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 : 1501023 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 : ['2710822'] with mtr_portfolio_ids : ['21925661'] and first list_photo_ids : [] new path : /proc/1501023/ 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 , BFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 10 ; length of list_pids : 10 ; length of list_args : 10 time to download the photos : 1.9588332176208496 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 Mon Mar 31 22:50:31 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 : 10593 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-31 22:50:34.240671: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-31 22:50:34.267319: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-31 22:50:34.269554: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f2dc8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-31 22:50:34.269607: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-31 22:50:34.273303: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-31 22:50:34.429376: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3fc9f470 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-31 22:50:34.429440: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-31 22:50:34.430470: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-31 22:50:34.430887: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 22:50:34.434225: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 22:50:34.437764: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 22:50:34.438378: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 22:50:34.442125: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 22:50:34.443681: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 22:50:34.449354: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 22:50:34.451197: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 22:50:34.451349: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 22:50:34.452208: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-31 22:50:34.452231: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-31 22:50:34.452240: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-31 22:50:34.454579: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9671 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-03-31 22:50:34.967918: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-31 22:50:34.968050: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 22:50:34.968076: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 22:50:34.968099: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 22:50:34.968120: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 22:50:34.968141: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 22:50:34.968162: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 22:50:34.968184: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 22:50:34.969847: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 22:50:34.971448: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-31 22:50:34.971552: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 22:50:34.971574: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 22:50:34.971594: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 22:50:34.971613: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 22:50:34.971631: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 22:50:34.971650: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 22:50:34.971670: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 22:50:34.973251: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 22:50:34.973302: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-31 22:50:34.973314: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-31 22:50:34.973323: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-31 22:50:34.975134: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9671 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-03-31 22:50:47.971967: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 22:50:48.184622: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 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 : 48 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 70 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 67 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 59 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 : 18 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 : 17 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 100 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 93 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 83 Detection mask done ! Trying to reset tf kernel 1501815 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 4111 tf kernel not reseted sub process len(results) : 10 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 10 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 : 9400 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 : 0.05878043174743652 nb_pixel_total : 28035 time to create 1 rle with old method : 0.0368504524230957 length of segment : 172 time for calcul the mask position with numpy : 0.062410831451416016 nb_pixel_total : 21197 time to create 1 rle with old method : 0.032401323318481445 length of segment : 226 time for calcul the mask position with numpy : 0.14553213119506836 