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 : 1110649 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 : ['2560894'] with mtr_portfolio_ids : ['20314836'] and first list_photo_ids : [] new path : /proc/1110649/ 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 , BFBFBFBFBFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 15 ; length of list_pids : 15 ; length of list_args : 15 time to download the photos : 3.4940412044525146 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 7 02:10:32 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 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 : 10109 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-07 02:10:35.799956: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-07 02:10:35.827062: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-07 02:10:35.829303: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f79cc000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-07 02:10:35.829343: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-07 02:10:35.833330: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-07 02:10:35.970701: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2e867360 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-07 02:10:35.970767: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-07 02:10:35.972250: 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 2025-02-07 02:10:35.972649: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-07 02:10:35.975413: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-07 02:10:35.977354: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-07 02:10:35.977699: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-07 02:10:35.979879: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-07 02:10:35.981121: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-07 02:10:35.985709: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-07 02:10:35.987478: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-07 02:10:35.987555: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-07 02:10:35.988707: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-07 02:10:35.988724: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-07 02:10:35.988734: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-07 02:10:35.990106: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9197 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. 2025-02-07 02:10:36.245677: 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 2025-02-07 02:10:36.245770: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-07 02:10:36.245798: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-07 02:10:36.245823: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-07 02:10:36.245847: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-07 02:10:36.245871: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-07 02:10:36.245895: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-07 02:10:36.245919: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-07 02:10:36.247495: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-07 02:10:36.248601: 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 2025-02-07 02:10:36.248630: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-07 02:10:36.248645: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-07 02:10:36.248659: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-07 02:10:36.248672: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-07 02:10:36.248686: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-07 02:10:36.248700: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-07 02:10:36.248713: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-07 02:10:36.249960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-07 02:10:36.249987: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-07 02:10:36.249996: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-07 02:10:36.250003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-07 02:10:36.251308: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9197 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 : [] 2025-02-07 02:10:49.548426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-07 02:10:49.781927: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-07 02:10:51.435305: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:51.436035: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:51.436693: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.24G (3478923264 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:51.437379: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3131030784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.233712: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.233827: 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. 2025-02-07 02:10:52.294587: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.294725: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB 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. 2025-02-07 02:10:52.295859: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.295912: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB 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. 2025-02-07 02:10:52.330719: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.330769: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB 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. 2025-02-07 02:10:52.331423: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.331443: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB 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. 2025-02-07 02:10:52.337979: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.338004: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB 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. 2025-02-07 02:10:52.338648: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.338670: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB 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. 2025-02-07 02:10:52.375644: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.375751: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 19.91MiB 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. 2025-02-07 02:10:52.375771: 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. 2025-02-07 02:10:52.376904: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.376933: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 16.00MiB 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. 2025-02-07 02:10:52.378063: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.378091: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 16.00MiB 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. 2025-02-07 02:10:52.386884: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.386919: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB 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. 2025-02-07 02:10:52.387694: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.388522: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.389221: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.405929: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.406596: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.423360: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.424138: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.424778: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.425404: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.429575: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.430208: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.430834: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.431482: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.432569: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.443460: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.444445: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.454383: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.455377: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.456351: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.457305: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.458271: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-07 02:10:52.459253: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 15 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 : 69 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 : 50 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 : 48 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 : 20 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 : 22 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 : 56 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 : 76 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 : 20 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 : 44 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 : 51 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 : 46 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 : 77 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 : 43 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 Detection mask done ! Trying to reset tf kernel 1111128 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 3305 tf kernel not reseted sub process len(results) : 15 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 15 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 : 5041 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 : 0.11171984672546387 nb_pixel_total : 53948 time to create 1 rle with old method : 0.0654146671295166 length of segment : 311 time for calcul the mask position with numpy : 0.15268588066101074 nb_pixel_total : 65070 time to create 1 rle with old method : 0.09783506393432617 length of segment : 667 time for calcul the mask position with numpy : 0.02515888214111328 nb_pixel_total : 38418 time to create 1 rle with old method : 0.04535841941833496 length of segment : 157 time for calcul the mask position with numpy : 0.30741024017333984 nb_pixel_total : 117777 time to create 1 rle with old method : 0.13437390327453613 length of segment : 883 time for calcul the mask position with numpy : 0.041962385177612305 nb_pixel_total : 20608 time to create 1 rle with old method : 0.023152828216552734 length of segment : 216 time for calcul the mask position with numpy : 0.022996902465820312 nb_pixel_total : 25272 time to create 1 rle with old method : 0.030824899673461914 length of segment : 246 time for calcul the mask position with numpy : 0.007180929183959961 nb_pixel_total : 21025 time to create 1 rle with old method : 0.03127408027648926 length of segment : 127 time for calcul the mask position with numpy : 0.031694889068603516 nb_pixel_total : 15699 time to create 1 rle with old method : 0.023537158966064453 length of segment : 149 time for calcul the mask position with numpy : 0.20537376403808594 nb_pixel_total : 243583 time to create 1 rle with new method : 0.015016317367553711 length of segment : 607 time for calcul the mask position with numpy : 0.04504537582397461 nb_pixel_total : 16198 time to create 1 rle with old method : 0.025073766708374023 length of segment : 192 time for calcul the mask position with numpy : 0.1164848804473877 nb_pixel_total : 69227 time to create 1 rle with old method : 0.08233070373535156 length of segment : 295 time for calcul the mask position with numpy : 0.0402529239654541 nb_pixel_total : 14680 time to create 1 rle with old method : 0.02205204963684082 length of segment : 176 time for calcul the mask position with numpy : 0.032534122467041016 nb_pixel_total : 17773 time to create 1 rle with old method : 0.024377822875976562 length of segment : 176 time for calcul the mask position with numpy : 0.07560443878173828 nb_pixel_total : 55421 time to create 1 rle with old method : 0.07085847854614258 length of segment : 231 time for calcul the mask position with numpy : 0.06441712379455566 nb_pixel_total : 55130 time to create 1 rle with old method : 0.0687413215637207 length of segment : 306 time for calcul the mask position with numpy : 0.11337924003601074 nb_pixel_total : 121811 time to create 1 rle with old method : 0.13983535766601562 length of segment : 577 time for calcul the mask position with numpy : 0.05676150321960449 nb_pixel_total : 20663 time to create 1 rle with old method : 0.028881072998046875 length of segment : 272 time for calcul the mask position with numpy : 0.08622384071350098 nb_pixel_total : 51046 time to create 1 rle with old method : 0.05875396728515625 length of segment : 386 time for calcul the mask position with numpy : 0.14014148712158203 nb_pixel_total : 35260 time to create 1 rle with old method : 0.0412297248840332 length of segment : 463 time for calcul the mask position with numpy : 0.2995889186859131 nb_pixel_total : 131554 time to create 1 rle with old method : 0.14452147483825684 length of segment : 518 time for calcul the mask position with numpy : 0.12635135650634766 nb_pixel_total : 20326 time to create 1 rle with old method : 0.028844594955444336 length of segment : 329 time for calcul the mask position with numpy : 0.2552213668823242 nb_pixel_total : 98977 time to create 1 rle with old method : 0.11055612564086914 length of segment : 572 time for calcul the mask position with numpy : 0.14960432052612305 nb_pixel_total : 73475 time to create 1 rle with old method : 0.22071361541748047 length of segment : 345 time for calcul the mask position with numpy : 0.15498781204223633 nb_pixel_total : 54800 time to create 1 rle with old method : 0.10310125350952148 length of segment : 372 time for calcul the mask position with numpy : 0.015325069427490234 nb_pixel_total : 25448 time to create 1 rle with old method : 0.04714012145996094 length of segment : 360 time for calcul the mask position with numpy : 0.020038127899169922 nb_pixel_total : 5994 time to create 1 rle with old method : 0.009950637817382812 length of segment : 73 time for calcul the mask position with numpy : 0.022223234176635742 nb_pixel_total : 25440 time to create 1 rle with old method : 0.0475618839263916 length of segment : 230 time for calcul the mask position with numpy : 0.037380218505859375 nb_pixel_total : 11603 time to create 1 rle with old method : 0.017760276794433594 length of segment : 128 time for calcul the mask position with numpy : 0.13169264793395996 nb_pixel_total : 58806 time to create 1 rle with old method : 0.07123136520385742 length of segment : 280 time for calcul the mask position with numpy : 0.05806779861450195 nb_pixel_total : 35828 time to create 1 rle with old method : 0.043193817138671875 length of segment : 406 time for calcul the mask position with numpy : 0.5729584693908691 nb_pixel_total : 206285 time to create 1 rle with new method : 0.022819995880126953 length of segment : 696 time for calcul the mask position with numpy : 0.11548280715942383 nb_pixel_total : 26337 time to create 1 rle with old method : 0.03320813179016113 length of segment : 288 time for calcul the mask position with numpy : 0.06673479080200195 nb_pixel_total : 24409 time to create 1 rle with old method : 0.02982807159423828 length of segment : 159 time for calcul the mask position with numpy : 0.056345224380493164 nb_pixel_total : 30033 time to create 1 rle with old method : 0.07646059989929199 length of segment : 128 time for calcul the mask position with numpy : 0.023420095443725586 nb_pixel_total : 21670 time to create 1 rle with old method : 0.028085947036743164 length of segment : 202 time for calcul the mask position with numpy : 0.07516121864318848 nb_pixel_total : 60729 time to create 1 rle with old method : 0.06995725631713867 length of segment : 430 time for calcul the mask position with numpy : 0.0514066219329834 nb_pixel_total : 16321 time to create 1 rle with old method : 0.023377418518066406 length of segment : 138 time for calcul the mask position with numpy : 0.1915740966796875 nb_pixel_total : 64776 time to create 1 rle with old method : 0.07628607749938965 length of segment : 390 time for calcul the mask position with numpy : 0.07225394248962402 nb_pixel_total : 23048 time to create 1 rle with old method : 0.02890181541442871 length of segment : 263 time for calcul the mask position with numpy : 0.0016567707061767578 nb_pixel_total : 28706 time to create 1 rle with old method : 0.033091068267822266 length of segment : 239 time for calcul the mask position with numpy : 0.047458648681640625 nb_pixel_total : 17307 time to create 1 rle with old method : 0.02371072769165039 length of segment : 269 time for calcul the mask position with numpy : 0.0052738189697265625 nb_pixel_total : 19595 time to create 1 rle with old method : 0.023871898651123047 length of segment : 140 time for calcul the mask position with numpy : 0.00955057144165039 nb_pixel_total : 5778 time to create 1 rle with old method : 0.011378288269042969 length of segment : 100 time for calcul the mask position with numpy : 0.035222768783569336 nb_pixel_total : 22766 time to create 1 rle with old method : 0.02813577651977539 length of segment : 224 time for calcul the mask position with numpy : 0.0038955211639404297 nb_pixel_total : 7820 time to create 1 rle with old method : 0.010957002639770508 length of segment : 128 time for calcul the mask position with numpy : 0.04389357566833496 nb_pixel_total : 25820 time to create 1 rle with old method : 0.03429865837097168 length of segment : 180 time for calcul the mask position with numpy : 0.10637068748474121 nb_pixel_total : 43168 time to create 1 rle with old method : 0.05281424522399902 length of segment : 236 time for calcul the mask position with numpy : 0.020809173583984375 nb_pixel_total : 5937 time to create 1 rle with old method : 0.01881241798400879 length of segment : 200 time for calcul the mask position with numpy : 0.5745656490325928 nb_pixel_total : 232758 time to create 1 rle with new method : 0.023358583450317383 length of segment : 706 time for calcul the mask position with numpy : 0.24511194229125977 nb_pixel_total : 43967 time to create 1 rle with old method : 0.06824183464050293 length of segment : 385 time for calcul the mask position with numpy : 0.17849993705749512 nb_pixel_total : 75312 time to create 1 rle with old method : 0.08461546897888184 length of segment : 625 time for calcul the mask position with numpy : 0.22043752670288086 nb_pixel_total : 86944 time to create 1 rle with old method : 0.10053110122680664 length of segment : 464 time for calcul the mask position with numpy : 0.004513263702392578 nb_pixel_total : 11836 time to create 1 rle with old method : 0.016491413116455078 length of segment : 108 time for calcul the mask position with numpy : 0.09647488594055176 nb_pixel_total : 34618 time to create 1 rle with old method : 0.044060468673706055 length of segment : 224 time for calcul the mask position with numpy : 0.000194549560546875 nb_pixel_total : 4748 time to create 1 rle with old method : 0.006887197494506836 length of segment : 68 time for calcul the mask position with numpy : 0.15482020378112793 nb_pixel_total : 26939 time to create 1 rle with old method : 0.035579681396484375 length of segment : 255 time for calcul the mask position with numpy : 0.262662410736084 nb_pixel_total : 209226 time to create 1 rle with new method : 0.026429176330566406 length of segment : 613 time for calcul the mask position with numpy : 0.024704933166503906 nb_pixel_total : 8753 time to create 1 rle with old method : 0.016465187072753906 length of segment : 106 time for calcul the mask position with numpy : 0.04885077476501465 nb_pixel_total : 49333 time to create 1 rle with old method : 0.061038970947265625 length of segment : 236 time for calcul the mask position with numpy : 0.010854959487915039 nb_pixel_total : 11460 time to create 1 rle with old method : 0.018802881240844727 length of segment : 115 time for calcul the mask position with numpy : 0.047460317611694336 nb_pixel_total : 20089 time to create 1 rle with old method : 0.026325464248657227 length of segment : 178 time for calcul the mask position with numpy : 0.025589704513549805 nb_pixel_total : 32773 time to create 1 rle with old method : 0.040375471115112305 length of segment : 269 time for calcul the mask position with numpy : 0.056321144104003906 nb_pixel_total : 66894 time to create 1 rle with old method : 0.0825338363647461 length of segment : 365 time for calcul the mask position with numpy : 0.037285804748535156 nb_pixel_total : 17966 time to create 1 rle with old method : 0.02185964584350586 length of segment : 131 time for calcul the mask position with numpy : 0.21671438217163086 nb_pixel_total : 146570 time to create 1 rle with old method : 0.17790842056274414 length of segment : 455 time for calcul the mask position with numpy : 0.23779034614562988 nb_pixel_total : 282694 time to create 1 rle with new method : 0.026549577713012695 length of segment : 1198 time for calcul the mask position with numpy : 0.13244843482971191 nb_pixel_total : 79341 time to create 1 rle with old method : 0.09026169776916504 length of segment : 299 time for calcul the mask position with numpy : 0.04731416702270508 nb_pixel_total : 98010 time to create 1 rle with old method : 0.11359119415283203 length of segment : 444 time for calcul the mask position with numpy : 0.1889660358428955 nb_pixel_total : 87010 time to create 1 rle with old method : 0.10249853134155273 length of segment : 384 time for calcul the mask position with numpy : 0.30926966667175293 nb_pixel_total : 233009 time to create 1 rle with new method : 0.037398338317871094 length of segment : 330 time for calcul the mask position with numpy : 0.18811845779418945 nb_pixel_total : 128921 time to create 1 rle with old method : 0.16269969940185547 length of segment : 512 time for calcul the mask position with numpy : 0.2429337501525879 nb_pixel_total : 129825 time to create 1 rle with old method : 0.17404508590698242 length of segment : 341 time for calcul the mask position with numpy : 0.1395888328552246 nb_pixel_total : 33007 time to create 1 rle with old method : 0.05040621757507324 length of segment : 306 time for calcul the mask position with numpy : 0.06585502624511719 nb_pixel_total : 21450 time to create 1 rle with old method : 0.029573678970336914 length of segment : 160 time for calcul the mask position with numpy : 0.07189321517944336 nb_pixel_total : 30279 time to create 1 rle with old method : 0.03860807418823242 length of segment : 306 time for calcul the mask position with numpy : 0.01698756217956543 nb_pixel_total : 25727 time to create 1 rle with old method : 0.031210899353027344 length of segment : 239 time for calcul the mask position with numpy : 0.04319620132446289 nb_pixel_total : 62619 time to create 1 rle with old method : 0.07261252403259277 length of segment : 220 time for calcul the mask position with numpy : 0.04753375053405762 nb_pixel_total : 29350 time to create 1 rle with old method : 0.0369257926940918 length of segment : 220 time for calcul the mask position with numpy : 0.10085892677307129 nb_pixel_total : 57148 time to create 1 rle with old method : 0.06716251373291016 length of segment : 348 time for calcul the mask position with numpy : 0.020620346069335938 nb_pixel_total : 18473 time to create 1 rle with old method : 0.02617645263671875 length of segment : 219 time for calcul the mask position with numpy : 0.04869508743286133 nb_pixel_total : 15302 time to create 1 rle with old method : 0.021221637725830078 length of segment : 231 time for calcul the mask position with numpy : 0.04405713081359863 nb_pixel_total : 61363 time to create 1 rle with old method : 0.0786902904510498 length of segment : 504 time for calcul the mask position with numpy : 0.17524170875549316 nb_pixel_total : 129720 time to create 1 rle with old method : 0.14524507522583008 length of segment : 407 time for calcul the mask position with numpy : 0.0370028018951416 nb_pixel_total : 19326 time to create 1 rle with old method : 0.02759528160095215 length of segment : 330 time for calcul the mask position with numpy : 0.15128612518310547 nb_pixel_total : 152071 time to create 1 rle with new method : 0.01022028923034668 length of segment : 514 time for calcul the mask position with numpy : 0.014203548431396484 nb_pixel_total : 20424 time to create 1 rle with old method : 0.026634931564331055 length of segment : 215 time for calcul the mask position with numpy : 0.08497214317321777 nb_pixel_total : 75664 time to create 1 rle with old method : 0.08548998832702637 length of segment : 471 time for calcul the mask position with numpy : 0.04255366325378418 nb_pixel_total : 87648 time to create 1 rle with old method : 0.1014702320098877 length of segment : 244 time for calcul the mask position with numpy : 0.00037360191345214844 nb_pixel_total : 18001 time to create 1 rle with old method : 0.02077198028564453 length of segment : 226 time for calcul the mask position with numpy : 0.09824490547180176 nb_pixel_total : 53507 time to create 1 rle with old method : 0.06830763816833496 length of segment : 360 time for calcul the mask position with numpy : 0.02701854705810547 nb_pixel_total : 12082 time to create 1 rle with old method : 0.018319129943847656 length of segment : 152 time for calcul the mask position with numpy : 0.1942298412322998 nb_pixel_total : 246501 time to create 1 rle with new method : 0.01279759407043457 length of segment : 462 time for calcul the mask position with numpy : 0.025345325469970703 nb_pixel_total : 10600 time to create 1 rle with old method : 0.014681100845336914 length of segment : 96 time for calcul the mask position with numpy : 0.24119186401367188 nb_pixel_total : 251902 time to create 1 rle with new method : 0.01615285873413086 length of segment : 1012 time for calcul the mask position with numpy : 0.07578516006469727 nb_pixel_total : 61713 time to create 1 rle with old method : 0.0998682975769043 length of segment : 531 time for calcul the mask position with numpy : 0.0017697811126708984 nb_pixel_total : 15009 time to create 1 rle with old method : 0.022007465362548828 length of segment : 161 time for calcul the mask position with numpy : 0.017013072967529297 nb_pixel_total : 3927 time to create 1 rle with old method : 0.0049016475677490234 length of segment : 109 time for calcul the mask position with numpy : 0.01203608512878418 nb_pixel_total : 19727 time to create 1 rle with old method : 0.028392553329467773 length of segment : 186 time for calcul the mask position with numpy : 0.03102731704711914 nb_pixel_total : 19436 time to create 1 rle with old method : 0.02637624740600586 length of segment : 188 time for calcul the mask position with numpy : 0.004521369934082031 nb_pixel_total : 3066 time to create 1 rle with old method : 0.0037622451782226562 length of segment : 84 time for calcul the mask position with numpy : 0.005533695220947266 nb_pixel_total : 19647 time to create 1 rle with old method : 0.02462458610534668 length of segment : 250 time for calcul the mask position with numpy : 0.1045835018157959 nb_pixel_total : 60620 time to create 1 rle with old method : 0.07285094261169434 length of segment : 347 time for calcul the mask position with numpy : 0.0569608211517334 nb_pixel_total : 33950 time to create 1 rle with old method : 0.05014395713806152 length of segment : 275 time for calcul the mask position with numpy : 0.16037464141845703 nb_pixel_total : 245544 time to create 1 rle with new method : 0.017499446868896484 length of segment : 377 time for calcul the mask position with numpy : 0.042156219482421875 nb_pixel_total : 14611 time to create 1 rle with old method : 0.020852327346801758 length of segment : 162 time for calcul the mask position with numpy : 0.041722774505615234 nb_pixel_total : 19076 time to create 1 rle with old method : 0.028882980346679688 length of segment : 238 time for calcul the mask position with numpy : 0.09352374076843262 nb_pixel_total : 76904 time to create 1 rle with old method : 0.14150285720825195 length of segment : 266 time for calcul the mask position with numpy : 0.036978721618652344 nb_pixel_total : 8137 time to create 1 rle with old method : 0.011826515197753906 length of segment : 140 time for calcul the mask position with numpy : 0.02754068374633789 nb_pixel_total : 5323 time to create 1 rle with old method : 0.007956981658935547 length of segment : 153 time for calcul the mask position with numpy : 0.00014162063598632812 nb_pixel_total : 6427 time to create 1 rle with old method : 0.007638454437255859 length of segment : 97 time for calcul the mask position with numpy : 0.020516157150268555 nb_pixel_total : 21886 time to create 1 rle with old method : 0.031156539916992188 length of segment : 186 time for calcul the mask position with numpy : 0.007414102554321289 nb_pixel_total : 17241 time to create 1 rle with old method : 0.030671119689941406 length of segment : 227 time for calcul the mask position with numpy : 0.28987741470336914 nb_pixel_total : 544763 time to create 1 rle with new method : 0.08276939392089844 length of segment : 1057 time for calcul the mask position with numpy : 0.0887763500213623 nb_pixel_total : 31816 time to create 1 rle with old method : 0.04885745048522949 length of segment : 207 time for calcul the mask position with numpy : 0.13298702239990234 nb_pixel_total : 89738 time to create 1 rle with old method : 0.10666751861572266 length of segment : 318 time for calcul the mask position with numpy : 0.07999992370605469 nb_pixel_total : 78771 time to create 1 rle with old method : 0.08978605270385742 length of segment : 217 time for calcul the mask position with numpy : 0.03225207328796387 nb_pixel_total : 19435 time to create 1 rle with old method : 0.025162458419799805 length of segment : 210 time for calcul the mask position with numpy : 0.06089615821838379 nb_pixel_total : 34122 time to create 1 rle with old method : 0.04511690139770508 length of segment : 220 time for calcul the mask position with numpy : 0.07530713081359863 nb_pixel_total : 34557 time to create 1 rle with old method : 0.05105113983154297 length of segment : 222 time for calcul the mask position with numpy : 0.10890507698059082 nb_pixel_total : 42149 time to create 1 rle with old method : 0.06015944480895996 length of segment : 203 time for calcul the mask position with numpy : 0.012490272521972656 nb_pixel_total : 12022 time to create 1 rle with old