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 : 2361629 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 : ['2758897'] with mtr_portfolio_ids : ['22396717'] and first list_photo_ids : [] new path : /proc/2361629/ 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 , BFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 17 ; length of list_pids : 17 ; length of list_args : 17 time to download the photos : 2.806548833847046 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 Thu Apr 24 20:40:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3249 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-04-24 20:40:33.236362: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-04-24 20:40:33.263209: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-04-24 20:40:33.265226: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fed08000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-04-24 20:40:33.265257: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-04-24 20:40:33.269373: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-04-24 20:40:33.506065: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1f42d770 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-04-24 20:40:33.506120: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-04-24 20:40:33.507019: 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 2025-04-24 20:40:33.507475: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-24 20:40:33.510637: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-24 20:40:33.513946: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-24 20:40:33.514580: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-24 20:40:33.517676: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-24 20:40:33.518874: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-24 20:40:33.524312: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-24 20:40:33.525498: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-24 20:40:33.525609: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-24 20:40:33.526198: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-24 20:40:33.526214: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-24 20:40:33.526224: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-04-24 20:40:33.527223: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2797 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. 2025-04-24 20:40:33.789743: 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 2025-04-24 20:40:33.789842: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-24 20:40:33.789864: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-24 20:40:33.789884: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-24 20:40:33.789903: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-24 20:40:33.789922: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-24 20:40:33.789940: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-24 20:40:33.789959: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-24 20:40:33.790994: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-24 20:40:33.791985: 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 2025-04-24 20:40:33.792022: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-24 20:40:33.792041: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-24 20:40:33.792059: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-24 20:40:33.792076: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-24 20:40:33.792094: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-24 20:40:33.792112: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-24 20:40:33.792129: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-24 20:40:33.793150: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-24 20:40:33.793180: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-24 20:40:33.793190: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-24 20:40:33.793200: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-04-24 20:40:33.794274: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2797 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 : [] 2025-04-24 20:40:44.545080: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-24 20:40:44.728337: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-24 20:40:46.180676: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.180755: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.181341: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.181362: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.188443: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.188464: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.189015: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.189029: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.195572: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.195593: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.196180: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.196196: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.227028: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.227065: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.227666: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.227684: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.233533: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.233557: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.234146: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.234164: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-04-24 20:40:46.267985: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.268591: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.270420: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.270980: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.314737: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.315316: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.317510: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.318061: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.348487: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.349078: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.350758: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.351343: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.357804: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.358357: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.360178: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.360771: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.366604: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.367184: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.368785: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.369336: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.395969: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.396578: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.397143: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.397687: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.401140: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.401691: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.417081: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.417635: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.418179: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.418752: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.430951: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.431502: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.432047: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.432589: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.437026: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.437621: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.442262: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.442826: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.455288: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.455894: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.460094: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.460643: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.461187: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.461730: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.462517: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.463108: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.473763: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.474358: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.474980: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.475566: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.476142: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.476681: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.491895: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.492457: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.541167: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.542106: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.550464: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.551386: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.568276: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.568908: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.569522: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.570111: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.574165: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.574758: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.575368: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.575959: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.577224: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.577247: 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. 2025-04-24 20:40:46.587196: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.587790: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.596750: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.597344: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.597941: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.598550: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.599290: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-24 20:40:46.599881: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.23G (2397962240 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 : 17 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 11.00000 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 : 23 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 : 40 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 18.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 20 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 23.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 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 : 16 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 : 66 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 12.00000 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 : 35 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 55.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 12 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 3.00000 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 : 21 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 31.00000 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 : 10 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 : 53 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 : 34 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 : 54 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 42.00000 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 : 21 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 : 57 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 24.00000 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 : 17 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 4.00000 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 : 42 Detection mask done ! Trying to reset tf kernel 2362278 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 863 tf kernel not reseted sub process len(results) : 17 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 17 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 : 2056 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 : 0.014004230499267578 nb_pixel_total : 26563 time to create 1 rle with old method : 0.03381156921386719 length of segment : 237 time for calcul the mask position with numpy : 0.018486976623535156 nb_pixel_total : 42716 time to create 1 rle with old method : 0.05162477493286133 length of segment : 311 time for calcul the mask position with numpy : 0.0024003982543945312 nb_pixel_total : 8574 time to create 1 rle with old method : 0.009760618209838867 length of segment : 110 time for calcul the mask position with numpy : 0.035399675369262695 nb_pixel_total : 158359 time to create 1 rle with new method : 0.01297760009765625 length of segment : 598 time for calcul the mask position with numpy : 0.008913278579711914 nb_pixel_total : 20347 time to create 1 rle with old method : 0.027364492416381836 length of segment : 188 time for calcul the mask position with numpy : 0.002597808837890625 nb_pixel_total : 4319 time to create 1 rle with old method : 0.005167961120605469 length of segment : 69 time for calcul the mask position with numpy : 0.042240142822265625 nb_pixel_total : 50253 time to create 1 rle with old method : 0.06276249885559082 length of segment : 416 time for calcul the mask position with numpy : 0.011436939239501953 nb_pixel_total : 113032 time to create 1 rle with old method : 0.12753081321716309 length of segment : 296 time for calcul the mask position with numpy : 0.00035834312438964844 nb_pixel_total : 13599 time to create 1 rle with old method : 0.016095399856567383 length of segment : 132 time for calcul the mask position with numpy : 0.0948338508605957 nb_pixel_total : 182042 time to create 1 rle with new method : 0.015309333801269531 length of segment : 717 time for calcul the mask position with numpy : 0.0020215511322021484 nb_pixel_total : 27410 time to create 1 rle with old method : 0.030618667602539062 length of segment : 221 time for calcul the mask position with numpy : 0.0173032283782959 nb_pixel_total : 102711 time to create 1 rle with old method : 0.1157839298248291 length of segment : 393 time for calcul the mask position with numpy : 0.005147218704223633 nb_pixel_total : 17548 time to create 1 rle with old method : 0.03090977668762207 length of segment : 163 time for calcul the mask position with numpy : 0.004342555999755859 nb_pixel_total : 13270 time to create 1 rle with old method : 0.017446279525756836 length of segment : 224 time for calcul the mask position with numpy : 0.03206634521484375 nb_pixel_total : 94496 time to create 1 rle with old method : 0.10615825653076172 length of segment : 320 time for calcul the mask position with numpy : 0.008274316787719727 nb_pixel_total : 33291 time to create 1 rle with old method : 0.04232645034790039 length of segment : 223 time for calcul the mask position with numpy : 0.00490570068359375 nb_pixel_total : 13146 time to create 1 rle with old method : 0.016681909561157227 length of segment : 153 time for calcul the mask position with numpy : 0.004450082778930664 nb_pixel_total : 35133 time to create 1 rle with old method : 0.04257321357727051 length of segment : 128 time for calcul the mask position with numpy : 0.0639181137084961 nb_pixel_total : 143862 time to create 1 rle with old method : 0.19145488739013672 length of segment : 523 time for calcul the mask position with numpy : 0.0033371448516845703 nb_pixel_total : 22449 time to create 1 rle with old method : 0.02785801887512207 length of segment : 152 time for calcul the mask position with numpy : 0.0014183521270751953 nb_pixel_total : 19592 time to create 1 rle with old method : 0.02209305763244629 length of segment : 105 time for calcul the mask position with numpy : 0.004746198654174805 nb_pixel_total : 6836 time to create 1 rle with old method : 0.009366273880004883 length of segment : 118 time for calcul the mask position with numpy : 0.0001881122589111328 nb_pixel_total : 4359 time to create 1 rle with old method : 0.005457401275634766 length of segment : 64 time for calcul the mask position with numpy : 0.02384185791015625 nb_pixel_total : 28641 time to create 1 rle with old method : 0.038297414779663086 length of segment : 212 time for calcul the mask position with numpy : 0.05410170555114746 nb_pixel_total : 113699 time to create 1 rle with old method : 0.12990498542785645 length of segment : 504 time for calcul the mask position with numpy : 0.0041046142578125 nb_pixel_total : 14687 time to create 1 rle with old method : 0.016527891159057617 length of segment : 128 time for calcul the mask position with numpy : 0.00089263916015625 nb_pixel_total : 13092 time to create 1 rle with old method : 0.021277427673339844 length of segment : 213 time for calcul the mask position with numpy : 0.021534442901611328 nb_pixel_total : 46756 time to create 1 rle with old method : 0.05027365684509277 length of segment : 378 time for calcul the mask position with numpy : 0.0019092559814453125 nb_pixel_total : 13564 time to create 1 rle with old method : 0.015054702758789062 length of segment : 142 time for calcul the mask position with numpy : 0.00041556358337402344 nb_pixel_total : 10192 time to create 1 rle with old method : 0.010974407196044922 length of segment : 171 time for calcul the mask position with numpy : 0.0011131763458251953 nb_pixel_total : 11708 time to create 1 rle with old method : 0.012591123580932617 length of segment : 156 time for calcul the mask position with numpy : 0.004372596740722656 nb_pixel_total : 9962 time to create 1 rle with old method : 0.010916948318481445 length of segment : 117 time for calcul the mask position with numpy : 0.013985633850097656 nb_pixel_total : 37812 time to create 1 rle with old method : 0.0409388542175293 length of segment : 267 time for calcul the mask position with numpy : 0.0017423629760742188 nb_pixel_total : 24129 time to create 1 rle with old method : 0.026550769805908203 length of segment : 169 time for calcul the mask position with numpy : 0.00523686408996582 nb_pixel_total : 11487 time to create 1 rle with old method : 0.012491941452026367 length of segment : 118 time for calcul the mask position with numpy : 0.0033593177795410156 nb_pixel_total : 14158 time to create 1 rle with old method : 0.020173072814941406 length of segment : 155 time for calcul the mask position with numpy : 0.00043010711669921875 nb_pixel_total : 15642 time to create 1 rle with old method : 0.018201589584350586 length of segment : 138 time for calcul the mask position with numpy : 0.002553224563598633 nb_pixel_total : 26730 time to create 1 rle with old method : 0.03034496307373047 length of segment : 197 time for calcul the mask position with numpy : 0.06912636756896973 nb_pixel_total : 309468 time to create 1 rle with new method : 0.0191500186920166 length of segment : 601 time for calcul the mask position with numpy : 0.002153635025024414 nb_pixel_total : 166645 time to create 1 rle with new method : 0.007109165191650391 length of segment : 454 time for calcul the mask position with numpy : 0.008574485778808594 nb_pixel_total : 29462 time to create 1 rle with old method : 0.03632783889770508 length of segment : 216 time for calcul the mask position with numpy : 0.003408670425415039 nb_pixel_total : 31371 time to create 1 rle with old method : 0.04605579376220703 length of segment : 291 time for calcul the mask position with numpy : 0.00030922889709472656 nb_pixel_total : 16590 time to create 1 rle with old method : 0.019156217575073242 length of segment : 187 time for calcul the mask position with numpy : 0.013652801513671875 nb_pixel_total : 34237 time to create 1 rle with old method : 0.04549121856689453 length of segment : 413 time for calcul the mask position with numpy : 0.23260760307312012 nb_pixel_total : 381996 time to create 1 rle with new method : 0.06344938278198242 length of segment : 1699 time for calcul the mask position with numpy : 0.0032150745391845703 nb_pixel_total : 234277 time to create 1 rle with new method : 0.009055852890014648 length of segment : 453 time for calcul the mask position with numpy : 0.00054168701171875 nb_pixel_total : 18522 time to create 1 rle with old method : 0.020482778549194336 length of segment : 159 time for calcul the mask position with numpy : 0.03173542022705078 nb_pixel_total : 269341 time to create 1 rle with new method : 0.08285355567932129 length of segment : 927 time for calcul the mask position with numpy : 0.0007994174957275391 nb_pixel_total : 16524 time to create 1 rle with old method : 0.01829671859741211 length of segment : 263 time for calcul the mask position with numpy : 0.0010213851928710938 nb_pixel_total : 27666 time to create 1 rle with old method : 0.031172990798950195 length of segment : 297 time for calcul the mask position with numpy : 0.0006663799285888672 nb_pixel_total : 17732 time to create 1 rle with old method : 0.020231008529663086 length of segment : 146 time for calcul the mask position with numpy : 0.00481867790222168 nb_pixel_total : 210893 time to create 1 rle with new method : 0.009034395217895508 length of segment : 518 time for calcul the mask position with numpy : 0.011692047119140625 nb_pixel_total : 20243 time to create 1 rle with old method : 0.02397465705871582 length of segment : 120 time for calcul the mask position with numpy : 0.011396169662475586 nb_pixel_total : 19300 time to create 1 rle with old method : 0.026441335678100586 length of segment : 149 time for calcul the mask position with numpy : 0.004309892654418945 nb_pixel_total : 22259 time to create 1 rle with old method : 0.02789592742919922 length of segment : 221 time for calcul the mask position with numpy : 0.0847005844116211 nb_pixel_total : 93682 time to create 1 rle with old method : 0.10605645179748535 length of segment : 445 time for calcul the mask position with numpy : 0.03068709373474121 nb_pixel_total : 53879 time to create 1 rle with old method : 0.06432771682739258 length of segment : 329 time for calcul the mask position with numpy : 0.008870840072631836 nb_pixel_total : 129632 time to create 1 rle with old method : 0.13753390312194824 length of segment : 693 time for calcul the mask position with numpy : 0.046849727630615234 nb_pixel_total : 186679 time to create 1 rle with new method : 0.009363889694213867 length of segment : 679 time for calcul the mask position with numpy : 0.0008530616760253906 nb_pixel_total : 23901 time to create 1 rle with old method : 0.026335716247558594 length of segment : 239 time for calcul the mask position with numpy : 0.000682830810546875 nb_pixel_total : 23692 time to create 1 rle with old method : 0.025753498077392578 length of segment : 203 time for calcul the mask position with numpy : 0.000972747802734375 nb_pixel_total : 29482 time to create 1 rle with old method : 0.032248497009277344 length of segment : 353 time for calcul the mask position with numpy : 0.02939128875732422 nb_pixel_total : 673831 time to create 1 rle with new method : 0.11571621894836426 length of segment : 992 time for calcul the mask position with numpy : 0.007199764251708984 nb_pixel_total : 133143 time to create 1 rle with old method : 0.1406996250152588 length of segment : 562 time for calcul the mask position with numpy : 0.002542734146118164 nb_pixel_total : 88321 time to create 1 rle with old method : 0.09655117988586426 length of segment : 257 time for calcul the mask position with numpy : 0.0017061233520507812 nb_pixel_total : 70154 time to create 1 rle with old method : 0.08039307594299316 length of segment : 460 time for calcul the mask position with numpy : 0.02171039581298828 nb_pixel_total : 202081 time to create 1 rle with new method : 0.009399890899658203 length of segment : 645 time for calcul the mask position with numpy : 0.006323575973510742 nb_pixel_total : 37808 time to create 1 rle with old method : 0.046360015869140625 length of segment : 115 time for calcul the mask position with numpy : 0.0008518695831298828 nb_pixel_total : 8616 time to create 1 rle with old method : 0.011709451675415039 length of segment : 107 time for calcul the mask position with numpy : 0.0008819103240966797 nb_pixel_total : 11267 time to create 1 rle with old method : 0.013424873352050781 length of segment : 132 time for calcul the mask position with numpy : 0.0004994869232177734 nb_pixel_total : 8483 time to create 1 rle with old method : 0.010195732116699219 length of segment : 112 time for calcul the mask position with numpy : 0.003351449966430664 nb_pixel_total : 45919 time to create 1 rle with