_pixel_total : 78316 time to create 1 rle with old method : 0.09902477264404297 time for calcul the mask position with numpy : 0.030499696731567383 nb_pixel_total : 98325 time to create 1 rle with old method : 0.10912227630615234 time for calcul the mask position with numpy : 0.0287017822265625 nb_pixel_total : 12053 time to create 1 rle with old method : 0.013065576553344727 time for calcul the mask position with numpy : 0.02986907958984375 nb_pixel_total : 9828 time to create 1 rle with old method : 0.015977144241333008 time for calcul the mask position with numpy : 0.033095598220825195 nb_pixel_total : 36091 time to create 1 rle with old method : 0.047188520431518555 time for calcul the mask position with numpy : 0.029123306274414062 nb_pixel_total : 5114 time to create 1 rle with old method : 0.005804300308227539 time for calcul the mask position with numpy : 0.02910923957824707 nb_pixel_total : 11343 time to create 1 rle with old method : 0.012842893600463867 time for calcul the mask position with numpy : 0.029612302780151367 nb_pixel_total : 60929 time to create 1 rle with old method : 0.0652155876159668 time for calcul the mask position with numpy : 0.028794527053833008 nb_pixel_total : 8860 time to create 1 rle with old method : 0.0098876953125 time for calcul the mask position with numpy : 0.029982805252075195 nb_pixel_total : 16812 time to create 1 rle with old method : 0.018413782119750977 time for calcul the mask position with numpy : 0.030414581298828125 nb_pixel_total : 36570 time to create 1 rle with old method : 0.04098057746887207 time for calcul the mask position with numpy : 0.028975725173950195 nb_pixel_total : 31783 time to create 1 rle with old method : 0.034319162368774414 time for calcul the mask position with numpy : 0.029399633407592773 nb_pixel_total : 29245 time to create 1 rle with old method : 0.031531333923339844 time for calcul the mask position with numpy : 0.028655290603637695 nb_pixel_total : 26660 time to create 1 rle with old method : 0.029192209243774414 time for calcul the mask position with numpy : 0.03038191795349121 nb_pixel_total : 18770 time to create 1 rle with old method : 0.02009105682373047 time for calcul the mask position with numpy : 0.02853989601135254 nb_pixel_total : 7711 time to create 1 rle with old method : 0.008682012557983398 time for calcul the mask position with numpy : 0.028861045837402344 nb_pixel_total : 18101 time to create 1 rle with old method : 0.01935863494873047 time for calcul the mask position with numpy : 0.029289722442626953 nb_pixel_total : 68941 time to create 1 rle with old method : 0.07570767402648926 time for calcul the mask position with numpy : 0.029439926147460938 nb_pixel_total : 32077 time to create 1 rle with old method : 0.03485226631164551 create new chi : 4.672809600830078 time to delete rle : 0.004160642623901367 batch 1 Loaded 89 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 24165 TO DO : save crop sub photo not yet done ! save time : 2.298947811126709 nb_obj : 24 nb_hashtags : 4 time to prepare the origin masks : 10.011097431182861 time for calcul the mask position with numpy : 0.3577103614807129 nb_pixel_total : 4640432 time to create 1 rle with new method : 0.5127499103546143 time for calcul the mask position with numpy : 0.03843808174133301 nb_pixel_total : 22197 time to create 1 rle with old method : 0.02417778968811035 time for calcul the mask position with numpy : 0.035590171813964844 nb_pixel_total : 4856 time to create 1 rle with old method : 0.006021022796630859 time for calcul the mask position with numpy : 0.037778615951538086 nb_pixel_total : 34870 time to create 1 rle with old method : 0.040376901626586914 time for calcul the mask position with numpy : 0.03566598892211914 nb_pixel_total : 68642 time to create 1 rle with old method : 0.07396578788757324 time for calcul the mask position with numpy : 0.039197683334350586 nb_pixel_total : 23137 time to create 1 rle with old method : 0.02576422691345215 time for calcul the mask position with numpy : 0.03633594512939453 nb_pixel_total : 89842 time to create 1 rle with old method : 0.09868288040161133 time for calcul the mask position with numpy : 0.03513026237487793 nb_pixel_total : 12713 time to create 1 rle with old method : 0.014380693435668945 time for calcul the mask position with numpy : 0.04203653335571289 nb_pixel_total : 588110 time to create 1 rle with new method : 0.3968515396118164 time for calcul the mask position with numpy : 0.04357266426086426 nb_pixel_total : 172766 time to create 1 rle with new method : 0.5865757465362549 time for calcul the mask position with numpy : 0.043259382247924805 nb_pixel_total : 14785 time to create 1 rle with old method : 0.016657352447509766 time for calcul the mask position with numpy : 0.04676365852355957 nb_pixel_total : 65654 time to create 1 rle with old method : 0.07093238830566406 time for calcul the mask position with numpy : 0.03880453109741211 nb_pixel_total : 109214 time to create 1 rle with old method : 0.11832785606384277 time for calcul the mask position with numpy : 0.028392791748046875 nb_pixel_total : 22182 time to create 1 rle with old method : 0.0247647762298584 time for calcul the mask position with numpy : 0.03542065620422363 nb_pixel_total : 464816 time to create 1 rle with new method : 0.506084680557251 time for calcul the mask position with numpy : 0.028381824493408203 nb_pixel_total : 246971 time to create 1 rle with new method : 0.7086782455444336 time for calcul the mask position with numpy : 0.026827096939086914 nb_pixel_total : 12814 time to create 1 rle with old method : 0.013948202133178711 time for calcul the mask position with numpy : 0.029178857803344727 nb_pixel_total : 103883 time to create 1 rle with old method : 0.11104655265808105 time for calcul the mask position with numpy : 0.02749466896057129 nb_pixel_total : 23638 time to create 1 rle with old method : 0.026088714599609375 time for calcul the mask position with numpy : 0.028110265731811523 nb_pixel_total : 121889 time to create 1 rle with old method : 0.15502357482910156 time for calcul the mask position with numpy : 0.02737736701965332 nb_pixel_total : 42905 time to create 1 rle with old method : 0.04652047157287598 time for calcul the mask position with numpy : 0.027301549911499023 nb_pixel_total : 25215 time to create 1 rle with old method : 0.02714395523071289 time for calcul the mask position with numpy : 0.027578353881835938 nb_pixel_total : 94920 time to create 1 rle with old method : 0.1031806468963623 time for calcul the mask position with numpy : 0.027186870574951172 nb_pixel_total : 28870 time to create 1 rle with old method : 0.03108668327331543 time for calcul the mask position with numpy : 0.029030561447143555 nb_pixel_total : 14919 time to create 1 rle with old method : 0.016275405883789062 create new chi : 5.111663103103638 time to delete rle : 0.005905628204345703 batch 1 Loaded 49 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++Number RLEs to save : 19290 TO DO : save crop sub photo not yet done ! save time : 2.5917556285858154 nb_obj : 22 nb_hashtags : 5 time to prepare the origin masks : 8.88855528831482 time for calcul the mask position with numpy : 0.4326357841491699 nb_pixel_total : 4632908 time to create 1 rle with new method : 0.8045034408569336 time for calcul the mask position with numpy : 0.05122041702270508 nb_pixel_total : 58335 time to create 1 rle with old method : 0.06783199310302734 time for calcul the mask position with numpy : 0.03294181823730469 nb_pixel_total : 8933 time to create 1 rle with old method : 0.010262727737426758 time for calcul the mask position with numpy : 0.024164915084838867 nb_pixel_total : 51365 time to create 1 rle with old method : 0.06084275245666504 time for calcul the mask position with numpy : 0.02550816535949707 nb_pixel_total : 263939 time to create 1 rle with new method : 0.6684167385101318 time for calcul the mask position with numpy : 0.02741551399230957 nb_pixel_total : 263487 time to create 1 rle with new method : 0.6040506362915039 time for calcul the mask position with numpy : 0.026718616485595703 nb_pixel_total : 123003 time to create 1 rle with old method : 0.17227911949157715 time for calcul the mask position with numpy : 0.028876543045043945 nb_pixel_total : 181346 time to create 1 rle with new method : 0.5378217697143555 time for calcul the mask position with numpy : 0.023415565490722656 nb_pixel_total : 11336 time to create 1 rle with old method : 0.012341499328613281 time for calcul the mask position with numpy : 0.023523807525634766 nb_pixel_total : 173310 time to create 1 rle with new method : 0.41120004653930664 time for calcul the mask position with numpy : 0.028179168701171875 nb_pixel_total : 40027 time to create 1 rle with old method : 0.06469273567199707 time for calcul the mask position with numpy : 0.03136420249938965 nb_pixel_total : 122903 time to create 1 rle with old method : 0.13712501525878906 time for calcul the mask position with numpy : 0.02648162841796875 nb_pixel_total : 4934 time to create 1 rle with old method : 0.005915641784667969 time for calcul the mask position with numpy : 0.030272960662841797 nb_pixel_total : 158712 time to create 1 rle with new method : 0.3738424777984619 time for calcul the mask position with numpy : 0.02436208724975586 nb_pixel_total : 72835 time to create 1 rle with old method : 0.07873725891113281 time for calcul the mask position with numpy : 0.02520155906677246 nb_pixel_total : 436318 time to create 1 rle with new method : 0.650648832321167 time for calcul the mask position with numpy : 0.023918628692626953 nb_pixel_total : 183540 time to create 1 rle with new method : 0.8286571502685547 time for calcul the mask position with numpy : 0.03280520439147949 nb_pixel_total : 15550 time to create 1 rle with old method : 0.017139673233032227 time for calcul the mask position with numpy : 0.02854299545288086 nb_pixel_total : 8235 time to create 1 rle with old method : 0.009437322616577148 time for calcul the mask position with numpy : 0.03163003921508789 nb_pixel_total : 21049 time to create 1 rle with old method : 0.024226665496826172 time for calcul the mask position with numpy : 0.04941558837890625 nb_pixel_total : 9518 time to create 1 rle with old method : 0.013775825500488281 time for calcul the mask position with numpy : 0.06485462188720703 nb_pixel_total : 7442 time to create 1 rle with old method : 0.010915994644165039 time for calcul the mask position with numpy : 0.05858302116394043 nb_pixel_total : 201215 time to create 1 rle with new method : 0.9445810317993164 create new chi : 7.928170204162598 time to delete rle : 0.0059511661529541016 batch 1 Loaded 45 chid ids of type : 3594 ++++++++++++++++++++++++++Number RLEs to save : 17432 TO DO : save crop sub photo not yet done ! save time : 4.05469822883606 nb_obj : 19 nb_hashtags : 3 time to prepare the origin masks : 8.816081523895264 time for calcul the mask position with numpy : 0.5381002426147461 nb_pixel_total : 5737372 time to create 1 rle with new method : 0.7356002330780029 time for calcul the mask position with numpy : 0.04696917533874512 nb_pixel_total : 16398 time to create 1 rle with old method : 0.018108129501342773 time for calcul the mask position with numpy : 0.041872262954711914 nb_pixel_total : 98110 time to create 1 rle with old method : 0.10806798934936523 time for calcul the mask position with numpy : 0.029675006866455078 nb_pixel_total : 129455 time to create 1 rle with old method : 0.13834691047668457 time for calcul the mask position with numpy : 0.043351173400878906 nb_pixel_total : 18256 time to create 1 rle with old method : 0.02277541160583496 time for calcul the mask position with numpy : 0.044423818588256836 nb_pixel_total : 59322 time to create 1 rle with old method : 0.09049248695373535 time for calcul the mask position with numpy : 0.04375815391540527 nb_pixel_total : 39998 time to create 1 rle with old method : 0.0433354377746582 time for calcul the mask position with numpy : 0.0420222282409668 nb_pixel_total : 28266 time to create 1 rle with old method : 0.033762216567993164 time for calcul the mask position with numpy : 0.04710674285888672 nb_pixel_total : 40272 time to create 1 rle with old method : 0.061810970306396484 time for calcul the mask position with numpy : 0.05038809776306152 nb_pixel_total : 32093 time to create 1 rle with old method : 0.035970449447631836 time for calcul the mask position with numpy : 0.04163837432861328 nb_pixel_total : 28761 time to create 1 rle with old method : 0.031682491302490234 time for calcul the mask position with numpy : 0.04900979995727539 nb_pixel_total : 9546 time to create 1 rle with old method : 0.011228084564208984 time for calcul the mask position with numpy : 0.041734933853149414 nb_pixel_total : 184949 time to create 1 rle with new method : 0.5279762744903564 time for calcul the mask position with numpy : 0.032588958740234375 nb_pixel_total : 64031 time to create 1 rle with old method : 0.07374954223632812 time for calcul the mask position with numpy : 0.03386235237121582 nb_pixel_total : 179187 time to create 1 rle with new method : 0.6135802268981934 time for calcul the mask position with numpy : 0.02553534507751465 nb_pixel_total : 20595 time to create 1 rle with old method : 0.026520729064941406 time for calcul the mask position with numpy : 0.027926921844482422 nb_pixel_total : 101916 time to create 1 rle with old method : 0.1237783432006836 time for calcul the mask position with numpy : 0.024811267852783203 nb_pixel_total : 76166 time to create 1 rle with old method : 0.0837697982788086 time for calcul the mask position with numpy : 0.026651859283447266 nb_pixel_total : 138917 time to create 1 rle with old method : 0.14832210540771484 time for calcul the mask position with numpy : 0.023845672607421875 nb_pixel_total : 46630 time to create 1 rle with old method : 0.05072021484375 create new chi : 4.702447891235352 time to delete rle : 0.004224538803100586 batch 1 Loaded 39 chid ids of type : 3594 ++++++++++++++++++++++++++Number RLEs to save : 16192 TO DO : save crop sub photo not yet done ! save time : 4.713423252105713 nb_obj : 20 nb_hashtags : 3 time to prepare the origin masks : 9.32947587966919 time for calcul the mask position with numpy : 0.2729785442352295 nb_pixel_total : 4634216 time to create 1 rle with new method : 1.2579662799835205 time for calcul the mask position with numpy : 0.03762555122375488 nb_pixel_total : 42150 time to create 1 rle with old method : 0.04668784141540527 time for calcul the mask position with numpy : 0.03765678405761719 nb_pixel_total : 39550 time to create 1 rle with old method : 0.043601274490356445 time for calcul the mask position with numpy : 0.03584623336791992 nb_pixel_total : 46678 time to create 1 rle with old method : 0.050420284271240234 time for calcul the mask position with numpy : 0.03703713417053223 nb_pixel_total : 46762 time to create 1 rle with old method : 0.050246477127075195 time for calcul the mask position with numpy : 0.04355812072753906 nb_pixel_total : 31827 time to create 1 rle with old method : 0.0352020263671875 time for calcul the mask position with numpy : 0.04013824462890625 nb_pixel_total : 44165 time to create 1 rle with old method : 0.048477888107299805 time for calcul the mask position with numpy : 0.04208636283874512 nb_pixel_total : 19240 time to create 1 rle with old method : 0.021322965621948242 time for calcul the mask position with numpy : 0.04929852485656738 nb_pixel_total : 42785 time to create 1 rle with old method : 0.04636788368225098 time for calcul the mask position with numpy : 0.04779195785522461 nb_pixel_total : 220582 time to create 1 rle with new method : 0.46374082565307617 time for calcul the mask position with numpy : 0.03167414665222168 nb_pixel_total : 12418 time to create 