method : 0.018367290496826172 length of segment : 124 time for calcul the mask position with numpy : 0.22016358375549316 nb_pixel_total : 163031 time to create 1 rle with new method : 0.009938955307006836 length of segment : 487 time for calcul the mask position with numpy : 0.15405654907226562 nb_pixel_total : 80602 time to create 1 rle with old method : 0.10743594169616699 length of segment : 341 time for calcul the mask position with numpy : 0.06586623191833496 nb_pixel_total : 31895 time to create 1 rle with old method : 0.040702104568481445 length of segment : 243 time for calcul the mask position with numpy : 0.006198883056640625 nb_pixel_total : 10112 time to create 1 rle with old method : 0.013469219207763672 length of segment : 135 time for calcul the mask position with numpy : 0.1393132209777832 nb_pixel_total : 56746 time to create 1 rle with old method : 0.06772994995117188 length of segment : 256 time for calcul the mask position with numpy : 0.01537466049194336 nb_pixel_total : 28232 time to create 1 rle with old method : 0.0349733829498291 length of segment : 238 time for calcul the mask position with numpy : 0.13144230842590332 nb_pixel_total : 78539 time to create 1 rle with old method : 0.0936589241027832 length of segment : 502 time for calcul the mask position with numpy : 0.02210259437561035 nb_pixel_total : 3960 time to create 1 rle with old method : 0.0063555240631103516 length of segment : 107 time for calcul the mask position with numpy : 0.03411722183227539 nb_pixel_total : 13547 time to create 1 rle with old method : 0.019184350967407227 length of segment : 131 time for calcul the mask position with numpy : 0.13162565231323242 nb_pixel_total : 57845 time to create 1 rle with old method : 0.07776880264282227 length of segment : 410 time for calcul the mask position with numpy : 0.03755474090576172 nb_pixel_total : 11358 time to create 1 rle with old method : 0.013021469116210938 length of segment : 194 time for calcul the mask position with numpy : 0.05622529983520508 nb_pixel_total : 7123 time to create 1 rle with old method : 0.012825965881347656 length of segment : 106 time for calcul the mask position with numpy : 0.17710590362548828 nb_pixel_total : 24481 time to create 1 rle with old method : 0.04026198387145996 length of segment : 357 time for calcul the mask position with numpy : 0.35214877128601074 nb_pixel_total : 127996 time to create 1 rle with old method : 0.1868884563446045 length of segment : 473 time for calcul the mask position with numpy : 0.0029096603393554688 nb_pixel_total : 11345 time to create 1 rle with old method : 0.015127897262573242 length of segment : 122 time for calcul the mask position with numpy : 0.044075727462768555 nb_pixel_total : 39435 time to create 1 rle with old method : 0.04736900329589844 length of segment : 570 time for calcul the mask position with numpy : 0.025269031524658203 nb_pixel_total : 8708 time to create 1 rle with old method : 0.013118743896484375 length of segment : 108 time for calcul the mask position with numpy : 0.0009891986846923828 nb_pixel_total : 39588 time to create 1 rle with old method : 0.04616665840148926 length of segment : 266 time for calcul the mask position with numpy : 0.12591886520385742 nb_pixel_total : 43599 time to create 1 rle with old method : 0.053743839263916016 length of segment : 219 time for calcul the mask position with numpy : 0.13663268089294434 nb_pixel_total : 32947 time to create 1 rle with old method : 0.040047645568847656 length of segment : 322 time for calcul the mask position with numpy : 0.250438928604126 nb_pixel_total : 62836 time to create 1 rle with old method : 0.07642149925231934 length of segment : 407 time for calcul the mask position with numpy : 0.04055047035217285 nb_pixel_total : 8767 time to create 1 rle with old method : 0.014258861541748047 length of segment : 97 time for calcul the mask position with numpy : 0.055356740951538086 nb_pixel_total : 11545 time to create 1 rle with old method : 0.02533435821533203 length of segment : 147 time for calcul the mask position with numpy : 0.14751148223876953 nb_pixel_total : 40307 time to create 1 rle with old method : 0.04841446876525879 length of segment : 294 time for calcul the mask position with numpy : 0.028125286102294922 nb_pixel_total : 9287 time to create 1 rle with old method : 0.013045549392700195 length of segment : 123 time for calcul the mask position with numpy : 0.055565595626831055 nb_pixel_total : 18643 time to create 1 rle with old method : 0.026346445083618164 length of segment : 126 time for calcul the mask position with numpy : 0.07584571838378906 nb_pixel_total : 26649 time to create 1 rle with old method : 0.03771495819091797 length of segment : 191 time for calcul the mask position with numpy : 0.039714813232421875 nb_pixel_total : 7031 time to create 1 rle with old method : 0.012008428573608398 length of segment : 121 time for calcul the mask position with numpy : 0.0423436164855957 nb_pixel_total : 13534 time to create 1 rle with old method : 0.021457195281982422 length of segment : 145 time for calcul the mask position with numpy : 0.02911972999572754 nb_pixel_total : 5042 time to create 1 rle with old method : 0.007599592208862305 length of segment : 104 time for calcul the mask position with numpy : 0.026823043823242188 nb_pixel_total : 22306 time to create 1 rle with old method : 0.03101825714111328 length of segment : 134 time for calcul the mask position with numpy : 0.41891932487487793 nb_pixel_total : 128499 time to create 1 rle with old method : 0.14862680435180664 length of segment : 616 time for calcul the mask position with numpy : 0.07255792617797852 nb_pixel_total : 26736 time to create 1 rle with old method : 0.04311561584472656 length of segment : 237 time for calcul the mask position with numpy : 0.2521240711212158 nb_pixel_total : 110604 time to create 1 rle with old method : 0.13161587715148926 length of segment : 369 time for calcul the mask position with numpy : 0.029171466827392578 nb_pixel_total : 8826 time to create 1 rle with old method : 0.014763116836547852 length of segment : 154 time for calcul the mask position with numpy : 0.02621173858642578 nb_pixel_total : 6287 time to create 1 rle with old method : 0.011731624603271484 length of segment : 114 time for calcul the mask position with numpy : 0.03632974624633789 nb_pixel_total : 21067 time to create 1 rle with old method : 0.027976274490356445 length of segment : 180 time for calcul the mask position with numpy : 0.1338670253753662 nb_pixel_total : 71530 time to create 1 rle with old method : 0.09309577941894531 length of segment : 346 time for calcul the mask position with numpy : 0.06562638282775879 nb_pixel_total : 19344 time to create 1 rle with old method : 0.022408723831176758 length of segment : 174 time for calcul the mask position with numpy : 0.180830717086792 nb_pixel_total : 76374 time to create 1 rle with old method : 0.08845782279968262 length of segment : 330 time for calcul the mask position with numpy : 0.04345226287841797 nb_pixel_total : 21851 time to create 1 rle with old method : 0.030230045318603516 length of segment : 229 time for calcul the mask position with numpy : 0.06477856636047363 nb_pixel_total : 26651 time to create 1 rle with old method : 0.03281116485595703 length of segment : 298 time for calcul the mask position with numpy : 0.11716794967651367 nb_pixel_total : 87330 time to create 1 rle with old method : 0.10169792175292969 length of segment : 347 time for calcul the mask position with numpy : 0.02752852439880371 nb_pixel_total : 6891 time to create 1 rle with old method : 0.011599063873291016 length of segment : 104 time for calcul the mask position with numpy : 0.09007930755615234 nb_pixel_total : 37821 time to create 1 rle with old method : 0.0513153076171875 length of segment : 213 time for calcul the mask position with numpy : 0.028966426849365234 nb_pixel_total : 18300 time to create 1 rle with old method : 0.02980637550354004 length of segment : 179 time for calcul the mask position with numpy : 0.1531352996826172 nb_pixel_total : 110958 time to create 1 rle with old method : 0.12602567672729492 length of segment : 365 time for calcul the mask position with numpy : 0.03411269187927246 nb_pixel_total : 13785 time to create 1 rle with old method : 0.0209805965423584 length of segment : 195 time for calcul the mask position with numpy : 0.020260095596313477 nb_pixel_total : 5596 time to create 1 rle with old method : 0.009750604629516602 length of segment : 110 time for calcul the mask position with numpy : 0.265392541885376 nb_pixel_total : 284757 time to create 1 rle with new method : 0.026499032974243164 length of segment : 470 time for calcul the mask position with numpy : 0.013781070709228516 nb_pixel_total : 10428 time to create 1 rle with old method : 0.01468515396118164 length of segment : 117 time for calcul the mask position with numpy : 0.5147020816802979 nb_pixel_total : 418799 time to create 1 rle with new method : 0.027390718460083008 length of segment : 659 time for calcul the mask position with numpy : 0.03281712532043457 nb_pixel_total : 87059 time to create 1 rle with old method : 0.09809446334838867 length of segment : 341 time for calcul the mask position with numpy : 0.28592681884765625 nb_pixel_total : 306643 time to create 1 rle with new method : 0.03048419952392578 length of segment : 736 time for calcul the mask position with numpy : 0.08163928985595703 nb_pixel_total : 82063 time to create 1 rle with old method : 0.09491705894470215 length of segment : 511 time for calcul the mask position with numpy : 0.0002560615539550781 nb_pixel_total : 5599 time to create 1 rle with old method : 0.007383108139038086 length of segment : 80 time for calcul the mask position with numpy : 0.02914881706237793 nb_pixel_total : 58945 time to create 1 rle with old method : 0.07134103775024414 length of segment : 308 time for calcul the mask position with numpy : 0.06312990188598633 nb_pixel_total : 39198 time to create 1 rle with old method : 0.050873756408691406 length of segment : 288 time for calcul the mask position with numpy : 0.014376640319824219 nb_pixel_total : 6559 time to create 1 rle with old method : 0.012015581130981445 length of segment : 107 time for calcul the mask position with numpy : 0.04228091239929199 nb_pixel_total : 35607 time to create 1 rle with old method : 0.06052899360656738 length of segment : 263 time for calcul the mask position with numpy : 0.007783412933349609 nb_pixel_total : 11721 time to create 1 rle with old method : 0.0166323184967041 length of segment : 142 time for calcul the mask position with numpy : 0.0055179595947265625 nb_pixel_total : 8950 time to create 1 rle with old method : 0.01353597640991211 length of segment : 47 time for calcul the mask position with numpy : 0.10266399383544922 nb_pixel_total : 266692 time to create 1 rle with new method : 0.018341779708862305 length of segment : 420 time for calcul the mask position with numpy : 0.01178288459777832 nb_pixel_total : 7494 time to create 1 rle with old method : 0.00968313217163086 length of segment : 75 time for calcul the mask position with numpy : 0.05124473571777344 nb_pixel_total : 52977 time to create 1 rle with old method : 0.06591606140136719 length of segment : 319 time for calcul the mask position with numpy : 0.026454687118530273 nb_pixel_total : 13346 time to create 1 rle with old method : 0.019888877868652344 length of segment : 159 time for calcul the mask position with numpy : 0.0036056041717529297 nb_pixel_total : 14143 time to create 1 rle with old method : 0.01848435401916504 length of segment : 137 time for calcul the mask position with numpy : 0.07491731643676758 nb_pixel_total : 75213 time to create 1 rle with old method : 0.08572721481323242 length of segment : 275 time for calcul the mask position with numpy : 0.03390908241271973 nb_pixel_total : 83852 time to create 1 rle with old method : 0.0971217155456543 length of segment : 407 time for calcul the mask position with numpy : 0.058091163635253906 nb_pixel_total : 44865 time to create 1 rle with old method : 0.05394101142883301 length of segment : 476 time for calcul the mask position with numpy : 0.028108835220336914 nb_pixel_total : 29005 time to create 1 rle with old method : 0.0499873161315918 length of segment : 185 time for calcul the mask position with numpy : 0.03905510902404785 nb_pixel_total : 29588 time to create 1 rle with old method : 0.03860878944396973 length of segment : 367 time for calcul the mask position with numpy : 0.009456157684326172 nb_pixel_total : 8987 time to create 1 rle with old method : 0.013806581497192383 length of segment : 76 time for calcul the mask position with numpy : 0.024857044219970703 nb_pixel_total : 45199 time to create 1 rle with old method : 0.05221724510192871 length of segment : 811 time for calcul the mask position with numpy : 0.058012962341308594 nb_pixel_total : 69857 time to create 1 rle with old method : 0.08006405830383301 length of segment : 351 time for calcul the mask position with numpy : 0.08545112609863281 nb_pixel_total : 221630 time to create 1 rle with new method : 0.016650915145874023 length of segment : 630 time for calcul the mask position with numpy : 0.009373664855957031 nb_pixel_total : 77489 time to create 1 rle with old method : 0.09014153480529785 length of segment : 681 time for calcul the mask position with numpy : 0.011007547378540039 nb_pixel_total : 43650 time to create 1 rle with old method : 0.054291725158691406 length of segment : 230 time for calcul the mask position with numpy : 0.1222834587097168 nb_pixel_total : 465126 time to create 1 rle with new method : 0.021687984466552734 length of segment : 812 time for calcul the mask position with numpy : 0.0019421577453613281 nb_pixel_total : 21910 time to create 1 rle with old method : 0.025895357131958008 length of segment : 117 time for calcul the mask position with numpy : 0.0008902549743652344 nb_pixel_total : 15452 time to create 1 rle with old method : 0.018186569213867188 length of segment : 207 time for calcul the mask position with numpy : 0.0033054351806640625 nb_pixel_total : 11693 time to create 1 rle with old method : 0.014656543731689453 length of segment : 146 time for calcul the mask position with numpy : 0.0029959678649902344 nb_pixel_total : 17910 time to create 1 rle with old method : 0.022469758987426758 length of segment : 150 time for calcul the mask position with numpy : 0.0048274993896484375 nb_pixel_total : 26799 time to create 1 rle with old method : 0.031484127044677734 length of segment : 179 time for calcul the mask position with numpy : 0.006951332092285156 nb_pixel_total : 47428 time to create 1 rle with old method : 0.054206132888793945 length of segment : 373 time for calcul the mask position with numpy : 0.00043392181396484375 nb_pixel_total : 7954 time to create 1 rle with old method : 0.009595394134521484 length of segment : 143 time for calcul the mask position with numpy : 0.0162351131439209 nb_pixel_total : 82510 time to create 1 rle with old method : 0.09706449508666992 length of segment : 556 time for calcul the mask position with numpy : 0.03362154960632324 nb_pixel_total : 120343 time to create 1 rle with old method : 0.16515779495239258 length of segment : 463 time for calcul the mask position with numpy : 0.12688899040222168 nb_pixel_total : 334782 time to create 1 rle with new method : 0.02965688705444336 length of segment : 639 time for calcul the mask position with numpy : 0.007321596145629883 nb_pixel_total : 45726 time to create 1 rle with old method : 0.05373096466064453 length of segment : 218 time for calcul the mask position with numpy : 0.08441734313964844 nb_pixel_total : 485594 time to create 1 rle with new method : 0.020650386810302734 length of segment : 846 time for calcul the mask position with numpy : 0.0165407657623291 nb_pixel_total : 101888 time to create 1 rle with old method : 0.1405487060546875 length of segment : 529 time for calcul the mask position with numpy : 0.011561155319213867 nb_pixel_total : 25252 time to create 1 rle with old method : 0.03281855583190918 length of segment : 233 time for calcul the mask position with numpy : 0.005817890167236328 nb_pixel_total : 62531 time to create 1 rle with old method : 0.07737112045288086 length of segment : 243 time for calcul the mask position with numpy : 0.03597664833068848 nb_pixel_total : 283450 time to create 1 rle with new method : 0.01485753059387207 length of segment : 662 time for calcul the mask position with numpy : 0.002335071563720703 nb_pixel_total : 1850 time to create 1 rle with old method : 0.0022776126861572266 length of segment : 74 time for calcul the mask position with numpy : 0.0014147758483886719 nb_pixel_total : 34056 time to create 1 rle with old method : 0.039286136627197266 length of segment : 358 time for calcul the mask position with numpy : 0.003915071487426758 nb_pixel_total : 28891 time to create 1 rle with old method : 0.035388946533203125 length of segment : 267 time for calcul the mask position with numpy : 0.002899646759033203 nb_pixel_total : 29856 time to create 1 rle with old method : 0.034529685974121094 length of segment : 236 time for calcul the mask position with numpy : 0.04409623146057129 nb_pixel_total : 131699 time to create 1 rle with old method : 0.14978766441345215 length of segment : 438 time for calcul the mask position with numpy : 0.009157896041870117 nb_pixel_total : 36944 time to create 1 rle with old method : 0.04378938674926758 length of segment : 208 time for calcul the mask position with numpy : 0.027777671813964844 nb_pixel_total : 75086 time to create 1 rle with old method : 0.08479738235473633 length of segment : 512 time for calcul the mask position with numpy : 0.01146078109741211 nb_pixel_total : 43747 time to create 1 rle with old method : 0.051552772521972656 length of segment : 272 time for calcul the mask position with numpy : 0.021188974380493164 nb_pixel_total : 78860 time to create 1 rle with old method : 0.14425969123840332 length of segment : 534 time for calcul the mask position with numpy : 0.004296064376831055 nb_pixel_total : 33776 time to create 1 rle with old method : 0.0439760684967041 length of segment : 228 time for calcul the mask position with numpy : 0.0031311511993408203 nb_pixel_total : 20571 time to create 1 rle with old method : 0.02419257164001465 length of segment : 163 time for calcul the mask position with numpy : 0.0015931129455566406 nb_pixel_total : 14814 time to create 1 rle with old method : 0.017464637756347656 length of segment : 144 time for calcul the mask position with numpy : 0.024518966674804688 nb_pixel_total : 98197 time to create 1 rle with old method : 0.10997962951660156 length of segment : 476 time for calcul the mask position with numpy : 0.004448652267456055 nb_pixel_total : 23134 time to create 1 rle with old method : 0.0317838191986084 length of segment : 165 time for calcul the mask position with numpy : 0.017705440521240234 nb_pixel_total : 14228 time to create 1 rle with old method : 0.021706581115722656 length of segment : 141 time for calcul the mask position with numpy : 0.032285213470458984 nb_pixel_total : 26509 time to create 1 rle with old method : 0.03643012046813965 length of segment : 186 time for calcul the mask position with numpy : 0.0057752132415771484 nb_pixel_total : 11315 time to create 1 rle with old method : 0.015144824981689453 length of segment : 155 time for calcul the mask position with numpy : 0.08361387252807617 nb_pixel_total : 185975 time to create 1 rle with new method : 0.02599501609802246 length of segment : 757 time for calcul the mask position with numpy : 0.013233184814453125 nb_pixel_total : 50711 time to create 1 rle with old method : 0.05842781066894531 length of segment : 271 time for calcul the mask position with numpy : 0.0161893367767334 nb_pixel_total : 199468 time to create 1 rle with new method : 0.00802922248840332 length of segment : 572 time for calcul the mask position with numpy : 0.009519100189208984 nb_pixel_total : 24720 time to create 1 rle with old method : 0.05162930488586426 length of segment : 198 time for calcul the mask position with numpy : 0.00189208984375 nb_pixel_total : 25988 time to create 1 rle with old method : 0.030108213424682617 length of segment : 282 time for calcul the mask position with numpy : 0.08148884773254395 nb_pixel_total : 257050 time to create 1 rle with new method : 0.016756534576416016 length of segment : 742 time for calcul the mask position with numpy : 0.0016548633575439453 nb_pixel_total : 12050 time to create 1 rle with old method : 0.014148473739624023 length of segment : 144 time for calcul the mask position with numpy : 0.07335114479064941 nb_pixel_total : 254882 time to create 1 rle with new method : 0.01803112030029297 length of segment : 808 time for calcul the mask position with numpy : 0.0009794235229492188 nb_pixel_total : 15868 time to create 1 rle with old method : 0.018521785736083984 length of segment : 198 time for calcul the mask position with numpy : 0.0011625289916992188 nb_pixel_total : 7630 time to create 1 rle with old method : 0.009418010711669922 length of segment : 105 time for calcul the mask position with numpy : 0.05127382278442383 nb_pixel_total : 293419 time to create 1 rle with new method : 0.02371072769165039 length of segment : 445 time for calcul the mask position with numpy : 0.001112222671508789 nb_pixel_total : 11100 time to create 1 rle with old method : 0.012712955474853516 length of segment : 123 time for calcul the mask position with numpy : 0.01034855842590332 nb_pixel_total : 53512 time to create 1 rle with old method : 0.060150146484375 length of segment : 412 time for calcul the mask position with numpy : 0.012295961380004883 nb_pixel_total : 64346 time to create 1 rle with old method : 0.07391142845153809 length of segment : 520 time for calcul the mask position with numpy : 0.0012309551239013672 nb_pixel_total : 4861 time to create 1 rle with old method : 0.005677461624145508 length of segment : 80 time for calcul the mask position with numpy : 0.006473064422607422 nb_pixel_total : 40243 time to create 1 rle with old method : 0.04707908630371094 length of segment : 194 time for calcul the mask position with numpy : 0.004276275634765625 nb_pixel_total : 39764 time to create 1 rle with old method : 0.04714083671569824 length of segment : 221 time for calcul the mask position with numpy : 0.05440688133239746 nb_pixel_total : 184735 time to create 1 rle with new method : 0.012693643569946289 length of segment : 667 time for calcul the mask position with numpy : 0.03758573532104492 nb_pixel_total : 29008 time to create 1 rle with old method : 0.0375978946685791 length of segment : 247 time for calcul the mask position with numpy : 0.016283512115478516 nb_pixel_total : 120236 time to create 1 rle with old method : 0.13511037826538086 length of segment : 451 time for calcul the mask position with numpy : 0.01517629623413086 nb_pixel_total : 221993 time to create 1 rle with new method : 0.014419794082641602 length of segment : 362 time for calcul the mask position with numpy : 0.0011250972747802734 nb_pixel_total : 10869 time to create 1 rle with old method : 0.012720108032226562 length of segment : 128 time for calcul the mask position with numpy : 0.002598285675048828 nb_pixel_total : 13166 time to create 1 rle with old method : 0.015586376190185547 length of segment : 188 time for calcul the mask position with numpy : 0.003956317901611328 nb_pixel_total : 47280 time to create 1 rle with old method : 0.057669639587402344 length of segment : 306 time for calcul the mask position with numpy : 0.051943302154541016 nb_pixel_total : 122115 time to create 1 rle with old method : 0.1356348991394043 length of segment : 555 time for calcul the mask position with numpy : 0.024505138397216797 nb_pixel_total : 222863 time to create 1 rle with new method : 0.016604900360107422 length of segment : 735 time for calcul the mask position with numpy : 0.0019788742065429688 nb_pixel_total : 31940 time to create 1 rle with old method : 0.03803539276123047 length of segment : 226 time for calcul the mask position with numpy : 0.004341840744018555 nb_pixel_total : 95235 time to create 1 rle with old method : 0.11404275894165039 length of segment : 398 time for calcul the mask position with numpy : 0.00421142578125 nb_pixel_total : 12570 time to create 1 rle with old method : 0.016663074493408203 length of segment : 160 time for calcul the mask position with numpy : 0.002295255661010742 nb_pixel_total : 19794 time to create 1 rle with old method : 0.02289438247680664 length of segment : 166 time for calcul the mask position with numpy : 0.002797365188598633 nb_pixel_total : 63844 time to create 1 rle with old method : 0.07945466041564941 length of segment : 281 time for calcul the mask position with numpy : 0.00028061866760253906 nb_pixel_total : 5479 time to create 1 rle with old method : 0.0069124698638916016 length of segment : 88 time for calcul the mask position with numpy : 0.006495237350463867 nb_pixel_total : 166966 time to create 1 rle with new method : 0.006176948547363281 length of segment : 553 time for calcul the mask position with numpy : 0.00036334991455078125 nb_pixel_total : 13619 time to create 1 rle with old method : 0.015841007232666016 length of segment : 126 time for calcul the mask position with numpy : 0.0021839141845703125 nb_pixel_total : 51542 time to create 1 rle with old method : 0.05776810646057129 length of segment : 341 time for calcul the mask position with numpy : 0.001073598861694336 nb_pixel_total : 30200 time to create 1 rle with old method : 0.034546613693237305 length of segment : 228 time for calcul the mask position with numpy : 0.008188247680664062 nb_pixel_total : 189770 time to create 1 rle with new method : 0.007490634918212891 length of segment : 415 time for calcul the mask position with numpy : 0.0008132457733154297 nb_pixel_total : 6074 time to create 1 rle with old method : 0.0074498653411865234 length of segment : 106 time for calcul the mask position with numpy : 0.015327930450439453 nb_pixel_total : 232436 time to create 1 rle with new method : 0.01080465316772461 length of segment : 733 time for calcul the mask position with numpy : 0.018291950225830078 nb_pixel_total : 188873 time to create 1 rle with new method : 0.007227182388305664 length of segment : 544 time for calcul the mask position with numpy : 0.002473115921020508 nb_pixel_total : 11860 time to create 1 rle with old method : 0.013549566268920898 length of segment : 154 time for calcul the mask position with numpy : 0.0007958412170410156 nb_pixel_total : 7590 time to create 1 rle with old method : 0.008913755416870117 length of segment : 110 time for calcul the mask position with numpy : 0.017924070358276367 nb_pixel_total : 289693 time to create 1 rle with new method : 0.02738165855407715 length of segment : 422 time for calcul the mask position with numpy : 0.008191108703613281 nb_pixel_total : 176503 time to create 1 rle with new method : 0.00961923599243164 length of segment : 385 time for calcul the mask position with numpy : 0.0007665157318115234 nb_pixel_total : 8757 time to create 1 rle with old method : 0.010161161422729492 length of segment : 202 time for calcul the mask position with numpy : 0.002654552459716797 nb_pixel_total : 58275 time to create 1 rle with old method : 0.07901215553283691 length of segment : 239 time for calcul the mask position with numpy : 0.0017237663269042969 nb_pixel_total : 34795 time to create 1 rle with old method : 0.04068112373352051 length of segment : 179 time for calcul the mask position with numpy : 0.0006551742553710938 nb_pixel_total : 8903 time to create 1 rle with old method : 0.010950565338134766 length of segment : 123 time for calcul the mask position with numpy : 0.0024242401123046875 nb_pixel_total : 29709 time to create 1 rle with old method : 0.03508448600769043 length of segment : 290 time for calcul the mask position with numpy : 0.004114389419555664 nb_pixel_total : 32246 time to create 1 rle with old method : 0.03873467445373535 length of segment : 459 time for calcul the mask position with numpy : 0.011111736297607422 nb_pixel_total : 118190 time to create 1 rle with old method : 0.15314435958862305 length of segment : 654 time for calcul the mask position with numpy : 0.005383968353271484 nb_pixel_total : 89808 time to create 1 rle with old method : 0.10101795196533203 length of segment : 334 time for calcul the mask position with numpy : 0.004066944122314453 nb_pixel_total : 93899 time to create 1 rle with old method : 0.1070549488067627 length of segment : 558 time for calcul the mask position with numpy : 0.0017023086547851562 nb_pixel_total : 13978 time to create 1 rle with old method : 0.016458511352539062 length of segment : 244 time for calcul the mask position with numpy : 0.001974344253540039 nb_pixel_total : 27221 time to create 1 rle with old method : 0.03202056884765625 length of segment : 265 time for calcul the mask position with numpy : 0.001203298568725586 nb_pixel_total : 21327 time to create 1 rle with old method : 0.025272130966186523 length of segment : 184 time for calcul the mask position with numpy : 0.013164043426513672 nb_pixel_total : 240412 time to create 1 rle with new method : 0.01547694206237793 length of segment : 651 time for calcul the mask position with numpy : 0.0030753612518310547 nb_pixel_total : 40603 time to create 1 rle with old method : 0.04770350456237793 length of segment : 317 time for calcul the mask position with numpy : 0.003939390182495117 nb_pixel_total : 108918 time to create 1 rle with old method : 0.12657403945922852 length of segment : 493 time for calcul the mask position with numpy : 0.0012507438659667969 nb_pixel_total : 17397 time to create 1 rle with old method : 0.020428895950317383 length of segment : 115 time for calcul the mask position with numpy : 0.0021812915802001953 nb_pixel_total : 19451 time to create 1 rle with old method : 0.02291703224182129 length of segment : 395 time for calcul the mask position with numpy : 0.0007824897766113281 nb_pixel_total : 9458 time to create 1 rle with old method : 0.012427568435668945 