old method : 0.05192756652832031 length of segment : 300 time for calcul the mask position with numpy : 0.0026030540466308594 nb_pixel_total : 39870 time to create 1 rle with old method : 0.0457005500793457 length of segment : 213 time for calcul the mask position with numpy : 0.0009529590606689453 nb_pixel_total : 9686 time to create 1 rle with old method : 0.011320829391479492 length of segment : 120 time for calcul the mask position with numpy : 0.0006425380706787109 nb_pixel_total : 8266 time to create 1 rle with old method : 0.009809732437133789 length of segment : 106 time for calcul the mask position with numpy : 0.0009100437164306641 nb_pixel_total : 10696 time to create 1 rle with old method : 0.012462854385375977 length of segment : 176 time for calcul the mask position with numpy : 0.004864692687988281 nb_pixel_total : 64773 time to create 1 rle with old method : 0.07191824913024902 length of segment : 366 time for calcul the mask position with numpy : 0.0011208057403564453 nb_pixel_total : 10861 time to create 1 rle with old method : 0.01300191879272461 length of segment : 113 time for calcul the mask position with numpy : 0.0013251304626464844 nb_pixel_total : 15831 time to create 1 rle with old method : 0.018575429916381836 length of segment : 176 time for calcul the mask position with numpy : 0.003436565399169922 nb_pixel_total : 54646 time to create 1 rle with old method : 0.06246137619018555 length of segment : 280 time for calcul the mask position with numpy : 0.0006403923034667969 nb_pixel_total : 9652 time to create 1 rle with old method : 0.011138916015625 length of segment : 133 time for calcul the mask position with numpy : 0.0007097721099853516 nb_pixel_total : 8167 time to create 1 rle with old method : 0.009418010711669922 length of segment : 154 time for calcul the mask position with numpy : 0.0006213188171386719 nb_pixel_total : 8756 time to create 1 rle with old method : 0.010023355484008789 length of segment : 82 time for calcul the mask position with numpy : 0.002044200897216797 nb_pixel_total : 22491 time to create 1 rle with old method : 0.025086164474487305 length of segment : 174 time for calcul the mask position with numpy : 0.002191305160522461 nb_pixel_total : 43093 time to create 1 rle with old method : 0.04593801498413086 length of segment : 314 time for calcul the mask position with numpy : 0.0005576610565185547 nb_pixel_total : 6310 time to create 1 rle with old method : 0.0073299407958984375 length of segment : 95 time for calcul the mask position with numpy : 0.0017747879028320312 nb_pixel_total : 33048 time to create 1 rle with old method : 0.03629922866821289 length of segment : 261 time for calcul the mask position with numpy : 0.005293130874633789 nb_pixel_total : 62536 time to create 1 rle with old method : 0.06665754318237305 length of segment : 324 time for calcul the mask position with numpy : 0.002692699432373047 nb_pixel_total : 49690 time to create 1 rle with old method : 0.08111357688903809 length of segment : 389 time for calcul the mask position with numpy : 0.004719734191894531 nb_pixel_total : 59687 time to create 1 rle with old method : 0.06649351119995117 length of segment : 345 time for calcul the mask position with numpy : 0.00046753883361816406 nb_pixel_total : 6240 time to create 1 rle with old method : 0.0073986053466796875 length of segment : 104 time for calcul the mask position with numpy : 0.0005469322204589844 nb_pixel_total : 11475 time to create 1 rle with old method : 0.012831926345825195 length of segment : 133 time for calcul the mask position with numpy : 0.0007138252258300781 nb_pixel_total : 8661 time to create 1 rle with old method : 0.009821891784667969 length of segment : 103 time for calcul the mask position with numpy : 0.0010983943939208984 nb_pixel_total : 15404 time to create 1 rle with old method : 0.017519474029541016 length of segment : 160 time for calcul the mask position with numpy : 0.000911712646484375 nb_pixel_total : 13837 time to create 1 rle with old method : 0.015706300735473633 length of segment : 124 time for calcul the mask position with numpy : 0.0011224746704101562 nb_pixel_total : 18671 time to create 1 rle with old method : 0.021363019943237305 length of segment : 116 time for calcul the mask position with numpy : 0.002852201461791992 nb_pixel_total : 48996 time to create 1 rle with old method : 0.05843043327331543 length of segment : 337 time for calcul the mask position with numpy : 0.0028448104858398438 nb_pixel_total : 55224 time to create 1 rle with old method : 0.06413054466247559 length of segment : 398 time for calcul the mask position with numpy : 0.0008373260498046875 nb_pixel_total : 6283 time to create 1 rle with old method : 0.008983850479125977 length of segment : 119 time for calcul the mask position with numpy : 0.0004572868347167969 nb_pixel_total : 7788 time to create 1 rle with old method : 0.009001016616821289 length of segment : 125 time for calcul the mask position with numpy : 0.0009410381317138672 nb_pixel_total : 12109 time to create 1 rle with old method : 0.01593756675720215 length of segment : 185 time for calcul the mask position with numpy : 0.0009226799011230469 nb_pixel_total : 15090 time to create 1 rle with old method : 0.01691269874572754 length of segment : 159 time for calcul the mask position with numpy : 0.01180410385131836 nb_pixel_total : 324999 time to create 1 rle with new method : 0.022556781768798828 length of segment : 516 time for calcul the mask position with numpy : 0.0009591579437255859 nb_pixel_total : 18552 time to create 1 rle with old method : 0.021483898162841797 length of segment : 150 time for calcul the mask position with numpy : 0.0021452903747558594 nb_pixel_total : 44718 time to create 1 rle with old method : 0.050661325454711914 length of segment : 329 time for calcul the mask position with numpy : 0.0013997554779052734 nb_pixel_total : 37204 time to create 1 rle with old method : 0.04199719429016113 length of segment : 280 time for calcul the mask position with numpy : 0.0018093585968017578 nb_pixel_total : 37447 time to create 1 rle with old method : 0.04225945472717285 length of segment : 345 time for calcul the mask position with numpy : 0.0006003379821777344 nb_pixel_total : 6881 time to create 1 rle with old method : 0.008645296096801758 length of segment : 142 time for calcul the mask position with numpy : 0.0005898475646972656 nb_pixel_total : 10452 time to create 1 rle with old method : 0.012300491333007812 length of segment : 129 time for calcul the mask position with numpy : 0.000705718994140625 nb_pixel_total : 11608 time to create 1 rle with old method : 0.01377105712890625 length of segment : 99 time for calcul the mask position with numpy : 0.0012249946594238281 nb_pixel_total : 19984 time to create 1 rle with old method : 0.023841381072998047 length of segment : 225 time for calcul the mask position with numpy : 0.0032660961151123047 nb_pixel_total : 64814 time to create 1 rle with old method : 0.07496523857116699 length of segment : 209 time for calcul the mask position with numpy : 0.0006968975067138672 nb_pixel_total : 17861 time to create 1 rle with old method : 0.020320653915405273 length of segment : 124 time for calcul the mask position with numpy : 0.0007967948913574219 nb_pixel_total : 20593 time to create 1 rle with old method : 0.02391958236694336 length of segment : 223 time for calcul the mask position with numpy : 0.0006151199340820312 nb_pixel_total : 15519 time to create 1 rle with old method : 0.017803430557250977 length of segment : 183 time for calcul the mask position with numpy : 0.020418405532836914 nb_pixel_total : 493371 time to create 1 rle with new method : 0.06537008285522461 length of segment : 911 time for calcul the mask position with numpy : 0.0006325244903564453 nb_pixel_total : 11932 time to create 1 rle with old method : 0.013990163803100586 length of segment : 91 time for calcul the mask position with numpy : 0.0005180835723876953 nb_pixel_total : 11136 time to create 1 rle with old method : 0.013006210327148438 length of segment : 91 time for calcul the mask position with numpy : 0.0005517005920410156 nb_pixel_total : 18176 time to create 1 rle with old method : 0.020853042602539062 length of segment : 111 time for calcul the mask position with numpy : 0.0011763572692871094 nb_pixel_total : 36777 time to create 1 rle with old method : 0.04152274131774902 length of segment : 199 time for calcul the mask position with numpy : 0.0003056526184082031 nb_pixel_total : 9755 time to create 1 rle with old method : 0.0111846923828125 length of segment : 102 time for calcul the mask position with numpy : 0.0028603076934814453 nb_pixel_total : 117398 time to create 1 rle with old method : 0.13109111785888672 length of segment : 506 time for calcul the mask position with numpy : 0.0007638931274414062 nb_pixel_total : 33006 time to create 1 rle with old method : 0.03688526153564453 length of segment : 199 time for calcul the mask position with numpy : 0.0007224082946777344 nb_pixel_total : 20828 time to create 1 rle with old method : 0.024489641189575195 length of segment : 296 time for calcul the mask position with numpy : 0.0008361339569091797 nb_pixel_total : 35556 time to create 1 rle with old method : 0.04523444175720215 length of segment : 204 time for calcul the mask position with numpy : 0.02312326431274414 nb_pixel_total : 411584 time to create 1 rle with new method : 0.5446562767028809 length of segment : 1014 time for calcul the mask position with numpy : 0.0005252361297607422 nb_pixel_total : 3843 time to create 1 rle with old method : 0.005264997482299805 length of segment : 118 time for calcul the mask position with numpy : 0.00891256332397461 nb_pixel_total : 303832 time to create 1 rle with new method : 0.029337406158447266 length of segment : 735 time for calcul the mask position with numpy : 0.001119375228881836 nb_pixel_total : 67520 time to create 1 rle with old method : 0.08692765235900879 length of segment : 371 time for calcul the mask position with numpy : 0.0008313655853271484 nb_pixel_total : 26598 time to create 1 rle with old method : 0.03507089614868164 length of segment : 220 time for calcul the mask position with numpy : 0.00058746337890625 nb_pixel_total : 14073 time to create 1 rle with old method : 0.016582489013671875 length of segment : 166 time for calcul the mask position with numpy : 0.00821542739868164 nb_pixel_total : 214680 time to create 1 rle with new method : 0.015390634536743164 length of segment : 573 time for calcul the mask position with numpy : 0.0033025741577148438 nb_pixel_total : 165035 time to create 1 rle with new method : 0.005712985992431641 length of segment : 400 time for calcul the mask position with numpy : 0.0005266666412353516 nb_pixel_total : 9842 time to create 1 rle with old method : 0.01318502426147461 length of segment : 112 time for calcul the mask position with numpy : 0.0008070468902587891 nb_pixel_total : 29287 time to create 1 rle with old method : 0.033535003662109375 length of segment : 214 time for calcul the mask position with numpy : 0.004353046417236328 nb_pixel_total : 147200 time to create 1 rle with old method : 0.1649460792541504 length of segment : 484 time for calcul the mask position with numpy : 0.002917051315307617 nb_pixel_total : 148507 time to create 1 rle with old method : 0.1649155616760254 length of segment : 393 time for calcul the mask position with numpy : 0.0016994476318359375 nb_pixel_total : 60392 time to create 1 rle with old method : 0.06673812866210938 length of segment : 326 time for calcul the mask position with numpy : 0.0006110668182373047 nb_pixel_total : 14660 time to create 1 rle with old method : 0.01763153076171875 length of segment : 104 time for calcul the mask position with numpy : 0.006078481674194336 nb_pixel_total : 327347 time to create 1 rle with new method : 0.010250568389892578 length of segment : 1047 time for calcul the mask position with numpy : 0.010773658752441406 nb_pixel_total : 200586 time to create 1 rle with new method : 0.03825783729553223 length of segment : 1378 time for calcul the mask position with numpy : 0.000316619873046875 nb_pixel_total : 10273 time to create 1 rle with old method : 0.01162099838256836 length of segment : 114 time for calcul the mask position with numpy : 0.0012154579162597656 nb_pixel_total : 22862 time to create 1 rle with old method : 0.026241779327392578 length of segment : 178 time for calcul the mask position with numpy : 0.0018284320831298828 nb_pixel_total : 28696 time to create 1 rle with old method : 0.032793283462524414 length of segment : 250 time for calcul the mask position with numpy : 0.0009415149688720703 nb_pixel_total : 15920 time to create 1 rle with old method : 0.01795053482055664 length of segment : 140 time for calcul the mask position with numpy : 0.0015726089477539062 nb_pixel_total : 36154 time to create 1 rle with old method : 0.039197683334350586 length of segment : 317 time for calcul the mask position with numpy : 0.0011572837829589844 nb_pixel_total : 22050 time to create 1 rle with old method : 0.02403402328491211 length of segment : 222 time for calcul the mask position with numpy : 0.0004570484161376953 nb_pixel_total : 14121 time to create 1 rle with old method : 0.016234397888183594 length of segment : 166 time for calcul the mask position with numpy : 0.0025358200073242188 nb_pixel_total : 43577 time to create 1 rle with old method : 0.06853699684143066 length of segment : 436 time for calcul the mask position with numpy : 0.0020575523376464844 nb_pixel_total : 38336 time to create 1 rle with old method : 0.043609619140625 length of segment : 207 time for calcul the mask position with numpy : 0.001641988754272461 nb_pixel_total : 30033 time to create 1 rle with old method : 0.03506064414978027 length of segment : 253 time for calcul the mask position with numpy : 0.0004239082336425781 nb_pixel_total : 6175 time to create 1 rle with old method : 0.007271289825439453 length of segment : 105 time for calcul the mask position with numpy : 0.0010666847229003906 nb_pixel_total : 21624 time to create 1 rle with old method : 0.024770259857177734 length of segment : 186 time for calcul the mask position with numpy : 0.0011992454528808594 nb_pixel_total : 22696 time to create 1 rle with old method : 0.025623321533203125 length of segment : 275 time for calcul the mask position with numpy : 0.0008518695831298828 nb_pixel_total : 19813 time to create 1 rle with old method : 0.022715091705322266 length of segment : 182 time for calcul the mask position with numpy : 0.0005941390991210938 nb_pixel_total : 15082 time to create 1 rle with old method : 0.017670869827270508 length of segment : 143 time for calcul the mask position with numpy : 0.0006783008575439453 nb_pixel_total : 13610 time to create 1 rle with old method : 0.015766143798828125 length of segment : 129 time for calcul the mask position with numpy : 0.00043964385986328125 nb_pixel_total : 8425 time to create 1 rle with old method : 0.010058403015136719 length of segment : 125 time for calcul the mask position with numpy : 0.000213623046875 nb_pixel_total : 4446 time to create 1 rle with old method : 0.00565338134765625 length of segment : 49 time for calcul the mask position with numpy : 0.0009431838989257812 nb_pixel_total : 10283 time to create 1 rle with old method : 0.012283086776733398 length of segment : 114 time for calcul the mask position with numpy : 0.0003368854522705078 nb_pixel_total : 5262 time to create 1 rle with old method : 0.006427288055419922 length of segment : 80 time for calcul the mask position with numpy : 0.0008230209350585938 nb_pixel_total : 15478 time to create 1 rle with old method : 0.018312931060791016 length of segment : 131 time for calcul the mask position with numpy : 0.0031936168670654297 nb_pixel_total : 66102 time to create 1 rle with old method : 0.07519698143005371 length of segment : 336 time for calcul the mask position with numpy : 0.000743865966796875 nb_pixel_total : 11502 time to create 1 rle with old method : 0.01313328742980957 length of segment : 182 time for calcul the mask position with numpy : 0.0015561580657958984 nb_pixel_total : 23808 time to create 1 rle with old method : 0.027728796005249023 length of segment : 317 time for calcul the mask position with numpy : 0.000644683837890625 nb_pixel_total : 10269 time to create 1 rle with old method : 0.011785268783569336 length of segment : 98 time for calcul the mask position with numpy : 0.00045418739318847656 nb_pixel_total : 8352 time to create 1 rle with old method : 0.009686708450317383 length of segment : 108 time for calcul the mask position with numpy : 0.0006961822509765625 nb_pixel_total : 11022 time to create 1 rle with old method : 0.01270437240600586 length of segment : 141 time for calcul the mask position with numpy : 0.0005514621734619141 nb_pixel_total : 8069 time to create 1 rle with old method : 0.009510993957519531 length of segment : 92 time for calcul the mask position with numpy : 0.0012009143829345703 nb_pixel_total : 20867 time to create 1 rle with old method : 0.023257017135620117 length of segment : 289 time for calcul the mask position with numpy : 0.0006818771362304688 nb_pixel_total : 16009 time to create 1 rle with old method : 0.017810583114624023 length of segment : 136 time for calcul the mask position with numpy : 0.0003261566162109375 nb_pixel_total : 5739 time to create 1 rle with old method : 0.0066297054290771484 length of segment : 95 time for calcul the mask position with numpy : 0.0015537738800048828 nb_pixel_total : 27624 time to create 1 rle with old method : 0.030917882919311523 length of segment : 363 time for calcul the mask position with numpy : 0.0005025863647460938 nb_pixel_total : 15062 time to create 1 rle with old method : 0.01689934730529785 length of segment : 133 time for calcul the mask position with numpy : 0.0006594657897949219 nb_pixel_total : 15276 time to create 1 rle with old method : 0.01691579818725586 length of segment : 186 time for calcul the mask position with numpy : 0.003517627716064453 nb_pixel_total : 89281 time to create 1 rle with old method : 0.09897923469543457 length of segment : 321 time for calcul the mask position with numpy : 0.0010483264923095703 nb_pixel_total : 25875 time to create 1 rle with old method : 0.029384136199951172 length of segment : 179 time for calcul the mask position with numpy : 0.0017476081848144531 nb_pixel_total : 55471 time to create 1 rle with old method : 0.061364173889160156 length of segment : 312 time for calcul the mask position with numpy : 0.0005681514739990234 nb_pixel_total : 10307 time to create 1 rle with old method : 0.012312173843383789 length of segment : 117 time for calcul the mask position with numpy : 0.0009226799011230469 nb_pixel_total : 25208 time to create 1 rle with old method : 0.028760910034179688 length of segment : 191 time for calcul the mask position with numpy : 0.0002663135528564453 nb_pixel_total : 13186 time to create 1 rle with old method : 0.015356063842773438 length of segment : 129 time for calcul the mask position with numpy : 0.001565694808959961 nb_pixel_total : 21263 time to create 1 rle with old method : 0.024765968322753906 length of segment : 170 time for calcul the mask position with numpy : 0.0010857582092285156 nb_pixel_total : 17192 time to create 1 rle with old method : 0.019919157028198242 length of segment : 244 time for calcul the mask position with numpy : 0.0010035037994384766 nb_pixel_total : 18681 time to create 1 rle with old method : 0.020700931549072266 length of segment : 212 time for calcul the mask position with numpy : 0.0011563301086425781 nb_pixel_total : 29118 time to create 1 rle with old method : 0.03285360336303711 length of segment : 346 time for calcul the mask position with numpy : 0.0009922981262207031 nb_pixel_total : 13454 time to create 1 rle with old method : 0.015285968780517578 length of segment : 157 time for calcul the mask position with numpy : 0.0026369094848632812 nb_pixel_total : 67538 time to create 1 rle with old method : 0.07504987716674805 length of segment : 329 time for calcul the mask position with numpy : 0.005465030670166016 nb_pixel_total : 91430 time to create 1 rle with old method : 0.10164904594421387 length of segment : 429 time for calcul the mask position with numpy : 0.0038213729858398438 nb_pixel_total : 82285 time to create 1 rle with old method : 0.09278583526611328 length of segment : 722 time for calcul the mask position with numpy : 0.0006611347198486328 nb_pixel_total : 19512 time to create 1 rle with old method : 0.022078275680541992 length of segment : 115 time for calcul the mask position with numpy : 0.0008795261383056641 nb_pixel_total : 16923 time to create 1 rle with old method : 0.019387006759643555 length of segment : 148 time for calcul the mask position with numpy : 0.0027360916137695312 nb_pixel_total : 50989 time to create 1 rle with old method : 0.05661511421203613 length of segment : 230 time for calcul the mask position with numpy : 0.002566099166870117 nb_pixel_total : 48677 time to create 1 rle with old method : 0.05378293991088867 length of segment : 307 time for calcul the mask position with numpy : 0.0010783672332763672 nb_pixel_total : 18961 time to create 1 rle with old method : 0.021143198013305664 length of segment : 138 time for calcul the mask position with numpy : 0.0007417201995849609 nb_pixel_total : 9918 time to create 1 rle with old method : 0.011174917221069336 length of segment : 116 time for calcul the mask position with numpy : 0.0003979206085205078 nb_pixel_total : 16992 time to create 1 rle with old method : 0.019545316696166992 length of segment : 165 time for calcul the mask position with numpy : 0.0007152557373046875 nb_pixel_total : 15587 time to create 1 rle with old method : 0.017856359481811523 length of segment : 164 time for calcul the mask position with numpy : 0.0006887912750244141 nb_pixel_total : 9359 time to create 1 rle with old method : 0.01114344596862793 length of segment : 115 time for calcul the mask position with numpy : 0.0015184879302978516 nb_pixel_total : 16482 time to create 1 rle with old method : 0.01924896240234375 length of segment : 196 time for calcul the mask position with numpy : 0.0033729076385498047 nb_pixel_total : 68926 time to create 1 rle with old method : 0.08008885383605957 length of segment : 214 time for calcul the mask position with numpy : 0.0006697177886962891 nb_pixel_total : 12767 time to create 1 rle with old method : 0.014792680740356445 length of segment : 113 time for calcul the mask position with numpy : 0.0011470317840576172 nb_pixel_total : 19412 time to create 1 rle with old method : 0.02276444435119629 length of segment : 128 time for calcul the mask position with numpy : 0.0005700588226318359 nb_pixel_total : 10605 time to create 1 rle with old method : 0.012456178665161133 length of segment : 82 time for calcul the mask position with numpy : 0.0020868778228759766 nb_pixel_total : 71052 time to create 1 rle with old method : 0.07985424995422363 length of segment : 204 time for calcul the mask position with numpy : 0.00024056434631347656 nb_pixel_total : 3885 time to create 1 rle with old method : 0.005875587463378906 length of segment : 72 time for calcul the mask position with numpy : 0.0020885467529296875 nb_pixel_total : 43030 time to create 1 rle with old method : 0.05273914337158203 length of segment : 290 time for calcul the mask position with numpy : 0.003207683563232422 nb_pixel_total : 69509 time to create 1 rle with old method : 0.09025716781616211 length of segment : 287 time for calcul the mask position with numpy : 0.0010726451873779297 nb_pixel_total : 15419 time to create 1 rle with old method : 0.0200350284576416 length of segment : 137 time for calcul the mask position with numpy : 0.0008916854858398438 nb_pixel_total : 19388 time to create 1 rle with old method : 0.024468183517456055 length of segment : 212 time for calcul the mask position with numpy : 0.0018320083618164062 nb_pixel_total : 35208 time to create 1 rle with old method : 0.04252982139587402 length of segment : 204 time for calcul the mask position with numpy : 0.009193897247314453 nb_pixel_total : 189489 time to create 1 rle with new method : 0.016934633255004883 length of segment : 449 time for calcul the mask position with numpy : 0.0005693435668945312 nb_pixel_total : 15779 time to create 1 rle with old method : 0.01827406883239746 length of segment : 119 time for calcul the mask position with numpy : 0.0017707347869873047 