1 rle with old method : 0.013497114181518555 time for calcul the mask position with numpy : 0.03556323051452637 nb_pixel_total : 33816 time to create 1 rle with old method : 0.03925156593322754 time for calcul the mask position with numpy : 0.042272329330444336 nb_pixel_total : 629457 time to create 1 rle with new method : 0.36400532722473145 time for calcul the mask position with numpy : 0.04142355918884277 nb_pixel_total : 117367 time to create 1 rle with old method : 0.15372204780578613 time for calcul the mask position with numpy : 0.03485369682312012 nb_pixel_total : 19868 time to create 1 rle with old method : 0.022338151931762695 time for calcul the mask position with numpy : 0.03199934959411621 nb_pixel_total : 11550 time to create 1 rle with old method : 0.012984037399291992 time for calcul the mask position with numpy : 0.029830455780029297 nb_pixel_total : 90224 time to create 1 rle with old method : 0.10023951530456543 time for calcul the mask position with numpy : 0.03435182571411133 nb_pixel_total : 43817 time to create 1 rle with old method : 0.04748654365539551 time for calcul the mask position with numpy : 0.03368663787841797 nb_pixel_total : 820194 time to create 1 rle with new method : 0.5024986267089844 time for calcul the mask position with numpy : 0.023356914520263672 nb_pixel_total : 46557 time to create 1 rle with old method : 0.056357622146606445 time for calcul the mask position with numpy : 0.024019479751586914 nb_pixel_total : 57017 time to create 1 rle with old method : 0.06260347366333008 create new chi : 4.561335563659668 time to delete rle : 0.004562854766845703 batch 1 Loaded 43 chid ids of type : 3594 +++++++++++++++++++++++++++++++Number RLEs to save : 17520 TO DO : save crop sub photo not yet done ! save time : 2.2691195011138916 map_output_result : {1338685154: (0.0, 'Should be the crop_list due to order', 0), 1338685152: (0.0, 'Should be the crop_list due to order', 0), 1338685150: (0.0, 'Should be the crop_list due to order', 0), 1338685147: (0.0, 'Should be the crop_list due to order', 0), 1338647445: (0.0, 'Should be the crop_list due to order', 0), 1338647408: (0.0, 'Should be the crop_list due to order', 0), 1338647395: (0.0, 'Should be the crop_list due to order', 0), 1338647392: (0.0, 'Should be the crop_list due to order', 0), 1338647390: (0.0, 'Should be the crop_list due to order', 0), 1338647353: (0.0, 'Should be the crop_list due to order', 0), 1338647351: (0.0, 'Should be the crop_list due to order', 0), 1338647350: (0.0, 'Should be the crop_list due to order', 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 [1338685154, 1338685152, 1338685150, 1338685147, 1338647445, 1338647408, 1338647395, 1338647392, 1338647390, 1338647353, 1338647351, 1338647350] Looping around the photos to save general results len do output : 12 /1338685154.Didn't retrieve data . /1338685152.Didn't retrieve data . /1338685150.Didn't retrieve data . /1338685147.Didn't retrieve data . /1338647445.Didn't retrieve data . /1338647408.Didn't retrieve data . /1338647395.Didn't retrieve data . /1338647392.Didn't retrieve data . /1338647390.Didn't retrieve data . /1338647353.Didn't retrieve data . /1338647351.Didn't retrieve data . /1338647350.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 ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685154', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685152', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685150', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685147', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647445', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647408', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647395', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647392', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647390', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647353', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647351', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647350', None, None, None, None, None, '2601861') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 36 time used for this insertion : 0.016779184341430664 save_final save missing photos in datou_result : time spend for datou_step_exec : 168.09762859344482 time spend to save output : 0.02198934555053711 total time spend for step 3 : 168.11961793899536 step4:ventilate_hashtags_in_portfolio Fri Feb 21 00:42:18 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 : 20699449 get user id for portfolio 20699449 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`=20699449 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_fonce','pehd','metal','flou','environnement','background','autre','mal_croppe','papier','carton','pet_clair')) AND mptpi.`min_score`=0.5 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`=20699449 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_fonce','pehd','metal','flou','environnement','background','autre','mal_croppe','papier','carton','pet_clair')) AND mptpi.`min_score`=0.5 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") 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`=20699449 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_fonce','pehd','metal','flou','environnement','background','autre','mal_croppe','papier','carton','pet_clair')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://www.fotonower.com/velours/20700482,20700483,20700484,20700485,20700486,20700487,20700488,20700489,20700490,20700491,20700492?tags=pet_fonce,pehd,metal,flou,environnement,background,autre,mal_croppe,papier,carton,pet_clair Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1338685154, 1338685152, 1338685150, 1338685147, 1338647445, 1338647408, 1338647395, 1338647392, 1338647390, 1338647353, 1338647351, 1338647350] Looping around the photos to save general results len do output : 1 /20699449. 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 ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685154', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685152', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685150', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685147', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647445', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647408', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647395', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647392', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647390', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647353', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647351', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647350', None, None, None, None, None, '2601861') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 13 time used for this insertion : 0.0905160903930664 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.2709267139434814 time spend to save output : 0.09085392951965332 total time spend for step 4 : 2.3617806434631348 step5:final Fri Feb 21 00:42:20 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step final ! Catched exception ! Connect or reconnect ! Inside saveOutput : final : False verbose : 0 original output for save of step final : {1338685154: ('0.2402460767293029',), 1338685152: ('0.2402460767293029',), 1338685150: ('0.2402460767293029',), 1338685147: ('0.2402460767293029',), 1338647445: ('0.2402460767293029',), 1338647408: ('0.2402460767293029',), 1338647395: ('0.2402460767293029',), 1338647392: ('0.2402460767293029',), 1338647390: ('0.2402460767293029',), 1338647353: ('0.2402460767293029',), 1338647351: ('0.2402460767293029',), 1338647350: ('0.2402460767293029',)} new output for save of step final : {1338685154: ('0.2402460767293029',), 1338685152: ('0.2402460767293029',), 1338685150: ('0.2402460767293029',), 1338685147: ('0.2402460767293029',), 1338647445: ('0.2402460767293029',), 1338647408: ('0.2402460767293029',), 1338647395: ('0.2402460767293029',), 1338647392: ('0.2402460767293029',), 1338647390: ('0.2402460767293029',), 1338647353: ('0.2402460767293029',), 1338647351: ('0.2402460767293029',), 1338647350: ('0.2402460767293029',)} [1338685154, 1338685152, 1338685150, 1338685147, 1338647445, 1338647408, 1338647395, 1338647392, 1338647390, 1338647353, 1338647351, 1338647350] Looping around the photos to save general results len do output : 12 /1338685154.Didn't retrieve data . /1338685152.Didn't retrieve data . /1338685150.Didn't retrieve data . /1338685147.Didn't retrieve data . /1338647445.Didn't retrieve data . /1338647408.Didn't retrieve data . /1338647395.Didn't retrieve data . /1338647392.Didn't retrieve data . /1338647390.Didn't retrieve data . /1338647353.Didn't retrieve data . /1338647351.Didn't retrieve data . /1338647350.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 ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685154', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685152', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685150', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685147', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647445', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647408', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647395', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647392', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647390', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647353', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647351', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647350', None, None, None, None, None, '2601861') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 36 time used for this insertion : 0.05430483818054199 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.17357301712036133 time spend to save output : 0.05556607246398926 total time spend for step 5 : 0.22913908958435059 step6:blur_detection Fri Feb 21 00:42:20 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828.jpg resize: (2160, 3264) 1338685154 -3.824013946970216 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377.jpg resize: (2160, 3264) 1338685152 -3.9444442486305014 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423.jpg resize: (2160, 3264) 1338685150 -5.747694009808559 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a.jpg resize: (2160, 3264) 1338685147 -6.093471387585504 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8.jpg resize: (2160, 3264) 1338647445 -5.197625278691478 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff.jpg resize: (2160, 3264) 1338647408 -5.846417291013054 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8.jpg resize: (2160, 3264) 1338647395 -5.022938057322903 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a.jpg resize: (2160, 3264) 1338647392 -5.401679345760704 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e.jpg resize: (2160, 3264) 1338647390 -3.5557902112651036 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee.jpg resize: (2160, 3264) 1338647353 -4.112816580140558 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17.jpg resize: (2160, 3264) 1338647351 -4.183785747825021 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451.jpg resize: (2160, 3264) 1338647350 -3.5525382313234153 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224666_0.png resize: (895, 413) 1338697758 -3.061226988729387 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224691_0.png resize: (130, 167) 1338697759 -2.140835581061715 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224684_0.png resize: (199, 115) 1338697760 -1.7862671854929308 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224688_0.png resize: (301, 499) 1338697761 -3.468759008774766 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224659_0.png resize: (111, 104) 1338697762 -2.6967458052788524 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224658_0.png resize: (88, 72) 1338697763 -0.23255990907520177 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224685_0.png resize: (370, 217) 1338697764 -2.363997830676475 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224667_0.png resize: (84, 88) 1338697765 -2.9445351441720056 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224663_0.png resize: (176, 152) 1338697766 -2.2924166204714833 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224681_0.png resize: (93, 139) 1338697767 -3.66187870565294 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224674_0.png resize: (263, 138) 1338697768 -3.25997848421653 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224699_0.png resize: (134, 113) 1338697769 -1.661932009337995 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224661_0.png resize: (234, 129) 1338697770 -1.8072191009723597 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224657_0.png resize: (419, 182) 1338697771 -2.6068914647188843 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224677_0.png resize: (160, 222) 1338697772 -2.7114294764380333 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224694_0.png resize: (246, 244) 1338697773 -1.7557719564478664 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224671_0.png resize: (203, 290) 1338697774 -2.509630850522011 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224696_0.png resize: (161, 130) 1338697775 -2.8717230280979456 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224676_0.png resize: (233, 203) 1338697776 -0.5073274508297362 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224687_0.png resize: (181, 214) 1338697777 -2.3946858692329367 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224679_0.png resize: (216, 155) 1338697778 -1.9426823080509203 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224692_0.png resize: (469, 311) 1338697779 -2.1962182786427755 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224686_0.png resize: (87, 195) 1338697780 -1.1352828384089115 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224665_0.png resize: (293, 310) 1338697781 -2.6832496182426158 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224670_0.png resize: (107, 149) 1338697782 -1.8937427525038162 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224703_0.png resize: (124, 263) 1338697783 -2.355516539103594 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224701_0.png resize: (302, 154) 1338697784 -2.8254811027482942 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224672_0.png resize: (118, 135) 1338697785 -2.7675181456440607 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224682_0.png resize: (373, 383) 1338697786 -3.483509203835251 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224675_0.png resize: (133, 249) 1338697787 -2.1047062846645876 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224698_0.png resize: (195, 114) 1338697788 -2.3442021809591167 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224690_0.png resize: (133, 271) 1338697789 -3.2777390008497376 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224693_0.png resize: (134, 201) 1338697790 -2.481154435023838 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224673_0.png resize: (252, 446) 1338697791 -2.8606626839533105 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224702_0.png resize: (94, 110) 1338697792 -2.7076273403365065 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224710_0.png resize: (398, 216) 1338697793 -3.1278836587835785 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224756_0.png resize: (236, 268) 1338697794 -2.3517971526698176 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224714_0.png resize: (481, 223) 1338697795 -2.603884307942809 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224711_0.png resize: (503, 226) 1338697796 -1.76677226851952 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224729_0.png resize: (156, 130) 1338697797 -2.660307695687504 