length of segment : 72 time for calcul the mask position with numpy : 0.007035017013549805 nb_pixel_total : 118879 time to create 1 rle with old method : 0.14054250717163086 length of segment : 532 time for calcul the mask position with numpy : 0.0014269351959228516 nb_pixel_total : 22143 time to create 1 rle with old method : 0.025560855865478516 length of segment : 167 time for calcul the mask position with numpy : 0.0014431476593017578 nb_pixel_total : 11328 time to create 1 rle with old method : 0.013695478439331055 length of segment : 250 time for calcul the mask position with numpy : 0.005636692047119141 nb_pixel_total : 68207 time to create 1 rle with old method : 0.07724952697753906 length of segment : 639 time for calcul the mask position with numpy : 0.0013155937194824219 nb_pixel_total : 17675 time to create 1 rle with old method : 0.02067708969116211 length of segment : 143 time for calcul the mask position with numpy : 0.0003352165222167969 nb_pixel_total : 1095 time to create 1 rle with old method : 0.0015842914581298828 length of segment : 67 time for calcul the mask position with numpy : 0.001146078109741211 nb_pixel_total : 16925 time to create 1 rle with old method : 0.020334243774414062 length of segment : 107 time for calcul the mask position with numpy : 0.0012748241424560547 nb_pixel_total : 15995 time to create 1 rle with old method : 0.018377065658569336 length of segment : 234 time for calcul the mask position with numpy : 0.0010137557983398438 nb_pixel_total : 14573 time to create 1 rle with old method : 0.016809701919555664 length of segment : 120 time for calcul the mask position with numpy : 0.0014748573303222656 nb_pixel_total : 9578 time to create 1 rle with old method : 0.011654853820800781 length of segment : 123 time for calcul the mask position with numpy : 0.0021262168884277344 nb_pixel_total : 32602 time to create 1 rle with old method : 0.04759478569030762 length of segment : 188 time for calcul the mask position with numpy : 0.015577077865600586 nb_pixel_total : 185960 time to create 1 rle with new method : 0.021487712860107422 length of segment : 538 time for calcul the mask position with numpy : 0.0003261566162109375 nb_pixel_total : 8797 time to create 1 rle with old method : 0.010998964309692383 length of segment : 80 time for calcul the mask position with numpy : 0.002708911895751953 nb_pixel_total : 39388 time to create 1 rle with old method : 0.0451810359954834 length of segment : 366 time for calcul the mask position with numpy : 0.0015599727630615234 nb_pixel_total : 27716 time to create 1 rle with old method : 0.032292842864990234 length of segment : 274 time for calcul the mask position with numpy : 0.003000020980834961 nb_pixel_total : 62286 time to create 1 rle with old method : 0.07175302505493164 length of segment : 328 time for calcul the mask position with numpy : 0.0011737346649169922 nb_pixel_total : 9460 time to create 1 rle with old method : 0.011577844619750977 length of segment : 208 time for calcul the mask position with numpy : 0.003031015396118164 nb_pixel_total : 69958 time to create 1 rle with old method : 0.08118176460266113 length of segment : 410 time for calcul the mask position with numpy : 0.0020148754119873047 nb_pixel_total : 25489 time to create 1 rle with old method : 0.029484272003173828 length of segment : 255 time for calcul the mask position with numpy : 0.00023794174194335938 nb_pixel_total : 7716 time to create 1 rle with old method : 0.00953054428100586 length of segment : 119 time for calcul the mask position with numpy : 0.0033991336822509766 nb_pixel_total : 67152 time to create 1 rle with old method : 0.0755159854888916 length of segment : 311 time for calcul the mask position with numpy : 0.0007476806640625 nb_pixel_total : 22419 time to create 1 rle with old method : 0.026441097259521484 length of segment : 224 time for calcul the mask position with numpy : 0.009299516677856445 nb_pixel_total : 208891 time to create 1 rle with new method : 0.0165407657623291 length of segment : 326 time for calcul the mask position with numpy : 0.0006535053253173828 nb_pixel_total : 10670 time to create 1 rle with old method : 0.012430429458618164 length of segment : 164 time for calcul the mask position with numpy : 0.0014209747314453125 nb_pixel_total : 44328 time to create 1 rle with old method : 0.051215171813964844 length of segment : 305 time for calcul the mask position with numpy : 0.010747671127319336 nb_pixel_total : 287447 time to create 1 rle with new method : 0.01547861099243164 length of segment : 918 time for calcul the mask position with numpy : 0.0005915164947509766 nb_pixel_total : 14086 time to create 1 rle with old method : 0.016599416732788086 length of segment : 144 time for calcul the mask position with numpy : 0.007600069046020508 nb_pixel_total : 298589 time to create 1 rle with new method : 0.013576030731201172 length of segment : 369 time for calcul the mask position with numpy : 0.0011882781982421875 nb_pixel_total : 26951 time to create 1 rle with old method : 0.03223085403442383 length of segment : 297 time for calcul the mask position with numpy : 0.004439592361450195 nb_pixel_total : 107421 time to create 1 rle with old method : 0.12007880210876465 length of segment : 402 time for calcul the mask position with numpy : 0.0010738372802734375 nb_pixel_total : 18987 time to create 1 rle with old method : 0.02137923240661621 length of segment : 167 time for calcul the mask position with numpy : 0.0009121894836425781 nb_pixel_total : 36179 time to create 1 rle with old method : 0.04178977012634277 length of segment : 250 time for calcul the mask position with numpy : 0.0018434524536132812 nb_pixel_total : 24220 time to create 1 rle with old method : 0.0345311164855957 length of segment : 205 time for calcul the mask position with numpy : 0.0009720325469970703 nb_pixel_total : 11884 time to create 1 rle with old method : 0.0184481143951416 length of segment : 162 time for calcul the mask position with numpy : 0.0009047985076904297 nb_pixel_total : 11955 time to create 1 rle with old method : 0.016332149505615234 length of segment : 127 time for calcul the mask position with numpy : 0.001960277557373047 nb_pixel_total : 22059 time to create 1 rle with old method : 0.026226043701171875 length of segment : 196 time for calcul the mask position with numpy : 0.003092050552368164 nb_pixel_total : 35132 time to create 1 rle with old method : 0.03925895690917969 length of segment : 292 time for calcul the mask position with numpy : 0.011014461517333984 nb_pixel_total : 142629 time to create 1 rle with old method : 0.16337132453918457 length of segment : 383 time for calcul the mask position with numpy : 0.0007171630859375 nb_pixel_total : 8310 time to create 1 rle with old method : 0.010480880737304688 length of segment : 94 time for calcul the mask position with numpy : 0.0012624263763427734 nb_pixel_total : 20296 time to create 1 rle with old method : 0.024194717407226562 length of segment : 128 time for calcul the mask position with numpy : 0.0014863014221191406 nb_pixel_total : 23430 time to create 1 rle with old method : 0.04021573066711426 length of segment : 159 time for calcul the mask position with numpy : 0.0004582405090332031 nb_pixel_total : 5319 time to create 1 rle with old method : 0.008990764617919922 length of segment : 64 time for calcul the mask position with numpy : 0.0025904178619384766 nb_pixel_total : 33370 time to create 1 rle with old method : 0.03750729560852051 length of segment : 246 time for calcul the mask position with numpy : 0.0015778541564941406 nb_pixel_total : 23097 time to create 1 rle with old method : 0.02639627456665039 length of segment : 228 time for calcul the mask position with numpy : 0.0029778480529785156 nb_pixel_total : 26547 time to create 1 rle with old method : 0.029964923858642578 length of segment : 227 time for calcul the mask position with numpy : 0.0029621124267578125 nb_pixel_total : 27011 time to create 1 rle with old method : 0.030501842498779297 length of segment : 300 time for calcul the mask position with numpy : 0.008887290954589844 nb_pixel_total : 128401 time to create 1 rle with old method : 0.15316176414489746 length of segment : 584 time for calcul the mask position with numpy : 0.0003514289855957031 nb_pixel_total : 4239 time to create 1 rle with old method : 0.0071964263916015625 length of segment : 93 time for calcul the mask position with numpy : 0.011991262435913086 nb_pixel_total : 31298 time to create 1 rle with old method : 0.04395866394042969 length of segment : 284 time for calcul the mask position with numpy : 0.0013217926025390625 nb_pixel_total : 19258 time to create 1 rle with old method : 0.022388935089111328 length of segment : 166 time for calcul the mask position with numpy : 0.0067446231842041016 nb_pixel_total : 63766 time to create 1 rle with old method : 0.07194280624389648 length of segment : 502 time for calcul the mask position with numpy : 0.0006699562072753906 nb_pixel_total : 7342 time to create 1 rle with old method : 0.008452415466308594 length of segment : 106 time for calcul the mask position with numpy : 0.01817631721496582 nb_pixel_total : 130062 time to create 1 rle with old method : 0.14157509803771973 length of segment : 499 time for calcul the mask position with numpy : 0.0013730525970458984 nb_pixel_total : 16890 time to create 1 rle with old method : 0.02001190185546875 length of segment : 181 time for calcul the mask position with numpy : 0.0021142959594726562 nb_pixel_total : 24825 time to create 1 rle with old method : 0.029987573623657227 length of segment : 184 time for calcul the mask position with numpy : 0.0022208690643310547 nb_pixel_total : 31615 time to create 1 rle with old method : 0.03595232963562012 length of segment : 200 time for calcul the mask position with numpy : 0.0010530948638916016 nb_pixel_total : 10470 time to create 1 rle with old method : 0.01284027099609375 length of segment : 115 time for calcul the mask position with numpy : 0.0005424022674560547 nb_pixel_total : 2874 time to create 1 rle with old method : 0.003638744354248047 length of segment : 143 time for calcul the mask position with numpy : 0.0008411407470703125 nb_pixel_total : 9734 time to create 1 rle with old method : 0.011628866195678711 length of segment : 109 time for calcul the mask position with numpy : 0.002342700958251953 nb_pixel_total : 36393 time to create 1 rle with old method : 0.0445401668548584 length of segment : 179 time for calcul the mask position with numpy : 0.0007333755493164062 nb_pixel_total : 12530 time to create 1 rle with old method : 0.014923572540283203 length of segment : 149 time for calcul the mask position with numpy : 0.005904197692871094 nb_pixel_total : 82598 time to create 1 rle with old method : 0.09093117713928223 length of segment : 479 time for calcul the mask position with numpy : 0.0005023479461669922 nb_pixel_total : 7738 time to create 1 rle with old method : 0.009321928024291992 length of segment : 134 time for calcul the mask position with numpy : 0.0012288093566894531 nb_pixel_total : 11755 time to create 1 rle with old method : 0.01433873176574707 length of segment : 155 time for calcul the mask position with numpy : 0.00046062469482421875 nb_pixel_total : 16411 time to create 1 rle with old method : 0.018701553344726562 length of segment : 225 time for calcul the mask position with numpy : 0.0018663406372070312 nb_pixel_total : 30423 time to create 1 rle with old method : 0.03531026840209961 length of segment : 199 time for calcul the mask position with numpy : 0.0011522769927978516 nb_pixel_total : 15233 time to create 1 rle with old method : 0.017879247665405273 length of segment : 180 time for calcul the mask position with numpy : 0.004874467849731445 nb_pixel_total : 74802 time to create 1 rle with old method : 0.08491301536560059 length of segment : 316 time for calcul the mask position with numpy : 0.000823974609375 nb_pixel_total : 14419 time to create 1 rle with old method : 0.0169217586517334 length of segment : 123 time for calcul the mask position with numpy : 0.002638101577758789 nb_pixel_total : 25617 time to create 1 rle with old method : 0.028159618377685547 length of segment : 234 time for calcul the mask position with numpy : 0.0044558048248291016 nb_pixel_total : 45734 time to create 1 rle with old method : 0.05529069900512695 length of segment : 300 time for calcul the mask position with numpy : 0.008205175399780273 nb_pixel_total : 87976 time to create 1 rle with old method : 0.10627102851867676 length of segment : 503 time for calcul the mask position with numpy : 0.00072479248046875 nb_pixel_total : 5345 time to create 1 rle with old method : 0.006342411041259766 length of segment : 117 time for calcul the mask position with numpy : 0.0008404254913330078 nb_pixel_total : 12659 time to create 1 rle with old method : 0.014348983764648438 length of segment : 171 time for calcul the mask position with numpy : 0.006615638732910156 nb_pixel_total : 133273 time to create 1 rle with old method : 0.14400887489318848 length of segment : 433 time for calcul the mask position with numpy : 0.0016243457794189453 nb_pixel_total : 21290 time to create 1 rle with old method : 0.024790048599243164 length of segment : 297 time for calcul the mask position with numpy : 0.0003516674041748047 nb_pixel_total : 3477 time to create 1 rle with old method : 0.004147052764892578 length of segment : 88 time for calcul the mask position with numpy : 0.0029439926147460938 nb_pixel_total : 30733 time to create 1 rle with old method : 0.0357666015625 length of segment : 353 time for calcul the mask position with numpy : 0.0009298324584960938 nb_pixel_total : 10646 time to create 1 rle with old method : 0.012162923812866211 length of segment : 101 time for calcul the mask position with numpy : 0.0008704662322998047 nb_pixel_total : 16533 time to create 1 rle with old method : 0.01926708221435547 length of segment : 175 time for calcul the mask position with numpy : 0.002238035202026367 nb_pixel_total : 34986 time to create 1 rle with old method : 0.03931450843811035 length of segment : 172 time for calcul the mask position with numpy : 0.012197494506835938 nb_pixel_total : 305286 time to create 1 rle with new method : 0.02525782585144043 length of segment : 827 time for calcul the mask position with numpy : 0.0025048255920410156 nb_pixel_total : 45362 time to create 1 rle with old method : 0.05007767677307129 length of segment : 356 time spent for convertir_results : 55.37599420547485 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 378 chid ids of type : 3594 Number RLEs to save : 112234 save missing photos in datou_result : time spend for datou_step_exec : 282.0142664909363 time spend to save output : 13.402171850204468 total time spend for step 1 : 295.41643834114075 step2:crop_condition Fri Feb 7 02:15:28 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 : 15 ! batch 1 Loaded 378 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 ! map_result returned by crop_photo_return_map_crop : length : 234 About to insert : list_path_to_insert length 234 new photo from crops ! About to upload 234 photos upload in portfolio : 3736932 init cache_photo without model_param we have 234 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738890976_1110649 we have uploaded 234 photos in the portfolio 3736932 time of upload the photos Elapsed time : 67.22437596321106 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 ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! 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 : 79 About to insert : list_path_to_insert length 79 new photo from crops ! About to upload 79 photos upload in portfolio : 3736932 init cache_photo without model_param we have 79 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738891069_1110649 we have uploaded 79 photos in the portfolio 3736932 time of upload the photos Elapsed time : 24.131514072418213 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 ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3736932 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738891096_1110649 we have uploaded 3 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.0877363681793213 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 ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! 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 : 52 About to insert : list_path_to_insert length 52 new photo from crops ! About to upload 52 photos upload in portfolio : 3736932 init cache_photo without model_param we have 52 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738891131_1110649 we have uploaded 52 photos in the portfolio 3736932 time of upload the photos Elapsed time : 13.047284364700317 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 ! map_result returned by crop_photo_return_map_crop : length : 8 About to insert : list_path_to_insert length 8 new photo from crops ! About to upload 8 photos upload in portfolio : 3736932 init cache_photo without model_param we have 8 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738891149_1110649 we have uploaded 8 photos in the portfolio 3736932 time of upload the photos Elapsed time : 2.54704213142395 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 ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 3736932 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738891153_1110649 we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.552492618560791 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 ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 3736932 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738891156_1110649 we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.9427497386932373 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 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 [1335225948, 1335225693, 1335225459, 1335225399, 1335219623, 1335219621, 1335219618, 1335219615, 1335219566, 1335219564, 1335219561, 1335219557, 1335219553, 1335219546, 1335219421] Looping around the photos to save general results len do output : 378 /1335343344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343392Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343394Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343396Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343398Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343399Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343401Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343404Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343405Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343406Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343408Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343409Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343410Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343412Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343413Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343414Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343415Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343416Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343417Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343418Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343419Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343420Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343421Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343422Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343423Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343424Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343425Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343426Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343427Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343428Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343460Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343578Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335343588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344219Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344221Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344226Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344231Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344232Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344233Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344234Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344236Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344238Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344239Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344240Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344241Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344242Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344243Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344244Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344245Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344246Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344248Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344291Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344295Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1335344303Didn'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, '2560894') ('3318', '20314836', '1335225948', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225693', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225459', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225399', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219623', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219621', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219618', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219615', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219566', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219564', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219561', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219557', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219553', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219546', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219421', None, None, None, None, None, '2560894') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1149 time used for this insertion : 0.0620272159576416 save_final save missing photos in datou_result : time spend for datou_step_exec : 228.7864067554474 time spend to save output : 0.07111454010009766 total time spend for step 2 : 228.85752129554749 step3:rle_unique_nms_with_priority Fri Feb 7 02:19:17 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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 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 378 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 18 nb_hashtags : 4 time to prepare the origin masks : 6.908201217651367 time for calcul the mask position with numpy : 0.6027987003326416 nb_pixel_total : 6029684 time to create 1 rle with new method : 0.657909631729126 time for calcul the mask position with numpy : 0.04285097122192383 nb_pixel_total : 51046 time to create 1 rle with old method : 0.060897111892700195 time for calcul the mask position with numpy : 0.02883768081665039 nb_pixel_total : 20663 time to create 1 rle with old method : 0.037041664123535156 time for calcul the mask position with numpy : 0.053328752517700195 nb_pixel_total : 120682 time to create 1 rle with old method : 0.16554045677185059 time for calcul the mask position with numpy : 0.036192893981933594 nb_pixel_total : 55130 time to create 1 rle with old method : 0.06369590759277344 time for calcul the mask position with numpy : 0.036974191665649414 nb_pixel_total : 55421 time to create 1 rle with old method : 0.06491303443908691 time for calcul the mask position with numpy : 0.04018688201904297 nb_pixel_total : 17773 time to create 1 rle with old method : 0.020969867706298828 time for calcul the mask position with numpy : 0.0573573112487793 nb_pixel_total : 14680 time to create 1 rle with old method : 0.03998112678527832 time for calcul the mask position with numpy : 0.05262041091918945 nb_pixel_total : 69227 time to create 1 rle with old method : 0.07744288444519043 time for calcul the mask position with numpy : 0.036786556243896484 nb_pixel_total : 16198 time to create 1 rle with old method : 0.02013397216796875 time for calcul the mask position with numpy : 0.028104066848754883 nb_pixel_total : 243583 time to create 1 rle with new method : 0.5862996578216553 time for calcul the mask position with numpy : 0.03656148910522461 nb_pixel_total : 15699 time to create 1 rle with old method : 0.018436431884765625 time for calcul the mask position with numpy : 0.024569034576416016 nb_pixel_total : 19361 time to create 1 rle with old method : 0.023700237274169922 time for calcul the mask position with numpy : 0.022287368774414062 nb_pixel_total : 25272 time to create 1 rle with old method : 0.02874588966369629 time for calcul the mask position with numpy : 0.025761842727661133 nb_pixel_total : 20608 time to create 1 rle with old method : 0.024218082427978516 time for calcul the mask position with numpy : 0.02652430534362793 nb_pixel_total : 117777 time to create 1 rle with old method : 0.14053058624267578 time for calcul the mask position with numpy : 0.02289128303527832 nb_pixel_total : 38418 time to create 1 rle with old method : 0.04583144187927246 time for calcul the mask position with numpy : 0.022255897521972656 nb_pixel_total : 65070 time to create 1 rle with old method : 0.07585000991821289 time for calcul the mask position with numpy : 0.024469614028930664 nb_pixel_total : 53948 time to create 1 rle with old method : 0.06069207191467285 create new chi : 3.5077857971191406 time to delete rle : 0.011994361877441406 batch 1 Loaded 37 chid ids of type : 3594 +++++++++++++++++++++++Number RLEs to save : 13947 TO DO : save crop sub photo not yet done ! save time : 2.050826072692871 nb_obj : 28 nb_hashtags : 4 time to prepare the origin masks : 3.9981672763824463 time for calcul the mask position with numpy : 0.08339500427246094 nb_pixel_total : 5874278 time to create 1 rle with new method : 0.2937602996826172 time for calcul the mask position with numpy : 0.03714585304260254 nb_pixel_total : 5994 time to create 1 rle with old method : 0.011562347412109375 time for calcul the mask position with numpy : 0.03711271286010742 nb_pixel_total : 20326 time to create 1 rle with old method : 0.03910398483276367 time for calcul the mask position with numpy : 0.036971330642700195 nb_pixel_total : 24409 time to create 1 rle with old method : 0.04645037651062012 time for calcul the mask position with numpy : 0.037543535232543945 nb_pixel_total : 25820 time to create 1 rle with old method : 0.04909515380859375 time for calcul the mask position with numpy : 0.03822803497314453 nb_pixel_total : 96057 time to create 1 rle with old method : 0.17482304573059082 time for calcul the mask position with numpy : 0.03169083595275879 nb_pixel_total : 23048 time to create 1 rle with old method : 0.03949713706970215 time for calcul the mask position with numpy : 0.034027814865112305 nb_pixel_total : 30033 time to create 1 rle with old method : 0.03437376022338867 time for calcul the mask position with numpy : 0.029581069946289062 nb_pixel_total : 25436 time to create 1 rle with old method : 0.03170585632324219 time for calcul the mask position with numpy : 0.030693531036376953 nb_pixel_total : 11603 time to create 1 rle with old method : 0.019080400466918945 time for calcul the mask position with numpy : 0.033147335052490234 nb_pixel_total : 25440 time to create 1 rle with old method : 0.029722929000854492 time for calcul the mask position with numpy : 0.029407024383544922 nb_pixel_total : 58806 time to create 1 rle with old method : 0.06701946258544922 time for calcul the mask position with numpy : 0.02954864501953125 nb_pixel_total : 54800 time to create 1 rle with old method : 0.06188559532165527 time for calcul the mask position with numpy : 0.03126192092895508 nb_pixel_total : 19578 time to create 1 rle with old method : 0.021736621856689453 time for calcul the mask position with numpy : 0.029395341873168945 nb_pixel_total : 35828 time to create 1 rle with old method : 0.0405120849609375 time for calcul the mask position with numpy : 0.029371023178100586 nb_pixel_total : 35260 time to create 1 rle with old method : 0.04028606414794922 time for calcul the mask position with numpy : 0.03428959846496582 nb_pixel_total : 60729 time to create 1 rle with old method : 0.06675148010253906 time for calcul the mask position with numpy : 0.029301166534423828 nb_pixel_total : 21670 time to create 1 rle with old method : 0.02602696418762207 time for calcul the mask position with numpy : 0.029697179794311523 nb_pixel_total : 73475 time to create 1 rle with old method : 0.08173799514770508 time for calcul the mask position with numpy : 0.031202316284179688 nb_pixel_total : 5778 time to create 1 rle with old method : 0.010570287704467773 time for calcul the mask position with numpy : 0.0338590145111084 nb_pixel_total : 28706 time to create 1 rle with old method : 0.03441500663757324 time for calcul the mask position with numpy : 0.031120777130126953 nb_pixel_total : 206285 time to create 1 rle with new method : 0.1357133388519287 time for calcul the mask position with numpy : 0.034015655517578125 nb_pixel_total : 131554 time to create 1 rle with old method : 0.14720702171325684 time for calcul the mask position with numpy : 0.029370784759521484 nb_pixel_total : 26337 time to create 1 rle with old method : 0.03065323829650879 time for calcul the mask position with numpy : 0.029445171356201172 nb_pixel_total : 22766 time to create 1 rle with old method : 0.025743484497070312 time for calcul the mask position with numpy : 0.0289459228515625 nb_pixel_total : 7820 time to create 1 rle with old method : 0.009139060974121094 time for calcul the mask position with numpy : 0.02901768684387207 nb_pixel_total : 17307 time to create 1 rle with old method : 0.019961118698120117 time for calcul the mask position with numpy : 0.030602216720581055 nb_pixel_total : 16321 time to create 1 rle with old method : 0.018268823623657227 