nb_pixel_total : 25295 time to create 1 rle with old method : 0.028621673583984375 length of segment : 338 time for calcul the mask position with numpy : 0.0005404949188232422 nb_pixel_total : 9240 time to create 1 rle with old method : 0.017601490020751953 length of segment : 114 time for calcul the mask position with numpy : 0.001079559326171875 nb_pixel_total : 18459 time to create 1 rle with old method : 0.031444549560546875 length of segment : 180 time for calcul the mask position with numpy : 0.0008180141448974609 nb_pixel_total : 13363 time to create 1 rle with old method : 0.016397476196289062 length of segment : 149 time for calcul the mask position with numpy : 0.0006947517395019531 nb_pixel_total : 14521 time to create 1 rle with old method : 0.017125844955444336 length of segment : 152 time for calcul the mask position with numpy : 0.0009331703186035156 nb_pixel_total : 33653 time to create 1 rle with old method : 0.03887343406677246 length of segment : 206 time for calcul the mask position with numpy : 0.0013897418975830078 nb_pixel_total : 46100 time to create 1 rle with old method : 0.051639556884765625 length of segment : 256 time for calcul the mask position with numpy : 0.0006542205810546875 nb_pixel_total : 15807 time to create 1 rle with old method : 0.018783092498779297 length of segment : 103 time for calcul the mask position with numpy : 0.0012161731719970703 nb_pixel_total : 18996 time to create 1 rle with old method : 0.02216053009033203 length of segment : 179 time for calcul the mask position with numpy : 0.0004949569702148438 nb_pixel_total : 9171 time to create 1 rle with old method : 0.010900735855102539 length of segment : 106 time for calcul the mask position with numpy : 0.0006709098815917969 nb_pixel_total : 10156 time to create 1 rle with old method : 0.011871099472045898 length of segment : 133 time for calcul the mask position with numpy : 0.0008084774017333984 nb_pixel_total : 12028 time to create 1 rle with old method : 0.014198780059814453 length of segment : 169 time for calcul the mask position with numpy : 0.0005619525909423828 nb_pixel_total : 8776 time to create 1 rle with old method : 0.01035928726196289 length of segment : 119 time for calcul the mask position with numpy : 0.0010921955108642578 nb_pixel_total : 15905 time to create 1 rle with old method : 0.018560171127319336 length of segment : 181 time for calcul the mask position with numpy : 0.00048041343688964844 nb_pixel_total : 6540 time to create 1 rle with old method : 0.007848262786865234 length of segment : 107 time for calcul the mask position with numpy : 0.0006248950958251953 nb_pixel_total : 8561 time to create 1 rle with old method : 0.010125160217285156 length of segment : 107 time for calcul the mask position with numpy : 0.0009675025939941406 nb_pixel_total : 8879 time to create 1 rle with old method : 0.010694503784179688 length of segment : 134 time for calcul the mask position with numpy : 0.0027451515197753906 nb_pixel_total : 42395 time to create 1 rle with old method : 0.04799365997314453 length of segment : 310 time for calcul the mask position with numpy : 0.0011179447174072266 nb_pixel_total : 12382 time to create 1 rle with old method : 0.015233993530273438 length of segment : 139 time for calcul the mask position with numpy : 0.0022249221801757812 nb_pixel_total : 28630 time to create 1 rle with old method : 0.0483095645904541 length of segment : 211 time for calcul the mask position with numpy : 0.00379180908203125 nb_pixel_total : 53087 time to create 1 rle with old method : 0.059586524963378906 length of segment : 285 time for calcul the mask position with numpy : 0.0010137557983398438 nb_pixel_total : 10007 time to create 1 rle with old method : 0.01162576675415039 length of segment : 128 time for calcul the mask position with numpy : 0.0006740093231201172 nb_pixel_total : 11551 time to create 1 rle with old method : 0.01376199722290039 length of segment : 116 time for calcul the mask position with numpy : 0.003775358200073242 nb_pixel_total : 59778 time to create 1 rle with old method : 0.06641888618469238 length of segment : 406 time for calcul the mask position with numpy : 0.0005438327789306641 nb_pixel_total : 6877 time to create 1 rle with old method : 0.008155584335327148 length of segment : 95 time for calcul the mask position with numpy : 0.0017054080963134766 nb_pixel_total : 25850 time to create 1 rle with old method : 0.02981400489807129 length of segment : 194 time for calcul the mask position with numpy : 0.0004975795745849609 nb_pixel_total : 7832 time to create 1 rle with old method : 0.009254217147827148 length of segment : 113 time for calcul the mask position with numpy : 0.0014996528625488281 nb_pixel_total : 28104 time to create 1 rle with old method : 0.031733036041259766 length of segment : 258 time for calcul the mask position with numpy : 0.0005922317504882812 nb_pixel_total : 8520 time to create 1 rle with old method : 0.010078191757202148 length of segment : 91 time for calcul the mask position with numpy : 0.0005235671997070312 nb_pixel_total : 7326 time to create 1 rle with old method : 0.008707761764526367 length of segment : 107 time for calcul the mask position with numpy : 0.0021924972534179688 nb_pixel_total : 48102 time to create 1 rle with old method : 0.05464577674865723 length of segment : 263 time for calcul the mask position with numpy : 0.0008680820465087891 nb_pixel_total : 10853 time to create 1 rle with old method : 0.012603521347045898 length of segment : 111 time for calcul the mask position with numpy : 0.0017507076263427734 nb_pixel_total : 33169 time to create 1 rle with old method : 0.03854942321777344 length of segment : 171 time for calcul the mask position with numpy : 0.0007517337799072266 nb_pixel_total : 9276 time to create 1 rle with old method : 0.010840177536010742 length of segment : 108 time for calcul the mask position with numpy : 0.0022950172424316406 nb_pixel_total : 33530 time to create 1 rle with old method : 0.055005788803100586 length of segment : 206 time for calcul the mask position with numpy : 0.002160787582397461 nb_pixel_total : 29878 time to create 1 rle with old method : 0.034664154052734375 length of segment : 170 time for calcul the mask position with numpy : 0.0024559497833251953 nb_pixel_total : 34273 time to create 1 rle with old method : 0.038988351821899414 length of segment : 259 time for calcul the mask position with numpy : 0.00026702880859375 nb_pixel_total : 5419 time to create 1 rle with old method : 0.006238698959350586 length of segment : 133 time for calcul the mask position with numpy : 0.0003421306610107422 nb_pixel_total : 4688 time to create 1 rle with old method : 0.005677700042724609 length of segment : 60 time for calcul the mask position with numpy : 0.001096487045288086 nb_pixel_total : 8463 time to create 1 rle with old method : 0.009834051132202148 length of segment : 302 time for calcul the mask position with numpy : 0.0003190040588378906 nb_pixel_total : 4665 time to create 1 rle with old method : 0.006219387054443359 length of segment : 87 time for calcul the mask position with numpy : 0.0031418800354003906 nb_pixel_total : 39536 time to create 1 rle with old method : 0.07095003128051758 length of segment : 225 time for calcul the mask position with numpy : 0.0011801719665527344 nb_pixel_total : 22720 time to create 1 rle with old method : 0.026188373565673828 length of segment : 157 time for calcul the mask position with numpy : 0.004720449447631836 nb_pixel_total : 34989 time to create 1 rle with old method : 0.0396878719329834 length of segment : 328 time for calcul the mask position with numpy : 0.004915475845336914 nb_pixel_total : 151909 time to create 1 rle with new method : 0.009224176406860352 length of segment : 398 time for calcul the mask position with numpy : 0.01363992691040039 nb_pixel_total : 265280 time to create 1 rle with new method : 0.04441976547241211 length of segment : 409 time for calcul the mask position with numpy : 0.0030677318572998047 nb_pixel_total : 114834 time to create 1 rle with old method : 0.15494227409362793 length of segment : 520 time for calcul the mask position with numpy : 0.00040984153747558594 nb_pixel_total : 8642 time to create 1 rle with old method : 0.010202169418334961 length of segment : 112 time for calcul the mask position with numpy : 0.0025382041931152344 nb_pixel_total : 46588 time to create 1 rle with old method : 0.0549466609954834 length of segment : 302 time for calcul the mask position with numpy : 0.001567840576171875 nb_pixel_total : 50854 time to create 1 rle with old method : 0.05741286277770996 length of segment : 488 time for calcul the mask position with numpy : 0.0012621879577636719 nb_pixel_total : 29714 time to create 1 rle with old method : 0.03369927406311035 length of segment : 341 time for calcul the mask position with numpy : 0.0005693435668945312 nb_pixel_total : 20319 time to create 1 rle with old method : 0.023502826690673828 length of segment : 181 time for calcul the mask position with numpy : 0.009639978408813477 nb_pixel_total : 497261 time to create 1 rle with new method : 0.03602290153503418 length of segment : 637 time for calcul the mask position with numpy : 0.0022857189178466797 nb_pixel_total : 144766 time to create 1 rle with old method : 0.17764639854431152 length of segment : 263 time for calcul the mask position with numpy : 0.0015201568603515625 nb_pixel_total : 20949 time to create 1 rle with old method : 0.023410558700561523 length of segment : 207 time for calcul the mask position with numpy : 0.0025374889373779297 nb_pixel_total : 70352 time to create 1 rle with old method : 0.07950472831726074 length of segment : 258 time for calcul the mask position with numpy : 0.0048389434814453125 nb_pixel_total : 41051 time to create 1 rle with old method : 0.0458831787109375 length of segment : 359 time for calcul the mask position with numpy : 0.0017392635345458984 nb_pixel_total : 44037 time to create 1 rle with old method : 0.04928755760192871 length of segment : 269 time for calcul the mask position with numpy : 0.0007574558258056641 nb_pixel_total : 19335 time to create 1 rle with old method : 0.022118806838989258 length of segment : 203 time for calcul the mask position with numpy : 0.0006434917449951172 nb_pixel_total : 14430 time to create 1 rle with old method : 0.016303300857543945 length of segment : 159 time for calcul the mask position with numpy : 0.0029311180114746094 nb_pixel_total : 73347 time to create 1 rle with old method : 0.0822145938873291 length of segment : 182 time for calcul the mask position with numpy : 0.0014004707336425781 nb_pixel_total : 20212 time to create 1 rle with old method : 0.022825241088867188 length of segment : 194 time for calcul the mask position with numpy : 0.0005588531494140625 nb_pixel_total : 10822 time to create 1 rle with old method : 0.012557029724121094 length of segment : 205 time for calcul the mask position with numpy : 0.0009706020355224609 nb_pixel_total : 22675 time to create 1 rle with old method : 0.026436567306518555 length of segment : 144 time for calcul the mask position with numpy : 0.002447843551635742 nb_pixel_total : 57138 time to create 1 rle with old method : 0.06495857238769531 length of segment : 227 time for calcul the mask position with numpy : 0.0012781620025634766 nb_pixel_total : 24810 time to create 1 rle with old method : 0.028916597366333008 length of segment : 314 time for calcul the mask position with numpy : 0.0008695125579833984 nb_pixel_total : 19957 time to create 1 rle with old method : 0.023975133895874023 length of segment : 195 time for calcul the mask position with numpy : 0.010024785995483398 nb_pixel_total : 212570 time to create 1 rle with new method : 0.07310676574707031 length of segment : 744 time for calcul the mask position with numpy : 0.0004975795745849609 nb_pixel_total : 19685 time to create 1 rle with old method : 0.023004770278930664 length of segment : 198 time for calcul the mask position with numpy : 0.0007472038269042969 nb_pixel_total : 10543 time to create 1 rle with old method : 0.012690305709838867 length of segment : 137 time for calcul the mask position with numpy : 0.0012941360473632812 nb_pixel_total : 25156 time to create 1 rle with old method : 0.031161785125732422 length of segment : 238 time for calcul the mask position with numpy : 0.0014374256134033203 nb_pixel_total : 32419 time to create 1 rle with old method : 0.03720259666442871 length of segment : 191 time for calcul the mask position with numpy : 0.0005908012390136719 nb_pixel_total : 9489 time to create 1 rle with old method : 0.011246204376220703 length of segment : 136 time for calcul the mask position with numpy : 0.0023136138916015625 nb_pixel_total : 50407 time to create 1 rle with old method : 0.058943986892700195 length of segment : 367 time for calcul the mask position with numpy : 0.0026688575744628906 nb_pixel_total : 60225 time to create 1 rle with old method : 0.07067561149597168 length of segment : 292 time spent for convertir_results : 24.087900400161743 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 287 chid ids of type : 3594 Number RLEs to save : 72843 save missing photos in datou_result : time spend for datou_step_exec : 127.65860366821289 time spend to save output : 4.716871500015259 total time spend for step 1 : 132.37547516822815 step2:crop_condition Thu Apr 24 20:42:42 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 17 ! batch 1 Loaded 287 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 ! map_result returned by crop_photo_return_map_crop : length : 206 About to insert : list_path_to_insert length 206 new photo from crops ! About to upload 206 photos upload in portfolio : 3736932 init cache_photo without model_param we have 206 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1745520202_2361629 we have uploaded 206 photos in the portfolio 3736932 time of upload the photos Elapsed time : 68.46591830253601 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 ! map_result returned by crop_photo_return_map_crop : length : 34 About to insert : list_path_to_insert length 34 new photo from crops ! About to upload 34 photos upload in portfolio : 3736932 init cache_photo without model_param we have 34 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1745520281_2361629 we have uploaded 34 photos in the portfolio 3736932 time of upload the photos Elapsed time : 9.560916900634766 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 ! 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/1745520293_2361629 we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.6189813613891602 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 ! map_result returned by crop_photo_return_map_crop : length : 36 About to insert : list_path_to_insert length 36 new photo from crops ! About to upload 36 photos upload in portfolio : 3736932 init cache_photo without model_param we have 36 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1745520318_2361629 we have uploaded 36 photos in the portfolio 3736932 time of upload the photos Elapsed time : 17.676482915878296 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.7} filtre for class : autre hashtag_id of this class : 494826614 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 9 About to insert : list_path_to_insert length 9 new photo from crops ! About to upload 9 photos upload in portfolio : 3736932 init cache_photo without model_param we have 9 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1745520339_2361629 we have uploaded 9 photos in the portfolio 3736932 time of upload the photos Elapsed time : 2.309602975845337 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 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/1745520343_2361629 we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.6362769603729248 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 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 [1353408839, 1353408833, 1353408830, 1353408827, 1353408782, 1353408716, 1353408529, 1353408451, 1353408445, 1353408440, 1353408406, 1353408354, 1353408350, 1353408338, 1353408332, 1353408229, 1353408175] Looping around the photos to save general results len do output : 287 /1353455546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455656Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353455998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1353456015Didn'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, '2758897') ('3318', '22396717', '1353408839', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408833', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408830', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408827', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408782', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408716', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408529', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408451', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408445', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408440', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408406', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408354', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408350', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408338', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408332', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408229', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408175', None, None, None, None, None, '2758897') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 878 time used for this insertion : 0.048725128173828125 save_final save missing photos in datou_result : time spend for datou_step_exec : 181.16206812858582 time spend to save output : 0.06223726272583008 total time spend for step 2 : 181.22430539131165 step3:rle_unique_nms_with_priority Thu Apr 24 20:45:44 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 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 287 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 12 nb_hashtags : 2 time to prepare the origin masks : 3.8897266387939453 time for calcul the mask position with numpy : 0.3843111991882324 nb_pixel_total : 6310762 time to create 1 rle with new method : 1.416111707687378 time for calcul the mask position with numpy : 0.025433778762817383 nb_pixel_total : 102711 time to create 1 rle with old method : 0.11063170433044434 time for calcul the mask position with numpy : 0.029674053192138672 nb_pixel_total : 27410 time to create 1 rle with old method : 0.03013753890991211 time for calcul the mask position with numpy : 0.02654242515563965 nb_pixel_total : 182042 time to create 1 rle with new method : 0.33607912063598633 time for calcul the mask position with numpy : 0.025234699249267578 nb_pixel_total : 3222 time to create 1 rle with old method : 0.0037908554077148438 time for calcul the mask position with numpy : 0.029702425003051758 nb_pixel_total : 113032 time to create 1 rle with old method : 0.13811683654785156 time for calcul the mask position with numpy : 0.023585796356201172 nb_pixel_total : 50253 time to create 1 rle with old method : 0.0573430061340332 time for calcul the mask position with numpy : 0.024715900421142578 nb_pixel_total : 4319 time to create 1 rle with old method : 0.005712270736694336 time for calcul the mask position with numpy : 0.023863792419433594 nb_pixel_total : 20347 time to create 1 rle with old method : 0.024916648864746094 time for calcul the mask position with numpy : 0.027657747268676758 nb_pixel_total : 158289 time to create 1 rle with new method : 0.531090259552002 time for calcul the mask position with numpy : 0.02193164825439453 nb_pixel_total : 8574 time to create 1 rle with old method : 0.009969234466552734 time for calcul the mask position with numpy : 0.02190542221069336 nb_pixel_total : 42716 time to create 1 rle with old method : 0.04959416389465332 time for calcul the mask position with numpy : 0.02225184440612793 nb_pixel_total : 26563 time to create 1 rle with old method : 0.03011608123779297 create new chi : 3.52892804145813 time to delete rle : 0.02995157241821289 batch 1 Loaded 25 chid ids of type : 3594 ++++++++++++++Number RLEs to save : 9351 TO DO : save crop sub photo not yet done ! save time : 0.6422200202941895 nb_obj : 24 nb_hashtags : 4 time to prepare the origin masks : 5.447270631790161 time for calcul the mask position with numpy : 0.4499173164367676 nb_pixel_total : 6298765 time to create 1 rle with new method : 0.5728623867034912 time for calcul the mask position with numpy : 0.0417180061340332 nb_pixel_total : 14158 time to create 1 rle with old method : 0.01813983917236328 time for calcul the mask position with numpy : 0.03523397445678711 nb_pixel_total : 11487 time to create 1 rle with old method : 0.012742280960083008 time for calcul the mask position with numpy : 0.03455805778503418 nb_pixel_total : 24129 time to create 1 rle with old method : 0.026699542999267578 time for calcul the mask position with numpy : 0.03332877159118652 nb_pixel_total : 37812 time to create 1 rle with old method : 0.04210925102233887 time for calcul the mask position with numpy : 0.03117060661315918 nb_pixel_total : 9962 time to create 1 rle with old method : 0.011095762252807617 time for calcul the mask position with numpy : 0.03497433662414551 nb_pixel_total : 11708 time to create 1 rle with old method : 0.013281106948852539 time for calcul the mask position with numpy : 0.03431510925292969 nb_pixel_total : 10192 time to create 1 rle with old method : 0.011062145233154297 time for calcul the mask position with numpy : 0.033891916275024414 nb_pixel_total : 11170 time to create 1 rle with old method : 0.012379646301269531 time for calcul the mask position with numpy : 0.03101038932800293 nb_pixel_total : 46756 time to create 1 rle with old method : 0.05073094367980957 time for calcul the mask position with numpy : 0.033545732498168945 nb_pixel_total : 13092 time to create 1 rle with old method : 0.014339685440063477 time for calcul the mask position with numpy : 0.036510467529296875 nb_pixel_total : 14687 time to create 1 rle with old method : 0.016301393508911133 time for calcul the mask position with numpy : 0.02257061004638672 nb_pixel_total : 113699 time to create 1 rle with old method : 0.12996315956115723 time for calcul the mask position with numpy : 0.02286982536315918 nb_pixel_total : 28641 time to create 1 rle with old method : 0.033014774322509766 time for calcul the mask position with numpy : 0.02742481231689453 nb_pixel_total : 4359 time to create 1 rle with old method : 0.004961252212524414 time for calcul the mask position with numpy : 0.026865243911743164 nb_pixel_total : 6836 time to create 1 rle with old method : 0.008793830871582031 time for calcul the mask position with numpy : 0.027395009994506836 nb_pixel_total : 19592 time to create 1 rle with old method : 0.024543046951293945 time for calcul the mask position with numpy : 0.03131461143493652 nb_pixel_total : 22449 time to create 1 rle with old method : 0.03201484680175781 time for calcul the mask position with numpy : 0.044764041900634766 nb_pixel_total : 143862 time to create 1 rle with old method : 0.16423869132995605 time for calcul the mask position with numpy : 0.040709495544433594 nb_pixel_total : 35133 time to create 1 rle with old method : 0.04219412803649902 time for calcul the mask position with numpy : 0.03889179229736328 nb_pixel_total : 13146 time to create 1 rle with old method : 0.016492843627929688 time for calcul the mask position with numpy : 0.041620492935180664 nb_pixel_total : 33291 time to create 1 rle with old method : 0.04132080078125 time for calcul the mask position with numpy : 0.03916358947753906 nb_pixel_total : 94496 time to create 1 rle with old method : 0.10812187194824219 time for calcul the mask position with numpy : 0.041873931884765625 nb_pixel_total : 13270 time to create 1 rle with old method : 0.016197681427001953 time for calcul the mask position with numpy : 0.03755497932434082 nb_pixel_total : 17548 time to create 1 rle with old method : 0.02227473258972168 create new chi : 2.768331527709961 time to delete rle : 0.003866910934448242 batch 1 Loaded 49 chid ids of type : 3594 ++++++++++++++++++++++++++Number RLEs to save : 11924 TO DO : save crop sub photo not yet done ! save time : 0.7853646278381348 nb_obj : 12 nb_hashtags : 3 time to prepare the origin masks : 3.161689043045044 time for calcul the mask position with numpy : 0.2566232681274414 nb_pixel_total : 5517782 time to create 1 rle with new method : 0.8180012702941895 time for calcul the mask position with numpy : 0.026886940002441406 nb_pixel_total : 269341 time to create 1 rle with new method : 0.8127171993255615 time for calcul the mask position with numpy : 0.026594877243041992 nb_pixel_total : 18522 time to create 1 rle with old method : 0.021395206451416016 time for calcul the mask position with numpy : 0.026522159576416016 nb_pixel_total : 234277 time to create 1 rle with new method : 0.7021386623382568 time for calcul the mask position with numpy : 0.025333166122436523 nb_pixel_total : 380715 time to create 1 rle with new method : 0.6739811897277832 time for calcul the mask position with numpy : 0.022383689880371094 nb_pixel_total : 34237 time to create 1 rle with old method : 0.038536787033081055 time for calcul the mask position with numpy : 0.028967618942260742 nb_pixel_total : 16590 time to create 1 rle with old method : 0.018573760986328125 time for calcul the mask position with numpy : 0.0224151611328125 nb_pixel_total : 31371 time to create 1 rle with old method : 0.03502988815307617 time for calcul the mask position with numpy : 0.022799253463745117 nb_pixel_total : 29462 time to create 1 rle with old method : 0.03141188621520996 time for calcul the mask position with numpy : 0.03261375427246094 nb_pixel_total : 166103 time to create 1 rle with new method : 0.3496115207672119 time for calcul the mask position with numpy : 0.038991689682006836 nb_pixel_total : 309468 time to create 1 rle with new method : 0.4325721263885498 time for calcul the mask position with numpy : 0.03554368019104004 nb_pixel_total : 26730 time to create 1 rle with old method : 0.029970169067382812 time for calcul the mask position with numpy : 0.03770852088928223 nb_pixel_total : 15642 time to create 1 rle with old method : 0.018474578857421875 create new chi : 4.745808362960815 time to delete rle : 0.0034067630767822266 batch 1 Loaded 25 chid ids of type : 3594 +++++++++++++++++Number RLEs to save : 13505 TO DO : save crop sub photo not yet done ! save time : 0.8770613670349121 nb_obj : 11 nb_hashtags : 3 time to prepare the origin masks : 3.1149742603302 time for calcul the mask position with numpy : 0.3785593509674072 nb_pixel_total : 6252042 time to create 1 rle with new method : 0.6933181285858154 time for calcul the mask position with numpy : 0.024115800857543945 nb_pixel_total : 186679 time to create 1 rle with new method : 0.5460343360900879 time for calcul the mask position with numpy : 0.022264957427978516 nb_pixel_total : 129632 time to create 1 rle with old method : 0.14339852333068848 time for calcul the mask position with numpy : 0.021787643432617188 nb_pixel_total : 53879 time to create 1 rle with old method : 0.06262469291687012 time for calcul the mask position with numpy : 0.023111820220947266 nb_pixel_total : 93682 time to create 1 rle with old method : 0.10698795318603516 time for calcul the mask position with numpy : 0.023952007293701172 nb_pixel_total : 22259 time to create 1 rle with old method : 0.026688337326049805 time for calcul the mask position with numpy : 0.024355649948120117 nb_pixel_total : 19300 time to create 1 rle with old method : 0.022832870483398438 time for calcul the mask position with numpy : 0.02431011199951172 nb_pixel_total : 20243 time to create 1 rle with old method : 0.032480716705322266 time for calcul the mask position with numpy : 0.02520442008972168 nb_pixel_total : 210602 time to create 1 rle with new method : 0.31594038009643555 time for calcul the mask position with numpy : 0.021518945693969727 nb_pixel_total : 17732 time to create 1 rle with old method : 0.019745349884033203 time for calcul the mask position with numpy : 0.02292490005493164 nb_pixel_total : 27666 time to create 1 rle with old method : 0.03069782257080078 time for calcul the mask position with numpy : 0.02187371253967285 nb_pixel_total : 16524 time to create 1 rle with old method : 0.01921820640563965 create new chi : 2.748840808868408 time to delete rle : 0.0023953914642333984 batch 1 Loaded 23 chid ids of type : 3594 ++++++++++++Number RLEs to save : 9828 TO DO : save crop sub photo not yet done ! save time : 0.6551973819732666 nb_obj : 9 nb_hashtags : 3 time to prepare the origin masks : 2.405634880065918 time for calcul the mask position with numpy : 0.5936226844787598 nb_pixel_total : 5767827 time to create 1 rle with new method : 0.7520043849945068 time for calcul the mask position with numpy : 0.02169060707092285 nb_pixel_total : 37808 time to create 1 rle with old method : 0.041954994201660156 time for calcul the mask position with numpy : 0.023322343826293945 nb_pixel_total : 202081 time to create 1 rle with new method : 0.41203856468200684 time for calcul the mask position with numpy : 0.02365398406982422 nb_pixel_total : 70154 time to create 1 rle with old method : 0.08792304992675781 time for calcul the mask position with numpy : 0.021133899688720703 nb_pixel_total : 88321 time to create 1 rle with old method : 0.10295891761779785 time for calcul the mask position with numpy : 0.02518463134765625 nb_pixel_total : 133143 time to create 1 rle with old method : 0.15865111351013184 time for calcul the mask position with numpy : 0.029102325439453125 nb_pixel_total : 673831 time to create 1 rle with new method : 0.3098578453063965 time for calcul the mask position with numpy : 0.021634340286254883 nb_pixel_total : 29482 time to create 1 rle with old method : 0.03277850151062012 time for calcul the mask position with numpy : 0.021161317825317383 nb_pixel_total : 23692 time to create 1 rle with old method : 0.026470184326171875 time for calcul the mask position with numpy : 0.020841360092163086 nb_pixel_total : 23901 time to create 1 rle with old method : 0.026749849319458008 create new chi : 2.836864948272705 time to delete rle : 0.0014400482177734375 batch 1 Loaded 19 chid ids of type : 3594 ++++++++++Number RLEs to save : 9812 TO DO : save crop sub photo not yet done ! save time : 0.6796340942382812 nb_obj : 31 nb_hashtags : 4 time to prepare the origin masks : 3.9600586891174316 time for calcul the mask position with numpy : 0.356982946395874 nb_pixel_total : 6274360 time to create 1 rle with new method : 0.3021407127380371 time for calcul the mask position with numpy : 0.03000044822692871 nb_pixel_total : 8661 time to create 1 rle with old method : 0.010269403457641602 time for calcul the mask position with numpy : 0.03298139572143555 nb_pixel_total : 6240 time to create 1 rle with old method : 0.007748842239379883 time for calcul the mask position with numpy : 0.03364276885986328 nb_pixel_total : 55224 time to create 1 rle with old method : 0.061676740646362305 time for calcul the mask position with numpy : 0.033513784408569336 nb_pixel_total : 6310 time to create 1 rle with old method : 0.007028818130493164 time for calcul the mask position with numpy : 0.029022216796875 nb_pixel_total : 49690 time to create 1 rle with old method : 0.055992841720581055 time for calcul the mask position with numpy : 0.028805017471313477 nb_pixel_total : 9652 time to create 1 rle with old method : 0.010861396789550781 time for calcul the mask position with numpy : 0.02873682975769043 nb_pixel_total : 8266 time to create 1 rle with old method : 0.009253263473510742 time for calcul the mask position with numpy : 0.02881026268005371 nb_pixel_total : 15831 time to create 1 rle with old method : 0.024381637573242188 time for calcul the mask position with numpy : 0.03298616409301758 nb_pixel_total : 64773 time to create 1 rle with old method : 0.08261895179748535 time for calcul the mask position with numpy : 0.029232263565063477 nb_pixel_total : 22491 time to create 1 rle with old method : 0.025133609771728516 time for calcul the mask position with numpy : 0.029175758361816406 nb_pixel_total : 9686 time to create 1 rle with old method : 0.011080741882324219 time for calcul the mask position with numpy : 0.02957773208618164 nb_pixel_total : 13837 time to create 1 rle with old method : 0.01576399803161621 time for calcul the mask position with numpy : 0.029999971389770508 nb_pixel_total : 62536 time to create 1 rle with old method : 0.0700678825378418 time for calcul the mask position with numpy : 0.029758214950561523 nb_pixel_total : 8167 time to create 1 rle with old method : 0.013266324996948242 time for calcul the mask position with numpy : 0.033048152923583984 nb_pixel_total : 11475 time to create 1 rle with old method : 0.018727779388427734 time for calcul the mask position with numpy : 0.02928304672241211 nb_pixel_total : 10696 time to create 1 rle with old method : 0.012029886245727539 time for calcul the mask position with numpy : 0.028893470764160156 nb_pixel_total : 39870 time to create 1 rle with old method : 0.04402947425842285 time for calcul the mask position with numpy : 0.030141592025756836 nb_pixel_total : 58432 time to create 1 rle with old method : 0.0635840892791748 time for calcul the mask position with numpy : 0.028084278106689453 nb_pixel_total : 11267 time to create 1 rle with old method : 0.012290239334106445 time for calcul the mask position with numpy : 0.028627395629882812 nb_pixel_total : 8756 time to create 1 rle with old method : 0.009827136993408203 time for calcul the mask position with numpy : 0.028947114944458008 nb_pixel_total : 15404 time to create 1 rle with old method : 0.017064332962036133 time for calcul the mask position with numpy : 0.029050588607788086 nb_pixel_total : 45919 time to create 1 rle with old method : 0.05159807205200195 time for calcul the mask position with numpy : 0.029000282287597656 nb_pixel_total : 54646 time to create 1 rle with old method : 0.060445308685302734 time for calcul the mask position with numpy : 0.028908491134643555 nb_pixel_total : 43093 time to create 1 rle with old method : 0.049310922622680664 time for calcul the mask position with numpy : 0.03486895561218262 nb_pixel_total : 18671 time to create 1 rle with old method : 0.022803544998168945 time for calcul the mask position with numpy : 0.030291318893432617 nb_pixel_total : 48996 time to create 1 rle with old method : 0.06400465965270996 time for calcul the mask position with numpy : 0.029741764068603516 nb_pixel_total : 8616 time to create 1 rle with old method : 0.010864973068237305 time for calcul the mask position with numpy : 0.029833555221557617 nb_pixel_total : 8483 time to create 1 rle with old method : 0.009572982788085938 time for calcul the mask position with numpy : 0.029074430465698242 nb_pixel_total : 10861 time to create 1 rle with old method : 0.01231837272644043 time for calcul the mask position with numpy : 0.02908039093017578 nb_pixel_total : 6283 time to create 1 rle with old method : 0.007546186447143555 time for calcul the mask position with numpy : 0.031238555908203125 nb_pixel_total : 33048 time to create 1 rle with old method : 0.04214215278625488 create new chi : 2.63967227935791 time to delete rle : 0.0030753612518310547 batch 1 Loaded 63 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 14129 TO DO : save crop sub photo not yet done ! save time : 0.9444015026092529 nb_obj : 19 nb_hashtags : 3 time to prepare the origin masks : 6.608800172805786 time for calcul the mask position with numpy : 0.5125980377197266 nb_pixel_total : 5868182 time to create 1 rle with new method : 0.812727689743042 time for calcul the mask position with numpy : 0.021690845489501953 nb_pixel_total : 11136 time to create 1 rle with old method : 0.012275934219360352 time for calcul the mask position with numpy : 0.02301025390625 nb_pixel_total : 11932 time to create 1 rle with old method : 0.013377904891967773 time for calcul the mask position with numpy : 0.02874898910522461 nb_pixel_total : 493371 time to create 1 rle with new method : 0.3892183303833008 time for calcul the mask position with numpy : 0.02174854278564453 nb_pixel_total : 15519 time to create 1 rle with old method : 0.017346620559692383 time for calcul the mask position with numpy : 0.021501779556274414 nb_pixel_total : 20593 time to create 1 rle with old method : 0.022790193557739258 time for calcul the mask position with numpy : 0.021435976028442383 nb_pixel_total : 17861 time to create 1 rle with old method : 0.02012920379638672 time for calcul the mask position with numpy : 0.022620439529418945 nb_pixel_total : 64814 time to create 1 rle with old method : 0.07769346237182617 time for calcul the mask position with numpy : 0.026464223861694336 nb_pixel_total : 19984 time to create 1 rle with old method : 0.0234987735748291 time for calcul the mask position with numpy : 0.026717424392700195 nb_pixel_total : 11608 time to create 1 rle with old method : 0.0139923095703125 time for calcul the mask position with numpy : 0.023241281509399414 nb_pixel_total : 10452 time to create 1 rle with old method : 0.012304544448852539 time for calcul the mask position with numpy : 0.023786544799804688 nb_pixel_total : 6881 time to create 1 rle with old method : 0.008090734481811523 time for calcul the mask position with numpy : 0.024940013885498047 nb_pixel_total : 37447 time to create 1 rle with old method : 0.04160618782043457 time for calcul the mask position with numpy : 0.0216214656829834 nb_pixel_total : 37204 time to create 1 rle with old method : 0.0427701473236084 time for calcul the mask position with numpy : 0.02275872230529785 nb_pixel_total : 44718 time to create 1 rle with old method : 0.05255913734436035 time for calcul the mask position with numpy : 0.023655176162719727 nb_pixel_total : 18552 time to create 1 rle with old method : 0.021561861038208008 time for calcul the mask position with numpy : 0.03230857849121094 nb_pixel_total : 324999 time to create 1 rle with new method : 0.6077213287353516 time for calcul the mask position with numpy : 0.0216372013092041 nb_pixel_total : 15090 time to create 1 rle with old method : 0.01687455177307129 time for calcul the mask position with numpy : 0.021162748336791992 nb_pixel_total : 12109 time to create 1 rle with old method : 0.013217926025390625 time for calcul the mask position with numpy : 0.021209001541137695 nb_pixel_total : 7788 time to create 1 rle with old method : 0.008629560470581055 create new chi : 3.271872043609619 time to delete rle : 0.0016820430755615234 batch 1 Loaded 39 chid ids of type : 3594 +++++++++++++++++++++Number RLEs to save : 11192 TO DO : save crop sub photo not yet done ! save time : 0.7605297565460205 nb_obj : 7 nb_hashtags : 3 time to prepare the origin masks : 4.97215461730957 time for calcul the mask position with numpy : 0.516873836517334 nb_pixel_total : 6811213 time to create 1 rle with new method : 0.772301197052002 time for calcul the mask position with numpy : 0.022016525268554688 nb_pixel_total : 3087 time to create 1 rle with old method : 0.0040073394775390625 time for calcul the mask position with numpy : 0.023804187774658203 nb_pixel_total : 20828 time to create 1 rle with old method : 0.02512359619140625 time for calcul the mask position with numpy : 0.022280216217041016 nb_pixel_total : 33006 time to create 1 rle with old method : 0.04097461700439453 time for calcul the mask position with numpy : 0.022939205169677734 nb_pixel_total : 117398 time to create 1 rle with old method : 0.1396641731262207 time for calcul the mask position with numpy : 0.0218050479888916 nb_pixel_total : 9755 time to create 1 rle with old method : 0.010858297348022461 time for calcul the mask position with numpy : 0.023705482482910156 nb_pixel_total : 36777 time to create 1 rle with old method : 0.058457374572753906 time for calcul the mask position with numpy : 0.021571636199951172 nb_pixel_total : 18176 time to create 1 rle with old method : 0.020126819610595703 create new chi : 1.7949483394622803 time to delete rle : 0.0007576942443847656 batch 1 Loaded 15 chid ids of type : 3594 +++++++Number RLEs to save : 5211 TO DO : save crop sub photo not yet done ! save time : 0.3969242572784424 nb_obj : 13 nb_hashtags : 4 time to prepare the origin masks : 4.900866746902466 time for calcul the mask position with numpy : 0.5804407596588135 nb_pixel_total : 5514011 time to create 1 rle with new method : 0.9330606460571289 time for calcul the mask position with numpy : 0.036359548568725586 nb_pixel_total : 60392 time to create 1 rle with old method : 0.07323026657104492 time for calcul the mask position with numpy : 0.04214644432067871 nb_pixel_total : 147368 time to create 1 rle with old method : 0.16791248321533203 time for calcul the mask position with numpy : 0.023445844650268555 nb_pixel_total : 147200 time to create 1 rle with old method : 0.16273784637451172 time for calcul the mask position with numpy : 0.02512335777282715 nb_pixel_total : 29287 time to create 1 rle with old method : 0.0326848030090332 time for calcul the mask position with numpy : 0.02341604232788086 nb_pixel_total : 9842 time to create 1 rle with old method : 0.011266708374023438 time for calcul the mask position with numpy : 0.024652957916259766 nb_pixel_total : 165035 time to create 1 rle with new method : 0.889136552810669 time for calcul the mask position with numpy : 0.021086931228637695 nb_pixel_total : 214680 time to create 1 rle with new method : 0.6217567920684814 time for calcul the mask position with numpy : 0.02260279655456543 nb_pixel_total : 14073 time to create 1 rle with old method : 0.015491247177124023 time for calcul the mask position with numpy : 0.025310516357421875 nb_pixel_total : 26598 time to create 1 rle with old method : 0.03468918800354004 time for calcul the mask position with numpy : 0.022482872009277344 nb_pixel_total : 2591 time to create 1 rle with old method : 0.0030364990234375 time for calcul the mask position with numpy : 0.024898529052734375 nb_pixel_total : 303736 time to create 1 rle with new method : 0.6556899547576904 time for calcul the mask position with numpy : 0.02225780487060547 nb_pixel_total : 3843 time to create 1 rle with old method : 0.004347085952758789 time for calcul the mask position with numpy : 0.02410721778869629 nb_pixel_total : 411584 time to create 1 rle with new method : 0.42322659492492676 create new chi : 5.080410957336426 time to delete rle : 0.0016894340515136719 batch 1 Loaded 27 chid ids of type : 3594 ++++++++++++++++++Number RLEs to save : 11757 TO DO : save crop sub photo not yet done ! save time : 0.7775864601135254 nb_obj : 4 nb_hashtags : 3 time to prepare the origin masks : 3.7015256881713867 time for calcul the mask position with numpy : 0.34712791442871094 nb_pixel_total : 6497374 time to create 1 rle with new method : 0.8886406421661377 time for calcul the mask position with numpy : 0.021746158599853516 nb_pixel_total : 10273 time to create 1 rle with old method : 0.011154651641845703 time for calcul the mask position with numpy : 0.022922039031982422 nb_pixel_total : 200586 time to create 1 rle with new method : 0.4538388252258301 time for calcul the mask position with numpy : 0.023901700973510742 nb_pixel_total : 327347 time to create 1 rle with new method : 0.7354371547698975 time for calcul the mask position with numpy : 0.02270030975341797 nb_pixel_total : 14660 time to create 1 rle with old method : 0.0180819034576416 create new chi : 2.63688063621521 time to delete rle : 0.0012025833129882812 batch 1 Loaded 9 chid ids of type : 3594 ++++++Number RLEs to save : 7446 TO DO : save crop sub photo not yet done ! save time : 0.5078048706054688 nb_obj : 30 nb_hashtags : 3 time to prepare the origin masks : 3.684504747390747 time for calcul the mask position with numpy : 0.535714864730835 nb_pixel_total : 6474089 time to create 1 rle with new method : 0.6118550300598145 time for calcul the mask position with numpy : 0.03173232078552246 nb_pixel_total : 6175 time to create 1 rle with old method : 0.007731199264526367 time for calcul the mask position with numpy : 0.031320810317993164 nb_pixel_total : 11502 time to create 1 rle with old method : 0.014471292495727539 time for calcul the mask position with numpy : 0.03209972381591797 nb_pixel_total : 36154 time to create 1 rle with old method : 0.0421299934387207 time for calcul the mask position with numpy : 0.032117605209350586 nb_pixel_total : 4215 time to create 1 rle with old method : 0.004892587661743164 time for calcul the mask position with numpy : 0.030248403549194336 nb_pixel_total : 22050 time to create 1 rle with old method : 0.02467799186706543 time for calcul the mask position with numpy : 0.029261350631713867 nb_pixel_total : 15478 time to create 1 rle with old method : 0.01941704750061035 time for calcul the mask position with numpy : 0.02929067611694336 nb_pixel_total : 16009 time to create 1 rle with old method : 0.018332958221435547 time for calcul the mask position with numpy : 0.03047943115234375 nb_pixel_total : 21624 time to create 1 rle with old method : 0.02539992332458496 time for calcul the mask position with numpy : 0.035192012786865234 nb_pixel_total : 11022 time to create 1 rle with old method : 0.01348257064819336 time for calcul the mask position with numpy : 0.030682086944580078 nb_pixel_total : 8069 time to create 1 rle with old method : 0.010377168655395508 time for calcul the mask position with numpy : 0.03446483612060547 nb_pixel_total : 14121 time to create 1 rle with old method : 0.021619319915771484 time for calcul the mask position with numpy : 0.028899192810058594 nb_pixel_total : 28696 time to create 1 rle with old method : 0.0321810245513916 time for calcul the mask position with numpy : 0.02899003028869629 nb_pixel_total : 30033 time to create 1 rle with old method : 0.03345537185668945 time for calcul the mask position with numpy : 0.02884840965270996 nb_pixel_total : 15920 time to create 1 rle with old method : 0.017911672592163086 time for calcul the mask position with numpy : 0.030539512634277344 nb_pixel_total : 43577 time to create 1 rle with old method : 0.04862070083618164 time for calcul the mask position with numpy : 0.0289156436920166 nb_pixel_total : 10283 time to create 1 rle with old method : 0.011592388153076172 time for calcul the mask position with numpy : 0.02887725830078125 nb_pixel_total : 19813 time to create 1 rle with old method : 0.022150516510009766 time for calcul the mask position with numpy : 0.02898430824279785 nb_pixel_total : 23808 time to create 1 rle with old method : 0.026764392852783203 time for calcul the mask position with numpy : 0.0301363468170166 nb_pixel_total : 66102 time to create 1 rle with old method : 0.07376670837402344 time for calcul the mask position with numpy : 0.02897953987121582 nb_pixel_total : 22696 time to create 1 rle with old method : 0.025496721267700195 time for calcul the mask position with numpy : 0.033231258392333984 nb_pixel_total : 22862 time to create 1 rle with old method : 0.026022672653198242 time for calcul the mask position with numpy : 0.029159069061279297 nb_pixel_total : 20867 time to create 1 rle with old method : 0.023544788360595703 time for calcul the mask position with numpy : 0.03355097770690918 nb_pixel_total : 15082 time to create 1 rle with old method : 0.016903400421142578 time for calcul the mask position with numpy : 0.028881311416625977 nb_pixel_total : 13610 time to create 1 rle with old method : 0.015200138092041016 time for calcul the mask position with numpy : 0.029035091400146484 nb_pixel_total : 38336 time to create 1 rle with old method : 0.042916297912597656 time for calcul the mask position with numpy : 0.02910614013671875 nb_pixel_total : 5739 time to create 1 rle with old method : 0.007353782653808594 time for calcul the mask position with numpy : 0.029552459716796875 nb_pixel_total : 8352 time to create 1 rle with old method : 0.009558439254760742 time for calcul the mask position with numpy : 0.02948141098022461 nb_pixel_total : 8425 time to create 1 rle with old method : 0.009505510330200195 time for calcul the mask position with numpy : 0.028763771057128906 nb_pixel_total : 10269 time to create 1 rle with old method : 0.011483192443847656 time for calcul the mask position with numpy : 0.029255151748657227 nb_pixel_total : 5262 time to create 1 rle with old method : 0.005898952484130859 create new chi : 2.7710089683532715 time to delete rle : 0.002065896987915039 batch 1 Loaded 61 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++Number RLEs to save : 13121 TO DO : save crop sub photo not yet done ! save time : 0.9795198440551758 nb_obj : 9 nb_hashtags : 3 time to prepare the origin masks : 3.733090400695801 time for calcul the mask position with numpy : 0.40480661392211914 nb_pixel_total : 6785476 time to create 1 rle with new method : 0.6831271648406982 