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224753_0.png resize: (174, 147) 1338697798 -3.0436248748487134 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224749_0.png resize: (117, 175) 1338697799 -2.373981330589027 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224722_0.png resize: (201, 285) 1338697800 -2.595053275166897 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224719_0.png resize: (138, 199) 1338697801 -1.8396628293576223 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224734_0.png resize: (126, 128) 1338697802 -2.851453295770477 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224721_0.png resize: (162, 272) 1338697803 -2.052080187488999 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224750_0.png resize: (187, 152) 1338697804 -3.5771879793023422 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224739_0.png resize: (94, 118) 1338697805 -2.4419887637151323 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224761_0.png resize: (105, 111) 1338697806 -3.359850512203115 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224718_0.png resize: (188, 213) 1338697807 -2.562801045006245 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224758_0.png resize: (263, 140) 1338697808 -2.029922963470642 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224762_0.png resize: (91, 124) 1338697809 -2.2031878220739696 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224708_0.png resize: (191, 179) 1338697810 -3.21299802819362 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224760_0.png resize: (174, 175) 1338697811 -2.9520525371314617 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224742_0.png resize: (188, 314) 1338697812 -2.7067306000299762 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224754_0.png resize: (215, 274) 1338697813 -2.167862178726984 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224726_0.png resize: (101, 185) 1338697814 -2.6819805053227226 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224705_0.png resize: (205, 171) 1338697815 -1.3981320081055855 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224724_0.png resize: (107, 50) 1338697816 -4.221315372113512 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224713_0.png resize: (90, 113) 1338697817 -0.3298656693847114 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224746_0.png resize: (367, 312) 1338697818 -2.3253220243965567 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224728_0.png resize: (103, 125) 1338697819 -1.912591956888197 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224737_0.png resize: (164, 166) 1338697820 -2.8700301314148406 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224747_0.png resize: (194, 119) 1338697821 -0.6542260124339203 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224723_0.png resize: (130, 115) 1338697822 -2.108675900232845 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224731_0.png resize: (156, 179) 1338697823 -2.1128810896230745 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224712_0.png resize: (182, 255) 1338697824 -2.3084156247088488 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224741_0.png resize: (153, 227) 1338697825 -2.4097245256663498 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224709_0.png resize: (415, 299) 1338697826 -2.8295897334987816 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224764_0.png resize: (230, 222) 1338697827 -3.0308678916062357 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224736_0.png resize: (143, 201) 1338697828 -3.7915873736392056 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224717_0.png resize: (301, 161) 1338697829 -2.480170090457383 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224759_0.png resize: (110, 190) 1338697830 -2.908229719005597 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224757_0.png resize: (123, 87) 1338697831 -2.0499756424739335 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224751_0.png resize: (164, 116) 1338697832 -3.867110022773188 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224740_0.png resize: (119, 149) 1338697833 -3.145371454965608 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224738_0.png resize: (138, 277) 1338697834 -1.9136431734618193 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224715_0.png resize: (196, 219) 1338697835 -2.5143302267851655 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224730_0.png resize: (168, 96) 1338697836 -2.488444649306741 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224755_0.png resize: (156, 182) 1338697837 -1.9763251807746995 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224768_0.png resize: (113, 175) 1338697838 -1.1721113449800111 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224707_0.png resize: (135, 158) 1338697839 -2.3865971785493447 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224706_0.png resize: (94, 141) 1338697840 -2.6088523217120443 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224720_0.png resize: (200, 127) 1338697841 -2.3835499550723003 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224727_0.png resize: (208, 171) 1338697842 -2.8716768563970025 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224733_0.png resize: (104, 98) 1338697843 -0.7387946823885577 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224776_0.png resize: (280, 333) 1338697844 -4.055670931923272 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224790_0.png resize: (114, 121) 1338697845 -3.930450503092558 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224778_0.png resize: (340, 156) 1338697846 -3.1953647223124904 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224809_0.png resize: (120, 155) 1338697847 -2.686588248452266 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224770_0.png resize: (181, 160) 1338697848 -3.3854603577910347 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224799_0.png resize: (76, 110) 1338697849 -1.300196172793903 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224794_0.png resize: (194, 204) 1338697850 -3.3614070786504042 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224797_0.png resize: (120, 159) 1338697851 -2.2141029989570367 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224779_0.png resize: (417, 214) 1338697852 -4.347876481452903 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224801_0.png resize: (318, 361) 1338697853 -4.203452985139886 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224773_0.png resize: (108, 148) 1338697854 -3.013772016579404 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224781_0.png resize: (183, 244) 1338697855 -3.79946658948251 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224805_0.png resize: (235, 264) 1338697856 -4.061792027985758 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224784_0.png resize: (260, 385) 1338697857 -3.2944653006044216 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224788_0.png resize: (168, 297) 1338697858 -4.443404490655062 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224791_0.png resize: (102, 111) 1338697859 -2.4186158938652604 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224792_0.png resize: (309, 409) 1338697860 -3.1049777156258647 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224783_0.png resize: (305, 410) 1338697861 -3.364336453095196 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224774_0.png resize: (144, 142) 1338697862 -3.9956974655680773 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224782_0.png resize: (258, 95) 1338697863 -3.0393914929052372 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224812_0.png resize: (252, 241) 1338697864 -4.413116461062522 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224777_0.png resize: (187, 284) 1338697865 -3.796331359167249 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224811_0.png resize: (117, 167) 1338697866 -2.73190039129081 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224786_0.png resize: (262, 182) 1338697867 -3.8082344644292747 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224775_0.png resize: (166, 164) 1338697868 -2.4096917604456247 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224802_0.png resize: (257, 168) 1338697869 -4.272436140487823 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224772_0.png resize: (324, 157) 1338697870 -3.6300584416725448 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224798_0.png resize: (150, 141) 1338697871 -3.1315331113109566 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224806_0.png resize: (191, 108) 1338697872 -2.9579600050892827 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224785_0.png resize: (321, 289) 1338697873 -3.8513047177129525 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224795_0.png resize: (156, 193) 1338697874 -4.0836040447663935 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224807_0.png resize: (180, 167) 1338697875 -3.9747336591034843 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224793_0.png resize: (152, 124) 1338697876 -3.124094357307736 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224789_0.png resize: (357, 173) 1338697877 -3.7193979024373625 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224810_0.png resize: (111, 131) 1338697878 -1.625876643936279 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224796_0.png resize: (181, 185) 1338697879 -3.270899179106727 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224803_0.png resize: (103, 90) 1338697880 -2.3191397568871817 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224804_0.png resize: (168, 294) 1338697881 -3.6150226319361796 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224771_0.png resize: (113, 114) 1338697882 -4.6081304707637765 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224780_0.png resize: (105, 156) 1338697883 -3.464668449041093 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224800_0.png resize: (135, 120) 1338697884 -1.9144576281559398 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224808_0.png resize: (219, 308) 1338697885 -3.241473739770583 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224787_0.png resize: (471, 223) 1338697886 -2.962340714623125 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224814_0.png resize: (279, 502) 1338697887 -3.5645678768093805 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224840_0.png resize: (235, 300) 1338697888 -3.4577489633866314 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224817_0.png resize: (167, 195) 1338697889 -2.686781911328501 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224823_0.png resize: (298, 300) 1338697890 -2.695344109179215 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224841_0.png resize: (169, 185) 1338697891 -4.467083765958646 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224850_0.png resize: (298, 362) 1338697892 -3.9443375445911286 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224819_0.png resize: (179, 159) 1338697893 -3.5239852997450622 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224843_0.png resize: (151, 124) 1338697894 -3.9769906824446744 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224825_0.png resize: (139, 171) 1338697895 -4.464869122931135 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224829_0.png resize: (188, 218) 1338697896 -3.1987139295842377 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224852_0.png resize: (184, 85) 1338697897 -4.1001573063561265 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224833_0.png resize: (94, 133) 1338697898 -2.960369591242489 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224822_0.png resize: (136, 156) 1338697899 -2.7078493222107074 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224837_0.png resize: (253, 186) 1338697900 -4.135572631991999 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224821_0.png resize: (241, 135) 1338697901 -4.014183540095087 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224826_0.png resize: (89, 89) 1338697902 -2.680668351045635 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224834_0.png resize: (155, 105) 1338697903 -2.817924942144195 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224839_0.png resize: (57, 59) 1338697904 2.262164289494413 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224848_0.png resize: (68, 99) 1338697905 -1.3617296217520254 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224836_0.png resize: (137, 80) 1338697906 -1.7403793229884519 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224838_0.png resize: (81, 100) 1338697907 -4.792823855722254 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224830_0.png resize: (226, 470) 1338697908 -2.6252732908213376 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224818_0.png resize: (196, 91) 1338697909 -4.431000267712448 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224827_0.png resize: (128, 114) 1338697910 -3.241785460382226 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224835_0.png resize: (122, 100) 1338697911 -4.147280406042065 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224828_0.png resize: (443, 314) 1338697912 -4.4866259676021585 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224845_0.png resize: (100, 70) 1338697913 -1.915308324718133 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224832_0.png resize: (403, 945) 1338697914 -4.298859078970726 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224820_0.png resize: (145, 199) 1338697915 -4.51394241888836 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224851_0.png resize: (182, 213) 1338697916 -4.250563625925538 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224866_0.png resize: (249, 331) 1338697917 -3.8274482523528466 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224877_0.png resize: (310, 231) 1338697918 -3.114029218961585 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224873_0.png resize: (98, 165) 1338697919 -3.3345460369405537 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224870_0.png resize: (146, 206) 1338697920 -3.70944148742427 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224884_0.png resize: (62, 53) 1338697921 -2.254634365069836 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224865_0.png resize: (125, 161) 1338697922 -3.2642970394720905 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224886_0.png resize: (141, 109) 1338697923 -3.7061771855594543 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224871_0.png resize: (190, 157) 1338697924 -4.601857965611352 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224868_0.png resize: (101, 147) 1338697925 -1.3302006206172972 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224859_0.png resize: (211, 98) 1338697926 -2.083227137097825 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224858_0.png resize: (97, 69) 1338697927 -2.813945711947101 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224876_0.png resize: (45, 81) 1338697928 -1.3326799112298944 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224881_0.png resize: (232, 210) 1338697929 -3.951203896395095 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224878_0.png resize: (160, 187) 1338697930 -3.713553695347864 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224860_0.png resize: (180, 140) 1338697931 -2.244406959017386 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224885_0.png resize: (194, 250) 1338697932 -2.611462386291024 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224872_0.png resize: (195, 125) 1338697934 -2.899123858502336 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224880_0.png resize: (148, 143) 1338697936 -2.835884493490581 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224861_0.png resize: (189, 