time for calcul the mask position with numpy : 0.030274152755737305 nb_pixel_total : 64776 time to create 1 rle with old method : 0.0746927261352539 create new chi : 2.7011985778808594 time to delete rle : 0.0049250125885009766 batch 1 Loaded 57 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 18113 TO DO : save crop sub photo not yet done ! save time : 1.6236674785614014 nb_obj : 22 nb_hashtags : 4 time to prepare the origin masks : 7.237734794616699 time for calcul the mask position with numpy : 0.9532246589660645 nb_pixel_total : 5462834 time to create 1 rle with new method : 0.505516529083252 time for calcul the mask position with numpy : 0.0232694149017334 nb_pixel_total : 98010 time to create 1 rle with old method : 0.10902953147888184 time for calcul the mask position with numpy : 0.022896289825439453 nb_pixel_total : 79341 time to create 1 rle with old method : 0.09571623802185059 time for calcul the mask position with numpy : 0.024469375610351562 nb_pixel_total : 282694 time to create 1 rle with new method : 0.5095951557159424 time for calcul the mask position with numpy : 0.02369523048400879 nb_pixel_total : 146570 time to create 1 rle with old method : 0.17203307151794434 time for calcul the mask position with numpy : 0.023396015167236328 nb_pixel_total : 17966 time to create 1 rle with old method : 0.02038717269897461 time for calcul the mask position with numpy : 0.02877020835876465 nb_pixel_total : 66894 time to create 1 rle with old method : 0.07845044136047363 time for calcul the mask position with numpy : 0.0368194580078125 nb_pixel_total : 32594 time to create 1 rle with old method : 0.039137840270996094 time for calcul the mask position with numpy : 0.04501485824584961 nb_pixel_total : 20089 time to create 1 rle with old method : 0.024712562561035156 time for calcul the mask position with numpy : 0.03856682777404785 nb_pixel_total : 11460 time to create 1 rle with old method : 0.012900114059448242 time for calcul the mask position with numpy : 0.036055803298950195 nb_pixel_total : 49333 time to create 1 rle with old method : 0.07099461555480957 time for calcul the mask position with numpy : 0.029166221618652344 nb_pixel_total : 8753 time to create 1 rle with old method : 0.011052608489990234 time for calcul the mask position with numpy : 0.024348974227905273 nb_pixel_total : 209226 time to create 1 rle with new method : 0.6305351257324219 time for calcul the mask position with numpy : 0.022730112075805664 nb_pixel_total : 26939 time to create 1 rle with old method : 0.0341649055480957 time for calcul the mask position with numpy : 0.02347278594970703 nb_pixel_total : 4748 time to create 1 rle with old method : 0.0053501129150390625 time for calcul the mask position with numpy : 0.021643400192260742 nb_pixel_total : 34618 time to create 1 rle with old method : 0.03846025466918945 time for calcul the mask position with numpy : 0.021401643753051758 nb_pixel_total : 10085 time to create 1 rle with old method : 0.01122736930847168 time for calcul the mask position with numpy : 0.022367000579833984 nb_pixel_total : 86944 time to create 1 rle with old method : 0.09546875953674316 time for calcul the mask position with numpy : 0.022064208984375 nb_pixel_total : 75312 time to create 1 rle with old method : 0.08406400680541992 time for calcul the mask position with numpy : 0.022732257843017578 nb_pixel_total : 43967 time to create 1 rle with old method : 0.04870128631591797 time for calcul the mask position with numpy : 0.022974252700805664 nb_pixel_total : 232758 time to create 1 rle with new method : 0.6410024166107178 time for calcul the mask position with numpy : 0.02640676498413086 nb_pixel_total : 5937 time to create 1 rle with old method : 0.007250785827636719 time for calcul the mask position with numpy : 0.02340245246887207 nb_pixel_total : 43168 time to create 1 rle with old method : 0.04828906059265137 create new chi : 4.949375867843628 time to delete rle : 0.0026879310607910156 batch 1 Loaded 45 chid ids of type : 3594 +++++++++++++++++++++++++++++Number RLEs to save : 17382 TO DO : save crop sub photo not yet done ! save time : 1.1414573192596436 nb_obj : 21 nb_hashtags : 3 time to prepare the origin masks : 4.285049200057983 time for calcul the mask position with numpy : 0.9272637367248535 nb_pixel_total : 5632784 time to create 1 rle with new method : 0.694239616394043 time for calcul the mask position with numpy : 0.022267818450927734 nb_pixel_total : 108 time to create 1 rle with old method : 0.00023674964904785156 time for calcul the mask position with numpy : 0.022702693939208984 nb_pixel_total : 87648 time to create 1 rle with old method : 0.0964818000793457 time for calcul the mask position with numpy : 0.023266077041625977 nb_pixel_total : 75664 time to create 1 rle with old method : 0.08939790725708008 time for calcul the mask position with numpy : 0.023248910903930664 nb_pixel_total : 20424 time to create 1 rle with old method : 0.02279067039489746 time for calcul the mask position with numpy : 0.02332162857055664 nb_pixel_total : 152071 time to create 1 rle with new method : 0.5984296798706055 time for calcul the mask position with numpy : 0.028568744659423828 nb_pixel_total : 19326 time to create 1 rle with old method : 0.022510290145874023 time for calcul the mask position with numpy : 0.023734331130981445 nb_pixel_total : 129720 time to create 1 rle with old method : 0.142653226852417 time for calcul the mask position with numpy : 0.0238039493560791 nb_pixel_total : 60375 time to create 1 rle with old method : 0.06641221046447754 time for calcul the mask position with numpy : 0.02300429344177246 nb_pixel_total : 15302 time to create 1 rle with old method : 0.019605159759521484 time for calcul the mask position with numpy : 0.025537729263305664 nb_pixel_total : 18473 time to create 1 rle with old method : 0.021781444549560547 time for calcul the mask position with numpy : 0.024550914764404297 nb_pixel_total : 57148 time to create 1 rle with old method : 0.06647396087646484 time for calcul the mask position with numpy : 0.025249004364013672 nb_pixel_total : 29350 time to create 1 rle with old method : 0.03442645072937012 time for calcul the mask position with numpy : 0.025065183639526367 nb_pixel_total : 62619 time to create 1 rle with old method : 0.06897473335266113 time for calcul the mask position with numpy : 0.022655248641967773 nb_pixel_total : 25727 time to create 1 rle with old method : 0.02947521209716797 time for calcul the mask position with numpy : 0.023447513580322266 nb_pixel_total : 30279 time to create 1 rle with old method : 0.034378767013549805 time for calcul the mask position with numpy : 0.021336793899536133 nb_pixel_total : 21450 time to create 1 rle with old method : 0.02599620819091797 time for calcul the mask position with numpy : 0.02207183837890625 nb_pixel_total : 33007 time to create 1 rle with old method : 0.03801703453063965 time for calcul the mask position with numpy : 0.02484416961669922 nb_pixel_total : 129825 time to create 1 rle with old method : 0.13997101783752441 time for calcul the mask position with numpy : 0.022872209548950195 nb_pixel_total : 128921 time to create 1 rle with old method : 0.14195799827575684 time for calcul the mask position with numpy : 0.024746179580688477 nb_pixel_total : 233009 time to create 1 rle with new method : 0.7428536415100098 time for calcul the mask position with numpy : 0.02412700653076172 nb_pixel_total : 87010 time to create 1 rle with old method : 0.09730672836303711 create new chi : 4.709248304367065 time to delete rle : 0.0041043758392333984 batch 1 Loaded 43 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++Number RLEs to save : 15218 TO DO : save crop sub photo not yet done ! save time : 0.9285368919372559 nb_obj : 12 nb_hashtags : 3 time to prepare the origin masks : 4.895992755889893 time for calcul the mask position with numpy : 0.37819457054138184 nb_pixel_total : 6345843 time to create 1 rle with new method : 0.6114981174468994 time for calcul the mask position with numpy : 0.024918317794799805 nb_pixel_total : 19647 time to create 1 rle with old method : 0.0257720947265625 time for calcul the mask position with numpy : 0.023015737533569336 nb_pixel_total : 3066 time to create 1 rle with old method : 0.003793954849243164 time for calcul the mask position with numpy : 0.0231935977935791 nb_pixel_total : 19436 time to create 1 rle with old method : 0.023361682891845703 time for calcul the mask position with numpy : 0.025404930114746094 nb_pixel_total : 19727 time to create 1 rle with old method : 0.024248600006103516 time for calcul the mask position with numpy : 0.02255105972290039 nb_pixel_total : 3927 time to create 1 rle with old method : 0.004679441452026367 time for calcul the mask position with numpy : 0.022901058197021484 nb_pixel_total : 2289 time to create 1 rle with old method : 0.0028891563415527344 time for calcul the mask position with numpy : 0.02357316017150879 nb_pixel_total : 61713 time to create 1 rle with old method : 0.07335925102233887 time for calcul the mask position with numpy : 0.02496051788330078 nb_pixel_total : 251902 time to create 1 rle with new method : 0.5377681255340576 time for calcul the mask position with numpy : 0.02488422393798828 nb_pixel_total : 10600 time to create 1 rle with old method : 0.012084484100341797 time for calcul the mask position with numpy : 0.02403879165649414 nb_pixel_total : 246501 time to create 1 rle with new method : 0.37764787673950195 time for calcul the mask position with numpy : 0.02241063117980957 nb_pixel_total : 12082 time to create 1 rle with old method : 0.0140533447265625 time for calcul the mask position with numpy : 0.022528409957885742 nb_pixel_total : 53507 time to create 1 rle with old method : 0.06480789184570312 create new chi : 2.5345730781555176 time to delete rle : 0.0016789436340332031 batch 1 Loaded 25 chid ids of type : 3594 ++++++++++++++Number RLEs to save : 9241 TO DO : save crop sub photo not yet done ! save time : 0.8864014148712158 nb_obj : 12 nb_hashtags : 5 time to prepare the origin masks : 3.5220680236816406 time for calcul the mask position with numpy : 0.577340841293335 nb_pixel_total : 6014344 time to create 1 rle with new method : 0.8208556175231934 time for calcul the mask position with numpy : 0.027575016021728516 nb_pixel_total : 527646 time to create 1 rle with new method : 0.4709208011627197 time for calcul the mask position with numpy : 0.021234750747680664 nb_pixel_total : 17241 time to create 1 rle with old method : 0.02016162872314453 time for calcul the mask position with numpy : 0.02159428596496582 nb_pixel_total : 21149 time to create 1 rle with old method : 0.02400493621826172 time for calcul the mask position with numpy : 0.020892620086669922 nb_pixel_total : 5695 time to create 1 rle with old method : 0.0067331790924072266 time for calcul the mask position with numpy : 0.02184271812438965 nb_pixel_total : 5323 time to create 1 rle with old method : 0.006055355072021484 time for calcul the mask position with numpy : 0.021265506744384766 nb_pixel_total : 8137 time to create 1 rle with old method : 0.009754419326782227 time for calcul the mask position with numpy : 0.022472620010375977 nb_pixel_total : 76904 time to create 1 rle with old method : 0.08582568168640137 time for calcul the mask position with numpy : 0.02177596092224121 nb_pixel_total : 19076 time to create 1 rle with old method : 0.022260665893554688 time for calcul the mask position with numpy : 0.02123713493347168 nb_pixel_total : 14611 time to create 1 rle with old method : 0.016299009323120117 time for calcul the mask position with numpy : 0.022318601608276367 nb_pixel_total : 245544 time to create 1 rle with new method : 0.39159321784973145 time for calcul the mask position with numpy : 0.021152973175048828 nb_pixel_total : 33950 time to create 1 rle with old method : 0.037503719329833984 time for calcul the mask position with numpy : 0.020997285842895508 nb_pixel_total : 60620 time to create 1 rle with old method : 0.0676112174987793 create new chi : 2.9019620418548584 time to delete rle : 0.002086639404296875 batch 1 Loaded 25 chid ids of type : 3594 ++++++++++++Number RLEs to save : 8809 TO DO : save crop sub photo not yet done ! save time : 0.7266936302185059 nb_obj : 26 nb_hashtags : 3 time to prepare the origin masks : 3.8088438510894775 time for calcul the mask position with numpy : 0.07724618911743164 nb_pixel_total : 5952640 time to create 1 rle with new method : 0.15035533905029297 time for calcul the mask position with numpy : 0.029953956604003906 nb_pixel_total : 34122 time to create 1 rle with old method : 0.0387568473815918 time for calcul the mask position with numpy : 0.02947854995727539 nb_pixel_total : 78771 time to create 1 rle with old method : 0.08977341651916504 time for calcul the mask position with numpy : 0.031105756759643555 nb_pixel_total : 31895 time to create 1 rle with old method : 0.03640484809875488 time for calcul the mask position with numpy : 0.030550718307495117 nb_pixel_total : 78539 time to create 1 rle with old method : 0.11071991920471191 time for calcul the mask position with numpy : 0.030082225799560547 nb_pixel_total : 8708 time to create 1 rle with old method : 0.016378164291381836 time for calcul the mask position with numpy : 0.03643536567687988 nb_pixel_total : 34557 time to create 1 rle with old method : 0.04173016548156738 time for calcul the mask position with numpy : 0.029327869415283203 nb_pixel_total : 11358 time to create 1 rle with old method : 0.013220787048339844 time for calcul the mask position with numpy : 0.02935957908630371 nb_pixel_total : 2961 time to create 1 rle with old method : 0.0034837722778320312 time for calcul the mask position with numpy : 0.029442310333251953 nb_pixel_total : 57845 time to create 1 rle with old method : 0.06461334228515625 time for calcul the mask position with numpy : 0.029932498931884766 nb_pixel_total : 80602 time to create 1 rle with old method : 0.08987545967102051 time for calcul the mask position with numpy : 0.029532909393310547 nb_pixel_total : 127996 time to create 1 rle with old method : 0.1418609619140625 time for calcul the mask position with numpy : 0.028984785079956055 nb_pixel_total : 7123 time to create 1 rle with old method : 0.008359432220458984 time for calcul the mask position with numpy : 0.029275894165039062 nb_pixel_total : 89738 time to create 1 rle with old method : 0.098419189453125 time for calcul the mask position with numpy : 0.028918981552124023 nb_pixel_total : 3960 time to create 1 rle with old method : 0.004618167877197266 time for calcul the mask position with numpy : 0.029262304306030273 nb_pixel_total : 8223 time to create 1 rle with old method : 0.009669065475463867 time for calcul the mask position with numpy : 0.029314279556274414 nb_pixel_total : 12022 time to create 1 rle with old method : 0.019190311431884766 time for calcul the mask position with numpy : 0.03307938575744629 nb_pixel_total : 39435 time to create 1 rle with old method : 0.06490945816040039 time for calcul the mask position with numpy : 0.03323984146118164 nb_pixel_total : 31816 time to create 1 rle with old method : 0.03497743606567383 time for calcul the mask position with numpy : 0.028998374938964844 nb_pixel_total : 19435 time to create 1 rle with old method : 0.02144598960876465 time for calcul the mask position with numpy : 0.028987646102905273 nb_pixel_total : 27195 time to create 1 rle with old method : 0.032415151596069336 time for calcul the mask position with numpy : 0.02935171127319336 nb_pixel_total : 56746 time to create 1 rle with old method : 0.06273913383483887 time for calcul the mask position with numpy : 0.029182910919189453 nb_pixel_total : 24481 time to create 1 rle with old method : 0.02879166603088379 time for calcul the mask position with numpy : 0.03126382827758789 nb_pixel_total : 42149 time to create 1 rle with old method : 0.04712557792663574 time for calcul the mask position with numpy : 0.029070138931274414 nb_pixel_total : 11345 time to create 1 rle with old method : 0.012706279754638672 time for calcul the mask position with numpy : 0.029593944549560547 nb_pixel_total : 163031 time to create 1 rle with new method : 0.1670970916748047 time for calcul the mask position with numpy : 0.030358314514160156 nb_pixel_total : 13547 time to create 1 rle with old method : 0.016866207122802734 create new chi : 2.320216417312622 time to delete rle : 0.002323150634765625 batch 1 Loaded 53 chid ids of type : 3594 ++++++++++++++++++++++++++++++++Number RLEs to save : 15192 TO DO : save crop sub photo not yet done ! save time : 1.1592254638671875 nb_obj : 39 nb_hashtags : 5 time to prepare the origin masks : 5.877389430999756 time for calcul the mask position with numpy : 0.0678718090057373 nb_pixel_total : 4774703 time to create 1 rle with new method : 0.1573476791381836 time for calcul the mask position with numpy : 0.030413389205932617 nb_pixel_total : 110958 time to create 1 rle with old method : 0.1478133201599121 time for calcul the mask position with numpy : 0.028741121292114258 nb_pixel_total : 5596 time to create 1 rle with old method : 0.006357669830322266 time for calcul the mask position with numpy : 0.028763771057128906 nb_pixel_total : 6891 time to create 1 rle with old method : 0.007857561111450195 time for calcul the mask position with numpy : 0.02884197235107422 nb_pixel_total : 26649 time to create 1 rle with old method : 0.03188300132751465 time for calcul the mask position with numpy : 0.04036521911621094 nb_pixel_total : 21067 time to create 1 rle with old method : 0.024457216262817383 time for calcul the mask position with numpy : 0.029419422149658203 nb_pixel_total : 13785 time to create 1 rle with old method : 0.015420675277709961 time for calcul the mask position with numpy : 0.03179216384887695 nb_pixel_total : 5042 time to create 1 rle with old method : 0.00814056396484375 time for calcul the mask position with numpy : 0.036460161209106445 nb_pixel_total : 110604 time to create 1 rle with old method : 0.1271059513092041 time for calcul the mask position with numpy : 0.030265331268310547 nb_pixel_total : 8826 time to create 1 rle with old method : 0.010590076446533203 time for calcul the mask position with numpy : 0.029690265655517578 nb_pixel_total : 21851 time to create 1 rle with old method : 0.024991750717163086 time for calcul the mask position with numpy : 0.03979659080505371 nb_pixel_total : 418799 time to create 1 rle with new method : 0.17117857933044434 time for calcul the mask position with numpy : 0.029945850372314453 nb_pixel_total : 7031 time to create 1 rle with old method : 0.008301973342895508 time for calcul the mask position with numpy : 0.030167818069458008 nb_pixel_total : 40307 time to create 1 rle with old method : 0.045786142349243164 time for calcul the mask position with numpy : 0.0305023193359375 nb_pixel_total : 82063 time to create 1 rle with old method : 0.09092068672180176 time for calcul the mask position with numpy : 0.029506206512451172 nb_pixel_total : 76374 time to create 1 rle with old method : 0.08350062370300293 time for calcul the mask position with numpy : 0.03098297119140625 nb_pixel_total : 16139 time to create 1 rle with old method : 0.018730640411376953 time for calcul the mask position with numpy : 0.031499624252319336 nb_pixel_total : 9287 time to create 1 rle with old method : 0.010689496994018555 time for calcul the mask position with numpy : 0.02938985824584961 nb_pixel_total : 32947 time to create 1 rle with old method : 0.03803110122680664 time for calcul the mask position with numpy : 0.032172203063964844 nb_pixel_total : 58945 time to create 1 rle with old method : 0.06637215614318848 time for calcul the mask position with numpy : 0.035868167877197266 nb_pixel_total : 18643 time to create 1 rle with old method : 0.021016836166381836 time for calcul the mask position with numpy : 0.03157305717468262 nb_pixel_total : 62836 time to create 1 rle with old method : 0.08877372741699219 time for calcul the mask position with numpy : 0.03753948211669922 nb_pixel_total : 87318 time to create 1 rle with old method : 0.1136021614074707 time for calcul the mask position with numpy : 0.03514599800109863 nb_pixel_total : 297876 time to create 1 rle with new method : 0.15612006187438965 time for calcul the mask position with numpy : 0.030112743377685547 nb_pixel_total : 128499 time to create 1 rle with old method : 0.16013741493225098 time for calcul the mask position with numpy : 0.03280949592590332 nb_pixel_total : 10428 time to create 1 rle with old method : 0.01604008674621582 time for calcul the mask position with numpy : 0.029596805572509766 nb_pixel_total : 71530 time to create 1 rle with old method : 0.07929062843322754 time for calcul the mask position with numpy : 0.029145479202270508 nb_pixel_total : 6287 time to create 1 rle with old method : 0.007210731506347656 time for calcul the mask position with numpy : 0.03139042854309082 nb_pixel_total : 43599 time to create 1 rle with old method : 0.05261516571044922 time for calcul the mask position with numpy : 0.03132820129394531 nb_pixel_total : 8767 time to create 1 rle with old method : 0.010066986083984375 time for calcul the mask position with numpy : 0.030783653259277344 nb_pixel_total : 26736 time to create 1 rle with old method : 0.033104658126831055 time for calcul the mask position with numpy : 0.02913641929626465 nb_pixel_total : 26651 time to create 1 rle with old method : 0.029738903045654297 time for calcul the mask position with numpy : 0.02912616729736328 nb_pixel_total : 11545 time to create 1 rle with old method : 0.013376712799072266 time for calcul the mask position with numpy : 0.03056812286376953 nb_pixel_total : 284757 time to create 1 rle with new method : 0.1882777214050293 time for calcul the mask position with numpy : 0.03373432159423828 nb_pixel_total : 19344 time to create 1 rle with old method : 0.02556586265563965 time for calcul the mask position with numpy : 0.02915811538696289 nb_pixel_total : 5599 time to create 1 rle with old method : 0.006439208984375 time for calcul the mask position with numpy : 0.03170275688171387 nb_pixel_total : 37821 time to create 1 rle with old method : 0.04189658164978027 time for calcul the mask position with numpy : 0.029325485229492188 nb_pixel_total : 13534 time to create 1 rle with old method : 0.015674352645874023 time for calcul the mask position with numpy : 0.03419947624206543 nb_pixel_total : 22306 time to create 1 rle with old method : 0.027039527893066406 time for calcul the mask position with numpy : 0.02908039093017578 nb_pixel_total : 18300 time to create 1 rle with old method : 0.020772218704223633 create new chi : 3.5621745586395264 time to delete rle : 0.0036809444427490234 batch 1 Loaded 79 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 22276 TO DO : save crop sub photo not yet done ! save time : 2.218820095062256 nb_obj : 11 nb_hashtags : 4 time to prepare the origin masks : 4.9935853481292725 time for calcul the mask position with numpy : 0.5161647796630859 nb_pixel_total : 6519610 time to create 1 rle with new method : 0.9633350372314453 time for calcul the mask position with numpy : 0.035611629486083984 nb_pixel_total : 75213 time to create 1 rle with old method : 0.08341550827026367 time for calcul the mask position with numpy : 0.027088165283203125 nb_pixel_total : 14143 time to create 1 rle with old method : 0.015743732452392578 time for calcul the mask position with numpy : 0.02477431297302246 nb_pixel_total : 13346 time to create 1 rle with old method : 0.016103267669677734 time for calcul the mask position with numpy : 0.028805255889892578 nb_pixel_total : 52977 time to create 1 rle with old method : 0.05998539924621582 time for calcul the mask position with numpy : 0.0293581485748291 nb_pixel_total : 7494 time to create 1 rle with old method : 0.008610248565673828 time for calcul the mask position with numpy : 0.04007887840270996 nb_pixel_total : 265923 time to create 1 rle with new method : 0.9638400077819824 time for calcul the mask position with numpy : 0.04661440849304199 nb_pixel_total : 8950 time to create 1 rle with old method : 0.014414548873901367 time for calcul the mask position with numpy : 0.04495501518249512 nb_pixel_total : 11220 time to create 1 rle with old method : 0.012698173522949219 time for calcul the mask position with numpy : 0.046082258224487305 nb_pixel_total : 35607 time to create 1 rle with old method : 0.05854630470275879 time for calcul the mask position with numpy : 0.04500460624694824 nb_pixel_total : 6559 time to create 1 rle with old method : 0.00811457633972168 time for calcul the mask position with numpy : 0.04485011100769043 nb_pixel_total : 39198 time to create 1 rle with old method : 0.0433812141418457 create new chi : 3.251920223236084 time to delete rle : 0.0022497177124023438 batch 1 Loaded 23 chid ids of type : 3594 ++++++++++++++Number RLEs to save : 6530 TO DO : save crop sub photo not yet done ! save time : 0.5948052406311035 nb_obj : 30 nb_hashtags : 3 time to prepare the origin masks : 5.448175668716431 time for calcul the mask position with numpy : 0.3488597869873047 nb_pixel_total : 4213634 time to create 1 rle with new method : 0.561525821685791 time for calcul the mask position with numpy : 0.02985525131225586 nb_pixel_total : 21461 time to create 1 rle with old method : 0.024734973907470703 time for calcul the mask position with numpy : 0.03532600402832031 nb_pixel_total : 83852 time to create 1 rle with old method : 0.10109758377075195 time for calcul the mask position with numpy : 0.03035283088684082 nb_pixel_total : 73626 time to create 1 rle with old method : 0.08102679252624512 time for calcul the mask position with numpy : 0.03214907646179199 nb_pixel_total : 29588 time to create 1 rle with old method : 0.03601408004760742 time for calcul the mask position with numpy : 0.03414344787597656 nb_pixel_total : 221630 time to create 1 rle with new method : 0.3311734199523926 time for calcul the mask position with numpy : 0.029692411422729492 nb_pixel_total : 7660 time to create 1 rle with old method : 0.009044170379638672 time for calcul the mask position with numpy : 0.03000473976135254 nb_pixel_total : 43634 time to create 1 rle with old method : 0.04938530921936035 time for calcul the mask position with numpy : 0.02957296371459961 nb_pixel_total : 4007 time to create 1 rle with old method : 0.005042552947998047 time for calcul the mask position with numpy : 0.029860973358154297 nb_pixel_total : 29005 time to create 1 rle with old method : 0.03615713119506836 time for calcul the mask position with numpy : 0.030463457107543945 nb_pixel_total : 14838 time to create 1 rle with old method : 0.016623973846435547 time for calcul the mask position with numpy : 0.03160595893859863 nb_pixel_total : 120311 time to create 1 rle with old method : 0.14620327949523926 time for calcul the mask position with numpy : 0.030552148818969727 nb_pixel_total : 101888 time to create 1 rle with old method : 0.11282777786254883 time for calcul the mask position with numpy : 0.03259992599487305 nb_pixel_total : 334782 time to create 1 rle with new method : 0.4142913818359375 time for calcul the mask position with numpy : 0.029430627822875977 nb_pixel_total : 43650 time to create 1 rle with old method : 0.05402016639709473 time for calcul the mask position with numpy : 0.03403067588806152 nb_pixel_total : 62531 time to create 1 rle with old method : 0.0833890438079834 time for calcul the mask position with numpy : 0.03661322593688965 nb_pixel_total : 465126 time to create 1 rle with new method : 1.3909485340118408 time for calcul the mask position with numpy : 0.029995203018188477 nb_pixel_total : 44865 time to create 1 rle with old method : 0.05302071571350098 time for calcul the mask position with numpy : 0.035486459732055664 nb_pixel_total : 485594 time to create 1 rle with new method : 1.0726912021636963 time for calcul the mask position with numpy : 0.029850006103515625 nb_pixel_total : 26799 time to create 1 rle with old method : 0.03074026107788086 time for calcul the mask position with numpy : 0.030983686447143555 nb_pixel_total : 283450 time to create 1 rle with new method : 0.4342508316040039 time for calcul the mask position with numpy : 0.029908180236816406 nb_pixel_total : 43931 time to create 1 rle with old method : 0.050701141357421875 time for calcul the mask position with numpy : 0.03343963623046875 nb_pixel_total : 69857 time to create 1 rle with old method : 0.08301758766174316 time for calcul the mask position with numpy : 0.030711889266967773 nb_pixel_total : 17910 time to create 1 rle with old method : 0.023534774780273438 time for calcul the mask position with numpy : 0.03583645820617676 nb_pixel_total : 82510 time to create 1 rle with old method : 0.11789631843566895 time for calcul the mask position with numpy : 0.030303478240966797 nb_pixel_total : 47428 time to create 1 rle with old method : 0.05342555046081543 time for calcul the mask position with numpy : 0.030101299285888672 nb_pixel_total : 11693 time to create 1 rle with old method : 0.013633251190185547 time for calcul the mask position with numpy : 0.03233170509338379 nb_pixel_total : 28891 time to create 1 rle with old method : 0.033014535903930664 time for calcul the mask position with numpy : 0.030599594116210938 nb_pixel_total : 25252 time to create 1 rle with old method : 0.02897024154663086 time for calcul the mask position with numpy : 0.030837059020996094 nb_pixel_total : 1850 time to create 1 rle with old method : 0.003045797348022461 time for calcul the mask position with numpy : 0.043021202087402344 nb_pixel_total : 8987 time to create 1 rle with old method : 0.014469623565673828 create new chi : 6.934629678726196 time to delete rle : 0.009984731674194336 batch 1 Loaded 61 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 24081 TO DO : save crop sub photo not yet done ! save time : 2.057698965072632 nb_obj : 29 nb_hashtags : 3 time to prepare the origin masks : 4.656689882278442 time for calcul the mask position with numpy : 0.742302656173706 nb_pixel_total : 4975918 time to create 1 rle with new method : 0.698662519454956 time for calcul the mask position