time for calcul the mask position with numpy : 0.023387432098388672 nb_pixel_total : 660 time to create 1 rle with old method : 0.0008873939514160156 time for calcul the mask position with numpy : 0.021555185317993164 nb_pixel_total : 25208 time to create 1 rle with old method : 0.027914762496948242 time for calcul the mask position with numpy : 0.02229452133178711 nb_pixel_total : 10307 time to create 1 rle with old method : 0.011189937591552734 time for calcul the mask position with numpy : 0.021703243255615234 nb_pixel_total : 55471 time to create 1 rle with old method : 0.06104421615600586 time for calcul the mask position with numpy : 0.02227497100830078 nb_pixel_total : 25875 time to create 1 rle with old method : 0.028573274612426758 time for calcul the mask position with numpy : 0.023241519927978516 nb_pixel_total : 89281 time to create 1 rle with old method : 0.09919309616088867 time for calcul the mask position with numpy : 0.022108793258666992 nb_pixel_total : 15276 time to create 1 rle with old method : 0.016393184661865234 time for calcul the mask position with numpy : 0.021988868713378906 nb_pixel_total : 15062 time to create 1 rle with old method : 0.01600050926208496 time for calcul the mask position with numpy : 0.021427631378173828 nb_pixel_total : 27624 time to create 1 rle with old method : 0.028971195220947266 create new chi : 1.6153743267059326 time to delete rle : 0.0008802413940429688 batch 1 Loaded 19 chid ids of type : 3594 +++++++++Number RLEs to save : 5799 TO DO : save crop sub photo not yet done ! save time : 0.4035830497741699 nb_obj : 30 nb_hashtags : 4 time to prepare the origin masks : 3.9516875743865967 time for calcul the mask position with numpy : 0.6036818027496338 nb_pixel_total : 6063828 time to create 1 rle with new method : 0.8164443969726562 time for calcul the mask position with numpy : 0.029294252395629883 nb_pixel_total : 10605 time to create 1 rle with old method : 0.011996269226074219 time for calcul the mask position with numpy : 0.02892279624938965 nb_pixel_total : 14347 time to create 1 rle with old method : 0.01682305335998535 time for calcul the mask position with numpy : 0.029380321502685547 nb_pixel_total : 29118 time to create 1 rle with old method : 0.0326848030090332 time for calcul the mask position with numpy : 0.029141902923583984 nb_pixel_total : 61910 time to create 1 rle with old method : 0.0693519115447998 time for calcul the mask position with numpy : 0.02876877784729004 nb_pixel_total : 13454 time to create 1 rle with old method : 0.015079021453857422 time for calcul the mask position with numpy : 0.02932453155517578 nb_pixel_total : 17192 time to create 1 rle with old method : 0.021085739135742188 time for calcul the mask position with numpy : 0.02912449836730957 nb_pixel_total : 91430 time to create 1 rle with old method : 0.09858369827270508 time for calcul the mask position with numpy : 0.028749704360961914 nb_pixel_total : 354 time to create 1 rle with old method : 0.00047016143798828125 time for calcul the mask position with numpy : 0.02863454818725586 nb_pixel_total : 18681 time to create 1 rle with old method : 0.020612001419067383 time for calcul the mask position with numpy : 0.030628204345703125 nb_pixel_total : 6189 time to create 1 rle with old method : 0.007422447204589844 time for calcul the mask position with numpy : 0.030103445053100586 nb_pixel_total : 69509 time to create 1 rle with old method : 0.07664680480957031 time for calcul the mask position with numpy : 0.028638362884521484 nb_pixel_total : 16923 time to create 1 rle with old method : 0.018615007400512695 time for calcul the mask position with numpy : 0.02926468849182129 nb_pixel_total : 189489 time to create 1 rle with new method : 0.8903040885925293 time for calcul the mask position with numpy : 0.02970147132873535 nb_pixel_total : 9359 time to create 1 rle with old method : 0.011583328247070312 time for calcul the mask position with numpy : 0.03217172622680664 nb_pixel_total : 12767 time to create 1 rle with old method : 0.02482151985168457 time for calcul the mask position with numpy : 0.036301612854003906 nb_pixel_total : 3170 time to create 1 rle with old method : 0.006777286529541016 time for calcul the mask position with numpy : 0.03730034828186035 nb_pixel_total : 68926 time to create 1 rle with old method : 0.08609700202941895 time for calcul the mask position with numpy : 0.029154539108276367 nb_pixel_total : 50989 time to create 1 rle with old method : 0.058824777603149414 time for calcul the mask position with numpy : 0.03205251693725586 nb_pixel_total : 18961 time to create 1 rle with old method : 0.021184206008911133 time for calcul the mask position with numpy : 0.02982020378112793 nb_pixel_total : 19412 time to create 1 rle with old method : 0.025654315948486328 time for calcul the mask position with numpy : 0.030741453170776367 nb_pixel_total : 16482 time to create 1 rle with old method : 0.02036595344543457 time for calcul the mask position with numpy : 0.0301663875579834 nb_pixel_total : 35208 time to create 1 rle with old method : 0.03902292251586914 time for calcul the mask position with numpy : 0.02919745445251465 nb_pixel_total : 21263 time to create 1 rle with old method : 0.024132490158081055 time for calcul the mask position with numpy : 0.02907729148864746 nb_pixel_total : 9918 time to create 1 rle with old method : 0.011145353317260742 time for calcul the mask position with numpy : 0.031801462173461914 nb_pixel_total : 3885 time to create 1 rle with old method : 0.004384517669677734 time for calcul the mask position with numpy : 0.02868199348449707 nb_pixel_total : 15419 time to create 1 rle with old method : 0.02568364143371582 time for calcul the mask position with numpy : 0.03349804878234863 nb_pixel_total : 48677 time to create 1 rle with old method : 0.05791473388671875 time for calcul the mask position with numpy : 0.029599666595458984 nb_pixel_total : 67538 time to create 1 rle with old method : 0.07514786720275879 time for calcul the mask position with numpy : 0.03063178062438965 nb_pixel_total : 43030 time to create 1 rle with old method : 0.04813814163208008 time for calcul the mask position with numpy : 0.029150724411010742 nb_pixel_total : 2207 time to create 1 rle with old method : 0.002614736557006836 create new chi : 4.213107109069824 time to delete rle : 0.0024518966674804688 batch 1 Loaded 61 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++Number RLEs to save : 14155 TO DO : save crop sub photo not yet done ! save time : 0.9619565010070801 nb_obj : 11 nb_hashtags : 2 time to prepare the origin masks : 3.240691900253296 time for calcul the mask position with numpy : 0.5391509532928467 nb_pixel_total : 6829856 time to create 1 rle with new method : 1.597440242767334 time for calcul the mask position with numpy : 0.03545546531677246 nb_pixel_total : 9171 time to create 1 rle with old method : 0.010310173034667969 time for calcul the mask position with numpy : 0.034879207611083984 nb_pixel_total : 18996 time to create 1 rle with old method : 0.02138042449951172 time for calcul the mask position with numpy : 0.034699440002441406 nb_pixel_total : 15807 time to create 1 rle with old method : 0.0177004337310791 time for calcul the mask position with numpy : 0.034081459045410156 nb_pixel_total : 46100 time to create 1 rle with old method : 0.05134248733520508 time for calcul the mask position with numpy : 0.031028032302856445 nb_pixel_total : 33653 time to create 1 rle with old method : 0.03763866424560547 time for calcul the mask position with numpy : 0.03277850151062012 nb_pixel_total : 14521 time to create 1 rle with old method : 0.01620197296142578 time for calcul the mask position with numpy : 0.0315699577331543 nb_pixel_total : 13363 time to create 1 rle with old method : 0.014839887619018555 time for calcul the mask position with numpy : 0.03247785568237305 nb_pixel_total : 18459 time to create 1 rle with old method : 0.020693302154541016 time for calcul the mask position with numpy : 0.02422952651977539 nb_pixel_total : 9240 time to create 1 rle with old method : 0.010490179061889648 time for calcul the mask position with numpy : 0.021339893341064453 nb_pixel_total : 25295 time to create 1 rle with old method : 0.02797698974609375 time for calcul the mask position with numpy : 0.02051520347595215 nb_pixel_total : 15779 time to create 1 rle with old method : 0.01732778549194336 create new chi : 2.750561475753784 time to delete rle : 0.001012563705444336 batch 1 Loaded 23 chid ids of type : 3594 ++++++++++++Number RLEs to save : 5964 TO DO : save crop sub photo not yet done ! save time : 0.4322948455810547 nb_obj : 34 nb_hashtags : 4 time to prepare the origin masks : 3.7579402923583984 time for calcul the mask position with numpy : 0.4745209217071533 nb_pixel_total : 6361131 time to create 1 rle with new method : 0.7015855312347412 time for calcul the mask position with numpy : 0.029052257537841797 nb_pixel_total : 11551 time to create 1 rle with old method : 0.013079166412353516 time for calcul the mask position with numpy : 0.029291629791259766 nb_pixel_total : 22720 time to create 1 rle with old method : 0.025617599487304688 time for calcul the mask position with numpy : 0.02894139289855957 nb_pixel_total : 6540 time to create 1 rle with old method : 0.007452249526977539 time for calcul the mask position with numpy : 0.028804779052734375 nb_pixel_total : 8879 time to create 1 rle with old method : 0.010551929473876953 time for calcul the mask position with numpy : 0.02912163734436035 nb_pixel_total : 8463 time to create 1 rle with old method : 0.009711265563964844 time for calcul the mask position with numpy : 0.03201866149902344 nb_pixel_total : 7326 time to create 1 rle with old method : 0.008881330490112305 time for calcul the mask position with numpy : 0.03169560432434082 nb_pixel_total : 59778 time to create 1 rle with old method : 0.0661928653717041 time for calcul the mask position with numpy : 0.02890801429748535 nb_pixel_total : 4658 time to create 1 rle with old method : 0.005299806594848633 time for calcul the mask position with numpy : 0.028887033462524414 nb_pixel_total : 6877 time to create 1 rle with old method : 0.007856607437133789 time for calcul the mask position with numpy : 0.029165267944335938 nb_pixel_total : 10156 time to create 1 rle with old method : 0.011555910110473633 time for calcul the mask position with numpy : 0.029039621353149414 nb_pixel_total : 29878 time to create 1 rle with old method : 0.03405165672302246 time for calcul the mask position with numpy : 0.030391693115234375 nb_pixel_total : 28630 time to create 1 rle with old method : 0.03252267837524414 time for calcul the mask position with numpy : 0.03075385093688965 nb_pixel_total : 10007 time to create 1 rle with old method : 0.013782262802124023 time for calcul the mask position with numpy : 0.030712604522705078 nb_pixel_total : 42395 time to create 1 rle with old method : 0.04710650444030762 time for calcul the mask position with numpy : 0.02955937385559082 nb_pixel_total : 34273 time to create 1 rle with old method : 0.03902864456176758 time for calcul the mask position with numpy : 0.028972387313842773 nb_pixel_total : 28104 time to create 1 rle with old method : 0.03206896781921387 time for calcul the mask position with numpy : 0.028989553451538086 nb_pixel_total : 12382 time to create 1 rle with old method : 0.014208316802978516 time for calcul the mask position with numpy : 0.02913355827331543 nb_pixel_total : 8520 time to create 1 rle with old method : 0.010394573211669922 time for calcul the mask position with numpy : 0.029807090759277344 nb_pixel_total : 53087 time to create 1 rle with old method : 0.06080985069274902 time for calcul the mask position with numpy : 0.030852556228637695 nb_pixel_total : 48102 time to create 1 rle with old method : 0.07822275161743164 time for calcul the mask position with numpy : 0.028954029083251953 nb_pixel_total : 25850 time to create 1 rle with old method : 0.029633760452270508 time for calcul the mask position with numpy : 0.029410600662231445 nb_pixel_total : 33530 time to create 1 rle with old method : 0.03861498832702637 time for calcul the mask position with numpy : 0.028997182846069336 nb_pixel_total : 33169 time to create 1 rle with old method : 0.03721356391906738 time for calcul the mask position with numpy : 0.029903650283813477 nb_pixel_total : 15905 time to create 1 rle with old method : 0.018008947372436523 time for calcul the mask position with numpy : 0.029295682907104492 nb_pixel_total : 12028 time to create 1 rle with old method : 0.013820409774780273 time for calcul the mask position with numpy : 0.02912282943725586 nb_pixel_total : 9276 time to create 1 rle with old method : 0.010601520538330078 time for calcul the mask position with numpy : 0.028917789459228516 nb_pixel_total : 8561 time to create 1 rle with old method : 0.009819746017456055 time for calcul the mask position with numpy : 0.029007673263549805 nb_pixel_total : 31583 time to create 1 rle with old method : 0.035192251205444336 time for calcul the mask position with numpy : 0.028990507125854492 nb_pixel_total : 5196 time to create 1 rle with old method : 0.006001949310302734 time for calcul the mask position with numpy : 0.02889275550842285 nb_pixel_total : 8776 time to create 1 rle with old method : 0.010089397430419922 time for calcul the mask position with numpy : 0.02894115447998047 nb_pixel_total : 10853 time to create 1 rle with old method : 0.012365102767944336 time for calcul the mask position with numpy : 0.02893853187561035 nb_pixel_total : 7832 time to create 1 rle with old method : 0.00902700424194336 time for calcul the mask position with numpy : 0.02888321876525879 nb_pixel_total : 4688 time to create 1 rle with old method : 0.005337715148925781 time for calcul the mask position with numpy : 0.028866052627563477 nb_pixel_total : 39536 time to create 1 rle with old method : 0.04543113708496094 create new chi : 3.023012161254883 time to delete rle : 0.0022821426391601562 batch 1 Loaded 69 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++Number RLEs to save : 13811 TO DO : save crop sub photo not yet done ! save time : 0.8933124542236328 nb_obj : 10 nb_hashtags : 3 time to prepare the origin masks : 3.348992109298706 time for calcul the mask position with numpy : 0.4697258472442627 nb_pixel_total : 5720073 time to create 1 rle with new method : 0.9107301235198975 time for calcul the mask position with numpy : 0.02257227897644043 nb_pixel_total : 144766 time to create 1 rle with old method : 0.16436052322387695 time for calcul the mask position with numpy : 0.025506258010864258 nb_pixel_total : 497261 time to create 1 rle with new method : 0.9553191661834717 time for calcul the mask position with numpy : 0.02825307846069336 nb_pixel_total : 20319 time to create 1 rle with old method : 0.023216962814331055 time for calcul the mask position with numpy : 0.03569221496582031 nb_pixel_total : 29714 time to create 1 rle with old method : 0.03388071060180664 time for calcul the mask position with numpy : 0.03606986999511719 nb_pixel_total : 50854 time to create 1 rle with old method : 0.06220197677612305 time for calcul the mask position with numpy : 0.03545522689819336 nb_pixel_total : 46588 time to create 1 rle with old method : 0.0522763729095459 time for calcul the mask position with numpy : 0.03621315956115723 nb_pixel_total : 8642 time to create 1 rle with old method : 0.009833812713623047 time for calcul the mask position with numpy : 0.035761356353759766 nb_pixel_total : 114834 time to create 1 rle with old method : 0.13099122047424316 time for calcul the mask position with numpy : 0.03968024253845215 nb_pixel_total : 265280 time to create 1 rle with new method : 0.4274318218231201 time for calcul the mask position with numpy : 0.04069089889526367 nb_pixel_total : 151909 time to create 1 rle with new method : 0.7770087718963623 create new chi : 4.459391832351685 time to delete rle : 0.0025644302368164062 batch 1 Loaded 21 chid ids of type : 3594 +++++++++++++Number RLEs to save : 9462 TO DO : save crop sub photo not yet done ! save time : 0.6184570789337158 nb_obj : 21 nb_hashtags : 3 time to prepare the origin masks : 7.415333271026611 time for calcul the mask position with numpy : 0.5674350261688232 nb_pixel_total : 6209109 time to create 1 rle with new method : 0.7372324466705322 time for calcul the mask position with numpy : 0.04355430603027344 nb_pixel_total : 60225 time to create 1 rle with old method : 0.07057070732116699 time for calcul the mask position with numpy : 0.034752607345581055 nb_pixel_total : 50407 time to create 1 rle with old method : 0.05648159980773926 time for calcul the mask position with numpy : 0.03439068794250488 nb_pixel_total : 9489 time to create 1 rle with old method : 0.010814666748046875 time for calcul the mask position with numpy : 0.03440546989440918 nb_pixel_total : 32419 time to create 1 rle with old method : 0.03644275665283203 time for calcul the mask position with numpy : 0.03568077087402344 nb_pixel_total : 25156 time to create 1 rle with old method : 0.028059720993041992 time for calcul the mask position with numpy : 0.03423118591308594 nb_pixel_total : 10543 time to create 1 rle with old method : 0.011827230453491211 time for calcul the mask position with numpy : 0.03545045852661133 nb_pixel_total : 19684 time to create 1 rle with old method : 0.0234220027923584 time for calcul the mask position with numpy : 0.03607511520385742 nb_pixel_total : 204468 time to create 1 rle with new method : 0.8414525985717773 time for calcul the mask position with numpy : 0.03392934799194336 nb_pixel_total : 19957 time to create 1 rle with old method : 0.022429227828979492 time for calcul the mask position with numpy : 0.03338885307312012 nb_pixel_total : 16671 time to create 1 rle with old method : 0.018853425979614258 time for calcul the mask position with numpy : 0.034233808517456055 nb_pixel_total : 57138 time to create 1 rle with old method : 0.06351065635681152 time for calcul the mask position with numpy : 0.0338895320892334 nb_pixel_total : 22675 time to create 1 rle with old method : 0.025493860244750977 time for calcul the mask position with numpy : 0.03404378890991211 nb_pixel_total : 10822 time to create 1 rle with old method : 0.01216435432434082 time for calcul the mask position with numpy : 0.03412771224975586 nb_pixel_total : 20212 time to create 1 rle with old method : 0.02282118797302246 time for calcul the mask position with numpy : 0.035861968994140625 nb_pixel_total : 73347 time to create 1 rle with old method : 0.08146262168884277 time for calcul the mask position with numpy : 0.03350114822387695 nb_pixel_total : 14430 time to create 1 rle with old method : 0.01616358757019043 time for calcul the mask position with numpy : 0.03531503677368164 nb_pixel_total : 17099 time to create 1 rle with old method : 0.019205093383789062 time for calcul the mask position with numpy : 0.03162026405334473 nb_pixel_total : 44037 time to create 1 rle with old method : 0.04918861389160156 time for calcul the mask position with numpy : 0.02999591827392578 nb_pixel_total : 41051 time to create 1 rle with old method : 0.046454668045043945 time for calcul the mask position with numpy : 0.03364968299865723 nb_pixel_total : 70352 time to create 1 rle with old method : 0.07860922813415527 time for calcul the mask position with numpy : 0.03456449508666992 nb_pixel_total : 20949 time to create 1 rle with old method : 0.023667335510253906 create new chi : 3.6671085357666016 time to delete rle : 0.0028171539306640625 batch 1 Loaded 43 chid ids of type : 3594 +++++++++++++++++++++++++++++Number RLEs to save : 12071 TO DO : save crop sub photo not yet done ! save time : 0.7940540313720703 map_output_result : {1353408839: (0.0, 'Should be the crop_list due to order', 0), 1353408833: (0.0, 'Should be the crop_list due to order', 0), 1353408830: (0.0, 'Should be the crop_list due to order', 0), 1353408827: (0.0, 'Should be the crop_list due to order', 0), 1353408782: (0.0, 'Should be the crop_list due to order', 0), 1353408716: (0.0, 'Should be the crop_list due to order', 0), 1353408529: (0.0, 'Should be the crop_list due to order', 0), 1353408451: (0.0, 'Should be the crop_list due to order', 0), 1353408445: (0.0, 'Should be the crop_list due to order', 0), 1353408440: (0.0, 'Should be the crop_list due to order', 0), 1353408406: (0.0, 'Should be the crop_list due to order', 0), 1353408354: (0.0, 'Should be the crop_list due to order', 0), 1353408350: (0.0, 'Should be the crop_list due to order', 0), 1353408338: (0.0, 'Should be the crop_list due to order', 0), 1353408332: (0.0, 'Should be the crop_list due to order', 0), 1353408229: (0.0, 'Should be the crop_list due to order', 0), 1353408175: (0.0, 'Should be the crop_list due to order', 0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1353408839, 1353408833, 1353408830, 1353408827, 1353408782, 1353408716, 1353408529, 1353408451, 1353408445, 1353408440, 1353408406, 1353408354, 1353408350, 1353408338, 1353408332, 1353408229, 1353408175] Looping around the photos to save general results len do output : 17 /1353408839.Didn't retrieve data . /1353408833.Didn't retrieve data . /1353408830.Didn't retrieve data . /1353408827.Didn't retrieve data . /1353408782.Didn't retrieve data . /1353408716.Didn't retrieve data . /1353408529.Didn't retrieve data . /1353408451.Didn't retrieve data . /1353408445.Didn't retrieve data . /1353408440.Didn't retrieve data . /1353408406.Didn't retrieve data . /1353408354.Didn't retrieve data . /1353408350.Didn't retrieve data . /1353408338.Didn't retrieve data . /1353408332.Didn't retrieve data . /1353408229.Didn't retrieve data . /1353408175.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, '2758897') ('3318', '22396717', '1353408839', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408833', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408830', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408827', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408782', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408716', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408529', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408451', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408445', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408440', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408406', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408354', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408350', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408338', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408332', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408229', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408175', None, None, None, None, None, '2758897') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 51 time used for this insertion : 0.014624595642089844 save_final save missing photos in datou_result : time spend for datou_step_exec : 139.9150321483612 time spend to save output : 0.016925811767578125 total time spend for step 3 : 139.93195796012878 step4:ventilate_hashtags_in_portfolio Thu Apr 24 20:48:04 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 : 22396717 get user id for portfolio 22396717 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`=22396717 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_clair','pehd','environnement','mal_croppe','flou','autre','background','papier','pet_fonce','carton','metal')) 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`=22396717 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_clair','pehd','environnement','mal_croppe','flou','autre','background','papier','pet_fonce','carton','metal')) 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`=22396717 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_clair','pehd','environnement','mal_croppe','flou','autre','background','papier','pet_fonce','carton','metal')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://www.fotonower.com/velours/22397850,22397851,22397852,22397853,22397854,22397855,22397856,22397857,22397858,22397859,22397860?tags=pet_clair,pehd,environnement,mal_croppe,flou,autre,background,papier,pet_fonce,carton,metal Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1353408839, 1353408833, 1353408830, 1353408827, 1353408782, 1353408716, 1353408529, 1353408451, 1353408445, 1353408440, 1353408406, 1353408354, 1353408350, 1353408338, 1353408332, 1353408229, 1353408175] Looping around the photos to save general results len do output : 1 /22396717. 