164) 1338697938 -1.2205482261792233 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224867_0.png resize: (139, 200) 1338697939 -2.665293334482456 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224874_0.png resize: (267, 167) 1338697940 -2.4910094041529174 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224863_0.png resize: (142, 120) 1338697941 -4.006338486421077 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224855_0.png resize: (100, 129) 1338697942 -0.8518476437887581 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224857_0.png resize: (274, 54) 1338697943 -1.8334410614215289 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224936_0.png resize: (520, 111) 1338697944 -4.02198692470415 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224920_0.png resize: (173, 121) 1338697945 -4.030386038700477 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224917_0.png resize: (188, 206) 1338697946 -4.263224500997175 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224893_0.png resize: (376, 401) 1338697947 -3.5672944235591295 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224896_0.png resize: (176, 163) 1338697948 -3.771437250355932 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224952_0.png resize: (66, 114) 1338697949 -3.3741737131181826 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224946_0.png resize: (140, 190) 1338697950 -2.312689792094907 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224887_0.png resize: (258, 95) 1338697951 -1.6607417235729136 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224943_0.png resize: (243, 65) 1338697952 -3.102452205806794 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224894_0.png resize: (150, 70) 1338697953 -4.452906842255263 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224913_0.png resize: (432, 213) 1338697954 -4.617828471009427 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224916_0.png resize: (81, 107) 1338697955 -0.6640271597878835 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224905_0.png resize: (210, 344) 1338697956 -4.847882287111189 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224942_0.png resize: (127, 46) 1338697957 -2.2707531998380177 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224890_0.png resize: (176, 119) 1338697958 -2.3017997888395887 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224907_0.png resize: (157, 146) 1338697959 -4.066750232484837 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224932_0.png resize: (120, 114) 1338697960 -2.122528307142501 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224900_0.png resize: (148, 128) 1338697961 -4.316622052481781 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224944_0.png resize: (69, 119) 1338697962 -1.7457765362837911 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224898_0.png resize: (174, 116) 1338697963 -3.3729770587056436 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224897_0.png resize: (130, 78) 1338697966 -3.3315193729823873 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224888_0.png resize: (130, 152) 1338697969 -2.728941154245585 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224934_0.png resize: (134, 150) 1338697970 -3.7177299419230283 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224938_0.png resize: (134, 191) 1338697971 -3.978309757531702 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224914_0.png resize: (195, 132) 1338697972 -3.549797737304021 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224895_0.png resize: (220, 220) 1338697973 -2.9245267294692243 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224940_0.png resize: (207, 281) 1338697974 -4.087886459248557 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224950_0.png resize: (157, 203) 1338697975 -3.6465111568400244 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224892_0.png resize: (227, 366) 1338697976 -4.361399179218628 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224902_0.png resize: (132, 192) 1338697977 -5.078777422941845 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224933_0.png resize: (195, 103) 1338697979 -1.6564367060689993 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224953_0.png resize: (144, 139) 1338697980 -2.782989469840145 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224911_0.png resize: (259, 567) 1338697981 -3.605505405842543 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224915_0.png resize: (169, 256) 1338697983 -3.5398543608807134 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224935_0.png resize: (235, 85) 1338697984 -3.8500952826987285 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224923_0.png resize: (70, 111) 1338697985 -0.7193583887068931 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224919_0.png resize: (188, 199) 1338697986 -2.9665931470527114 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224925_0.png resize: (175, 190) 1338697987 -3.152135995234082 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224891_0.png resize: (107, 145) 1338697988 -2.4479822857628886 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224909_0.png resize: (118, 96) 1338697989 -2.2434564522391787 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224904_0.png resize: (186, 177) 1338697990 -1.7897860484504193 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224910_0.png resize: (403, 309) 1338697991 -1.7900804007739297 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224945_0.png resize: (53, 70) 1338697992 -0.6705832717045946 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224922_0.png resize: (121, 100) 1338697993 -3.608673453322036 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224947_0.png resize: (241, 105) 1338697994 -3.612448189045935 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224908_0.png resize: (208, 104) 1338697995 -3.7724253125683087 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224937_0.png resize: (69, 66) 1338697996 -2.8385144722386344 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224931_0.png resize: (79, 68) 1338697998 -4.300852898064586 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224901_0.png resize: (83, 88) 1338697999 -0.7520509236713534 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224903_0.png resize: (335, 197) 1338698000 -3.4870256664484156 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224889_0.png resize: (148, 129) 1338698001 -3.1601330554780866 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224926_0.png resize: (157, 158) 1338698002 -2.06821649368602 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224918_0.png resize: (79, 89) 1338698006 -3.2301599730747124 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224912_0.png resize: (210, 240) 1338698007 -3.6528780667264766 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224906_0.png resize: (365, 250) 1338698008 -4.155486587469821 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224930_0.png resize: (182, 174) 1338698009 -3.5914865414590076 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224951_0.png resize: (263, 256) 1338698010 -3.273933755147255 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224978_0.png resize: (286, 154) 1338698011 -2.5199869655974303 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224971_0.png resize: (242, 177) 1338698012 -3.2925703915978644 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224961_0.png resize: (208, 172) 1338698013 -2.8816129046312873 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224972_0.png resize: (199, 158) 1338698015 -2.0691170820558087 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224993_0.png resize: (133, 90) 1338698016 -3.743155194785676 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224980_0.png resize: (106, 176) 1338698017 -2.635420988268618 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224983_0.png resize: (412, 244) 1338698018 -4.779604843334254 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224965_0.png resize: (234, 208) 1338698019 -2.0288305103687088 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224995_0.png resize: (116, 120) 1338698020 -2.6086468510662315 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224959_0.png resize: (422, 386) 1338698022 -3.061312134847553 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224954_0.png resize: (443, 634) 1338698023 -0.7778102624672039 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224979_0.png resize: (137, 201) 1338698024 -2.848591945573099 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224985_0.png resize: (155, 200) 1338698025 -2.9017252000434404 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224977_0.png resize: (109, 76) 1338698026 -3.40503229632332 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224981_0.png resize: (74, 89) 1338698027 -3.444445387889003 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224962_0.png resize: (120, 137) 1338698028 -1.8113159046326446 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224974_0.png resize: (171, 148) 1338698029 -4.350994425326539 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224994_0.png resize: (308, 477) 1338698030 -3.8303392205487845 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224956_0.png resize: (145, 99) 1338698031 -2.150560067174382 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224988_0.png resize: (133, 192) 1338698032 -3.4276437752881233 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224976_0.png resize: (89, 60) 1338698033 -4.1678041488395134 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224960_0.png resize: (194, 213) 1338698035 -3.4353164541265246 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224987_0.png resize: (150, 255) 1338698036 -4.15772689650456 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224969_0.png resize: (232, 210) 1338698037 -3.962663085383645 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224982_0.png resize: (122, 111) 1338698038 -1.3189321707260906 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224958_0.png resize: (77, 99) 1338698039 -2.077078107003465 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224963_0.png resize: (167, 243) 1338698040 -4.303547693665565 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224992_0.png resize: (280, 120) 1338698041 -3.357476076869213 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224955_0.png resize: (122, 207) 1338698042 -2.781401793864313 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224990_0.png resize: (238, 233) 1338698043 -3.2141305840324765 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224986_0.png resize: (152, 146) 1338698045 -2.8117672271929948 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224957_0.png resize: (213, 211) 1338698046 -3.7915788482547588 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224966_0.png resize: (166, 209) 1338698047 -4.214950145033096 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224991_0.png resize: (247, 195) 1338698048 -3.6259753347816774 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224967_0.png resize: (199, 194) 1338698049 -4.100316267807422 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224973_0.png resize: (130, 163) 1338698050 -3.0789146448333446 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224970_0.png resize: (200, 124) 1338698051 -3.75791064550346 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225016_0.png resize: (172, 227) 1338698052 -3.666497192573238 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225024_0.png resize: (204, 277) 1338698053 -2.609033932952732 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225007_0.png resize: (88, 140) 1338698054 -2.325496863200965 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225000_0.png resize: (253, 546) 1338698055 -2.2508439667047333 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225023_0.png resize: (138, 172) 1338698056 -3.9096203332508837 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225014_0.png resize: (204, 127) 1338698057 -3.5133598862968567 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225003_0.png resize: (169, 307) 1338698058 -2.823849026405234 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225031_0.png resize: (184, 315) 1338698059 -3.437202572492039 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681224999_0.png resize: (362, 600) 1338698060 -4.157477932081022 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225029_0.png resize: (322, 247) 1338698061 -3.4623357720582684 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225026_0.png resize: (206, 174) 1338698062 -4.1713694609048 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225033_0.png resize: (337, 177) 1338698063 -3.7519525424205273 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225015_0.png resize: (220, 184) 1338698064 -3.9388692796422284 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225018_0.png resize: (287, 152) 1338698065 -3.0783897637792452 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225011_0.png resize: (94, 122) 1338698066 -1.0962225946917783 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225008_0.png resize: (218, 247) 1338698067 -4.6926439945329825 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225001_0.png resize: (420, 341) 1338698069 -4.001569488912401 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225035_0.png resize: (115, 161) 1338698070 -3.0285452668343362 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225036_0.png resize: (110, 156) 1338698071 -1.6765969077284955 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225002_0.png resize: (140, 135) 1338698072 -3.1189564327608728 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225010_0.png resize: (84, 81) 1338698073 -3.5055537847024762 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225030_0.png resize: (140, 111) 1338698074 -3.345116172260702 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225028_0.png resize: (168, 217) 1338698075 -3.6123834334204625 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225022_0.png resize: (193, 69) 1338698076 -2.8592843129358236 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225039_0.png resize: (146, 116) 1338698077 -1.7222860266445237 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225012_0.png resize: (449, 403) 1338698078 -2.604534522692933 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225013_0.png resize: (131, 335) 1338698079 -1.8548451134659156 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225020_0.png resize: (165, 115) 1338698080 -2.6151392412622005 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225004_0.png resize: (252, 99) 1338698081 -2.9979608603177526 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225025_0.png resize: (156, 142) 1338698082 -3.030644872382917 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225044_0.png resize: (248, 281) 1338698083 -1.684706839233246 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225053_0.png resize: (430, 330) 1338698084 -2.1497784859546836 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225056_0.png resize: (621, 1047) 1338698085 -1.1957526673755712 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225059_0.png resize: (237, 716) 1338698086 -0.7704452771575205 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225061_0.png resize: (272, 270) 1338698087 -3.4558327914838283 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225048_0.png resize: (189, 135) 1338698088 -2.758021110856634 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225055_0.png resize: (626, 467) 1338698089 -3.2640164927190245 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225054_0.png resize: (165, 177) 1338698090 -2.586465352142036 