with numpy : 0.030229568481445312 nb_pixel_total : 23134 time to create 1 rle with old method : 0.02630329132080078 time for calcul the mask position with numpy : 0.029779672622680664 nb_pixel_total : 20571 time to create 1 rle with old method : 0.02355504035949707 time for calcul the mask position with numpy : 0.032376766204833984 nb_pixel_total : 169365 time to create 1 rle with new method : 2.0486888885498047 time for calcul the mask position with numpy : 0.029263019561767578 nb_pixel_total : 4861 time to create 1 rle with old method : 0.005906820297241211 time for calcul the mask position with numpy : 0.029642343521118164 nb_pixel_total : 12050 time to create 1 rle with old method : 0.013798952102661133 time for calcul the mask position with numpy : 0.029189348220825195 nb_pixel_total : 14814 time to create 1 rle with old method : 0.01789999008178711 time for calcul the mask position with numpy : 0.02977919578552246 nb_pixel_total : 29856 time to create 1 rle with old method : 0.03430914878845215 time for calcul the mask position with numpy : 0.029284238815307617 nb_pixel_total : 33776 time to create 1 rle with old method : 0.03884243965148926 time for calcul the mask position with numpy : 0.03245377540588379 nb_pixel_total : 75086 time to create 1 rle with old method : 0.09021592140197754 time for calcul the mask position with numpy : 0.031323909759521484 nb_pixel_total : 131699 time to create 1 rle with old method : 0.1516718864440918 time for calcul the mask position with numpy : 0.031528472900390625 nb_pixel_total : 257050 time to create 1 rle with new method : 0.3956778049468994 time for calcul the mask position with numpy : 0.02985978126525879 nb_pixel_total : 11315 time to create 1 rle with old method : 0.012990474700927734 time for calcul the mask position with numpy : 0.03177165985107422 nb_pixel_total : 199468 time to create 1 rle with new method : 0.6834573745727539 time for calcul the mask position with numpy : 0.029792308807373047 nb_pixel_total : 26509 time to create 1 rle with old method : 0.030751943588256836 time for calcul the mask position with numpy : 0.030007600784301758 nb_pixel_total : 9743 time to create 1 rle with old method : 0.01149749755859375 time for calcul the mask position with numpy : 0.02976059913635254 nb_pixel_total : 14228 time to create 1 rle with old method : 0.016501426696777344 time for calcul the mask position with numpy : 0.03405928611755371 nb_pixel_total : 254882 time to create 1 rle with new method : 0.5335283279418945 time for calcul the mask position with numpy : 0.030683279037475586 nb_pixel_total : 64346 time to create 1 rle with old method : 0.07200241088867188 time for calcul the mask position with numpy : 0.030643701553344727 nb_pixel_total : 76212 time to create 1 rle with old method : 0.08446025848388672 time for calcul the mask position with numpy : 0.02977728843688965 nb_pixel_total : 11100 time to create 1 rle with old method : 0.012830495834350586 time for calcul the mask position with numpy : 0.02953028678894043 nb_pixel_total : 36944 time to create 1 rle with old method : 0.04446220397949219 time for calcul the mask position with numpy : 0.035691261291503906 nb_pixel_total : 25988 time to create 1 rle with old method : 0.02945423126220703 time for calcul the mask position with numpy : 0.030171632766723633 nb_pixel_total : 52901 time to create 1 rle with old method : 0.0618593692779541 time for calcul the mask position with numpy : 0.030590534210205078 nb_pixel_total : 43747 time to create 1 rle with old method : 0.04744291305541992 time for calcul the mask position with numpy : 0.029193401336669922 nb_pixel_total : 7630 time to create 1 rle with old method : 0.00862431526184082 time for calcul the mask position with numpy : 0.029924392700195312 nb_pixel_total : 50711 time to create 1 rle with old method : 0.05754852294921875 time for calcul the mask position with numpy : 0.029458999633789062 nb_pixel_total : 98197 time to create 1 rle with old method : 0.10952448844909668 time for calcul the mask position with numpy : 0.030643701553344727 nb_pixel_total : 24720 time to create 1 rle with old method : 0.028042078018188477 time for calcul the mask position with numpy : 0.03086090087890625 nb_pixel_total : 293419 time to create 1 rle with new method : 0.7063608169555664 create new chi : 7.893194913864136 time to delete rle : 0.005059242248535156 batch 1 Loaded 59 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 20511 TO DO : save crop sub photo not yet done ! save time : 2.0227532386779785 nb_obj : 27 nb_hashtags : 4 time to prepare the origin masks : 4.751555681228638 time for calcul the mask position with numpy : 0.9720392227172852 nb_pixel_total : 4872143 time to create 1 rle with new method : 0.7782654762268066 time for calcul the mask position with numpy : 0.03009486198425293 nb_pixel_total : 7590 time to create 1 rle with old method : 0.009021997451782227 time for calcul the mask position with numpy : 0.030974864959716797 nb_pixel_total : 19794 time to create 1 rle with old method : 0.022940635681152344 time for calcul the mask position with numpy : 0.02926325798034668 nb_pixel_total : 11860 time to create 1 rle with old method : 0.013235092163085938 time for calcul the mask position with numpy : 0.030033111572265625 nb_pixel_total : 6074 time to create 1 rle with old method : 0.007122993469238281 time for calcul the mask position with numpy : 0.03393197059631348 nb_pixel_total : 30200 time to create 1 rle with old method : 0.035180091857910156 time for calcul the mask position with numpy : 0.032820701599121094 nb_pixel_total : 184735 time to create 1 rle with new method : 1.5244081020355225 time for calcul the mask position with numpy : 0.030111074447631836 nb_pixel_total : 31940 time to create 1 rle with old method : 0.0346987247467041 time for calcul the mask position with numpy : 0.033974647521972656 nb_pixel_total : 120236 time to create 1 rle with old method : 0.13207459449768066 time for calcul the mask position with numpy : 0.031986236572265625 nb_pixel_total : 231347 time to create 1 rle with new method : 0.4961085319519043 time for calcul the mask position with numpy : 0.030498743057250977 nb_pixel_total : 188873 time to create 1 rle with new method : 1.6113793849945068 time for calcul the mask position with numpy : 0.03471088409423828 nb_pixel_total : 29008 time to create 1 rle with old method : 0.03764081001281738 time for calcul the mask position with numpy : 0.03336000442504883 nb_pixel_total : 12570 time to create 1 rle with old method : 0.015743732452392578 time for calcul the mask position with numpy : 0.0302584171295166 nb_pixel_total : 122115 time to create 1 rle with old method : 0.18619847297668457 time for calcul the mask position with numpy : 0.03916645050048828 nb_pixel_total : 222863 time to create 1 rle with new method : 0.6810882091522217 time for calcul the mask position with numpy : 0.03045058250427246 nb_pixel_total : 40243 time to create 1 rle with old method : 0.06413841247558594 time for calcul the mask position with numpy : 0.035433292388916016 nb_pixel_total : 12898 time to create 1 rle with old method : 0.02155613899230957 time for calcul the mask position with numpy : 0.03575539588928223 nb_pixel_total : 39764 time to create 1 rle with old method : 0.06074786186218262 time for calcul the mask position with numpy : 0.03506302833557129 nb_pixel_total : 13166 time to create 1 rle with old method : 0.0208132266998291 time for calcul the mask position with numpy : 0.03974509239196777 nb_pixel_total : 51542 time to create 1 rle with old method : 0.0762791633605957 time for calcul the mask position with numpy : 0.03759431838989258 nb_pixel_total : 10869 time to create 1 rle with old method : 0.016213417053222656 time for calcul the mask position with numpy : 0.034543752670288086 nb_pixel_total : 47280 time to create 1 rle with old method : 0.057837486267089844 time for calcul the mask position with numpy : 0.030040264129638672 nb_pixel_total : 5322 time to create 1 rle with old method : 0.006659507751464844 time for calcul the mask position with numpy : 0.030635356903076172 nb_pixel_total : 63844 time to create 1 rle with old method : 0.07349610328674316 time for calcul the mask position with numpy : 0.036980628967285156 nb_pixel_total : 166966 time to create 1 rle with new method : 1.0854318141937256 time for calcul the mask position with numpy : 0.032235145568847656 nb_pixel_total : 95235 time to create 1 rle with old method : 0.1084601879119873 time for calcul the mask position with numpy : 0.03306388854980469 nb_pixel_total : 189770 time to create 1 rle with new method : 0.5542316436767578 time for calcul the mask position with numpy : 0.0330357551574707 nb_pixel_total : 221993 time to create 1 rle with new method : 0.9911420345306396 create new chi : 10.853754043579102 time to delete rle : 0.008972883224487305 batch 1 Loaded 55 chid ids of type : 3594 +++++++++++++++++++++++++++++++Number RLEs to save : 19336 TO DO : save crop sub photo not yet done ! save time : 2.0818355083465576 nb_obj : 33 nb_hashtags : 3 time to prepare the origin masks : 4.637789726257324 time for calcul the mask position with numpy : 0.404860258102417 nb_pixel_total : 5089451 time to create 1 rle with new method : 0.6410925388336182 time for calcul the mask position with numpy : 0.03301692008972168 nb_pixel_total : 93899 time to create 1 rle with old method : 0.12065005302429199 time for calcul the mask position with numpy : 0.030896425247192383 nb_pixel_total : 176503 time to create 1 rle with new method : 0.45860815048217773 time for calcul the mask position with numpy : 0.03064250946044922 nb_pixel_total : 108799 time to create 1 rle with old method : 0.11959958076477051 time for calcul the mask position with numpy : 0.02927541732788086 nb_pixel_total : 11328 time to create 1 rle with old method : 0.015796661376953125 time for calcul the mask position with numpy : 0.03310585021972656 nb_pixel_total : 31922 time to create 1 rle with old method : 0.04629206657409668 time for calcul the mask position with numpy : 0.030658960342407227 nb_pixel_total : 89808 time to create 1 rle with old method : 0.09941887855529785 time for calcul the mask position with numpy : 0.029548168182373047 nb_pixel_total : 9578 time to create 1 rle with old method : 0.011195659637451172 time for calcul the mask position with numpy : 0.028962135314941406 nb_pixel_total : 8757 time to create 1 rle with old method : 0.010993719100952148 time for calcul the mask position with numpy : 0.030560731887817383 nb_pixel_total : 29709 time to create 1 rle with old method : 0.0351262092590332 time for calcul the mask position with numpy : 0.029733896255493164 nb_pixel_total : 40603 time to create 1 rle with old method : 0.04465651512145996 time for calcul the mask position with numpy : 0.029170989990234375 nb_pixel_total : 66495 time to create 1 rle with old method : 0.07364296913146973 time for calcul the mask position with numpy : 0.02888035774230957 nb_pixel_total : 9458 time to create 1 rle with old method : 0.011019706726074219 time for calcul the mask position with numpy : 0.02948737144470215 nb_pixel_total : 118190 time to create 1 rle with old method : 0.13237476348876953 time for calcul the mask position with numpy : 0.030910015106201172 nb_pixel_total : 22143 time to create 1 rle with old method : 0.02505970001220703 time for calcul the mask position with numpy : 0.03036975860595703 nb_pixel_total : 17397 time to create 1 rle with old method : 0.028092622756958008 time for calcul the mask position with numpy : 0.03537297248840332 nb_pixel_total : 240412 time to create 1 rle with new method : 0.5910773277282715 time for calcul the mask position with numpy : 0.029565095901489258 nb_pixel_total : 32246 time to create 1 rle with old method : 0.035674095153808594 time for calcul the mask position with numpy : 0.02883291244506836 nb_pixel_total : 14573 time to create 1 rle with old method : 0.01608419418334961 time for calcul the mask position with numpy : 0.028301715850830078 nb_pixel_total : 13978 time to create 1 rle with old method : 0.01570296287536621 time for calcul the mask position with numpy : 0.027582883834838867 nb_pixel_total : 21327 time to create 1 rle with old method : 0.024096250534057617 time for calcul the mask position with numpy : 0.02855086326599121 nb_pixel_total : 17675 time to create 1 rle with old method : 0.019742488861083984 time for calcul the mask position with numpy : 0.029011249542236328 nb_pixel_total : 27221 time to create 1 rle with old method : 0.030148983001708984 time for calcul the mask position with numpy : 0.029927492141723633 nb_pixel_total : 118879 time to create 1 rle with old method : 0.13066744804382324 time for calcul the mask position with numpy : 0.028796672821044922 nb_pixel_total : 8903 time to create 1 rle with old method : 0.01073145866394043 time for calcul the mask position with numpy : 0.029993057250976562 nb_pixel_total : 185960 time to create 1 rle with new method : 0.3517475128173828 time for calcul the mask position with numpy : 0.029178857803344727 nb_pixel_total : 16925 time to create 1 rle with old method : 0.01989150047302246 time for calcul the mask position with numpy : 0.029415130615234375 nb_pixel_total : 8797 time to create 1 rle with old method : 0.01041722297668457 time for calcul the mask position with numpy : 0.029530048370361328 nb_pixel_total : 15995 time to create 1 rle with old method : 0.01778888702392578 time for calcul the mask position with numpy : 0.030808687210083008 nb_pixel_total : 289693 time to create 1 rle with new method : 0.35013246536254883 time for calcul the mask position with numpy : 0.0331270694732666 nb_pixel_total : 34795 time to create 1 rle with old method : 0.03892683982849121 time for calcul the mask position with numpy : 0.029059171676635742 nb_pixel_total : 19451 time to create 1 rle with old method : 0.022746801376342773 time for calcul the mask position with numpy : 0.03051137924194336 nb_pixel_total : 58275 time to create 1 rle with old method : 0.06385588645935059 time for calcul the mask position with numpy : 0.029183626174926758 nb_pixel_total : 1095 time to create 1 rle with old method : 0.0013785362243652344 create new chi : 5.182183742523193 time to delete rle : 0.0036916732788085938 batch 1 Loaded 67 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 21489 TO DO : save crop sub photo not yet done ! save time : 2.5940606594085693 nb_obj : 19 nb_hashtags : 4 time to prepare the origin masks : 20.185045957565308 time for calcul the mask position with numpy : 3.9277851581573486 nb_pixel_total : 5714190 time to create 1 rle with new method : 2.228010892868042 time for calcul the mask position with numpy : 1.0226738452911377 nb_pixel_total : 4316 time to create 1 rle with old method : 0.03115057945251465 time for calcul the mask position with numpy : 0.9098408222198486 nb_pixel_total : 18987 time to create 1 rle with old method : 0.0491938591003418 time for calcul the mask position with numpy : 1.235513687133789 nb_pixel_total : 101236 time to create 1 rle with old method : 0.18959355354309082 time for calcul the mask position with numpy : 0.2997865676879883 nb_pixel_total : 21472 time to create 1 rle with old method : 0.036920785903930664 time for calcul the mask position with numpy : 0.6288366317749023 nb_pixel_total : 298589 time to create 1 rle with new method : 0.8368330001831055 time for calcul the mask position with numpy : 0.67801833152771 nb_pixel_total : 14086 time to create 1 rle with old method : 0.03548550605773926 time for calcul the mask position with numpy : 0.696422815322876 nb_pixel_total : 287447 time to create 1 rle with new method : 0.5319750308990479 time for calcul the mask position with numpy : 0.0842130184173584 nb_pixel_total : 44328 time to create 1 rle with old method : 0.06198692321777344 time for calcul the mask position with numpy : 0.0605010986328125 nb_pixel_total : 10670 time to create 1 rle with old method : 0.015135765075683594 time for calcul the mask position with numpy : 0.06359672546386719 nb_pixel_total : 208891 time to create 1 rle with new method : 0.9692974090576172 time for calcul the mask position with numpy : 0.07607507705688477 nb_pixel_total : 22389 time to create 1 rle with old method : 0.04675173759460449 time for calcul the mask position with numpy : 0.09140992164611816 nb_pixel_total : 67152 time to create 1 rle with old method : 0.0854179859161377 time for calcul the mask position with numpy : 0.08566832542419434 nb_pixel_total : 2190 time to create 1 rle with old method : 0.005251169204711914 time for calcul the mask position with numpy : 0.05577993392944336 nb_pixel_total : 25489 time to create 1 rle with old method : 0.03696608543395996 time for calcul the mask position with numpy : 0.10625100135803223 nb_pixel_total : 69958 time to create 1 rle with old method : 0.10181379318237305 time for calcul the mask position with numpy : 0.0869295597076416 nb_pixel_total : 9460 time to create 1 rle with old method : 0.04397320747375488 time for calcul the mask position with numpy : 0.06955313682556152 nb_pixel_total : 62286 time to create 1 rle with old method : 0.1076962947845459 time for calcul the mask position with numpy : 0.08498954772949219 nb_pixel_total : 27716 time to create 1 rle with old method : 0.06176614761352539 time for calcul the mask position with numpy : 0.08595156669616699 nb_pixel_total : 39388 time to create 1 rle with old method : 0.06488418579101562 create new chi : 16.070575714111328 time to delete rle : 0.016473770141601562 batch 1 Loaded 39 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++Number RLEs to save : 13173 TO DO : save crop sub photo not yet done ! save time : 2.844825506210327 nb_obj : 51 nb_hashtags : 5 time to prepare the origin masks : 5.746376037597656 time for calcul the mask position with numpy : 0.5403852462768555 nb_pixel_total : 5085218 time to create 1 rle with new method : 1.0856263637542725 time for calcul the mask position with numpy : 0.03024578094482422 nb_pixel_total : 45734 time to create 1 rle with old method : 0.05309772491455078 time for calcul the mask position with numpy : 0.03036785125732422 nb_pixel_total : 36393 time to create 1 rle with old method : 0.04080843925476074 time for calcul the mask position with numpy : 0.0296633243560791 nb_pixel_total : 27011 time to create 1 rle with old method : 0.03019237518310547 time for calcul the mask position with numpy : 0.031042814254760742 nb_pixel_total : 45362 time to create 1 rle with old method : 0.053116798400878906 time for calcul the mask position with numpy : 0.03397369384765625 nb_pixel_total : 142629 time to create 1 rle with old method : 0.23186111450195312 time for calcul the mask position with numpy : 0.03750157356262207 nb_pixel_total : 130062 time to create 1 rle with old method : 0.17124438285827637 time for calcul the mask position with numpy : 0.029762983322143555 nb_pixel_total : 31298 time to create 1 rle with old method : 0.03587222099304199 time for calcul the mask position with numpy : 0.03075575828552246 nb_pixel_total : 12659 time to create 1 rle with old method : 0.01420283317565918 time for calcul the mask position with numpy : 0.030689716339111328 nb_pixel_total : 11955 time to create 1 rle with old method : 0.014013290405273438 time for calcul the mask position with numpy : 0.029996871948242188 nb_pixel_total : 82598 time to create 1 rle with old method : 0.09177446365356445 time for calcul the mask position with numpy : 0.03278851509094238 nb_pixel_total : 305286 time to create 1 rle with new method : 0.35236167907714844 time for calcul the mask position with numpy : 0.029872894287109375 nb_pixel_total : 14419 time to create 1 rle with old method : 0.01636338233947754 time for calcul the mask position with numpy : 0.030130863189697266 nb_pixel_total : 128401 time to create 1 rle with old method : 0.14127779006958008 time for calcul the mask position with numpy : 0.02976846694946289 nb_pixel_total : 24220 time to create 1 rle with old method : 0.02791452407836914 time for calcul the mask position with numpy : 0.029401302337646484 nb_pixel_total : 9734 time to create 1 rle with old method : 0.010993719100952148 time for calcul the mask position with numpy : 0.029726505279541016 nb_pixel_total : 30423 time to create 1 rle with old method : 0.03512859344482422 time for calcul the mask position with numpy : 0.029700517654418945 nb_pixel_total : 87976 time to create 1 rle with old method : 0.09629368782043457 time for calcul the mask position with numpy : 0.0295407772064209 nb_pixel_total : 16890 time to create 1 rle with old method : 0.01861858367919922 time for calcul the mask position with numpy : 0.028968095779418945 nb_pixel_total : 31615 time to create 1 rle with old method : 0.035099029541015625 time for calcul the mask position with numpy : 0.029315948486328125 nb_pixel_total : 34986 time to create 1 rle with old method : 0.03881573677062988 time for calcul the mask position with numpy : 0.02926015853881836 nb_pixel_total : 12530 time to create 1 rle with old method : 0.014699697494506836 time for calcul the mask position with numpy : 0.03000497817993164 nb_pixel_total : 63766 time to create 1 rle with old method : 0.0704030990600586 time for calcul the mask position with numpy : 0.029525041580200195 nb_pixel_total : 16411 time to create 1 rle with old method : 0.019312143325805664 time for calcul the mask position with numpy : 0.03020954132080078 nb_pixel_total : 7342 time to create 1 rle with old method : 0.008813858032226562 time for calcul the mask position with numpy : 0.03160285949707031 nb_pixel_total : 7738 time to create 1 rle with old method : 0.009505033493041992 time for calcul the mask position with numpy : 0.029816389083862305 nb_pixel_total : 21290 time to create 1 rle with old method : 0.024524211883544922 time for calcul the mask position with numpy : 0.02993154525756836 nb_pixel_total : 16280 time to create 1 rle with old method : 0.019713401794433594 time for calcul the mask position with numpy : 0.03007960319519043 nb_pixel_total : 26547 time to create 1 rle with old method : 0.032631635665893555 time for calcul the mask position with numpy : 0.029938936233520508 nb_pixel_total : 10646 time to create 1 rle with old method : 0.01258540153503418 time for calcul the mask position with numpy : 0.03069162368774414 nb_pixel_total : 35132 time to create 1 rle with old method : 0.042458295822143555 time for calcul the mask position with numpy : 0.030439376831054688 nb_pixel_total : 26592 time to create 1 rle with old method : 0.03196263313293457 time for calcul the mask position with numpy : 0.030719518661499023 nb_pixel_total : 74802 time to create 1 rle with old method : 0.0915069580078125 time for calcul the mask position with numpy : 0.03477883338928223 nb_pixel_total : 125437 time to create 1 rle with old method : 0.18016839027404785 time for calcul the mask position with numpy : 0.034221649169921875 nb_pixel_total : 25617 time to create 1 rle with old method : 0.03453993797302246 time for calcul the mask position with numpy : 0.03011298179626465 nb_pixel_total : 19258 time to create 1 rle with old method : 0.021800518035888672 time for calcul the mask position with numpy : 0.030071258544921875 nb_pixel_total : 24825 time to create 1 rle with old method : 0.02986431121826172 time for calcul the mask position with numpy : 0.03016805648803711 nb_pixel_total : 3477 time to create 1 rle with old method : 0.005051851272583008 time for calcul the mask position with numpy : 0.030309438705444336 nb_pixel_total : 8310 time to create 1 rle with old method : 0.009660005569458008 time for calcul the mask position with numpy : 0.030818462371826172 nb_pixel_total : 5345 time to create 1 rle with old method : 0.009168863296508789 time for calcul the mask position with numpy : 0.034001827239990234 nb_pixel_total : 15233 time to create 1 rle with old method : 0.02514481544494629 time for calcul the mask position with numpy : 0.032674551010131836 nb_pixel_total : 33370 time to create 1 rle with old method : 0.03860306739807129 time for calcul the mask position with numpy : 0.030565738677978516 nb_pixel_total : 23097 time to create 1 rle with old method : 0.049031972885131836 time for calcul the mask position with numpy : 0.04175758361816406 nb_pixel_total : 2874 time to create 1 rle with old method : 0.00704193115234375 time for calcul the mask position with numpy : 0.03796100616455078 nb_pixel_total : 11755 time to create 1 rle with old method : 0.02175283432006836 time for calcul the mask position with numpy : 0.03922724723815918 nb_pixel_total : 22059 time to create 1 rle with old method : 0.0282747745513916 time for calcul the mask position with numpy : 0.02973484992980957 nb_pixel_total : 10470 time to create 1 rle with old method : 0.017263174057006836 time for calcul the mask position with numpy : 0.0314788818359375 nb_pixel_total : 11884 time to create 1 rle with old method : 0.014430522918701172 time for calcul the mask position with numpy : 0.02974700927734375 nb_pixel_total : 23430 time to create 1 rle with old method : 0.032486677169799805 time for calcul the mask position with numpy : 0.031706809997558594 nb_pixel_total : 4239 time to create 1 rle with old method : 0.006819963455200195 time for calcul the mask position with numpy : 0.030697107315063477 nb_pixel_total : 20296 time to create 1 rle with old method : 0.031795501708984375 time for calcul the mask position with numpy : 0.03277730941772461 nb_pixel_total : 5319 time to create 1 rle with old method : 0.007834434509277344 create new chi : 5.74024224281311 time to delete rle : 0.0062503814697265625 batch 1 Loaded 103 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 26254 TO DO : save crop sub photo not yet done ! save time : 4.4825170040130615 map_output_result : {1335225948: (0.0, 'Should be the crop_list due to order', 0.0), 1335225693: (0.0, 'Should be the crop_list due to order', 0.0), 1335225459: (0.0, 'Should be the crop_list due to order', 0.0), 1335225399: (0.0, 'Should be the crop_list due to order', 0.0), 1335219623: (0.0, 'Should be the crop_list due to order', 0.0), 1335219621: (0.0, 'Should be the crop_list due to order', 0.0), 1335219618: (0.0, 'Should be the crop_list due to order', 0.0), 1335219615: (0.0, 'Should be the crop_list due to order', 0.0), 1335219566: (0.0, 'Should be the crop_list due to order', 0.0), 1335219564: (0.0, 'Should be the crop_list due to order', 0.0), 1335219561: (0.0, 'Should be the crop_list due to order', 0.0), 1335219557: (0.0, 'Should be the crop_list due to order', 0.0), 1335219553: (0.0, 'Should be the crop_list due to order', 0.0), 1335219546: (0.0, 'Should be the crop_list due to order', 0.0), 1335219421: (0.0, 'Should be the crop_list due to order', 0.0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1335225948, 1335225693, 1335225459, 1335225399, 1335219623, 1335219621, 1335219618, 1335219615, 1335219566, 1335219564, 1335219561, 1335219557, 1335219553, 1335219546, 1335219421] Looping around the photos to save general results len do output : 15 /1335225948.Didn't retrieve data . /1335225693.Didn't retrieve data . /1335225459.Didn't retrieve data . /1335225399.Didn't retrieve data . /1335219623.Didn't retrieve data . /1335219621.Didn't retrieve data . /1335219618.Didn't retrieve data . /1335219615.Didn't retrieve data . /1335219566.Didn't retrieve data . /1335219564.Didn't retrieve data . /1335219561.Didn't retrieve data . /1335219557.Didn't retrieve data . /1335219553.Didn't retrieve data . /1335219546.Didn't retrieve data . /1335219421.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, '2560894') ('3318', '20314836', '1335225948', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225693', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225459', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225399', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219623', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219621', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219618', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219615', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219566', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219564', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219561', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219557', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219553', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219546', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219421', None, None, None, None, None, '2560894') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 45 time used for this insertion : 0.013324260711669922 save_final save missing photos in datou_result : time spend for datou_step_exec : 204.0157175064087 time spend to save output : 0.023242712020874023 total time spend for step 3 : 204.03896021842957 step4:ventilate_hashtags_in_portfolio Fri Feb 7 02:22:41 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 : 20314836 get user id for portfolio 20314836 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`=20314836 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('carton','papier','pet_fonce','metal','autre','pet_clair','background','pehd','environnement','mal_croppe','flou')) 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`=20314836 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('carton','papier','pet_fonce','metal','autre','pet_clair','background','pehd','environnement','mal_croppe','flou')) 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`=20314836 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('carton','papier','pet_fonce','metal','autre','pet_clair','background','pehd','environnement','mal_croppe','flou')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://www.fotonower.com/velours/20315496,20315497,20315498,20315499,20315500,20315501,20315502,20315503,20315504,20315505,20315506?tags=carton,papier,pet_fonce,metal,autre,pet_clair,background,pehd,environnement,mal_croppe,flou Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1335225948, 1335225693, 1335225459, 1335225399, 1335219623, 1335219621, 1335219618, 1335219615, 1335219566, 1335219564, 1335219561, 1335219557, 1335219553, 1335219546, 1335219421] Looping around the photos to save general results len do output : 1 /20314836. 