nb_pixel_total : 76173 time to create 1 rle with old method : 0.099609375 length of segment : 507 time for calcul the mask position with numpy : 0.03421354293823242 nb_pixel_total : 12785 time to create 1 rle with old method : 0.02069997787475586 length of segment : 105 time for calcul the mask position with numpy : 0.021191835403442383 nb_pixel_total : 6427 time to create 1 rle with old method : 0.01036977767944336 length of segment : 113 time for calcul the mask position with numpy : 0.05222654342651367 nb_pixel_total : 30539 time to create 1 rle with old method : 0.05086636543273926 length of segment : 156 time for calcul the mask position with numpy : 0.1584465503692627 nb_pixel_total : 90627 time to create 1 rle with old method : 0.1263110637664795 length of segment : 304 time for calcul the mask position with numpy : 0.06307554244995117 nb_pixel_total : 24219 time to create 1 rle with old method : 0.03154492378234863 length of segment : 226 time for calcul the mask position with numpy : 0.14089727401733398 nb_pixel_total : 61316 time to create 1 rle with old method : 0.0876154899597168 length of segment : 339 time for calcul the mask position with numpy : 0.03409624099731445 nb_pixel_total : 10509 time to create 1 rle with old method : 0.017886638641357422 length of segment : 204 time for calcul the mask position with numpy : 0.08353066444396973 nb_pixel_total : 31494 time to create 1 rle with old method : 0.03997206687927246 length of segment : 280 time for calcul the mask position with numpy : 0.14644122123718262 nb_pixel_total : 80454 time to create 1 rle with old method : 0.10269737243652344 length of segment : 479 time for calcul the mask position with numpy : 0.014571428298950195 nb_pixel_total : 17048 time to create 1 rle with old method : 0.023400068283081055 length of segment : 281 time for calcul the mask position with numpy : 0.04940509796142578 nb_pixel_total : 51510 time to create 1 rle with old method : 0.06884288787841797 length of segment : 456 time for calcul the mask position with numpy : 0.04851865768432617 nb_pixel_total : 20977 time to create 1 rle with old method : 0.030488014221191406 length of segment : 165 time for calcul the mask position with numpy : 0.045554161071777344 nb_pixel_total : 18445 time to create 1 rle with old method : 0.026062488555908203 length of segment : 140 time for calcul the mask position with numpy : 0.07709193229675293 nb_pixel_total : 30008 time to create 1 rle with old method : 0.03971672058105469 length of segment : 408 time for calcul the mask position with numpy : 0.018401622772216797 nb_pixel_total : 11038 time to create 1 rle with old method : 0.01676011085510254 length of segment : 120 time for calcul the mask position with numpy : 0.0441436767578125 nb_pixel_total : 56725 time to create 1 rle with old method : 0.06953573226928711 length of segment : 354 time for calcul the mask position with numpy : 0.05112934112548828 nb_pixel_total : 55204 time to create 1 rle with old method : 0.08765625953674316 length of segment : 182 time for calcul the mask position with numpy : 0.05408358573913574 nb_pixel_total : 15974 time to create 1 rle with old method : 0.024333477020263672 length of segment : 224 time for calcul the mask position with numpy : 0.06708192825317383 nb_pixel_total : 33424 time to create 1 rle with old method : 0.046080589294433594 length of segment : 284 time for calcul the mask position with numpy : 0.005784034729003906 nb_pixel_total : 4299 time to create 1 rle with old method : 0.006696462631225586 length of segment : 76 time for calcul the mask position with numpy : 0.25867772102355957 nb_pixel_total : 203233 time to create 1 rle with new method : 0.025202274322509766 length of segment : 585 time for calcul the mask position with numpy : 0.007370710372924805 nb_pixel_total : 13131 time to create 1 rle with old method : 0.015081167221069336 length of segment : 119 time for calcul the mask position with numpy : 0.11660480499267578 nb_pixel_total : 132677 time to create 1 rle with old method : 0.1579296588897705 length of segment : 544 time for calcul the mask position with numpy : 0.008774280548095703 nb_pixel_total : 6109 time to create 1 rle with old method : 0.007883787155151367 length of segment : 335 time for calcul the mask position with numpy : 0.0005519390106201172 nb_pixel_total : 13215 time to create 1 rle with old method : 0.01575756072998047 length of segment : 166 time for calcul the mask position with numpy : 0.0005927085876464844 nb_pixel_total : 15147 time to create 1 rle with old method : 0.018364667892456055 length of segment : 189 time for calcul the mask position with numpy : 0.2424468994140625 nb_pixel_total : 242009 time to create 1 rle with new method : 0.021654844284057617 length of segment : 645 time for calcul the mask position with numpy : 0.06918168067932129 nb_pixel_total : 14225 time to create 1 rle with old method : 0.020541906356811523 length of segment : 215 time for calcul the mask position with numpy : 0.1282212734222412 nb_pixel_total : 38879 time to create 1 rle with old method : 0.04772043228149414 length of segment : 218 time for calcul the mask position with numpy : 0.043430328369140625 nb_pixel_total : 10781 time to create 1 rle with old method : 0.017301082611083984 length of segment : 129 