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225046_0.png resize: (209, 180) 1338698091 -4.48921157664755 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225073_0.png resize: (465, 691) 1338698092 -3.9133056608011616 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225065_0.png resize: (127, 92) 1338698093 -4.103945541135243 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225084_0.png resize: (91, 172) 1338698094 -3.864021736541155 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225066_0.png resize: (131, 94) 1338698095 -0.24901616695473122 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225074_0.png resize: (101, 59) 1338698096 -2.4940844572680714 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225079_0.png resize: (542, 472) 1338698097 -2.005054175059067 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225075_0.png resize: (233, 679) 1338698098 -2.0988561660047376 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225069_0.png resize: (240, 157) 1338698099 -3.161026531142047 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225087_0.png resize: (440, 486) 1338698100 -2.1113667419485105 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225096_0.png resize: (159, 272) 1338698101 -0.48271895172425316 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225095_0.png resize: (282, 187) 1338698102 -1.53869995751481 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225094_0.png resize: (514, 435) 1338698103 -1.1081752385399182 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225103_0.png resize: (429, 364) 1338698104 -2.16179053817729 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225100_0.png resize: (300, 284) 1338698105 -1.6083700564946728 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225089_0.png resize: (399, 480) 1338698106 -1.8010171528305148 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225107_0.png resize: (965, 1386) 1338698107 -1.4815098141185332 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225124_0.png resize: (282, 242) 1338698108 -2.684085321007486 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225118_0.png resize: (404, 185) 1338698109 -0.7561312330188508 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225105_0.png resize: (284, 275) 1338698110 0.39588584823958334 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225115_0.png resize: (160, 213) 1338698111 -2.134289868509216 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225108_0.png resize: (184, 408) 1338698112 -1.1027631248751315 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225117_0.png resize: (468, 730) 1338698113 -1.943152448535381 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225121_0.png resize: (92, 102) 1338698114 -2.0195259874584552 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225126_0.png resize: (292, 251) 1338698115 -3.5317312111067887 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225119_0.png resize: (184, 146) 1338698116 -0.5263867372258386 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225112_0.png resize: (474, 567) 1338698117 -1.674842801819257 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225123_0.png resize: (314, 251) 1338698118 -4.388563310010948 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225109_0.png resize: (395, 342) 1338698119 -3.680920393251411 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225114_0.png resize: (299, 163) 1338698120 -4.016010105364285 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224704_0.png resize: (188, 276) 1338698677 -2.6008119580428497 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224697_0.png resize: (114, 155) 1338698679 -2.1091111854886346 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224660_0.png resize: (212, 180) 1338698682 -0.9736754409006159 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224669_0.png resize: (187, 131) 1338698684 -0.9155425678338182 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224662_0.png resize: (324, 167) 1338698686 -2.660677821193585 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224664_0.png resize: (95, 121) 1338698689 -2.9291441650648893 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224668_0.png resize: (136, 148) 1338698692 -2.6945974773998382 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224683_0.png resize: (175, 193) 1338698696 -3.044439676060024 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224766_0.png resize: (191, 209) 1338698699 -1.4760747082581878 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224752_0.png resize: (167, 109) 1338698702 -1.6210948943129897 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224725_0.png resize: (216, 253) 1338698705 -2.8108154072368223 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224765_0.png resize: (189, 255) 1338698707 -3.691873944143943 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224763_0.png resize: (154, 120) 1338698710 -2.986989565610547 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224716_0.png resize: (271, 325) 1338698713 -3.1346957106826303 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224748_0.png resize: (172, 201) 1338698716 -3.2070254742734785 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224732_0.png resize: (145, 170) 1338698719 -2.688985287516943 treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224769_0.png resize: (206, 229) 1338698721 -3.589240340384492 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224816_0.png resize: (147, 258) 1338698724 -3.630631083060211 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224831_0.png resize: (69, 113) 1338698726 -2.47002048839305 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224849_0.png resize: (48, 70) 1338698728 -1.9692307455763682 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224847_0.png resize: (76, 93) 1338698730 -2.501715835107198 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224842_0.png resize: (79, 104) 1338698733 -3.274088140872235 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224854_0.png resize: (499, 788) 1338698735 -4.217821678622276 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224815_0.png resize: (655, 1456) 1338698738 -2.077475531882831 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224813_0.png resize: (404, 657) 1338698741 -2.887477139768326 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224846_0.png resize: (261, 173) 1338698743 -3.7790902789998464 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224869_0.png resize: (136, 168) 1338698746 -3.2992778001841043 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224875_0.png resize: (117, 145) 1338698748 -2.6547644111902486 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224862_0.png resize: (137, 137) 1338698752 -2.2473151931269086 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224864_0.png resize: (195, 282) 1338698754 -1.9964093701814982 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224921_0.png resize: (173, 214) 1338698756 -2.984326709928257 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224941_0.png resize: (98, 167) 1338698759 -1.4325321169218652 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224939_0.png resize: (231, 219) 1338698762 -2.3202212986504653 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224929_0.png resize: (205, 300) 1338698765 -3.614687124280462 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224984_0.png resize: (486, 571) 1338698768 -3.576478761592706 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224968_0.png resize: (131, 216) 1338698771 -3.6756195644644234 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681224996_0.png resize: (209, 175) 1338698773 -0.8612787459689915 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225009_0.png resize: (189, 316) 1338698775 -3.2415750434436656 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225005_0.png resize: (191, 250) 1338698776 -4.681537473839059 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681224998_0.png resize: (224, 200) 1338698777 -3.5823829517715375 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225050_0.png resize: (945, 854) 1338698778 -2.191307787484727 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225041_0.png resize: (215, 270) 1338698779 -2.5580792127451843 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225062_0.png resize: (68, 99) 1338698780 -2.29302800953684 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225040_0.png resize: (144, 182) 1338698781 -2.618433506254484 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225058_0.png resize: (349, 395) 1338698782 -2.6829837313559644 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225049_0.png resize: (573, 802) 1338698783 -2.066066645917726 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225051_0.png resize: (355, 133) 1338698784 -2.9484497213946494 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225045_0.png resize: (600, 312) 1338698785 -2.755401744477754 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225072_0.png resize: (371, 345) 1338698786 -2.2000534931659264 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225070_0.png resize: (360, 750) 1338698787 -3.6613875770234663 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225067_0.png resize: (111, 241) 1338698788 -1.879271198282606 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225081_0.png resize: (482, 865) 1338698789 -2.680645697516136 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225064_0.png resize: (644, 547) 1338698790 -1.9505953054632843 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225077_0.png resize: (574, 484) 1338698791 -2.024212992090911 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225083_0.png resize: (252, 369) 1338698792 -4.466987592946277 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225076_0.png resize: (356, 242) 1338698794 -3.985341283238215 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225088_0.png resize: (448, 235) 1338698797 -2.5026119121149435 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225090_0.png resize: (211, 153) 1338698799 -2.601805718018785 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225102_0.png resize: (515, 307) 1338698802 -2.731240593423459 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225086_0.png resize: (187, 514) 1338698804 -2.706560657238858 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225098_0.png resize: (227, 173) 1338698807 -2.9654964923321048 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225091_0.png resize: (650, 556) 1338698809 -2.167809836658771 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225097_0.png resize: (268, 264) 1338698812 -1.7351845801062054 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225093_0.png resize: (408, 796) 1338698814 -1.6223352051253033 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225092_0.png resize: (245, 356) 1338698816 -3.112064548347645 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225101_0.png resize: (177, 214) 1338698818 -2.5592584573007877 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225113_0.png resize: (1049, 795) 1338698821 -2.2296212101669455 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225125_0.png resize: (181, 294) 1338698822 -2.0600132686333428 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225106_0.png resize: (409, 316) 1338698825 -1.8740336306946885 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225122_0.png resize: (214, 402) 1338698827 -2.593025436616223 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225110_0.png resize: (167, 178) 1338698830 -3.2444013726898713 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225111_0.png resize: (191, 256) 1338698833 -3.301727566231374 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225116_0.png resize: (120, 152) 1338698835 -3.1825683959153257 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224689_0.png resize: (88, 152) 1338698891 -3.518305577104365 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224883_0.png resize: (66, 77) 1338698892 -1.2438207198859947 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224989_0.png resize: (198, 95) 1338698893 -3.552989398562497 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225068_0.png resize: (176, 155) 1338698894 -2.695167300583788 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224678_0.png resize: (207, 191) 1338698985 -3.2278528692717243 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224680_0.png resize: (440, 320) 1338698986 -1.304755432342677 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224744_0.png resize: (253, 340) 1338698987 -2.0792517404986848 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224743_0.png resize: (533, 294) 1338698988 -3.2159533176780086 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224853_0.png resize: (145, 367) 1338698989 -4.585586400375605 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224824_0.png resize: (268, 285) 1338698990 -2.7141409081626 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224856_0.png resize: (209, 548) 1338698991 -5.136498538627391 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224879_0.png resize: (472, 337) 1338698992 -2.568485360312905 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224927_0.png resize: (280, 340) 1338698993 -4.028785153797734 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224899_0.png resize: (672, 318) 1338698994 -3.32468381189583 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224964_0.png resize: (232, 521) 1338698995 -3.6830760001770693 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225027_0.png resize: (286, 367) 1338698996 -4.527007335386878 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225006_0.png resize: (334, 491) 1338698997 -3.7603435475047577 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225021_0.png resize: (295, 453) 1338698998 -2.0327730938706052 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225019_0.png resize: (197, 429) 1338698999 -3.2190564452744446 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225017_0.png resize: (369, 207) 1338699000 -3.572583297683611 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225038_0.png resize: (145, 299) 1338699001 -3.406571623624666 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225060_0.png resize: (248, 436) 1338699002 -1.9305433560816745 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225052_0.png resize: (278, 595) 1338699003 -3.4627384492387665 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225063_0.png resize: (104, 272) 1338699004 -0.8433616915832689 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225042_0.png resize: (370, 328) 1338699005 -3.8780048172529917 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225047_0.png resize: (378, 377) 1338699007 -4.207817018324149 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225085_0.png resize: (250, 322) 1338699008 -3.062542900622109 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225080_0.png resize: (278, 659) 1338699009 -2.0517579536393686 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225071_0.png resize: (649, 969) 1338699010 -3.0104691194023476 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225082_0.png resize: (490, 850) 1338699011 -2.2925211219579733 treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225120_0.png resize: (255, 236) 1338699012 -2.314520713549295 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224695_0.png resize: (75, 89) 1338699019 -0.6837919941618015 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224735_0.png resize: (111, 93) 1338699020 -1.0498796327798445 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224767_0.png resize: (170, 151) 1338699022 -1.9498760168465505 treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224844_0.png