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, '2560894') ('3318', '20314836', '1335225948', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225693', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225459', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225399', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219623', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219621', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219618', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219615', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219566', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219564', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219561', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219557', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219553', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219546', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219421', None, None, None, None, None, '2560894') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 16 time used for this insertion : 0.015740394592285156 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.156477451324463 time spend to save output : 0.01616668701171875 total time spend for step 4 : 2.1726441383361816 step5:final Fri Feb 7 02:22:43 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 : {1335225948: ('0.21934313347252485',), 1335225693: ('0.21934313347252485',), 1335225459: ('0.21934313347252485',), 1335225399: ('0.21934313347252485',), 1335219623: ('0.21934313347252485',), 1335219621: ('0.21934313347252485',), 1335219618: ('0.21934313347252485',), 1335219615: ('0.21934313347252485',), 1335219566: ('0.21934313347252485',), 1335219564: ('0.21934313347252485',), 1335219561: ('0.21934313347252485',), 1335219557: ('0.21934313347252485',), 1335219553: ('0.21934313347252485',), 1335219546: ('0.21934313347252485',), 1335219421: ('0.21934313347252485',)} new output for save of step final : {1335225948: ('0.21934313347252485',), 1335225693: ('0.21934313347252485',), 1335225459: ('0.21934313347252485',), 1335225399: ('0.21934313347252485',), 1335219623: ('0.21934313347252485',), 1335219621: ('0.21934313347252485',), 1335219618: ('0.21934313347252485',), 1335219615: ('0.21934313347252485',), 1335219566: ('0.21934313347252485',), 1335219564: ('0.21934313347252485',), 1335219561: ('0.21934313347252485',), 1335219557: ('0.21934313347252485',), 1335219553: ('0.21934313347252485',), 1335219546: ('0.21934313347252485',), 1335219421: ('0.21934313347252485',)} [1335225948, 1335225693, 1335225459, 1335225399, 1335219623, 1335219621, 1335219618, 1335219615, 1335219566, 1335219564, 1335219561, 1335219557, 1335219553, 1335219546, 1335219421] Looping around the photos to save general results len do output : 15 /1335225948.Didn't retrieve data . /1335225693.Didn't retrieve data . /1335225459.Didn't retrieve data . /1335225399.Didn't retrieve data . /1335219623.Didn't retrieve data . /1335219621.Didn't retrieve data . /1335219618.Didn't retrieve data . /1335219615.Didn't retrieve data . /1335219566.Didn't retrieve data . /1335219564.Didn't retrieve data . /1335219561.Didn't retrieve data . /1335219557.Didn't retrieve data . /1335219553.Didn't retrieve data . /1335219546.Didn't retrieve data . /1335219421.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, '2560894') ('3318', '20314836', '1335225948', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225693', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225459', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225399', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219623', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219621', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219618', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219615', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219566', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219564', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219561', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219557', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219553', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219546', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219421', None, None, None, None, None, '2560894') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 45 time used for this insertion : 0.013143062591552734 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.13286781311035156 time spend to save output : 0.013903379440307617 total time spend for step 5 : 0.14677119255065918 step6:blur_detection Fri Feb 7 02:22:43 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/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143.jpg resize: (2160, 3264) 1335225948 -4.719259332605742 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7.jpg resize: (2160, 3264) 1335225693 -6.706028975045214 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c.jpg resize: (2160, 3264) 1335225459 -6.072495598915214 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95.jpg resize: (2160, 3264) 1335225399 -5.460320966663146 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526.jpg resize: (2160, 3264) 1335219623 -3.701866269876599 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389.jpg resize: (2160, 3264) 1335219621 -6.353417185847009 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb.jpg resize: (2160, 3264) 1335219618 -5.471980896116209 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852.jpg resize: (2160, 3264) 1335219615 -5.81692199713472 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d.jpg resize: (2160, 3264) 1335219566 -3.7804287139309425 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89.jpg resize: (2160, 3264) 1335219564 -5.431141047109782 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284.jpg resize: (2160, 3264) 1335219561 -6.399307803714703 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b.jpg resize: (2160, 3264) 1335219557 -4.996716735252738 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd.jpg resize: (2160, 3264) 1335219553 -6.318759888728304 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a.jpg resize: (2160, 3264) 1335219546 -4.814423980984235 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e.jpg resize: (2160, 3264) 1335219421 -5.6245022722702185 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560323_0.png resize: (169, 138) 1335343344 -2.847763849989605 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560327_0.png resize: (554, 358) 1335343345 -2.3620556150116836 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560326_0.png resize: (230, 460) 1335343346 -4.223712083492752 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560320_0.png resize: (532, 608) 1335343347 -2.203834421836099 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560313_0.png resize: (417, 303) 1335343348 -3.797898029036401 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560318_0.png resize: (118, 249) 1335343349 -2.7204265013324664 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560319_0.png resize: (147, 128) 1335343350 -2.7810579566081417 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560331_0.png resize: (518, 346) 1335343351 -4.503688120856973 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560348_0.png resize: (132, 157) 1335343352 -4.083012764889368 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560330_0.png resize: (344, 182) 1335343353 -4.627721692233588 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560353_0.png resize: (140, 175) 1335343354 -2.077978285842652 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560347_0.png resize: (314, 354) 1335343355 -5.160676755159903 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560340_0.png resize: (245, 315) 1335343356 -5.31390128659933 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560351_0.png resize: (220, 234) 1335343357 -4.110354966541433 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560345_0.png resize: (125, 342) 1335343358 -4.5446635949619205 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560356_0.png resize: (121, 125) 1335343359 -4.261889679738496 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560339_0.png resize: (120, 143) 1335343360 -3.7024933406002 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560352_0.png resize: (172, 221) 1335343361 -4.0943518481985555 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560332_0.png resize: (329, 202) 1335343362 -4.493919548383618 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560333_0.png resize: (627, 305) 1335343363 -5.207821658373074 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560336_0.png resize: (237, 168) 1335343364 -4.665650326227816 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560338_0.png resize: (222, 204) 1335343365 -4.3976068323305935 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560341_0.png resize: (402, 148) 1335343366 -4.0358679642748125 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560343_0.png resize: (284, 166) 1335343367 -4.464672731414251 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560346_0.png resize: (201, 159) 1335343368 -4.10948879247839 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560335_0.png resize: (290, 293) 1335343369 -4.276349043577104 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560354_0.png resize: (100, 80) 1335343370 -3.700116247966438 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560365_0.png resize: (204, 246) 1335343371 -2.6147079311623553 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560377_0.png resize: (890, 501) 1335343372 -4.461675565094602 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560359_0.png resize: (143, 84) 1335343374 -3.72251666374115 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560366_0.png resize: (62, 118) 1335343375 -2.593679861457999 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560358_0.png resize: (235, 258) 1335343376 -3.260770784678158 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560360_0.png resize: (675, 755) 1335343377 -5.020909958703751 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560375_0.png resize: (131, 225) 1335343378 -3.130964284840118 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560372_0.png resize: (167, 177) 1335343379 -3.7562204680708904 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560363_0.png resize: (461, 244) 1335343380 -4.035631972088897 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560379_0.png resize: (444, 341) 1335343381 -5.048428835450155 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560364_0.png resize: (94, 176) 1335343382 -3.750770169532857 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560362_0.png resize: (441, 259) 1335343383 -4.671202804659242 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560374_0.png resize: (340, 306) 1335343384 -5.584980552599808 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560367_0.png resize: (255, 531) 1335343385 -3.146368837177891 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560387_0.png resize: (241, 260) 1335343386 -3.7431178056730023 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560386_0.png resize: (253, 309) 1335343387 -4.189909168922907 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560390_0.png resize: (318, 350) 1335343388 -3.8562932300515036 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560398_0.png resize: (305, 390) 1335343389 -4.37495711419668 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560380_0.png resize: (313, 407) 1335343390 -4.180757893755657 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560397_0.png resize: (214, 165) 1335343391 -3.643832270578184 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560384_0.png resize: (239, 345) 1335343392 -3.641229049840364 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560393_0.png resize: (326, 275) 1335343393 -4.44918566405452 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560394_0.png resize: (398, 462) 1335343394 -4.653318975595506 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560388_0.png resize: (213, 448) 1335343395 -3.850474569631231 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560385_0.png resize: (159, 263) 1335343396 -3.5354197136336287 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560383_0.png resize: (338, 495) 1335343397 -4.02616055555671 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560400_0.png resize: (217, 104) 1335343398 -2.6817094292771744 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560401_0.png resize: (360, 537) 1335343399 -2.2525987174084743 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560406_0.png resize: (525, 232) 1335343400 -2.9127658431932444 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560407_0.png resize: (161, 127) 1335343401 -1.2155304492911703 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560408_0.png resize: (108, 57) 1335343402 -2.1765838642520974 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560409_0.png resize: (175, 167) 1335343403 -3.44483259181092 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560404_0.png resize: (83, 171) 1335343404 -2.9743724557362827 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560412_0.png resize: (249, 104) 1335343405 -3.048061965179652 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560402_0.png resize: (152, 120) 1335343406 -2.2328197272105275 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560411_0.png resize: (83, 47) 1335343408 0.6519691458114599 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560413_0.png resize: (347, 565) 1335343409 -3.8772461228003983 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560421_0.png resize: (95, 95) 1335343410 -3.6661764696082018 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560414_0.png resize: (272, 203) 1335343411 -4.2869714234501535 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560416_0.png resize: (162, 119) 1335343412 -2.532796019096512 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560420_0.png resize: (153, 60) 1335343413 -4.095800321868963 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560422_0.png resize: (176, 195) 1335343414 -5.051700833407362 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560423_0.png resize: (217, 125) 1335343415 -4.722992467433233 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560417_0.png resize: (238, 116) 1335343416 -5.328549610985641 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560443_0.png resize: (193, 82) 1335343417 -2.594874538657335 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560448_0.png resize: (267, 290) 1335343418 -4.031901896552663 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560432_0.png resize: (123, 114) 1335343419 -3.5635478066119903 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560439_0.png resize: (349, 445) 1335343420 -2.639619566325343 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560428_0.png resize: (206, 124) 1335343421 -3.6517136114349573 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560442_0.png resize: (319, 325) 1335343422 -3.9115470349375427 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560426_0.png resize: (318, 405) 1335343423 -4.350113567903799 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560447_0.png resize: (122, 146) 1335343424 -2.3755137852386863 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560425_0.png resize: (207, 221) 1335343425 -3.3864013691860637 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560436_0.png resize: (135, 152) 1335343426 -2.51276015082098 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560430_0.png resize: (220, 217) 1335343427 -2.6192800657115005 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560434_0.png resize: (337, 312) 1335343428 -4.292428338189929 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560445_0.png resize: (281, 149) 1335343429 -4.3541054408887385 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560441_0.png resize: (130, 188) 1335343430 -2.4404839254660633 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560444_0.png resize: (105, 130) 1335343431 -5.314276365505797 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560440_0.png resize: (107, 49) 1335343432 -2.160299166170831 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560461_0.png resize: (145, 124) 1335343433 -2.836951128178631 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560471_0.png resize: (136, 189) 1335343435 -3.693414577610621 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560463_0.png resize: (134, 213) 1335343436 -2.074075377941513 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560468_0.png resize: (111, 79) 1335343437 -2.605803546828046 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560483_0.png resize: (115, 129) 1335343438 -5.115452761581054 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560453_0.png resize: (365, 276) 1335343439 -4.763167983567833 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560475_0.png resize: (341, 455) 1335343440 -2.840787323402315 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560456_0.png resize: (294, 319) 1335343441 -3.430538023496588 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560457_0.png resize: (121, 101) 1335343443 -1.7746308421386832 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560478_0.png resize: (179, 183) 1335343444 -3.6297282012337573 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560476_0.png resize: (100, 94) 1335343445 -3.898898360481099 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560462_0.png resize: (102, 71) 1335343446 -3.425430068337593 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560466_0.png resize: (338, 465) 1335343447 -4.377898544315052 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560489_0.png resize: (246, 439) 1335343448 -4.622478380041708 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560465_0.png resize: (233, 190) 1335343449 -4.313700269290198 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560469_0.png resize: (178, 195) 1335343450 -4.383847527832654 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560472_0.png resize: (327, 372) 1335343451 -4.566530832390856 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560455_0.png resize: (124, 141) 1335343452 -4.146716022427875 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560474_0.png resize: (240, 181) 1335343453 -4.212666444201445 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560480_0.png resize: (194, 94) 1335343454 -4.251919512373548 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560473_0.png resize: (227, 131) 1335343455 -4.59129219742558 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560454_0.png resize: (97, 121) 1335343456 -3.26950522567896 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560460_0.png resize: (121, 100) 1335343457 -2.4216078054949106 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560487_0.png resize: (367, 367) 1335343458 -4.228959459638128 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560467_0.png resize: (151, 81) 1335343459 -4.447526587215116 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560452_0.png resize: (321, 150) 1335343460 -4.515580119867614 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560497_0.png resize: (319, 512) 1335343461 -2.5898419120292915 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560491_0.png resize: (99, 105) 1335343462 -3.256130194019683 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560492_0.png resize: (262, 202) 1335343463 -3.086067736170623 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560498_0.png resize: (159, 115) 1335343464 -0.8914248093110099 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560496_0.png resize: (75, 140) 1335343465 -2.443383503134856 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560493_0.png resize: (142, 118) 1335343466 -2.824878215605926 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560490_0.png resize: (279, 210) 1335343467 -3.5939618952923347 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560499_0.png resize: (115, 167) 1335343468 -3.6592139053608412 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560520_0.png resize: (416, 486) 1335343469 -4.414217883987338 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560514_0.png resize: (145, 108) 1335343470 -3.8497156675101136 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560528_0.png resize: (67, 44) 1335343472 -2.2484925325003404 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560505_0.png resize: (73, 141) 1335343473 -1.4223341651498225 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560510_0.png resize: (212, 341) 1335343475 -5.400872667682421 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560516_0.png resize: (166, 235) 1335343476 -5.198990358987594 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560522_0.png resize: (208, 317) 1335343477 -4.910888917153547 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560524_0.png resize: (479, 465) 1335343479 -3.6172760205890353 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560525_0.png resize: (146, 243) 1335343480 -2.887261812164732 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560503_0.png resize: (185, 210) 1335343481 -2.1170663946436257 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560513_0.png resize: (207, 160) 1335343482 -4.405376739450203 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560509_0.png resize: (679, 240) 1335343483 -4.311226627368446 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560529_0.png resize: (301, 157) 1335343484 -5.093813529207865 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560506_0.png resize: (520, 198) 1335343485 -4.668460620935729 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560518_0.png resize: (129, 102) 1335343486 -3.484576814798693 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560504_0.png resize: (298, 167) 1335343487 -2.8728362805073906 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560540_0.png resize: (470, 248) 1335343488 -2.4535489197200318 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560558_0.png resize: (428, 252) 1335343489 -3.53561335427356 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560546_0.png resize: (253, 342) 1335343490 -5.446499945324255 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560551_0.png resize: (143, 103) 1335343491 -2.466561202536286 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560544_0.png resize: (155, 104) 1335343492 -4.138188764614925 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560557_0.png resize: (305, 323) 1335343493 -5.830891453238333 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560550_0.png resize: (742, 586) 1335343495 -3.930614530373572 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560554_0.png resize: (92, 118) 1335343496 -5.155463368218013 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560537_0.png resize: (198, 298) 1335343497 -5.3176092013301215 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560533_0.png resize: (208, 217) 1335343498 -4.0739905593895855 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560545_0.png resize: (775, 907) 1335343499 -3.9633099659392945 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560549_0.png resize: (166, 263) 1335343500 -4.379760483020185 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560532_0.png resize: (408, 508) 1335343501 -5.234800136076759 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560542_0.png resize: (131, 228) 1335343502 -4.530672231885907 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560538_0.png resize: (163, 163) 1335343503 -2.197448459875243 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560539_0.png resize: (121, 250) 1335343504 -4.3154465699637345 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560577_0.png resize: (547, 378) 1335343505 -2.3885277650927805 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560560_0.png resize: (194, 341) 1335343506 -0.6792492577743316 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560575_0.png resize: (278, 349) 1335343507 -4.7254095820282025 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560568_0.png resize: (289, 275) 1335343508 -4.802449898896806 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560583_0.png resize: (732, 506) 1335343509 -2.892137603217607 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560576_0.png resize: (72, 104) 1335343510 -3.4971800713189274 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560571_0.png resize: (204, 286) 1335343511 -4.616696304869713 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560573_0.png resize: (160, 162) 1335343512 -3.077779216161513 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560567_0.png resize: (188, 205) 1335343513 -3.904716423046393 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560574_0.png resize: (166, 162) 1335343514 -1.6323536368711502 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560582_0.png resize: (106, 92) 1335343515 -2.0980062967522843 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560610_0.png resize: (412, 310) 1335343516 -3.8396109029111747 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560606_0.png resize: (74, 215) 1335343517 -3.922593816940135 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560599_0.png resize: (241, 221) 1335343518 -3.5877485110192944 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560611_0.png resize: (140, 230) 1335343519 -2.5753978770246655 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560591_0.png resize: (176, 249) 1335343520 -1.4653016434041621 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560592_0.png resize: (122, 92) 1335343521 -3.668977320503285 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560598_0.png resize: (244, 130) 1335343522 -1.3523327029491132 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560614_0.png resize: (153, 154) 1335343523 -4.323631139401073 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560609_0.png resize: (234, 100) 1335343524 -4.681554996955525 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560608_0.png resize: (139, 234) 1335343525 -4.639670344876707 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560612_0.png resize: (55, 63) 1335343526 -3.468940519408939 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560594_0.png resize: (443, 131) 1335343527 -4.386722393331721 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560619_0.png resize: (77, 181) 1335343528 -4.162962816662297 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560605_0.png resize: (232, 208) 1335343529 -4.28827492781829 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560595_0.png resize: (380, 573) 1335343530 -4.804989893918537 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560602_0.png resize: (317, 288) 1335343531 -3.0504146015937836 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560593_0.png resize: (280, 161) 1335343532 -4.104762215776712 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560616_0.png resize: (117, 127) 1335343533 -4.707216852447309 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560604_0.png resize: (111, 202) 1335343534 -4.693506971593442 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560622_0.png resize: (226, 572) 1335343535 -3.623509656170092 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560625_0.png resize: (255, 268) 1335343536 -3.035321700213957 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560638_0.png resize: (221, 304) 1335343537 -4.579690879272996 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560636_0.png resize: (314, 525) 1335343538 -4.786508737339487 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560620_0.png resize: (322, 218) 1335343539 -4.559954250716167 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560626_0.png resize: (117, 91) 1335343540 -4.014789119781869 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560628_0.png resize: (222, 189) 1335343541 -4.529268452139217 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560627_0.png resize: (301, 374) 1335343542 -3.616331603375015 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560634_0.png resize: (358, 957) 1335343543 -1.811461281402031 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560624_0.png resize: (410, 307) 1335343544 -3.208767494914627 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560689_0.png resize: (341, 188) 1335343545 -2.1819813701249773 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560681_0.png resize: (418, 478) 1335343546 -4.033655887784102 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560639_0.png resize: (205, 190) 1335343547 -4.398933028236601 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560641_0.png resize: (127, 136) 1335343548 -1.7940968690347434 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560652_0.png resize: (190, 296) 1335343549 -3.6605786947900913 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560680_0.png resize: (171, 110) 1335343550 -3.8976309098388553 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560672_0.png resize: (194, 195) 1335343551 -3.448233881914025 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560642_0.png resize: (186, 174) 1335343552 -3.7253874910059666 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560677_0.png resize: (206, 388) 1335343553 -3.0649410961310437 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560655_0.png resize: (164, 295) 1335343554 -2.5666929027475036 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560669_0.png resize: (134, 81) 1335343556 -3.645543943279512 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560661_0.png resize: (180, 220) 1335343557 -3.8798754063477507 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560667_0.png resize: (148, 125) 1335343558 -2.717689249285967 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560670_0.png resize: (134, 149) 1335343559 -3.0098755559685384 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560658_0.png resize: (106, 115) 1335343560 -2.8047802408959193 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560660_0.png resize: (175, 144) 1335343561 -2.484336163509491 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560686_0.png resize: (173, 143) 1335343562 -3.0079075001260387 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560643_0.png resize: (239, 226) 1335343563 -4.011120312019548 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560684_0.png resize: (320, 229) 1335343564 -3.2396533990461926 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560685_0.png resize: (86, 169) 1335343565 -3.5367842219949814 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560676_0.png resize: (234, 166) 1335343568 -4.210509798618935 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560687_0.png resize: (163, 295) 1335343569 -3.962791781929939 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560663_0.png resize: (115, 122) 1335343570 -0.809424013994024 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560651_0.png resize: (221, 234) 1335343571 -3.1029399356003498 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560650_0.png resize: (225, 146) 1335343572 -4.374011885058082 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560647_0.png resize: (159, 205) 1335343573 -4.826592209462487 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560645_0.png resize: (94, 115) 1335343574 -3.4720492997713417 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560678_0.png resize: (321, 454) 1335343575 -3.7381920195564744 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560656_0.png resize: (166, 162) 1335343576 -4.054280919280704 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560664_0.png resize: (89, 68) 1335343577 -4.591306922697114 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560679_0.png resize: (109, 78) 1335343578 -3.2324481039269193 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560683_0.png resize: (88, 50) 1335343579 1.3994483814741154 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560640_0.png resize: (162, 96) 1335343580 -2.423041294525232 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560673_0.png resize: (170, 129) 1335343581 -3.845514609938147 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560654_0.png resize: (91, 67) 1335343582 -3.7579381740194213 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560648_0.png resize: (64, 109) 1335343583 -2.71792409732977 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560662_0.png resize: (200, 200) 1335343584 -3.316363565274483 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560682_0.png resize: (220, 179) 1335343585 -4.567480925629597 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560657_0.png resize: (451, 269) 1335343586 -3.950817902205075 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560671_0.png resize: (224, 121) 1335343587 -4.203376667069144 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560653_0.png resize: (576, 289) 1335343588 -1.8285685239212326 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560321_0.png resize: (188, 125) 1335344032 -2.091235016411733 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560324_0.png resize: (176, 168) 1335344033 -2.079689059583968 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560315_0.png resize: (871, 340) 1335344034 -1.6178126920693758 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560317_0.png resize: (246, 192) 1335344035 -3.796239455762349 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560342_0.png resize: (538, 752) 1335344036 -4.9850416483009115 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560344_0.png resize: (159, 242) 1335344037 -3.2993485763705785 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560337_0.png resize: (73, 114) 1335344038 -3.3664191296146 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560350_0.png resize: (237, 189) 1335344039 -4.502463797688787 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560355_0.png resize: (219, 141) 1335344040 -3.663557034018073 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560361_0.png resize: (383, 395) 1335344041 -3.1122294790255 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560371_0.png resize: (115, 118) 1335344042 -1.0015287541641946 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560376_0.png resize: (333, 766) 1335344043 -4.278247085820707 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560373_0.png resize: (264, 184) 1335344044 -4.067038378598741 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560378_0.png resize: (285, 429) 1335344045 -3.638716513748552 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560370_0.png resize: (236, 293) 1335344046 -3.201064259861251 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560389_0.png resize: (212, 184) 1335344047 -4.237758940784989 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560396_0.png resize: (440, 505) 1335344048 -4.629764456573818 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560392_0.png resize: (188, 133) 1335344049 -3.7370725255012878 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560395_0.png resize: (165, 282) 1335344050 -3.486151714578851 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560391_0.png resize: (217, 105) 1335344051 -2.427451043178954 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560410_0.png resize: (182, 153) 1335344052 -2.6968823181079804 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560405_0.png resize: (877, 531) 1335344053 -3.58789132036683 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560424_0.png resize: (1013, 972) 1335344054 -5.971269337885107 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560431_0.png resize: (189, 377) 1335344055 -3.4290072114330474 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560450_0.png resize: (240, 267) 1335344056 -3.9137921172090535 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560438_0.png resize: (217, 237) 1335344057 -4.530972736460099 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560437_0.png resize: (253, 446) 1335344058 -3.352623393584198 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560449_0.png resize: (108, 108) 1335344059 -4.290529883604209 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560451_0.png resize: (219, 303) 1335344060 -3.9291487177634594 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560458_0.png resize: (126, 195) 1335344061 -2.3487082847698866 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560477_0.png resize: (199, 271) 1335344062 -2.896889826493819 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560464_0.png resize: (466, 578) 1335344063 -5.026340181971661 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560485_0.png resize: (324, 400) 1335344064 -4.872875510247796 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560486_0.png resize: (702, 606) 1335344065 -4.2670658146341545 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560459_0.png resize: (182, 198) 1335344066 -3.252397179259354 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560481_0.png resize: (110, 74) 1335344067 -3.864316384850186 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560494_0.png resize: (45, 251) 1335344068 -1.980871771545221 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560511_0.png resize: (804, 716) 1335344069 -4.0975701443504935 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560519_0.png resize: (513, 341) 1335344070 -2.9280859057999242 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560521_0.png resize: (605, 865) 1335344071 -4.8614266675600435 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560517_0.png resize: (267, 289) 1335344072 -4.236435628579747 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560515_0.png resize: (146, 187) 1335344074 -4.607319596112237 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560502_0.png resize: (474, 178) 1335344075 -5.147618374709623 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560559_0.png resize: (79, 94) 1335344076 -4.801985086427713 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560534_0.png resize: (468, 254) 1335344077 -4.491472837951541 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560531_0.png resize: (236, 227) 1335344078 -4.113578832421789 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560535_0.png resize: (246, 255) 1335344080 -5.685258923437193 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560556_0.png resize: (107, 165) 1335344081 -4.628442955453628 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560553_0.png resize: (196, 190) 1335344082 -3.9936770710987006 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560543_0.png resize: (179, 219) 1335344083 -4.5988617572461035 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560548_0.png resize: (153, 234) 1335344084 -2.85442214395774 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560562_0.png resize: (656, 373) 1335344085 -3.8892881968513717 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560580_0.png resize: (228, 264) 1335344086 -3.332401634130561 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560581_0.png resize: (413, 636) 1335344087 -3.3517266372025585 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560579_0.png resize: (299, 253) 1335344088 -4.619246209849841 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560569_0.png resize: (493, 657) 1335344089 -2.9301294321088402 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560578_0.png resize: (105, 186) 1335344090 -3.5453544777599375 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560566_0.png resize: (115, 156) 1335344092 -4.5913074285625175 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560561_0.png resize: (220, 240) 1335344093 -3.8142248967901518 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560563_0.png resize: (196, 259) 1335344094 -4.052569952615503 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560564_0.png resize: (429, 468) 1335344095 -4.139959133599095 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560589_0.png resize: (184, 78) 1335344096 -2.9806836243799872 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560607_0.png resize: (532, 394) 1335344097 -2.798090988574764 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560618_0.png resize: (534, 551) 1335344098 -2.7905104332357373 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560613_0.png resize: (99, 230) 1335344099 -4.37143462173237 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560617_0.png resize: (188, 257) 1335344100 -3.7503891013595094 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560615_0.png resize: (120, 168) 1335344101 -3.944790267381872 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560600_0.png resize: (161, 161) 1335344102 -4.056163719233794 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560623_0.png resize: (128, 195) 1335344103 -4.225556564268764 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560633_0.png resize: (139, 119) 1335344104 -3.1527424865399696 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560621_0.png resize: (251, 226) 1335344105 -2.4991841623898283 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560635_0.png resize: (189, 230) 1335344106 -4.452472254168358 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560637_0.png resize: (167, 205) 1335344107 -2.8217457169496747 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560630_0.png resize: (147, 112) 1335344108 -2.270467186226641 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560674_0.png resize: (302, 391) 1335344109 -2.678577181340724 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560649_0.png resize: (241, 202) 1335344110 -3.454186708089193 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560659_0.png resize: (445, 629) 1335344111 -4.042690080465508 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560666_0.png resize: (176, 284) 1335344112 -3.8802258736735213 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560668_0.png resize: (382, 364) 1335344113 -4.399847190932979 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560419_0.png resize: (118, 104) 1335344118 -4.961133068538454 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560488_0.png resize: (68, 154) 1335344119 -4.429021971668249 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560586_0.png resize: (109, 104) 1335344120 -3.6580117188317516 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560328_0.png resize: (272, 88) 1335344216 -2.1572018563830966 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560329_0.png resize: (340, 260) 1335344217 -2.5658358074038605 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560325_0.png resize: (227, 360) 1335344218 -1.4417550990134511 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560322_0.png resize: (295, 395) 1335344219 -2.3845506803920857 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560312_0.png resize: (310, 260) 1335344220 -2.2246530049591557 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560314_0.png resize: (146, 325) 1335344221 -3.5411220468187135 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560349_0.png resize: (294, 327) 1335344222 -4.506768814835924 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560368_0.png resize: (460, 706) 1335344224 -4.8430530315944464 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560381_0.png resize: (328, 1219) 1335344225 -1.6178510984476528 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560399_0.png resize: (235, 542) 1335344226 -4.499735338347866 treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560382_0.png resize: (493, 351) 1335344227 -3.8207774992713337 treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560403_0.png resize: (375, 1204) 1335344228 -1.8183497635168424 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560415_0.png resize: (312, 1210) 1335344229 -1.8312374259269917 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560446_0.png resize: (453, 656) 1335344230 -3.6062380126289355 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560429_0.png resize: (154, 318) 1335344231 -1.537689062866892 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560427_0.png resize: (213, 463) 1335344232 -3.3312350807600777 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560435_0.png resize: (235, 189) 1335344233 -4.087892246844621 treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560433_0.png resize: (386, 623) 1335344234 -2.1200987374923073 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560479_0.png resize: (325, 419) 1335344235 -4.002077637635597 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560470_0.png resize: (333, 342) 1335344236 -4.1388695490236875 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560482_0.png resize: (463, 1237) 1335344237 -1.2647037908423981 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560495_0.png resize: (348, 1205) 1335344238 -1.5360015521456991 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560530_0.png resize: (167, 247) 1335344239 -4.673941676441265 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560507_0.png resize: (349, 286) 1335344240 -5.229306152599698 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560501_0.png resize: (394, 345) 1335344241 -4.441744404408022 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560512_0.png resize: (99, 350) 1335344242 -4.518088570535412 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560527_0.png resize: (662, 505) 1335344243 -4.871991818280316 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560508_0.png resize: (624, 486) 1335344244 -3.4546085207010337 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560526_0.png resize: (220, 414) 1335344245 -3.3305121353371043 treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560523_0.png resize: (846, 678) 1335344246 -3.1135831256913473 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560552_0.png resize: (705, 587) 1335344247 -4.641338759549954 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560555_0.png resize: (414, 1265) 1335344248 -1.513643335975092 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560536_0.png resize: (501, 267) 1335344249 -3.895794313815771 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560541_0.png resize: (160, 187) 1335344250 -4.563876057244065 treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560547_0.png resize: (567, 444) 1335344251 -5.310678670056644 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560570_0.png resize: (696, 563) 1335344252 -4.014506060509351 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560572_0.png resize: (385, 372) 1335344253 -4.902234856422062 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560565_0.png resize: (333, 1258) 1335344254 -1.9738928083255218 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560585_0.png resize: (151, 107) 1335344255 -4.868182139822458 treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560584_0.png resize: (544, 437) 1335344256 -4.308641523222467 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560590_0.png resize: (238, 274) 1335344257 -1.9090669808846965 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560603_0.png resize: (473, 307) 1335344258 -3.8707939019924003 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560596_0.png resize: (332, 426) 1335344259 -2.9523978292781607 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560601_0.png resize: (633, 525) 1335344260 -5.182351091457124 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560588_0.png resize: (366, 675) 1335344261 -3.709523679660612 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560587_0.png resize: (400, 1305) 1335344262 -1.6982093501898776 treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560597_0.png resize: (554, 203) 1335344263 -2.937069917256962 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560632_0.png resize: (656, 690) 1335344264 -2.778796824704101 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560629_0.png resize: (277, 1068) 1335344265 -1.8161939192944052 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560646_0.png resize: (128, 195) 1335344266 -2.1749359917150213 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560644_0.png resize: (380, 480) 1335344267 -2.454307471070165 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560688_0.png resize: (799, 561) 1335344268 -3.2084808207547812 treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560316_0.png resize: (161, 199) 1335344289 -3.1236446548328285 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560357_0.png resize: (178, 210) 1335344290 -4.340036495702917 treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560334_0.png resize: (241, 473) 1335344291 -4.654314163617884 treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560369_0.png resize: (106, 156) 1335344292 -3.21633293488673 treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560418_0.png resize: (266, 529) 1335344293 -3.969599649389891 treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560484_0.png resize: (658, 866) 1335344294 -4.078292843977907 treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560500_0.png resize: (271, 552) 1335344295 -2.728596358603401 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560675_0.png resize: (123, 152) 1335344296 -1.2662270414514245 treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560665_0.png resize: (109, 114) 1335344299 -1.0114479565980976 treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560631_0.png resize: (295, 192) 1335344303 -2.5899159700951055 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 : 393 time used for this insertion : 0.0377957820892334 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 393 time used for this insertion : 0.32196760177612305 save missing photos in datou_result : time spend for datou_step_exec : 63.131457805633545 time spend to save output : 0.39289307594299316 total time spend for step 6 : 63.52435088157654 step7:brightness Fri Feb 7 02:23:47 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/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143.jpg treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7.jpg treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c.jpg treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95.jpg treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526.jpg treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389.jpg treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb.jpg treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852.jpg treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d.jpg treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89.jpg treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284.jpg treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b.jpg treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd.jpg treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a.jpg treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e.jpg treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560323_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560327_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560326_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560320_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560313_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560318_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560319_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560331_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560348_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560330_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560353_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560347_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560340_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560351_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560345_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560356_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560339_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560352_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560332_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560333_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560336_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560338_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560341_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560343_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560346_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560335_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560354_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560365_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560377_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560359_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560366_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560358_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560360_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560375_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560372_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560363_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560379_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560364_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560362_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560374_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560367_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560387_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560386_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560390_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560398_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560380_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560397_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560384_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560393_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560394_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560388_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560385_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560383_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560400_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560401_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560406_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560407_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560408_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560409_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560404_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560412_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560402_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560411_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560413_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560421_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560414_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560416_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560420_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560422_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560423_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560417_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560443_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560448_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560432_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560439_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560428_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560442_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560426_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560447_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560425_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560436_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560430_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560434_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560445_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560441_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560444_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560440_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560461_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560471_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560463_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560468_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560483_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560453_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560475_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560456_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560457_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560478_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560476_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560462_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560466_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560489_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560465_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560469_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560472_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560455_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560474_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560480_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560473_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560454_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560460_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560487_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560467_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560452_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560497_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560491_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560492_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560498_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560496_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560493_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560490_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560499_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560520_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560514_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560528_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560505_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560510_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560516_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560522_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560524_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560525_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560503_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560513_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560509_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560529_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560506_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560518_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560504_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560540_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560558_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560546_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560551_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560544_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560557_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560550_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560554_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560537_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560533_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560545_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560549_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560532_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560542_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560538_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560539_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