time for calcul the mask position with numpy : 0.2238941192626953 nb_pixel_total : 92352 time to create 1 rle with old method : 0.12526583671569824 length of segment : 492 time for calcul the mask position with numpy : 0.055196285247802734 nb_pixel_total : 20596 time to create 1 rle with old method : 0.03644108772277832 length of segment : 120 time for calcul the mask position with numpy : 0.05023813247680664 nb_pixel_total : 14743 time to create 1 rle with old method : 0.0209352970123291 length of segment : 136 time for calcul the mask position with numpy : 0.0458528995513916 nb_pixel_total : 18860 time to create 1 rle with old method : 0.02450084686279297 length of segment : 216 time for calcul the mask position with numpy : 0.10826730728149414 nb_pixel_total : 37362 time to create 1 rle with old method : 0.046617746353149414 length of segment : 233 time for calcul the mask position with numpy : 0.06243896484375 nb_pixel_total : 12330 time to create 1 rle with old method : 0.021112680435180664 length of segment : 165 time for calcul the mask position with numpy : 0.026341915130615234 nb_pixel_total : 10772 time to create 1 rle with old method : 0.013319015502929688 length of segment : 105 time for calcul the mask position with numpy : 0.06031084060668945 nb_pixel_total : 18140 time to create 1 rle with old method : 0.028425216674804688 length of segment : 124 time for calcul the mask position with numpy : 0.03737306594848633 nb_pixel_total : 14674 time to create 1 rle with old method : 0.022231340408325195 length of segment : 92 time for calcul the mask position with numpy : 0.09291648864746094 nb_pixel_total : 31503 time to create 1 rle with old method : 0.050463199615478516 length of segment : 218 time for calcul the mask position with numpy : 0.4454653263092041 nb_pixel_total : 99618 time to create 1 rle with old method : 0.11852574348449707 length of segment : 606 time for calcul the mask position with numpy : 0.016426563262939453 nb_pixel_total : 20041 time to create 1 rle with old method : 0.02854299545288086 length of segment : 234 time for calcul the mask position with numpy : 0.0538022518157959 nb_pixel_total : 14914 time to create 1 rle with old method : 0.03008723258972168 length of segment : 156 time for calcul the mask position with numpy : 0.08647871017456055 nb_pixel_total : 16117 time to create 1 rle with old method : 0.024291515350341797 length of segment : 163 time for calcul the mask position with numpy : 0.023401260375976562 nb_pixel_total : 18436 time to create 1 rle with old method : 0.026400089263916016 length of segment : 159 time for calcul the mask position with numpy : 0.005591392517089844 nb_pixel_total : 6846 time to create 1 rle with old method : 0.009798526763916016 length of segment : 85 time for calcul the mask position with numpy : 0.06139230728149414 nb_pixel_total : 20156 time to create 1 rle with old method : 0.02966618537902832 length of segment : 128 time for calcul the mask position with numpy : 0.04381990432739258 nb_pixel_total : 9919 time to create 1 rle with old method : 0.014478921890258789 length of segment : 131 time for calcul the mask position with numpy : 0.07915711402893066 nb_pixel_total : 23955 time to create 1 rle with old method : 0.03148937225341797 length of segment : 256 time for calcul the mask position with numpy : 0.0342869758605957 nb_pixel_total : 12371 time to create 1 rle with old method : 0.019608259201049805 length of segment : 94 time for calcul the mask position with numpy : 0.004004478454589844 nb_pixel_total : 4791 time to create 1 rle with old method : 0.006165981292724609 length of segment : 66 time for calcul the mask position with numpy : 0.11367058753967285 nb_pixel_total : 58620 time to create 1 rle with old method : 0.07168793678283691 length of segment : 358 time for calcul the mask position with numpy : 0.0014297962188720703 nb_pixel_total : 21338 time to create 1 rle with old method : 0.024285316467285156 length of segment : 192 time for calcul the mask position with numpy : 0.04776954650878906 nb_pixel_total : 15386 time to create 1 rle with old method : 0.02390599250793457 length of segment : 161 time for calcul the mask position with numpy : 0.13162899017333984 nb_pixel_total : 35486 time to create 1 rle with old method : 0.05115199089050293 length of segment : 315 time for calcul the mask position with numpy : 0.06698250770568848 nb_pixel_total : 33331 time to create 1 rle with old method : 0.0392303466796875 length of segment : 271 time for calcul the mask position with numpy : 0.043096303939819336 nb_pixel_total : 15127 time to create 1 rle with old method : 0.021559476852416992 length of segment : 123 time for calcul the mask position with numpy : 0.008110761642456055 nb_pixel_total : 11102 time to create 1 rle with old method : 0.01569533348083496 length of segment : 195 time for calcul the mask position with numpy : 0.09503746032714844 nb_pixel_total : 32854 time to create 1 rle with old method : 0.05092930793762207 length of segment : 349 time for calcul the mask position with numpy : 0.041753530502319336 nb_pixel_total : 8275 time to create 1 rle with old method : 0.013304471969604492 length of segment : 168 time for calcul the mask position with numpy : 0.03820443153381348 nb_pixel_total : 21547 time to create 1 rle