resize: (93, 111) 1338699023 -3.80161615645 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224948_0.png resize: (95, 197) 1338699024 -3.057101962200665 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224949_0.png resize: (72, 108) 1338699025 -1.3762057148864995 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225032_0.png resize: (252, 290) 1338699026 -1.007587175035425 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681224997_0.png resize: (275, 305) 1338699027 -1.4395398483418707 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225057_0.png resize: (121, 154) 1338699028 -2.506775745293992 treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225043_0.png resize: (122, 316) 1338699029 -1.8789147515623406 treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225078_0.png resize: (130, 135) 1338699030 -2.2999867685454607 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225104_0.png resize: (172, 128) 1338699031 -3.3961782555822153 treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225099_0.png resize: (520, 321) 1338699032 -2.0166242737928894 treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224745_0.png resize: (120, 73) 1338699035 -0.12848967251674295 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224924_0.png resize: (213, 163) 1338699036 -4.017855181171144 treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224700_0.png resize: (231, 106) 1338699041 -3.2505368729911703 treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224882_0.png resize: (74, 201) 1338699042 -3.6417221892670844 treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224928_0.png resize: (114, 209) 1338699043 -2.8562733883621743 treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224975_0.png resize: (190, 260) 1338699044 -4.116243682374086 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225037_0.png resize: (151, 329) 1338699045 -5.332109119605875 treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225034_0.png resize: (135, 454) 1338699046 -2.889323228015975 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 : 482 time used for this insertion : 0.03962516784667969 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 482 time used for this insertion : 0.08803892135620117 save missing photos in datou_result : time spend for datou_step_exec : 54.29033136367798 time spend to save output : 0.15553665161132812 total time spend for step 6 : 54.44586801528931 step7:brightness Fri Feb 21 00:43:15 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 inside step calcul brightness treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828.jpg treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377.jpg treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423.jpg treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a.jpg treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8.jpg treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff.jpg treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8.jpg treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a.jpg treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e.jpg treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee.jpg treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17.jpg treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451.jpg treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224666_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224691_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224684_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224688_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224659_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224658_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224685_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224667_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224663_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224681_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224674_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224699_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224661_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224657_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224677_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224694_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224671_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224696_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224676_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224687_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224679_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224692_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224686_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224665_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224670_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224703_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224701_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224672_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224682_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224675_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224698_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224690_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224693_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224673_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224702_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224710_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224756_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224714_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224711_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224729_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224753_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224749_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224722_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224719_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224734_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224721_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224750_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224739_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224761_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224718_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224758_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224762_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224708_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224760_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224742_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224754_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224726_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224705_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224724_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224713_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224746_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224728_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224737_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224747_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224723_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224731_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224712_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224741_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224709_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224764_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224736_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224717_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224759_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224757_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224751_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224740_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224738_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224715_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224730_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224755_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224768_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224707_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224706_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224720_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224727_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224733_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224776_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224790_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224778_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224809_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224770_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224799_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224794_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224797_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224779_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224801_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224773_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224781_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224805_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224784_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224788_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224791_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224792_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224783_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224774_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224782_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224812_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224777_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224811_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224786_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224775_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224802_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224772_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224798_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224806_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224785_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224795_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224807_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224793_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224789_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224810_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224796_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224803_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224804_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224771_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224780_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224800_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224808_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224787_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224814_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224840_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224817_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224823_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224841_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224850_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224819_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224843_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224825_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224829_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224852_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224833_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224822_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224837_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224821_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224826_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224834_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224839_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224848_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224836_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224838_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224830_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224818_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224827_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224835_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224828_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224845_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224832_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224820_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224851_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224866_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224877_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224873_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224870_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224884_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224865_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224886_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224871_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224868_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224859_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224858_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224876_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224881_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224878_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224860_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224885_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224872_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224880_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224861_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224867_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224874_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224863_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224855_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224857_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224936_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224920_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224917_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224893_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224896_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224952_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224946_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224887_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224943_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224894_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224913_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224916_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224905_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224942_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224890_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224907_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224932_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224900_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224944_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224898_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224897_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224888_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224934_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224938_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224914_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