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, '2758897') ('3318', '22396717', '1353408839', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408833', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408830', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408827', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408782', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408716', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408529', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408451', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408445', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408440', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408406', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408354', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408350', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408338', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408332', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408229', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408175', None, None, None, None, None, '2758897') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 18 time used for this insertion : 0.01537942886352539 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.6807148456573486 time spend to save output : 0.015648603439331055 total time spend for step 4 : 1.6963634490966797 step5:final Thu Apr 24 20:48:05 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 : {1353408839: ('0.11929673149216118',), 1353408833: ('0.11929673149216118',), 1353408830: ('0.11929673149216118',), 1353408827: ('0.11929673149216118',), 1353408782: ('0.11929673149216118',), 1353408716: ('0.11929673149216118',), 1353408529: ('0.11929673149216118',), 1353408451: ('0.11929673149216118',), 1353408445: ('0.11929673149216118',), 1353408440: ('0.11929673149216118',), 1353408406: ('0.11929673149216118',), 1353408354: ('0.11929673149216118',), 1353408350: ('0.11929673149216118',), 1353408338: ('0.11929673149216118',), 1353408332: ('0.11929673149216118',), 1353408229: ('0.11929673149216118',), 1353408175: ('0.11929673149216118',)} new output for save of step final : {1353408839: ('0.11929673149216118',), 1353408833: ('0.11929673149216118',), 1353408830: ('0.11929673149216118',), 1353408827: ('0.11929673149216118',), 1353408782: ('0.11929673149216118',), 1353408716: ('0.11929673149216118',), 1353408529: ('0.11929673149216118',), 1353408451: ('0.11929673149216118',), 1353408445: ('0.11929673149216118',), 1353408440: ('0.11929673149216118',), 1353408406: ('0.11929673149216118',), 1353408354: ('0.11929673149216118',), 1353408350: ('0.11929673149216118',), 1353408338: ('0.11929673149216118',), 1353408332: ('0.11929673149216118',), 1353408229: ('0.11929673149216118',), 1353408175: ('0.11929673149216118',)} [1353408839, 1353408833, 1353408830, 1353408827, 1353408782, 1353408716, 1353408529, 1353408451, 1353408445, 1353408440, 1353408406, 1353408354, 1353408350, 1353408338, 1353408332, 1353408229, 1353408175] Looping around the photos to save general results len do output : 17 /1353408839.Didn't retrieve data . /1353408833.Didn't retrieve data . /1353408830.Didn't retrieve data . /1353408827.Didn't retrieve data . /1353408782.Didn't retrieve data . /1353408716.Didn't retrieve data . /1353408529.Didn't retrieve data . /1353408451.Didn't retrieve data . /1353408445.Didn't retrieve data . /1353408440.Didn't retrieve data . /1353408406.Didn't retrieve data . /1353408354.Didn't retrieve data . /1353408350.Didn't retrieve data . /1353408338.Didn't retrieve data . /1353408332.Didn't retrieve data . /1353408229.Didn't retrieve data . /1353408175.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, '2758897') ('3318', '22396717', '1353408839', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408833', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408830', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408827', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408782', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408716', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408529', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408451', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408445', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408440', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408406', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408354', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408350', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408338', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408332', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408229', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408175', None, None, None, None, None, '2758897') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 51 time used for this insertion : 0.018362045288085938 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12255191802978516 time spend to save output : 0.019179105758666992 total time spend for step 5 : 0.14173102378845215 step6:blur_detection Thu Apr 24 20:48:05 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/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a.jpg resize: (2160, 3264) 1353408839 -1.2121173099949893 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af.jpg resize: (2160, 3264) 1353408833 -1.7548256439460082 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222.jpg resize: (2160, 3264) 1353408830 -1.1141628485954511 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361.jpg resize: (2160, 3264) 1353408827 -1.3726798806468268 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e.jpg resize: (2160, 3264) 1353408782 -1.6372368440175742 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407.jpg resize: (2160, 3264) 1353408716 -4.361914151342719 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158.jpg resize: (2160, 3264) 1353408529 -0.6456408925351814 treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9.jpg resize: (2160, 3264) 1353408451 0.7700766488721549 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110.jpg resize: (2160, 3264) 1353408445 0.579255937863176 treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0.jpg resize: (2160, 3264) 1353408440 0.02706554188186605 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609.jpg resize: (2160, 3264) 1353408406 -2.5526863420420542 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f.jpg resize: (2160, 3264) 1353408354 -1.2719344401271362 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0.jpg resize: (2160, 3264) 1353408350 -3.851185967312291 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6.jpg resize: (2160, 3264) 1353408338 1.3342641648442872 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c.jpg resize: (2160, 3264) 1353408332 -6.040901504051467 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb.jpg resize: (2160, 3264) 1353408229 0.25174783967417963 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f.jpg resize: (2160, 3264) 1353408175 -1.9969931222201749 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968430_0.png resize: (597, 363) 1353455546 -0.629098780440414 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968428_0.png resize: (267, 211) 1353455547 -1.7031141488010135 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968435_0.png resize: (132, 140) 1353455548 -1.1629109389931565 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968429_0.png resize: (110, 141) 1353455550 -2.0124671669230194 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968437_0.png resize: (223, 214) 1353455551 -1.8801139595847878 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968427_0.png resize: (237, 192) 1353455552 -0.9190481123638231 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968438_0.png resize: (393, 334) 1353455554 0.9235286551206779 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968431_0.png resize: (177, 168) 1353455555 -2.6383303888200724 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968434_0.png resize: (285, 515) 1353455556 -1.8167786024183268 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968433_0.png resize: (416, 173) 1353455558 -0.6765559483219231 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968439_0.png resize: (163, 216) 1353455559 -2.3270619210923154 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968443_0.png resize: (153, 128) 1353455560 -0.80500538463307 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968446_0.png resize: (130, 240) 1353455562 -0.6135636862394237 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968455_0.png resize: (142, 120) 1353455563 -0.7765068211978879 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968445_0.png resize: (523, 423) 1353455564 -0.6875200494527569 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968456_0.png resize: (167, 77) 1353455565 -0.11984028316503116 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968447_0.png resize: (98, 254) 1353455567 -0.8324823682519417 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968460_0.png resize: (166, 224) 1353455568 -1.7602696385454428 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968458_0.png resize: (117, 172) 1353455569 -1.1692621130626188 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968451_0.png resize: (395, 437) 1353455571 -0.7265884290573971 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968440_0.png resize: (218, 131) 1353455572 -1.4787772273098723 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968450_0.png resize: (214, 274) 1353455573 -1.531998839441876 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968449_0.png resize: (63, 113) 1353455575 -1.313663508897016 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968452_0.png resize: (128, 148) 1353455576 -1.161790036916883 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968462_0.png resize: (155, 131) 1353455577 -2.242073126601249 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968453_0.png resize: (176, 96) 1353455579 -1.416810780965145 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968472_0.png resize: (453, 915) 1353455581 0.04780775783609202 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968470_0.png resize: (334, 226) 1353455582 -2.265693878189522 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968474_0.png resize: (927, 778) 1353455584 -0.2826904619306073 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968473_0.png resize: (159, 212) 1353455585 -0.8512423465414394 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968467_0.png resize: (216, 278) 1353455586 -0.12113644017587548 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968464_0.png resize: (196, 290) 1353455588 -0.9639687993892396 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968484_0.png resize: (693, 328) 1353455589 -1.4391175157379847 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968475_0.png resize: (263, 121) 1353455590 -2.0758385144618487 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968478_0.png resize: (517, 577) 1353455592 -0.6857029820668178 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968476_0.png resize: (296, 141) 1353455593 -0.8439357053278539 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968480_0.png resize: (135, 179) 1353455594 -0.7899424152040332 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968479_0.png resize: (120, 277) 1353455596 -1.1777039248878245 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968477_0.png resize: (146, 142) 1353455597 -0.9018637447838591 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968486_0.png resize: (239, 195) 1353455598 -1.0358373397849763 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968488_0.png resize: (339, 161) 1353455600 -1.6519153137165519 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968494_0.png resize: (110, 447) 1353455601 0.03139739306918444 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968491_0.png resize: (233, 526) 1353455602 -1.068045922959681 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968513_0.png resize: (156, 304) 1353455604 -2.188172130707486 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968512_0.png resize: (94, 84) 1353455605 -0.293806732937532 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968501_0.png resize: (104, 108) 1353455606 -1.7669602482492124 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968508_0.png resize: (154, 73) 1353455608 -0.9497662874887222 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968520_0.png resize: (150, 147) 1353455609 -2.594919472633314 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968518_0.png resize: (121, 121) 1353455610 -1.9478492380817956 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968503_0.png resize: (358, 260) 1353455612 -2.8073451501747018 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968509_0.png resize: (80, 148) 1353455613 -2.1360796806470526 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968515_0.png resize: (235, 374) 1353455614 -3.3930115199673674 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968516_0.png resize: (374, 418) 1353455616 -2.9181604680273097 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968499_0.png resize: (211, 256) 1353455617 -3.6398429465376076 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968511_0.png resize: (246, 238) 1353455618 -3.2838716975026476 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968514_0.png resize: (267, 448) 1353455620 -2.781703089920731 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968498_0.png resize: (263, 329) 1353455621 -2.72129830337009 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968505_0.png resize: (170, 146) 1353455622 -2.458676621238406 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968497_0.png resize: (105, 126) 1353455623 -2.1611770320852988 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968506_0.png resize: (278, 279) 1353455625 -3.578659065733299 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968496_0.png resize: (132, 165) 1353455626 -1.1627780096031737 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968521_0.png resize: (122, 148) 1353455627 -2.4090103563087655 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968502_0.png resize: (140, 125) 1353455629 -1.1789060762659027 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968500_0.png resize: (120, 154) 1353455630 -3.238640578840434 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968522_0.png resize: (115, 200) 1353455631 -1.3820104370260289 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968507_0.png resize: (133, 89) 1353455633 -2.2240700602491854 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968533_0.png resize: (344, 143) 1353455634 -1.5311509232371125 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968528_0.png resize: (159, 139) 1353455635 -1.5313913026651171 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968541_0.png resize: (168, 143) 1353455637 -1.3791669801509319 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968537_0.png resize: (225, 207) 1353455638 -0.9690642247818428 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968534_0.png resize: (123, 104) 1353455639 -2.4280199918864893 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968544_0.png resize: (88, 189) 1353455641 -0.520029342718543 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968526_0.png resize: (125, 69) 1353455642 3.8236676107206 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968538_0.png resize: (200, 432) 1353455643 -1.8462329100106416 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968539_0.png resize: (123, 165) 1353455645 2.6259867492526183 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968531_0.png resize: (329, 227) 1353455646 -0.09126506820444628 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968535_0.png resize: (129, 129) 1353455647 0.6058880034104106 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968527_0.png resize: (185, 123) 1353455648 -1.3707422748153344 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968536_0.png resize: (85, 221) 1353455650 -1.6974496954113834 treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968546_0.png resize: (199, 293) 1353455651 -1.1118548234514485 treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968550_0.png resize: (296, 91) 1353455652 0.8670463222900815 treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968549_0.png resize: (191, 227) 1353455654 -0.1021865763757265 treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968547_0.png resize: (102, 130) 1353455655 -0.6290150563796617 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968553_0.png resize: (117, 75) 1353455656 -2.886828497575434 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968552_0.png resize: (1092, 1235) 1353455658 0.6480024401153142 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968554_0.png resize: (734, 763) 1353455659 -0.30444224660766583 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968562_0.png resize: (292, 841) 1353455660 -1.8766911609526704 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968561_0.png resize: (205, 208) 1353455662 -0.31407999173182183 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968556_0.png resize: (218, 149) 1353455663 -0.36320171811789465 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968560_0.png resize: (112, 139) 1353455664 -0.17884205461162542 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968558_0.png resize: (573, 718) 1353455666 1.2423945734980462 treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0_rle_crop_3767968568_0.png resize: (114, 166) 1353455667 -1.1938231413809506 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968572_0.png resize: (272, 171) 1353455668 -2.0337786914667535 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968591_0.png resize: (280, 170) 1353455670 -1.399879037227817 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968573_0.png resize: (206, 139) 1353455671 -0.5959219495643628 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968585_0.png resize: (45, 149) 1353455672 -0.6868276742816193 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968587_0.png resize: (78, 96) 1353455673 -1.4339729545885747 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968593_0.png resize: (108, 93) 1353455675 0.38858817502055415 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968570_0.png resize: (178, 280) 1353455676 -2.536063600839075 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968575_0.png resize: (416, 180) 1353455677 -2.4003660098601505 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968590_0.png resize: (171, 117) 1353455679 -1.7160617683535908 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968577_0.png resize: (253, 222) 1353455680 -1.0346251132676625 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968574_0.png resize: (166, 111) 1353455681 -0.4842413032689633 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968589_0.png resize: (302, 336) 1353455683 -2.233451903750062 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968592_0.png resize: (98, 140) 1353455684 0.03793378451643784 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968579_0.png resize: (176, 162) 1353455685 0.9504155523787794 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968586_0.png resize: (111, 175) 1353455687 -1.9293312012116945 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968581_0.png resize: (182, 132) 1353455689 0.22212750775410287 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968598_0.png resize: (94, 107) 1353455690 -0.6364919464867604 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968596_0.png resize: (289, 111) 1353455692 -1.6060829996423387 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968584_0.png resize: (103, 105) 1353455693 -0.2682328222461395 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968576_0.png resize: (178, 355) 1353455694 -1.0720938924451824 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968582_0.png resize: (143, 132) 1353455696 -0.18009722565761743 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968588_0.png resize: (131, 206) 1353455697 -1.2122577546187423 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968580_0.png resize: (272, 121) 1353455698 -0.7750026997745209 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968594_0.png resize: (141, 102) 1353455700 -0.3091257955457356 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968604_0.png resize: (311, 222) 1353455701 -1.606188600697311 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968599_0.png resize: (363, 146) 1353455702 -1.3407557660935587 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968601_0.png resize: (186, 120) 1353455704 -1.1851510628499462 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968603_0.png resize: (178, 207) 1353455705 -0.7656506567920485 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968606_0.png resize: (188, 196) 1353455706 -1.198871002381319 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968602_0.png resize: (315, 505) 1353455708 0.16607786765061336 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968607_0.png resize: (109, 177) 1353455709 0.018979547133099104 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968629_0.png resize: (82, 147) 1353455710 1.384278287034556 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968634_0.png resize: (137, 150) 1353455712 -1.5584494576587504 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968621_0.png resize: (113, 168) 1353455713 -1.8920660756279462 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968624_0.png resize: (121, 123) 1353455714 -1.820058229733807 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968608_0.png resize: (170, 278) 1353455716 -1.3821318615631641 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968626_0.png resize: (190, 437) 1353455717 -1.9095338760259257 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968631_0.png resize: (72, 66) 1353455718 4.259029979766196 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968625_0.png resize: (195, 136) 1353455720 -1.853659537371486 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968610_0.png resize: (212, 119) 1353455721 -2.224596349644265 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968628_0.png resize: (126, 198) 1353455722 0.21622067915515233 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968636_0.png resize: (196, 257) 1353455724 -1.5733505344144167 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968611_0.png resize: (332, 111) 1353455725 -2.7853370784207283 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968609_0.png resize: (244, 98) 1353455726 -2.1067668316650785 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968618_0.png resize: (230, 293) 1353455728 -2.64248900532354 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968616_0.png resize: (114, 228) 1353455729 3.409452065493551 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968633_0.png resize: (287, 324) 1353455730 -2.150231688559207 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968615_0.png resize: (330, 487) 1353455732 -2.744117692280418 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968614_0.png resize: (373, 411) 1353455733 -3.1021534982619015 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968622_0.png resize: (157, 145) 1353455734 -1.3382468280873439 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968627_0.png resize: (113, 146) 1353455737 -1.491936221360363 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968612_0.png resize: (136, 170) 1353455738 -2.300209696469468 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968623_0.png resize: (140, 203) 1353455739 -3.218657893794225 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968632_0.png resize: (251, 258) 1353455741 -2.939502729045566 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968641_0.png resize: (165, 156) 1353455742 -0.3208631543372106 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968643_0.png resize: (152, 143) 1353455743 -0.3541438405767262 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968640_0.png resize: (114, 153) 1353455745 -1.1579205053314834 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968646_0.png resize: (102, 197) 1353455746 1.2372809124386936 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968644_0.png resize: (206, 229) 1353455747 1.3119056945709504 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968638_0.png