with old method : 0.032862186431884766 length of segment : 219 time for calcul the mask position with numpy : 0.029185771942138672 nb_pixel_total : 12622 time to create 1 rle with old method : 0.0310819149017334 length of segment : 132 time for calcul the mask position with numpy : 0.09688186645507812 nb_pixel_total : 31032 time to create 1 rle with old method : 0.04408407211303711 length of segment : 301 time for calcul the mask position with numpy : 0.09133577346801758 nb_pixel_total : 34038 time to create 1 rle with old method : 0.06798982620239258 length of segment : 231 time for calcul the mask position with numpy : 0.02229022979736328 nb_pixel_total : 12692 time to create 1 rle with old method : 0.015104293823242188 length of segment : 131 time for calcul the mask position with numpy : 0.04862642288208008 nb_pixel_total : 13301 time to create 1 rle with old method : 0.01885533332824707 length of segment : 133 time for calcul the mask position with numpy : 0.10478401184082031 nb_pixel_total : 47067 time to create 1 rle with old method : 0.05773305892944336 length of segment : 278 time for calcul the mask position with numpy : 0.08144640922546387 nb_pixel_total : 23660 time to create 1 rle with old method : 0.033103227615356445 length of segment : 208 time for calcul the mask position with numpy : 0.17526793479919434 nb_pixel_total : 58657 time to create 1 rle with old method : 0.07717680931091309 length of segment : 403 time for calcul the mask position with numpy : 0.19595694541931152 nb_pixel_total : 49860 time to create 1 rle with old method : 0.06688475608825684 length of segment : 391 time for calcul the mask position with numpy : 0.03818202018737793 nb_pixel_total : 11363 time to create 1 rle with old method : 0.013183116912841797 length of segment : 139 time for calcul the mask position with numpy : 0.06457185745239258 nb_pixel_total : 27031 time to create 1 rle with old method : 0.0433499813079834 length of segment : 128 time for calcul the mask position with numpy : 0.14511704444885254 nb_pixel_total : 35997 time to create 1 rle with old method : 0.04890131950378418 length of segment : 314 time for calcul the mask position with numpy : 0.03926897048950195 nb_pixel_total : 10288 time to create 1 rle with old method : 0.017164230346679688 length of segment : 104 time for calcul the mask position with numpy : 0.25338125228881836 nb_pixel_total : 34274 time to create 1 rle with old method : 0.04780006408691406 length of segment : 294 time for calcul the mask position with numpy : 0.09052324295043945 nb_pixel_total : 25615 time to create 1 rle with old method : 0.047623395919799805 length of segment : 274 time for calcul the mask position with numpy : 0.03334808349609375 nb_pixel_total : 11523 time to create 1 rle with old method : 0.02160501480102539 length of segment : 118 time for calcul the mask position with numpy : 0.05760622024536133 nb_pixel_total : 20082 time to create 1 rle with old method : 0.02358841896057129 length of segment : 125 time for calcul the mask position with numpy : 0.05272960662841797 nb_pixel_total : 17485 time to create 1 rle with old method : 0.020366430282592773 length of segment : 198 time for calcul the mask position with numpy : 0.1344139575958252 nb_pixel_total : 43222 time to create 1 rle with old method : 0.056127309799194336 length of segment : 421 time for calcul the mask position with numpy : 0.10216283798217773 nb_pixel_total : 30861 time to create 1 rle with old method : 0.04361557960510254 length of segment : 235 time for calcul the mask position with numpy : 0.05199122428894043 nb_pixel_total : 25094 time to create 1 rle with old method : 0.03446483612060547 length of segment : 163 time for calcul the mask position with numpy : 0.10632944107055664 nb_pixel_total : 34092 time to create 1 rle with old method : 0.051099538803100586 length of segment : 325 time for calcul the mask position with numpy : 0.06763410568237305 nb_pixel_total : 18519 time to create 1 rle with old method : 0.02956080436706543 length of segment : 214 time for calcul the mask position with numpy : 0.05513310432434082 nb_pixel_total : 39770 time to create 1 rle with old method : 0.05134129524230957 length of segment : 362 time for calcul the mask position with numpy : 0.16855835914611816 nb_pixel_total : 44537 time to create 1 rle with old method : 0.05738091468811035 length of segment : 285 time for calcul the mask position with numpy : 0.3173978328704834 nb_pixel_total : 131184 time to create 1 rle with old method : 0.16514253616333008 length of segment : 536 time for calcul the mask position with numpy : 0.10567331314086914 nb_pixel_total : 51234 time to create 1 rle with old method : 0.06952476501464844 length of segment : 451 time for calcul the mask position with numpy : 0.05102396011352539 nb_pixel_total : 18668 time to create 1 rle with old method : 0.03705143928527832 length of segment : 198 time for calcul the mask position with numpy : 0.08116006851196289 nb_pixel_total : 30842 time to create 1 rle with old method : 0.05513119697570801 length of segment : 237 time for calcul the mask position with numpy : 0.0671229362487793 nb_pixel_total : 14119 time to create 1 rle with old method : 0.021321535110473633 length of segment : 271 time for calcul the mask position with numpy : 