224895_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224940_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224950_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224892_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224902_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224933_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224953_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224911_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224915_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224935_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224923_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224919_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224925_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224891_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224909_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224904_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224910_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224945_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224922_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224947_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224908_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224937_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224931_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224901_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224903_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224889_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224926_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224918_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224912_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224906_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224930_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224951_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224978_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224971_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224961_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224972_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224993_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224980_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224983_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224965_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224995_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224959_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224954_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224979_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224985_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224977_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224981_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224962_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224974_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224994_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224956_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224988_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224976_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224960_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224987_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224969_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224982_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224958_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224963_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224992_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224955_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224990_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224986_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224957_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224966_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224991_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224967_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224973_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224970_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225016_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225024_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225007_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225000_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225023_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225014_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225003_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225031_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681224999_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225029_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225026_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225033_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225015_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225018_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225011_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225008_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225001_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225035_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225036_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225002_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225010_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225030_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225028_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225022_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225039_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225012_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225013_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225020_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225004_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225025_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225044_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225053_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225056_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225059_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225061_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225048_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225055_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225054_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225046_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225073_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225065_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225084_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225066_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225074_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225079_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225075_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225069_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225087_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225096_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225095_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225094_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225103_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225100_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225089_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225107_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225124_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225118_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225105_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225115_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225108_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225117_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225121_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225126_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225119_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225112_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225123_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225109_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225114_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224704_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224697_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224660_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224669_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224662_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224664_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224668_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224683_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224766_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224752_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224725_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224765_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224763_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224716_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224748_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224732_0.png treat image : temp/1740094227_55244_1338685150_86df91924cf541872711d6cebceb9423_rle_crop_3681224769_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224816_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224831_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224849_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224847_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224842_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224854_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224815_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224813_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224846_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224869_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224875_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224862_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224864_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224921_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224941_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224939_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224929_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224984_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224968_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681224996_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225009_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225005_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681224998_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225050_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225041_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225062_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225040_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225058_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225049_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225051_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225045_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225072_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225070_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225067_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225081_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225064_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225077_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225083_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225076_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225088_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225090_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225102_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225086_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225098_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225091_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225097_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225093_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225092_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225101_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225113_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225125_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225106_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225122_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225110_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225111_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225116_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224689_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224883_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224989_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225068_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224678_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224680_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224744_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224743_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224853_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224824_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224856_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224879_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224927_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224899_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224964_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225027_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225006_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225021_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225019_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225017_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225038_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225060_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225052_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225063_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225042_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225047_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225085_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225080_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225071_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225082_0.png treat image : temp/1740094227_55244_1338647350_9cd3dd320fae1520d51613faa8ef8451_rle_crop_3681225120_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224695_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224735_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224767_0.png treat image : temp/1740094227_55244_1338685147_e4f10558284a679aa093c123fba9125a_rle_crop_3681224844_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224948_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224949_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225032_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681224997_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225057_0.png treat image : temp/1740094227_55244_1338647390_a8fb7af5abb2c4707b828f76ff67bf5e_rle_crop_3681225043_0.png treat image : temp/1740094227_55244_1338647353_d540ae01b89283c5a5d579e5f42e13ee_rle_crop_3681225078_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225104_0.png treat image : temp/1740094227_55244_1338647351_749904638fe96c421d35cb0c53e22f17_rle_crop_3681225099_0.png treat image : temp/1740094227_55244_1338685152_5ed73efcdf6c2cea47a30b4b504a9377_rle_crop_3681224745_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224924_0.png treat image : temp/1740094227_55244_1338685154_e00350589deb24e3368935f54609d828_rle_crop_3681224700_0.png treat image : temp/1740094227_55244_1338647445_c85c5ed35219ba1e9c2b1d01d32340f8_rle_crop_3681224882_0.png