560577_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560560_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560575_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560568_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560583_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560576_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560571_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560573_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560567_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560574_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560582_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560610_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560606_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560599_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560611_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560591_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560592_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560598_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560614_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560609_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560608_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560612_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560594_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560619_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560605_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560595_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560602_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560593_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560616_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560604_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560622_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560625_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560638_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560636_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560620_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560626_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560628_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560627_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560634_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560624_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560689_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560681_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560639_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560641_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560652_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560680_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560672_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560642_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560677_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560655_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560669_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560661_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560667_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560670_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560658_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560660_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560686_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560643_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560684_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560685_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560676_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560687_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560663_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560651_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560650_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560647_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560645_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560678_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560656_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560664_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560679_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560683_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560640_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560673_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560654_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560648_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560662_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560682_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560657_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560671_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560653_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560321_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560324_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560315_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560317_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560342_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560344_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560337_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560350_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560355_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560361_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560371_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560376_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560373_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560378_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560370_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560389_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560396_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560392_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560395_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560391_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560410_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560405_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560424_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560431_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560450_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560438_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560437_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560449_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560451_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560458_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560477_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560464_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560485_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560486_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560459_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560481_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560494_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560511_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560519_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560521_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560517_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560515_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560502_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560559_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560534_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560531_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560535_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560556_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560553_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560543_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560548_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560562_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560580_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560581_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560579_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560569_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560578_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560566_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560561_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560563_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560564_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560589_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560607_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560618_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560613_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560617_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560615_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560600_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560623_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560633_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560621_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560635_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560637_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560630_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560674_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560649_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560659_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560666_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560668_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560419_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560488_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560586_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560328_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560329_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560325_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560322_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560312_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560314_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560349_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560368_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560381_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560399_0.png treat image : temp/1738890629_1110649_1335225399_f71859d7cc31a8be9a0bece4a10eca95_rle_crop_3658560382_0.png treat image : temp/1738890629_1110649_1335219623_f538027372ac1178e7127864e15ac526_rle_crop_3658560403_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560415_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560446_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560429_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560427_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560435_0.png treat image : temp/1738890629_1110649_1335219618_9f1c6a003d7bfd83d3bead6076fce6fb_rle_crop_3658560433_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560479_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560470_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560482_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560495_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560530_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560507_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560501_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560512_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560527_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560508_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560526_0.png treat image : temp/1738890629_1110649_1335219564_5a98b5c6246a9949f0cfb6e2532e5f89_rle_crop_3658560523_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560552_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560555_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560536_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560541_0.png treat image : temp/1738890629_1110649_1335219561_d693f0e15ba5b1a81167344b558b5284_rle_crop_3658560547_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560570_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560572_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560565_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560585_0.png treat image : temp/1738890629_1110649_1335219557_2fd8b98741f0bfbff663fa105d9ee83b_rle_crop_3658560584_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560590_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560603_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560596_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560601_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560588_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560587_0.png treat image : temp/1738890629_1110649_1335219553_35270ef7a71ebf037301be7621fd29dd_rle_crop_3658560597_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560632_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560629_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560646_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560644_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560688_0.png treat image : temp/1738890629_1110649_1335225948_c63803fd68282cddcbfc82ffc1efb143_rle_crop_3658560316_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560357_0.png treat image : temp/1738890629_1110649_1335225693_f03e776da57d9b0a6f47f7d14d0d6ce7_rle_crop_3658560334_0.png treat image : temp/1738890629_1110649_1335225459_1cc520116cbbfffec882f156e7463f5c_rle_crop_3658560369_0.png treat image : temp/1738890629_1110649_1335219621_1a4fe4f880ab2651e92bdc61319c7389_rle_crop_3658560418_0.png treat image : temp/1738890629_1110649_1335219615_b79b48be17849aec0ba08ab58a876852_rle_crop_3658560484_0.png treat image : temp/1738890629_1110649_1335219566_1518b732aa744c08eb069eff30b58c6d_rle_crop_3658560500_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560675_0.png treat image : temp/1738890629_1110649_1335219421_fda346d6d0f5c9f73f5d2bbdc89fc01e_rle_crop_3658560665_0.png treat image : temp/1738890629_1110649_1335219546_3a19d5dc8f9b3aff32c3132072eac43a_rle_crop_3658560631_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 : 393 time used for this insertion : 0.5980091094970703 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 393 time used for this insertion : 0.8299062252044678 save missing photos in datou_result : time spend for datou_step_exec : 18.54745888710022 time spend to save output : 1.4362094402313232 total time spend for step 7 : 19.983668327331543 step8:velours_tree Fri Feb 7 02:24:07 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 : 2.23608660697937 time spend to save output : 6.604194641113281e-05 total time spend for step 8 : 2.2361526489257812 step9:send_mail_cod Fri Feb 7 02:24:09 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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_P20314836_07-02-2025_02_24_09.pdf 20315496 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette203154961738891449 20315497 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette203154971738891450 20315498 change filename to text .imagette203154981738891452 20315499 change filename to text .change filename to text .change filename to text .imagette203154991738891452 20315500 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette203155001738891452 20315501 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette203155011738891453 20315502 imagette203155021738891455 20315503 change filename to text .imagette203155031738891455 20315505 imagette203155051738891455 20315506 imagette203155061738891455 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20314836 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20315496,20315497,20315498,20315499,20315500,20315501,20315502,20315503,20315504,20315505,20315506?tags=carton,papier,pet_fonce,metal,autre,pet_clair,background,pehd,environnement,mal_croppe,flou args[1335225948] : ((1335225948, -4.719259332605742, 492609224), (1335225948, 0.11742158098283322, 2107752395), '0.21934313347252485') apple ((1335225948, -4.719259332605742, 492609224), (1335225948, 0.11742158098283322, 2107752395), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335225693] : ((1335225693, -6.706028975045214, 492609224), (1335225693, -0.36751736492534487, 496442774), '0.21934313347252485') apple ((1335225693, -6.706028975045214, 492609224), (1335225693, -0.36751736492534487, 496442774), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335225459] : ((1335225459, -6.072495598915214, 492609224), (1335225459, -0.2468924162231977, 496442774), '0.21934313347252485') apple ((1335225459, -6.072495598915214, 492609224), (1335225459, -0.2468924162231977, 496442774), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335225399] : ((1335225399, -5.460320966663146, 492609224), (1335225399, -0.28720368900202903, 496442774), '0.21934313347252485') apple ((1335225399, -5.460320966663146, 492609224), (1335225399, -0.28720368900202903, 496442774), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219623] : ((1335219623, -3.701866269876599, 492609224), (1335219623, 0.3848430619379359, 2107752395), '0.21934313347252485') apple ((1335219623, -3.701866269876599, 492609224), (1335219623, 0.3848430619379359, 2107752395), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219621] : ((1335219621, -6.353417185847009, 492609224), (1335219621, 0.31434585246961694, 2107752395), '0.21934313347252485') apple ((1335219621, -6.353417185847009, 492609224), (1335219621, 0.31434585246961694, 2107752395), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219618] : ((1335219618, -5.471980896116209, 492609224), (1335219618, 0.007344944117847618, 2107752395), '0.21934313347252485') apple ((1335219618, -5.471980896116209, 492609224), (1335219618, 0.007344944117847618, 2107752395), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219615] : ((1335219615, -5.81692199713472, 492609224), (1335219615, -0.5857402549044533, 501862349), '0.21934313347252485') apple ((1335219615, -5.81692199713472, 492609224), (1335219615, -0.5857402549044533, 501862349), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219566] : ((1335219566, -3.7804287139309425, 492609224), (1335219566, 0.3996367763046506, 2107752395), '0.21934313347252485') apple ((1335219566, -3.7804287139309425, 492609224), (1335219566, 0.3996367763046506, 2107752395), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219564] : ((1335219564, -5.431141047109782, 492609224), (1335219564, -0.20672617405127125, 496442774), '0.21934313347252485') apple ((1335219564, -5.431141047109782, 492609224), (1335219564, -0.20672617405127125, 496442774), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219561] : ((1335219561, -6.399307803714703, 492609224), (1335219561, -0.35779886324543037, 496442774), '0.21934313347252485') apple ((1335219561, -6.399307803714703, 492609224), (1335219561, -0.35779886324543037, 496442774), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219557] : ((1335219557, -4.996716735252738, 492609224), (1335219557, -0.3491963016021358, 496442774), '0.21934313347252485') apple ((1335219557, -4.996716735252738, 492609224), (1335219557, -0.3491963016021358, 496442774), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219553] : ((1335219553, -6.318759888728304, 492609224), (1335219553, -0.17318354077217965, 496442774), '0.21934313347252485') apple ((1335219553, -6.318759888728304, 492609224), (1335219553, -0.17318354077217965, 496442774), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219546] : ((1335219546, -4.814423980984235, 492609224), (1335219546, 0.01715606960938015, 2107752395), '0.21934313347252485') apple ((1335219546, -4.814423980984235, 492609224), (1335219546, 0.01715606960938015, 2107752395), '0.21934313347252485') We are sending mail with results at report@fotonower.com args[1335219421] : ((1335219421, -5.6245022722702185, 492609224), (1335219421, -0.09142617512088026, 496442774), '0.21934313347252485') apple ((1335219421, -5.6245022722702185, 492609224), (1335219421, -0.09142617512088026, 496442774), '0.21934313347252485') We are sending mail with results at report@fotonower.com refus_total : 0.21934313347252485 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=20314836 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 SELECT photo_id, url FROM MTRBack.photos ph WHERE photo_id IN (1335219546,1335225459,1335225693,1335219421,1335219553,1335219557,1335219561,1335219564,1335219566,1335219615,1335219618,1335219621,1335219623,1335225399,1335225948) Found this number of photos: 15 begin to download photo : 1335219546 begin to download photo : 1335219553 begin to download photo : 1335219566 begin to download photo : 1335219623 download finish for photo 1335219566 begin to download photo : 1335219615 download finish for photo 1335219623 begin to download photo : 1335225399 download finish for photo 1335219546 begin to download photo : 1335225459 download finish for photo 1335219553 begin to download photo : 1335219557 download finish for photo 1335225399 begin to download photo : 1335225948 download finish for photo 1335219615 begin to download photo : 1335219618 download finish for photo 1335225459 begin to download photo : 1335225693 download finish for photo 1335219557 begin to download photo : 1335219561 download finish for photo 1335225948 download finish for photo 1335225693 begin to download photo : 1335219421 download finish for photo 1335219618 begin to download photo : 1335219621 download finish for photo 1335219561 begin to download photo : 1335219564 download finish for photo 1335219421 download finish for photo 1335219621 download finish for photo 1335219564 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314836_07-02-2025_02_24_09.pdf results_Auto_P20314836_07-02-2025_02_24_09.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314836_07-02-2025_02_24_09.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','20314836','results_Auto_P20314836_07-02-2025_02_24_09.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314836_07-02-2025_02_24_09.pdf','pdf','','1.3','0.21934313347252485') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/20314836

https://www.fotonower.com/image?json=false&list_photos_id=1335225948
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335225693
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335225459
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335225399
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219623
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219621
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219618
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219615
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219566
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219564
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219561
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219557
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219553
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219546
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1335219421
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 21.93%
Veuillez trouver les photos des contaminants.

exemples de contaminants: carton: https://www.fotonower.com/view/20315496?limit=200
exemples de contaminants: papier: https://www.fotonower.com/view/20315497?limit=200
exemples de contaminants: pet_fonce: https://www.fotonower.com/view/20315498?limit=200
exemples de contaminants: metal: https://www.fotonower.com/view/20315499?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/20315500?limit=200
exemples de contaminants: pet_clair: https://www.fotonower.com/view/20315501?limit=200
exemples de contaminants: pehd: https://www.fotonower.com/view/20315503?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314836_07-02-2025_02_24_09.pdf.

Lien vers velours :https://www.fotonower.com/velours/20315496,20315497,20315498,20315499,20315500,20315501,20315502,20315503,20315504,20315505,20315506?tags=carton,papier,pet_fonce,metal,autre,pet_clair,background,pehd,environnement,mal_croppe,flou.


L'équipe Fotonower 202 b'' Server: nginx Date: Fri, 07 Feb 2025 01:24:20 GMT Content-Length: 0 Connection: close X-Message-Id: TWUCiCrKTR6JPX9Hgk-3iw 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 [1335225948, 1335225693, 1335225459, 1335225399, 1335219623, 1335219621, 1335219618, 1335219615, 1335219566, 1335219564, 1335219561, 1335219557, 1335219553, 1335219546, 1335219421] 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, '2560894') ('3318', '20314836', '1335225948', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225693', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225459', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225399', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219623', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219621', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219618', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219615', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219566', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219564', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219561', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219557', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219553', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219546', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219421', None, None, None, None, None, '2560894') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.014815092086791992 save_final save missing photos in datou_result : time spend for datou_step_exec : 10.647028923034668 time spend to save output : 0.015474081039428711 total time spend for step 9 : 10.662503004074097 step10:split_time_score Fri Feb 7 02:24:20 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 ! 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'}] (('12', 11), ('13', 4)) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 06022025 20314836 Nombre de photos uploadées : 15 / 23040 (0%) 06022025 20314836 Nombre de photos taguées (types de déchets): 0 / 15 (0%) 06022025 20314836 Nombre de photos taguées (volume) : 0 / 15 (0%) elapsed_time : load_data_split_time_score 6.4373016357421875e-06 elapsed_time : order_list_meta_photo_and_scores 1.4781951904296875e-05 ??????????????? elapsed_time : fill_and_build_computed_from_old_data 0.0007841587066650391 elapsed_time : insert_dashboard_record_day_entry 0.028995037078857422 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314812 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314823 order by id desc limit 1 Qualite : 0.07702728454025964 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314827_07-02-2025_01_57_52.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314827 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`=20314827 AND mptpi.`type`=3726 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314835 order by id desc limit 1 Qualite : 0.21934313347252485 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314836_07-02-2025_02_24_09.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314836 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`=20314836 AND mptpi.`type`=3594 To do Qualite : 0.20801924237094532 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314842_07-02-2025_02_02_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314842 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`=20314842 AND mptpi.`type`=3594 To do Qualite : 0.08977715635017561 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314846_07-02-2025_01_55_45.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314846 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`=20314846 AND mptpi.`type`=3726 To do Qualite : 0.08573655308919938 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314853_07-02-2025_01_44_23.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314853 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`=20314853 AND mptpi.`type`=3726 To do Qualite : 0.2245652913943355 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P20314855_07-02-2025_01_50_41.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20314855 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`=20314855 AND mptpi.`type`=3594 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'06022025': {'nb_upload': 15, '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 [1335225948, 1335225693, 1335225459, 1335225399, 1335219623, 1335219621, 1335219618, 1335219615, 1335219566, 1335219564, 1335219561, 1335219557, 1335219553, 1335219546, 1335219421] Looping around the photos to save general results len do output : 1 /20314836Didn'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, '2560894') ('3318', '20314836', '1335225948', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225693', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225459', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335225399', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219623', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219621', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219618', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219615', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219566', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219564', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219561', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219557', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219553', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219546', None, None, None, None, None, '2560894') ('3318', None, None, None, None, None, None, None, '2560894') ('3318', '20314836', '1335219421', None, None, None, None, None, '2560894') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 16 time used for this insertion : 0.9920427799224854 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.9299488067626953 time spend to save output : 0.9925041198730469 total time spend for step 10 : 3.922452926635742 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 15 set_done_treatment 384.74user 229.23system 13:59.75elapsed 73%CPU (0avgtext+0avgdata 5105008maxresident)k 16808864inputs+340976outputs (458509major+29012887minor)pagefaults 0swaps