0.024036169052124023 nb_pixel_total : 11566 time to create 1 rle with old method : 0.013690948486328125 length of segment : 112 time for calcul the mask position with numpy : 0.005303144454956055 nb_pixel_total : 10269 time to create 1 rle with old method : 0.016208410263061523 length of segment : 102 time for calcul the mask position with numpy : 0.08522248268127441 nb_pixel_total : 43278 time to create 1 rle with old method : 0.055548667907714844 length of segment : 216 time for calcul the mask position with numpy : 0.04572319984436035 nb_pixel_total : 37463 time to create 1 rle with old method : 0.057730913162231445 length of segment : 281 time for calcul the mask position with numpy : 0.036477088928222656 nb_pixel_total : 11550 time to create 1 rle with old method : 0.020681381225585938 length of segment : 128 time for calcul the mask position with numpy : 0.00046372413635253906 nb_pixel_total : 9420 time to create 1 rle with old method : 0.011770486831665039 length of segment : 102 time for calcul the mask position with numpy : 0.06934309005737305 nb_pixel_total : 25571 time to create 1 rle with old method : 0.0342862606048584 length of segment : 131 time for calcul the mask position with numpy : 0.08332967758178711 nb_pixel_total : 31224 time to create 1 rle with old method : 0.04684901237487793 length of segment : 212 time for calcul the mask position with numpy : 0.006910085678100586 nb_pixel_total : 7782 time to create 1 rle with old method : 0.015359640121459961 length of segment : 88 time for calcul the mask position with numpy : 0.0013356208801269531 nb_pixel_total : 25220 time to create 1 rle with old method : 0.029793500900268555 length of segment : 187 time for calcul the mask position with numpy : 0.03851675987243652 nb_pixel_total : 8217 time to create 1 rle with old method : 0.014041662216186523 length of segment : 126 time for calcul the mask position with numpy : 0.006209373474121094 nb_pixel_total : 44178 time to create 1 rle with old method : 0.06404423713684082 length of segment : 320 time for calcul the mask position with numpy : 0.0033066272735595703 nb_pixel_total : 14333 time to create 1 rle with old method : 0.01695704460144043 length of segment : 171 time for calcul the mask position with numpy : 0.005280017852783203 nb_pixel_total : 38913 time to create 1 rle with old method : 0.04693889617919922 length of segment : 197 time for calcul the mask position with numpy : 0.0020706653594970703 nb_pixel_total : 14201 time to create 1 rle with old method : 0.017416954040527344 length of segment : 205 time for calcul the mask position with numpy : 0.009602069854736328 nb_pixel_total : 27957 time to create 1 rle with old method : 0.03538107872009277 length of segment : 189 time for calcul the mask position with numpy : 0.011167287826538086 nb_pixel_total : 21784 time to create 1 rle with old method : 0.033097028732299805 length of segment : 224 time for calcul the mask position with numpy : 0.0409088134765625 nb_pixel_total : 15967 time to create 1 rle with old method : 0.020934343338012695 length of segment : 241 time for calcul the mask position with numpy : 0.001920461654663086 nb_pixel_total : 12444 time to create 1 rle with old method : 0.014936447143554688 length of segment : 146 time for calcul the mask position with numpy : 0.0057294368743896484 nb_pixel_total : 30569 time to create 1 rle with old method : 0.03769683837890625 length of segment : 222 time for calcul the mask position with numpy : 0.0444638729095459 nb_pixel_total : 44795 time to create 1 rle with old method : 0.06114649772644043 length of segment : 258 time for calcul the mask position with numpy : 0.004435062408447266 nb_pixel_total : 17030 time to create 1 rle with old method : 0.019897937774658203 length of segment : 239 time for calcul the mask position with numpy : 0.1703357696533203 nb_pixel_total : 95398 time to create 1 rle with old method : 0.11181902885437012 length of segment : 500 time for calcul the mask position with numpy : 0.0010874271392822266 nb_pixel_total : 10519 time to create 1 rle with old method : 0.0128173828125 length of segment : 133 time for calcul the mask position with numpy : 0.07240796089172363 nb_pixel_total : 25935 time to create 1 rle with old method : 0.035711050033569336 length of segment : 259 time for calcul the mask position with numpy : 0.008132696151733398 nb_pixel_total : 27926 time to create 1 rle with old method : 0.037694692611694336 length of segment : 211 time for calcul the mask position with numpy : 0.0018801689147949219 nb_pixel_total : 18410 time to create 1 rle with old method : 0.023604631423950195 length of segment : 151 time for calcul the mask position with numpy : 0.0029206275939941406 nb_pixel_total : 30007 time to create 1 rle with old method : 0.03664827346801758 length of segment : 267 time for calcul the mask position with numpy : 0.0011637210845947266 nb_pixel_total : 13744 time to create 1 rle with old method : 0.024717092514038086 length of segment : 139 time for calcul the mask position with numpy : 0.0008652210235595703 nb_pixel_total : 3288 time to create 1 rle with old method : 0.0038933753967285156 length of segment : 186 time for calcul the mask position with numpy : 0.03328657150268555 nb_pixel_total : 18716 time to create 1 rle with old method : 