resize: (119, 158) 1353455749 0.9067606477939686 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968647_0.png resize: (143, 222) 1353455750 -0.30404414708092503 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968639_0.png resize: (316, 260) 1353455751 0.821712959596658 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968645_0.png resize: (256, 205) 1353455753 2.4965883059080514 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968642_0.png resize: (149, 143) 1353455754 -0.21769111659572932 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968680_0.png resize: (156, 341) 1353455755 -1.8399211178647448 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968678_0.png resize: (295, 40) 1353455757 -3.5384656759741246 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968663_0.png resize: (94, 96) 1353455758 -0.7276517732558099 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968656_0.png resize: (310, 193) 1353455759 -2.8641322016312385 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968671_0.png resize: (168, 265) 1353455761 -2.5916697398149684 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968653_0.png resize: (107, 72) 1353455762 0.1650365386866666 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968667_0.png resize: (91, 116) 1353455763 -1.7880192968203674 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968674_0.png resize: (167, 318) 1353455765 -4.516965325727252 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968675_0.png resize: (231, 243) 1353455766 -4.640389283182119 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968662_0.png resize: (333, 298) 1353455767 -4.403970067289867 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968664_0.png resize: (187, 197) 1353455769 -5.006455277754304 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968652_0.png resize: (181, 130) 1353455770 -4.453674679364645 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968670_0.png resize: (111, 188) 1353455771 -2.7433908427943408 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968673_0.png resize: (204, 247) 1353455773 -4.247788835398421 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968659_0.png resize: (255, 362) 1353455774 -4.44183140264709 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968654_0.png resize: (105, 121) 1353455775 -3.645475406060829 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968668_0.png resize: (106, 87) 1353455777 -3.877769553196604 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968666_0.png resize: (257, 155) 1353455778 -4.966527307135228 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968665_0.png resize: (94, 112) 1353455779 -1.9559027042690373 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968679_0.png resize: (84, 75) 1353455781 -4.090616637417478 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968676_0.png resize: (125, 62) 1353455782 -3.02751555131222 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968650_0.png resize: (167, 85) 1353455783 -1.8486015817488788 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968669_0.png resize: (263, 260) 1353455784 -4.225328369295189 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968651_0.png resize: (116, 98) 1353455786 -3.2778290586057945 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968682_0.png resize: (249, 240) 1353455787 -3.5720435385974723 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968657_0.png resize: (139, 164) 1353455788 -2.8072272804726026 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968660_0.png resize: (128, 159) 1353455790 -3.448310443283322 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968649_0.png resize: (133, 94) 1353455791 -3.2329174669543956 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968689_0.png resize: (292, 222) 1353455792 -1.4688101742300985 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968685_0.png resize: (372, 449) 1353455794 -1.669144310698609 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968687_0.png resize: (302, 554) 1353455795 -1.2995905164755894 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968690_0.png resize: (181, 145) 1353455796 -1.1914561111829944 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968686_0.png resize: (112, 159) 1353455798 -2.179234818576948 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968692_0.png resize: (246, 788) 1353455799 -1.3604543559629902 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968688_0.png resize: (441, 179) 1353455800 -0.9676566506737655 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968698_0.png resize: (153, 152) 1353455802 -1.54222116950664 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968707_0.png resize: (180, 147) 1353455803 -1.0282220474608479 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968695_0.png resize: (343, 504) 1353455804 -0.6831065935073557 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968700_0.png resize: (187, 189) 1353455806 -0.8540666862997564 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968697_0.png resize: (201, 253) 1353455807 -1.412607212786102 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968711_0.png resize: (136, 106) 1353455808 -1.208694390189144 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968710_0.png resize: (190, 270) 1353455810 -0.8833425563643221 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968709_0.png resize: (234, 206) 1353455811 -0.5633804539449798 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968696_0.png resize: (265, 247) 1353455812 -0.3020868472957867 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968706_0.png resize: (601, 574) 1353455814 -1.9476231149574594 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968702_0.png resize: (134, 252) 1353455815 -1.2713412703298346 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968704_0.png resize: (247, 258) 1353455816 -2.4384116438530588 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968693_0.png resize: (198, 205) 1353455818 -0.6666109172059226 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968701_0.png resize: (158, 125) 1353455819 -3.3255845517563487 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968708_0.png resize: (137, 127) 1353455820 -1.5279864648312809 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968436_0.png resize: (711, 413) 1353455905 -0.7818165213349381 treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968432_0.png resize: (69, 77) 1353455906 2.7821332360709237 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968448_0.png resize: (118, 100) 1353455907 -1.8878586443792862 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968441_0.png resize: (294, 477) 1353455908 -1.2912972551363568 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968459_0.png resize: (267, 178) 1353455909 0.6808654179372932 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968442_0.png resize: (228, 277) 1353455910 -0.39953668071050513 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968457_0.png resize: (156, 108) 1353455911 -1.5880342402357603 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968469_0.png resize: (172, 151) 1353455913 -1.0193022525876354 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968481_0.png resize: (162, 235) 1353455914 -1.7674947319677157 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968487_0.png resize: (203, 198) 1353455915 -2.002536717715848 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968519_0.png resize: (94, 125) 1353455916 -1.3500033844417572 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968517_0.png resize: (104, 72) 1353455917 2.4424698567373944 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968510_0.png resize: (166, 261) 1353455918 -1.6824307307597868 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968504_0.png resize: (113, 193) 1353455919 -2.619984466049616 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968525_0.png resize: (118, 98) 1353455920 -2.5639555004223715 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968529_0.png resize: (514, 763) 1353455921 -0.1868629693229966 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968530_0.png resize: (130, 209) 1353455922 -1.4217595786549915 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968540_0.png resize: (190, 154) 1353455923 -0.924885834387182 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968543_0.png resize: (89, 203) 1353455924 -1.453725086101717 treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968551_0.png resize: (196, 239) 1353455925 -0.3589344356779598 treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968545_0.png resize: (110, 207) 1353455926 -1.2738035592618329 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968557_0.png resize: (165, 124) 1353455927 -1.6374625997951318 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968564_0.png resize: (326, 289) 1353455929 0.15894684584136173 treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0_rle_crop_3767968566_0.png resize: (814, 619) 1353455930 -1.5049035894194627 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968569_0.png resize: (176, 166) 1353455931 -0.4999641968587714 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968595_0.png resize: (92, 117) 1353455932 -0.3102839377609626 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968571_0.png resize: (140, 164) 1353455933 -1.0747746100299844 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968605_0.png resize: (117, 163) 1353455934 -1.434394186630639 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968617_0.png resize: (116, 201) 1353455935 -0.7509984273177596 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968655_0.png resize: (104, 218) 1353455936 -2.8100953068952004 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968658_0.png resize: (165, 298) 1353455937 -3.538934473062574 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968684_0.png resize: (386, 1061) 1353455938 -1.653597534666903 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968712_0.png resize: (247, 341) 1353455939 -2.404577289098215 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968705_0.png resize: (180, 186) 1353455940 -1.8814743393681035 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968635_0.png resize: (210, 124) 1353455943 -2.3004477215161487 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968444_0.png resize: (126, 469) 1353455963 -1.015840497057321 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968454_0.png resize: (350, 198) 1353455964 -1.353928822712509 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968471_0.png resize: (1061, 930) 1353455965 -1.5852268407606223 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968463_0.png resize: (135, 147) 1353455966 -4.582729469700955 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968468_0.png resize: (291, 154) 1353455967 -1.923085103283602 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968466_0.png resize: (454, 525) 1353455968 -1.8825616428651337 treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968465_0.png resize: (571, 698) 1353455969 -0.6672328067704807 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968485_0.png resize: (621, 424) 1353455970 -1.2419742147642734 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968482_0.png resize: (445, 425) 1353455971 -0.6415273008610028 treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968483_0.png resize: (320, 339) 1353455972 -0.5975891923180281 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968489_0.png resize: (935, 901) 1353455973 -0.16060835479031388 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968490_0.png resize: (562, 366) 1353455974 -2.119418097529797 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968493_0.png resize: (644, 369) 1353455975 -1.1729554621027993 treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968492_0.png resize: (460, 188) 1353455976 -1.693428374241461 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968524_0.png resize: (396, 178) 1353455977 -2.11684227723949 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968523_0.png resize: (329, 186) 1353455978 -2.5933757876655394 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968532_0.png resize: (280, 172) 1353455979 -3.5262821836022575 treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968542_0.png resize: (911, 670) 1353455980 -0.23358784666523882 treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968548_0.png resize: (506, 364) 1353455981 -0.4485950629391074 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968555_0.png resize: (371, 248) 1353455982 -0.21387265501159952 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968563_0.png resize: (334, 560) 1353455983 -1.2590836529604859 treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0_rle_crop_3767968565_0.png resize: (99, 177) 1353455984 -3.4738833528301702 treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0_rle_crop_3767968567_0.png resize: (824, 924) 1353455985 -0.0725786497669907 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968613_0.png resize: (324, 289) 1353455986 -2.842022265762863 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968630_0.png resize: (193, 459) 1353455987 -2.005079616736503 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968619_0.png resize: (305, 209) 1353455988 -4.135748887475905 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968637_0.png resize: (436, 622) 1353455989 -3.0232724826948094 treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968620_0.png resize: (129, 208) 1353455990 -3.2492622382754566 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968661_0.png resize: (108, 135) 1353455991 -4.79457941051344 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968681_0.png resize: (152, 172) 1353455992 -3.9875289745397247 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968683_0.png resize: (396, 511) 1353455993 -0.107474469923837 treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968691_0.png resize: (635, 986) 1353455994 -1.050125004570117 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968694_0.png resize: (235, 413) 1353455995 -2.010136709558347 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968713_0.png resize: (283, 318) 1353455996 -2.4096370018696973 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968703_0.png resize: (226, 394) 1353455997 -2.5201545615337513 treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968699_0.png resize: (179, 514) 1353455998 -1.629848234596216 treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968495_0.png resize: (106, 106) 1353456003 -0.5537246549170224 treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968559_0.png resize: (396, 496) 1353456004 -0.1436888248565737 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968583_0.png resize: (129, 141) 1353456005 -0.7640137697569717 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968578_0.png resize: (105, 67) 1353456006 3.418421833357465 treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968597_0.png resize: (136, 146) 1353456007 0.4332879919385891 treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968600_0.png resize: (133, 140) 1353456008 0.0622004126706758 treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968648_0.png resize: (106, 103) 1353456009 1.5359867474972042 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968677_0.png resize: (59, 93) 1353456010 0.5528306045531779 treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968672_0.png resize: (108, 112) 1353456011 -1.6269463419609242 treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968461_0.png resize: (116, 121) 1353456015 -0.8046056868917155 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 : 304 time used for this insertion : 0.027214765548706055 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 304 time used for this insertion : 0.05965614318847656 save missing photos in datou_result : time spend for datou_step_exec : 65.50726699829102 time spend to save output : 0.09340524673461914 total time spend for step 6 : 65.60067224502563 step7:brightness Thu Apr 24 20:49:11 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/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a.jpg treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af.jpg treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222.jpg treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361.jpg treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e.jpg treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407.jpg treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158.jpg treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9.jpg treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110.jpg treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0.jpg treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609.jpg treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f.jpg treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0.jpg treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6.jpg treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c.jpg treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb.jpg treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f.jpg treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968430_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968428_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968435_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968429_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968437_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968427_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968438_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968431_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968434_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968433_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968439_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968443_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968446_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968455_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968445_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968456_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968447_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968460_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968458_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968451_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968440_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968450_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968449_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968452_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968462_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968453_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968472_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968470_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968474_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968473_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968467_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968464_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968484_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968475_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968478_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968476_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968480_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968479_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968477_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968486_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968488_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968494_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968491_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968513_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968512_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968501_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968508_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968520_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968518_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968503_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968509_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968515_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968516_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968499_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968511_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968514_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968498_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968505_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968497_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968506_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968496_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968521_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968502_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968500_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968522_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968507_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968533_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968528_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968541_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968537_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968534_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968544_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968526_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968538_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968539_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968531_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968535_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968527_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968536_0.png treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968546_0.png treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968550_0.png treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968549_0.png treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968547_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968553_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968552_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968554_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968562_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968561_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968556_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968560_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968558_0.png treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0_rle_crop_3767968568_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968572_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968591_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968573_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968585_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968587_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968593_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968570_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968575_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968590_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968577_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968574_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968589_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968592_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968579_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968586_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968581_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968598_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968596_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968584_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968576_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968582_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968588_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968580_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968594_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968604_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968599_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968601_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968603_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968606_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968602_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968607_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968629_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968634_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968621_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968624_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968608_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968626_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968631_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968625_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968610_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968628_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968636_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968611_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968609_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968618_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968616_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968633_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968615_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968614_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968622_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968627_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968612_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968623_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968632_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968641_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968643_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968640_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968646_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968644_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968638_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968647_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968639_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968645_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968642_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968680_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968678_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968663_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968656_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968671_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968653_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968667_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968674_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968675_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968662_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968664_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968652_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968670_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968673_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968659_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968654_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968668_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968666_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968665_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968679_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968676_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968650_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968669_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968651_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968682_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968657_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968660_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968649_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968689_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968685_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968687_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968690_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968686_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968692_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968688_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968698_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968707_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968695_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968700_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968697_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968711_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968710_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968709_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968696_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968706_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968702_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968704_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968693_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968701_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968708_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968436_0.png treat image : temp/1745520027_2361629_1353408839_07e531c71ad0503fc64658fd4d98d94a_rle_crop_3767968432_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968448_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968441_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968459_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968442_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968457_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968469_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968481_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968487_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968519_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968517_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968510_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968504_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968525_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968529_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968530_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968540_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968543_0.png treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968551_0.png treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968545_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968557_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968564_0.png treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0_rle_crop_3767968566_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968569_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968595_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968571_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968605_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968617_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968655_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968658_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968684_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968712_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968705_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968635_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968444_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968454_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968471_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968463_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968468_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968466_0.png treat image : temp/1745520027_2361629_1353408830_ebc336e09123e8023ee47671f136d222_rle_crop_3767968465_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968485_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968482_0.png treat image : temp/1745520027_2361629_1353408827_f6554687b6b5513fc6aa0079b0898361_rle_crop_3767968483_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968489_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968490_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968493_0.png treat image : temp/1745520027_2361629_1353408782_d3053072171fba201bc402ff84068d9e_rle_crop_3767968492_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968524_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968523_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968532_0.png treat image : temp/1745520027_2361629_1353408529_f4f999e17af3aec3774e9cab7fbf2158_rle_crop_3767968542_0.png treat image : temp/1745520027_2361629_1353408451_7785b4ebb80acce50a6e35a5779a0fb9_rle_crop_3767968548_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968555_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968563_0.png treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0_rle_crop_3767968565_0.png treat image : temp/1745520027_2361629_1353408440_21d623009761c55984f75168013e32f0_rle_crop_3767968567_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968613_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968630_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968619_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968637_0.png treat image : temp/1745520027_2361629_1353408350_2c1e09d6e3216408c235adf2f772e0b0_rle_crop_3767968620_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968661_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968681_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968683_0.png treat image : temp/1745520027_2361629_1353408229_932ff232c2b3faab8c73b33b8bb7fdeb_rle_crop_3767968691_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968694_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968713_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968703_0.png treat image : temp/1745520027_2361629_1353408175_a2d64f38c8e268bbc84a087a4fca8f8f_rle_crop_3767968699_0.png treat image : temp/1745520027_2361629_1353408716_f0beb381334a76099cf2f7d227fed407_rle_crop_3767968495_0.png treat image : temp/1745520027_2361629_1353408445_dcbeaeaddc85e001d7b47480098ca110_rle_crop_3767968559_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968583_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968578_0.png treat image : temp/1745520027_2361629_1353408406_2d1cffd4123ee46b538376391d319609_rle_crop_3767968597_0.png treat image : temp/1745520027_2361629_1353408354_cf33511ebc861886eb8330b57c276a9f_rle_crop_3767968600_0.png treat image : temp/1745520027_2361629_1353408338_6778ecba723aa8a42324a9c2db727cd6_rle_crop_3767968648_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968677_0.png treat image : temp/1745520027_2361629_1353408332_84f4a85e794a06f9ec17f07fee248d0c_rle_crop_3767968672_0.png treat image : temp/1745520027_2361629_1353408833_6ff7d46ff41c28cd90dcfe9e296623af_rle_crop_3767968461_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 : 304 time used for this insertion : 0.027597427368164062 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 304 time used for this insertion : 0.06676316261291504 save missing photos in datou_result : time spend for datou_step_exec : 15.886779546737671 time spend to save output : 0.10111880302429199 total time spend for step 7 : 15.987898349761963 step8:velours_tree Thu Apr 24 20:49:27 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 : 1.7968568801879883 time spend to save output : 6.031990051269531e-05 total time spend for step 8 : 1.796917200088501 step9:send_mail_cod Thu Apr 24 20:49:29 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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_P22396717_24-04-2025_20_49_29.pdf 22397850 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 .imagette223978501745520569 22397851 imagette223978511745520570 22397853 imagette223978531745520570 22397854 imagette223978541745520570 22397855 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 .imagette223978551745520570 22397856 imagette223978561745520571 22397857 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 .imagette223978571745520571 22397858 change filename to text .imagette223978581745520572 22397859 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 .imagette223978591745520573 22397860 change filename to text .imagette223978601745520574 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=22396717 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/22397850,22397851,22397852,22397853,22397854,22397855,22397856,22397857,22397858,22397859,22397860?tags=pet_clair,pehd,environnement,mal_croppe,flou,autre,background,papier,pet_fonce,carton,metal args[1353408839] : ((1353408839, -1.2121173099949893, 492688767), (1353408839, 0.0665632204946474, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408833] : ((1353408833, -1.7548256439460082, 492688767), (1353408833, 0.10599690842207125, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408830] : ((1353408830, -1.1141628485954511, 492688767), (1353408830, 0.03729050147656377, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408827] : ((1353408827, -1.3726798806468268, 492688767), (1353408827, 0.10373711603036778, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408782] : ((1353408782, -1.6372368440175742, 492688767), (1353408782, -0.11352849158762006, 496442774), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408716] : ((1353408716, -4.361914151342719, 492609224), (1353408716, -0.21354054427339025, 496442774), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408529] : ((1353408529, -0.6456408925351814, 492688767), (1353408529, 0.08446877733988159, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408451] : ((1353408451, 0.7700766488721549, 492688767), (1353408451, 0.5302058231720158, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408445] : ((1353408445, 0.579255937863176, 492688767), (1353408445, -0.19338892371154243, 496442774), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408440] : ((1353408440, 0.02706554188186605, 492688767), (1353408440, 0.17415838837066178, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408406] : ((1353408406, -2.5526863420420542, 492609224), (1353408406, -0.03643517274301141, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408354] : ((1353408354, -1.2719344401271362, 492688767), (1353408354, -0.02006515759599495, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408350] : ((1353408350, -3.851185967312291, 492609224), (1353408350, -0.03149241941594916, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408338] : ((1353408338, 1.3342641648442872, 492688767), (1353408338, 0.4313964959251235, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408332] : ((1353408332, -6.040901504051467, 492609224), (1353408332, -0.1385549353511009, 496442774), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408229] : ((1353408229, 0.25174783967417963, 492688767), (1353408229, 0.07845056374238626, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com args[1353408175] : ((1353408175, -1.9969931222201749, 492688767), (1353408175, 0.20077364473764978, 2107752395), '0.11929673149216118') We are sending mail with results at report@fotonower.com refus_total : 0.11929673149216118 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=22396717 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22396717_24-04-2025_20_49_29.pdf results_Auto_P22396717_24-04-2025_20_49_29.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22396717_24-04-2025_20_49_29.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','22396717','results_Auto_P22396717_24-04-2025_20_49_29.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22396717_24-04-2025_20_49_29.pdf','pdf','','0.88','0.11929673149216118') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/22396717

https://www.fotonower.com/image?json=false&list_photos_id=1353408839
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408833
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408830
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408827
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408782
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408716
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408529
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408451
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408445
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408440
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408406
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408354
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408350
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408338
La photo est trop floue, merci de reprendre une photo.(avec le score = 1.3342641648442872)
https://www.fotonower.com/image?json=false&list_photos_id=1353408332
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408229
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1353408175
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 11.93%
Veuillez trouver les photos des contaminants.

exemples de contaminants: pet_clair: https://www.fotonower.com/view/22397850?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/22397855?limit=200
exemples de contaminants: papier: https://www.fotonower.com/view/22397857?limit=200
exemples de contaminants: pet_fonce: https://www.fotonower.com/view/22397858?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/22397859?limit=200
exemples de contaminants: metal: https://www.fotonower.com/view/22397860?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22396717_24-04-2025_20_49_29.pdf.

Lien vers velours :https://www.fotonower.com/velours/22397850,22397851,22397852,22397853,22397854,22397855,22397856,22397857,22397858,22397859,22397860?tags=pet_clair,pehd,environnement,mal_croppe,flou,autre,background,papier,pet_fonce,carton,metal.


L'équipe Fotonower 202 b'' Server: nginx Date: Thu, 24 Apr 2025 18:49:38 GMT Content-Length: 0 Connection: close X-Message-Id: 5YxUWCfhT2qnHDAz1406jw 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 [1353408839, 1353408833, 1353408830, 1353408827, 1353408782, 1353408716, 1353408529, 1353408451, 1353408445, 1353408440, 1353408406, 1353408354, 1353408350, 1353408338, 1353408332, 1353408229, 1353408175] 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, '2758897') ('3318', '22396717', '1353408839', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408833', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408830', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408827', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408782', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408716', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408529', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408451', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408445', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408440', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408406', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408354', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408350', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408338', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408332', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408229', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408175', None, None, None, None, None, '2758897') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 17 time used for this insertion : 0.018489360809326172 save_final save missing photos in datou_result : time spend for datou_step_exec : 9.042268514633179 time spend to save output : 0.01877307891845703 total time spend for step 9 : 9.061041593551636 step10:split_time_score Thu Apr 24 20:49:38 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'}] (('16', 17),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 24042025 22396717 Nombre de photos uploadées : 17 / 23040 (0%) 24042025 22396717 Nombre de photos taguées (types de déchets): 0 / 17 (0%) 24042025 22396717 Nombre de photos taguées (volume) : 0 / 17 (0%) elapsed_time : load_data_split_time_score 2.1457672119140625e-06 elapsed_time : order_list_meta_photo_and_scores 6.4373016357421875e-06 ????????????????? elapsed_time : fill_and_build_computed_from_old_data 0.0020356178283691406 elapsed_time : insert_dashboard_record_day_entry 0.029484272003173828 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.15991931890933772 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22375561_24-04-2025_08_54_07.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22375561 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`=22375561 AND mptpi.`type`=3594 To do Qualite : 0.04825650604752327 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22381160_24-04-2025_13_29_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22381160 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`=22381160 AND mptpi.`type`=3726 To do Qualite : 0.14264551885569046 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22380034_24-04-2025_12_29_39.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22380034 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`=22380034 AND mptpi.`type`=3594 To do Qualite : 0.14242511602441907 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22381162_24-04-2025_13_37_46.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22381162 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`=22381162 AND mptpi.`type`=3594 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22396716 order by id desc limit 1 Qualite : 0.11929673149216118 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22396717_24-04-2025_20_49_29.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22396717 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`=22396717 AND mptpi.`type`=3594 To do Qualite : 0.037089267553703925 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22390901_24-04-2025_18_01_02.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22390901 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`=22390901 AND mptpi.`type`=3726 To do Qualite : 0.1403813794518579 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22396719_24-04-2025_20_37_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22396719 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`=22396719 AND mptpi.`type`=3594 To do Qualite : 0.13299057904411762 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P22396721_24-04-2025_20_26_03.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 22396721 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`=22396721 AND mptpi.`type`=3594 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'24042025': {'nb_upload': 17, '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 [1353408839, 1353408833, 1353408830, 1353408827, 1353408782, 1353408716, 1353408529, 1353408451, 1353408445, 1353408440, 1353408406, 1353408354, 1353408350, 1353408338, 1353408332, 1353408229, 1353408175] Looping around the photos to save general results len do output : 1 /22396717Didn'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, '2758897') ('3318', '22396717', '1353408839', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408833', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408830', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408827', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408782', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408716', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408529', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408451', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408445', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408440', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408406', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408354', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408350', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408338', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408332', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408229', None, None, None, None, None, '2758897') ('3318', None, None, None, None, None, None, None, '2758897') ('3318', '22396717', '1353408175', None, None, None, None, None, '2758897') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 18 time used for this insertion : 0.016623973846435547 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.494720220565796 time spend to save output : 0.016881465911865234 total time spend for step 10 : 1.5116016864776611 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 17 set_done_treatment 255.57user 175.29system 9:15.25elapsed 77%CPU (0avgtext+0avgdata 6218056maxresident)k 3862896inputs+138784outputs (142648major+24406881minor)pagefaults 0swaps