treat image : temp/1740094227_55244_1338647408_ff874459ef346d9c523d5214ea66d6ff_rle_crop_3681224928_0.png treat image : temp/1740094227_55244_1338647395_8ad13f8d27cc613fc8920cd26db459a8_rle_crop_3681224975_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225037_0.png treat image : temp/1740094227_55244_1338647392_98d8f1d083f77975d7b0849fbd49900a_rle_crop_3681225034_0.png 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 : 482 time used for this insertion : 0.03913140296936035 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 482 time used for this insertion : 0.158111572265625 save missing photos in datou_result : time spend for datou_step_exec : 14.561983108520508 time spend to save output : 0.20724749565124512 total time spend for step 7 : 14.769230604171753 step8:velours_tree Fri Feb 21 00:43:30 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 can't find the photo_desc_type Inside saveOutput : final : False verbose : 0 ouput is None No outpout to save, returning out of save general time spend for datou_step_exec : 2.0233471393585205 time spend to save output : 6.127357482910156e-05 total time spend for step 8 : 2.0234084129333496 step9:send_mail_cod Fri Feb 21 00:43:32 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 2 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 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_Auto_P20699449_21-02-2025_00_43_32.pdf 20700482 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette207004821740095012 20700483 change filename to text .change filename to text .imagette207004831740095012 20700484 change filename to text .change filename to text .change filename to text .change filename to text .imagette207004841740095012 20700485 imagette207004851740095013 20700487 imagette207004871740095013 20700488 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette207004881740095013 20700489 imagette207004891740095013 20700490 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette207004901740095013 20700491 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette207004911740095014 20700492 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette207004921740095016 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20699449 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20700482,20700483,20700484,20700485,20700486,20700487,20700488,20700489,20700490,20700491,20700492?tags=pet_fonce,pehd,metal,flou,environnement,background,autre,mal_croppe,papier,carton,pet_clair args[1338685154] : ((1338685154, -3.824013946970216, 492609224), (1338685154, -0.043656101262930076, 2107752395), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338685152] : ((1338685152, -3.9444442486305014, 492609224), (1338685152, 0.020004043974943236, 2107752395), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338685150] : ((1338685150, -5.747694009808559, 492609224), (1338685150, -0.06951215880568912, 2107752395), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338685147] : ((1338685147, -6.093471387585504, 492609224), (1338685147, -0.09366264472362647, 496442774), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338647445] : ((1338647445, -5.197625278691478, 492609224), (1338647445, -0.40107858529615115, 496442774), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338647408] : ((1338647408, -5.846417291013054, 492609224), (1338647408, -0.2638022676481089, 496442774), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338647395] : ((1338647395, -5.022938057322903, 492609224), (1338647395, -0.2678015117552451, 496442774), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338647392] : ((1338647392, -5.401679345760704, 492609224), (1338647392, -0.049949324336201605, 2107752395), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338647390] : ((1338647390, -3.5557902112651036, 492609224), (1338647390, -0.19701336758750174, 496442774), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338647353] : ((1338647353, -4.112816580140558, 492609224), (1338647353, -0.23980887296697076, 496442774), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338647351] : ((1338647351, -4.183785747825021, 492609224), (1338647351, 0.18373921192408493, 2107752395), '0.2402460767293029') We are sending mail with results at report@fotonower.com args[1338647350] : ((1338647350, -3.5525382313234153, 492609224), (1338647350, 0.044996722190508785, 2107752395), '0.2402460767293029') We are sending mail with results at report@fotonower.com refus_total : 0.2402460767293029 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=20699449 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 SELECT photo_id, url FROM MTRBack.photos ph WHERE photo_id IN (1338647350,1338647353,1338647390,1338685147,1338647395,1338685152,1338647351,1338647392,1338647408,1338647445,1338685150,1338685154) Found this number of photos: 12 begin to download photo : 1338647350 begin to download photo : 1338685147 begin to download photo : 1338647351 begin to download photo : 1338647445 download finish for photo 1338647350 begin to download photo : 1338647353 download finish for photo 1338647445 begin to download photo : 1338685150 download finish for photo 1338685147 begin to download photo : 1338647395 download finish for photo 1338647351 begin to download photo : 1338647392 download finish for photo 1338647353 begin to download photo : 1338647390 download finish for photo 1338685150 begin to download photo : 1338685154 download finish for photo 1338647395 begin to download photo : 1338685152 download finish for photo 1338647392 begin to download photo : 1338647408 download finish for photo 1338647390 download finish for photo 1338685154 download finish for photo 1338685152 download finish for photo 1338647408 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699449_21-02-2025_00_43_32.pdf results_Auto_P20699449_21-02-2025_00_43_32.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699449_21-02-2025_00_43_32.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('3318','20699449','results_Auto_P20699449_21-02-2025_00_43_32.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699449_21-02-2025_00_43_32.pdf','pdf','','1.16','0.2402460767293029') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/20699449

https://www.fotonower.com/image?json=false&list_photos_id=1338685154
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338685152
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338685150
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338685147
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338647445
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338647408
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338647395
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338647392
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338647390
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338647353
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338647351
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1338647350
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 24.02%
Veuillez trouver les photos des contaminants.

exemples de contaminants: pet_fonce: https://www.fotonower.com/view/20700482?limit=200
exemples de contaminants: pehd: https://www.fotonower.com/view/20700483?limit=200
exemples de contaminants: metal: https://www.fotonower.com/view/20700484?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/20700488?limit=200
exemples de contaminants: papier: https://www.fotonower.com/view/20700490?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/20700491?limit=200
exemples de contaminants: pet_clair: https://www.fotonower.com/view/20700492?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699449_21-02-2025_00_43_32.pdf.

Lien vers velours :https://www.fotonower.com/velours/20700482,20700483,20700484,20700485,20700486,20700487,20700488,20700489,20700490,20700491,20700492?tags=pet_fonce,pehd,metal,flou,environnement,background,autre,mal_croppe,papier,carton,pet_clair.


L'équipe Fotonower 202 b'' Server: nginx Date: Thu, 20 Feb 2025 23:43:42 GMT Content-Length: 0 Connection: close X-Message-Id: 3dT_WBCVSje8eZNFW67xnA Access-Control-Allow-Origin: https://sendgrid.api-docs.io Access-Control-Allow-Methods: POST Access-Control-Allow-Headers: Authorization, Content-Type, On-behalf-of, x-sg-elas-acl Access-Control-Max-Age: 600 X-No-CORS-Reason: https://sendgrid.com/docs/Classroom/Basics/API/cors.html Strict-Transport-Security: max-age=31536000; includeSubDomains Content-Security-Policy: frame-ancestors 'none' Cache-Control: no-cache X-Content-Type-Options: no-sniff Referrer-Policy: strict-origin-when-cross-origin Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1338685154, 1338685152, 1338685150, 1338685147, 1338647445, 1338647408, 1338647395, 1338647392, 1338647390, 1338647353, 1338647351, 1338647350] 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 ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685154', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685152', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685150', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685147', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647445', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647408', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647395', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647392', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647390', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647353', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647351', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647350', None, None, None, None, None, '2601861') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.11958861351013184 save_final save missing photos in datou_result : time spend for datou_step_exec : 10.465046167373657 time spend to save output : 0.12012457847595215 total time spend for step 9 : 10.58517074584961 step10:split_time_score Fri Feb 21 00:43:42 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 1 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': 861, 'mtr_user_id': 31, 'name': 'Rungis_class_dechets_1212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Rungis_Aluminium,Rungis_Carton,Rungis_Papier,Rungis_Plastique_clair,Rungis_Plastique_dur,Rungis_Plastique_fonce,Rungis_Tapis_vide,Rungis_Tetrapak', 'svm_portfolios_learning': '1160730,571842,571844,571839,571933,571840,571841,572307', 'photo_hashtag_type': 999, 'photo_desc_type': 3963, 'type_classification': 'caffe', 'hashtag_id_list': '2107751280,2107750907,2107750908,2107750909,2107750910,2107750911,2107750912,2107750913'}] 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'}] (('18', 12),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 20022025 20699449 Nombre de photos uploadées : 12 / 23040 (0%) 20022025 20699449 Nombre de photos taguées (types de déchets): 0 / 12 (0%) 20022025 20699449 Nombre de photos taguées (volume) : 0 / 12 (0%) elapsed_time : load_data_split_time_score 1.430511474609375e-06 elapsed_time : order_list_meta_photo_and_scores 4.5299530029296875e-06 ???????????? elapsed_time : fill_and_build_computed_from_old_data 0.0009877681732177734 elapsed_time : insert_dashboard_record_day_entry 0.02452874183654785 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.9608671591978778 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699402_21-02-2025_00_41_30.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699402 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=20699402 AND mptpi.`type`=3726 To do Qualite : 0.6267786478778448 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699403_21-02-2025_00_40_12.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699403 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=20699403 AND mptpi.`type`=3726 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699404 order by id desc limit 1 Qualite : 0.3329848280211983 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699406_21-02-2025_00_39_22.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699406 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=20699406 AND mptpi.`type`=3726 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699408 order by id desc limit 1 Qualite : 0.6814549659204545 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699412_21-02-2025_00_35_10.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699412 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=20699412 AND mptpi.`type`=3726 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699421 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699422 order by id desc limit 1 Qualite : 0.7519938324117397 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699439_21-02-2025_00_19_28.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699439 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : 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 ! WARNING : type of output 2 of step 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 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`=20699439 AND mptpi.`type`=3726 To do Qualite : 0.2402460767293029 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699449_21-02-2025_00_43_32.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699449 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 ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 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 : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( 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`=20699449 AND mptpi.`type`=3594 To do Qualite : 0.16941512806656225 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20699470_21-02-2025_00_37_56.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20699470 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 ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 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 : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( 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`=20699470 AND mptpi.`type`=3594 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'20022025': {'nb_upload': 12, '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 [1338685154, 1338685152, 1338685150, 1338685147, 1338647445, 1338647408, 1338647395, 1338647392, 1338647390, 1338647353, 1338647351, 1338647350] Looping around the photos to save general results len do output : 1 /20699449Didn'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 ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685154', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685152', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685150', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338685147', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647445', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647408', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647395', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647392', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647390', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647353', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647351', None, None, None, None, None, '2601861') ('3318', None, None, None, None, None, None, None, '2601861') ('3318', '20699449', '1338647350', None, None, None, None, None, '2601861') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 13 time used for this insertion : 0.01934504508972168 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.238251209259033 time spend to save output : 0.019637346267700195 total time spend for step 10 : 4.257888555526733 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 12 set_done_treatment 350.18user 198.64system 13:22.60elapsed 68%CPU (0avgtext+0avgdata 7574556maxresident)k 10117056inputs+281184outputs (310772major+32600853minor)pagefaults 0swaps