0.027265310287475586 length of segment : 179 time for calcul the mask position with numpy : 0.03850412368774414 nb_pixel_total : 14075 time to create 1 rle with old method : 0.021164894104003906 length of segment : 191 time for calcul the mask position with numpy : 0.09637594223022461 nb_pixel_total : 115886 time to create 1 rle with old method : 0.1606147289276123 length of segment : 305 time for calcul the mask position with numpy : 0.006304740905761719 nb_pixel_total : 55063 time to create 1 rle with old method : 0.07088851928710938 length of segment : 404 time for calcul the mask position with numpy : 0.006460905075073242 nb_pixel_total : 29068 time to create 1 rle with old method : 0.035591840744018555 length of segment : 178 time for calcul the mask position with numpy : 0.0005273818969726562 nb_pixel_total : 5672 time to create 1 rle with old method : 0.006680488586425781 length of segment : 107 time for calcul the mask position with numpy : 0.06261396408081055 nb_pixel_total : 83697 time to create 1 rle with old method : 0.09896683692932129 length of segment : 340 time for calcul the mask position with numpy : 0.023122549057006836 nb_pixel_total : 15692 time to create 1 rle with old method : 0.022313356399536133 length of segment : 156 time for calcul the mask position with numpy : 0.0028390884399414062 nb_pixel_total : 21068 time to create 1 rle with old method : 0.024393558502197266 length of segment : 234 time for calcul the mask position with numpy : 0.0034852027893066406 nb_pixel_total : 8396 time to create 1 rle with old method : 0.013617753982543945 length of segment : 126 time for calcul the mask position with numpy : 0.029181957244873047 nb_pixel_total : 22069 time to create 1 rle with old method : 0.05229544639587402 length of segment : 191 time for calcul the mask position with numpy : 0.008005142211914062 nb_pixel_total : 15788 time to create 1 rle with old method : 0.021780729293823242 length of segment : 148 time for calcul the mask position with numpy : 0.004401445388793945 nb_pixel_total : 7688 time to create 1 rle with old method : 0.010596513748168945 length of segment : 79 time for calcul the mask position with numpy : 0.003988981246948242 nb_pixel_total : 17257 time to create 1 rle with old method : 0.023623943328857422 length of segment : 175 time for calcul the mask position with numpy : 0.01961684226989746 nb_pixel_total : 13017 time to create 1 rle with old method : 0.019939899444580078 length of segment : 183 time for calcul the mask position with numpy : 0.012263059616088867 nb_pixel_total : 39105 time to create 1 rle with old method : 0.04468846321105957 length of segment : 201 time for calcul the mask position with numpy : 0.003330230712890625 nb_pixel_total : 32526 time to create 1 rle with old method : 0.037177324295043945 length of segment : 260 time for calcul the mask position with numpy : 0.08537721633911133 nb_pixel_total : 167107 time to create 1 rle with new method : 0.018917560577392578 length of segment : 579 time for calcul the mask position with numpy : 0.04364967346191406 nb_pixel_total : 58148 time to create 1 rle with old method : 0.07041430473327637 length of segment : 413 time for calcul the mask position with numpy : 0.0006043910980224609 nb_pixel_total : 8422 time to create 1 rle with old method : 0.010150909423828125 length of segment : 107 time for calcul the mask position with numpy : 0.003455638885498047 nb_pixel_total : 83706 time to create 1 rle with old method : 0.12189269065856934 length of segment : 355 time for calcul the mask position with numpy : 0.06690168380737305 nb_pixel_total : 52010 time to create 1 rle with old method : 0.08394622802734375 length of segment : 318 time for calcul the mask position with numpy : 0.0020751953125 nb_pixel_total : 11462 time to create 1 rle with old method : 0.019297361373901367 length of segment : 103 time for calcul the mask position with numpy : 0.0196535587310791 nb_pixel_total : 28401 time to create 1 rle with old method : 0.04667162895202637 length of segment : 176 time for calcul the mask position with numpy : 0.02511763572692871 nb_pixel_total : 13652 time to create 1 rle with old method : 0.023159265518188477 length of segment : 155 time for calcul the mask position with numpy : 0.0048427581787109375 nb_pixel_total : 26997 time to create 1 rle with old method : 0.0444483757019043 length of segment : 177 time for calcul the mask position with numpy : 0.1077277660369873 nb_pixel_total : 51532 time to create 1 rle with old method : 0.06269979476928711 length of segment : 298 time for calcul the mask position with numpy : 0.0027914047241210938 nb_pixel_total : 15089 time to create 1 rle with old method : 0.01751089096069336 length of segment : 131 time for calcul the mask position with numpy : 0.0011889934539794922 nb_pixel_total : 3641 time to create 1 rle with old method : 0.00456690788269043 length of segment : 55 time for calcul the mask position with numpy : 0.0467376708984375 nb_pixel_total : 34369 time to create 1 rle with old method : 0.04287004470825195 length of segment : 206 time for calcul the mask position with numpy : 0.005904197692871094 nb_pixel_total : 40516 time to create 1 rle with old method : 0.049881935119628906 length of segment : 341 time for calcul the mask position with numpy : 0.002521038055419922 nb_pixel_total : 35832 time to create 1 rle with old method : 0.0419306755065918 length of segment : 171 time for calcul the mask position with numpy : 0.02008986473083496 nb_pixel_total : 34684 time to create 1 rle with old method : 0.042113542556762695 length of segment : 266 time for calcul the mask position with numpy : 0.028082609176635742 nb_pixel_total : 14850 time to create 1 rle with old method : 0.021514177322387695 length of segment : 217 time for calcul the mask position with numpy : 0.008492469787597656 nb_pixel_total : 4321 time to create 1 rle with old method : 0.005877017974853516 length of segment : 65 time for calcul the mask position with numpy : 0.004510641098022461 nb_pixel_total : 19889 time to create 1 rle with old method : 0.02633833885192871 length of segment : 201 time for calcul the mask position with numpy : 0.004882335662841797 nb_pixel_total : 9602 time to create 1 rle with old method : 0.012058496475219727 length of segment : 114 time for calcul the mask position with numpy : 0.0029866695404052734 nb_pixel_total : 10979 time to create 1 rle with old method : 0.01299905776977539 length of segment : 100 time for calcul the mask position with numpy : 0.0008475780487060547 nb_pixel_total : 8770 time to create 1 rle with old method : 0.01052713394165039 length of segment : 81 time for calcul the mask position with numpy : 0.029397249221801758 nb_pixel_total : 51164 time to create 1 rle with old method : 0.05748701095581055 length of segment : 224 time for calcul the mask position with numpy : 0.022043228149414062 nb_pixel_total : 13376 time to create 1 rle with old method : 0.014657020568847656 length of segment : 240 time for calcul the mask position with numpy : 0.001983165740966797 nb_pixel_total : 16559 time to create 1 rle with old method : 0.0178525447845459 length of segment : 184 time for calcul the mask position with numpy : 0.07752561569213867 nb_pixel_total : 31254 time to create 1 rle with old method : 0.0392611026763916 length of segment : 198 time for calcul the mask position with numpy : 0.004587650299072266 nb_pixel_total : 28540 time to create 1 rle with old method : 0.035158634185791016 length of segment : 206 time for calcul the mask position with numpy : 0.0017359256744384766 nb_pixel_total : 8515 time to create 1 rle with old method : 0.010146379470825195 length of segment : 121 time for calcul the mask position with numpy : 0.05646395683288574 nb_pixel_total : 25924 time to create 1 rle with old method : 0.035629987716674805 length of segment : 348 time for calcul the mask position with numpy : 0.035031795501708984 nb_pixel_total : 12781 time to create 1 rle with old method : 0.0242459774017334 length of segment : 168 time for calcul the mask position with numpy : 0.02572321891784668 nb_pixel_total : 22016 time to create 1 rle with old method : 0.02940678596496582 length of segment : 182 time for calcul the mask position with numpy : 0.021660804748535156 nb_pixel_total : 29003 time to create 1 rle with old method : 0.03917193412780762 length of segment : 271 time for calcul the mask position with numpy : 0.05011487007141113 nb_pixel_total : 131495 time to create 1 rle with old method : 0.15118861198425293 length of segment : 510 time for calcul the mask position with numpy : 0.016967296600341797 nb_pixel_total : 60470 time to create 1 rle with old method : 0.09270811080932617 length of segment : 193 time for calcul the mask position with numpy : 0.001653432846069336 nb_pixel_total : 11373 time to create 1 rle with old method : 0.013530254364013672 length of segment : 107 time for calcul the mask position with numpy : 0.004825592041015625 nb_pixel_total : 13248 time to create 1 rle with old method : 0.01754450798034668 length of segment : 319 time for calcul the mask position with numpy : 0.0008783340454101562 nb_pixel_total : 19675 time to create 1 rle with old method : 0.03131723403930664 length of segment : 155 time for calcul the mask position with numpy : 0.002655506134033203 nb_pixel_total : 9288 time to create 1 rle with old method : 0.0155487060546875 length of segment : 249 time for calcul the mask position with numpy : 0.0005955696105957031 nb_pixel_total : 9056 time to create 1 rle with old method : 0.010650873184204102 length of segment : 165 time for calcul the mask position with numpy : 0.04066610336303711 nb_pixel_total : 57243 time to create 1 rle with old method : 0.06944775581359863 length of segment : 350 time for calcul the mask position with numpy : 0.0015230178833007812 nb_pixel_total : 18341 time to create 1 rle with old method : 0.021352767944335938 length of segment : 134 time for calcul the mask position with numpy : 0.00127410888671875 nb_pixel_total : 6226 time to create 1 rle with old method : 0.007421255111694336 length of segment : 68 time for calcul the mask position with numpy : 0.017101764678955078 nb_pixel_total : 61267 time to create 1 rle with old method : 0.08759498596191406 length of segment : 473 time for calcul the mask position with numpy : 0.0018429756164550781 nb_pixel_total : 12839 time to create 1 rle with old method : 0.015036821365356445 length of segment : 107 time for calcul the mask position with numpy : 0.002178192138671875 nb_pixel_total : 11298 time to create 1 rle with old method : 0.013130903244018555 length of segment : 107 time for calcul the mask position with numpy : 0.031135082244873047 nb_pixel_total : 69996 time to create 1 rle with old method : 0.08432555198669434 length of segment : 340 time for calcul the mask position with numpy : 0.01183629035949707 nb_pixel_total : 23480 time to create 1 rle with old method : 0.0329747200012207 length of segment : 251 time for calcul the mask position with numpy : 0.0054318904876708984 nb_pixel_total : 21545 time to create 1 rle with old method : 0.027143478393554688 length of segment : 165 time for calcul the mask position with numpy : 0.004456043243408203 nb_pixel_total : 12745 time to create 1 rle with old method : 0.02040839195251465 length of segment : 138 time for calcul the mask position with numpy : 0.004379987716674805 nb_pixel_total : 29429 time to create 1 rle with old method : 0.03857231140136719 length of segment : 173 time for calcul the mask position with numpy : 0.0012326240539550781 nb_pixel_total : 43843 time to create 1 rle with old method : 0.05046367645263672 length of segment : 154 time for calcul the mask position with numpy : 0.0019488334655761719 nb_pixel_total : 52134 time to create 1 rle with old method : 0.06969261169433594 length of segment : 289 time for calcul the mask position with numpy : 0.0003235340118408203 nb_pixel_total : 7807 time to create 1 rle with old method : 0.009282588958740234 length of segment : 62 time for calcul the mask position with numpy : 0.0008435249328613281 nb_pixel_total : 17125 time to create 1 rle with old method : 0.019705533981323242 length of segment : 315 time for calcul the mask position with numpy : 0.004171609878540039 nb_pixel_total : 21091 time to create 1 rle with old method : 0.026569604873657227 length of segment : 167 time for calcul the mask position with numpy : 0.000392913818359375 nb_pixel_total : 13477 time to create 1 rle with old method : 0.016047239303588867 length of segment : 137 time for calcul the mask position with numpy : 0.0005743503570556641 nb_pixel_total : 19174 time to create 1 rle with old method : 0.022591352462768555 length of segment : 157 time for calcul the mask position with numpy : 0.004566192626953125 nb_pixel_total : 15670 time to create 1 rle with old method : 0.01853156089782715 length of segment : 138 time for calcul the mask position with numpy : 0.009285926818847656 nb_pixel_total : 40483 time to create 1 rle with old method : 0.04944920539855957 length of segment : 428 time for calcul the mask position with numpy : 0.002511262893676758 nb_pixel_total : 16853 time to create 1 rle with old method : 0.019632577896118164 length of segment : 137 time for calcul the mask position with numpy : 0.0008313655853271484 nb_pixel_total : 11613 time to create 1 rle with old method : 0.013834953308105469 length of segment : 102 time for calcul the mask position with numpy : 0.0033926963806152344 nb_pixel_total : 24649 time to create 1 rle with old method : 0.02777576446533203 length of segment : 260 time for calcul the mask position with numpy : 0.009755849838256836 nb_pixel_total : 147345 time to create 1 rle with old method : 0.16864752769470215 length of segment : 493 time for calcul the mask position with numpy : 0.008575201034545898 nb_pixel_total : 48173 time to create 1 rle with old method : 0.07001829147338867 length of segment : 362 time for calcul the mask position with numpy : 0.0022842884063720703 nb_pixel_total : 18568 time to create 1 rle with old method : 0.021587610244750977 length of segment : 154 time for calcul the mask position with numpy : 0.0012784004211425781 nb_pixel_total : 12131 time to create 1 rle with old method : 0.014293193817138672 length of segment : 100 time for calcul the mask position with numpy : 0.002832651138305664 nb_pixel_total : 13171 time to create 1 rle with old method : 0.017628908157348633 length of segment : 124 time for calcul the mask position with numpy : 0.004927396774291992 nb_pixel_total : 5931 time to create 1 rle with old method : 0.008578300476074219 length of segment : 99 time for calcul the mask position with numpy : 0.03265714645385742 nb_pixel_total : 13567 time to create 1 rle with old method : 0.021724939346313477 length of segment : 209 time for calcul the mask position with numpy : 0.01732921600341797 nb_pixel_total : 37503 time to create 1 rle with old method : 0.04553699493408203 length of segment : 488 time for calcul the mask position with numpy : 0.010313987731933594 nb_pixel_total : 19118 time to create 1 rle with old method : 0.026160717010498047 length of segment : 203 time for calcul the mask position with numpy : 0.016288280487060547 nb_pixel_total : 20674 time to create 1 rle with old method : 0.02892899513244629 length of segment : 237 time for calcul the mask position with numpy : 0.061289310455322266 nb_pixel_total : 23473 time to create 1 rle with old method : 0.030315160751342773 length of segment : 151 time for calcul the mask position with numpy : 0.05554914474487305 nb_pixel_total : 20164 time to create 1 rle with old method : 0.026595115661621094 length of segment : 282 time for calcul the mask position with numpy : 0.003244161605834961 nb_pixel_total : 7759 time to create 1 rle with old method : 0.009602546691894531 length of segment : 124 time for calcul the mask position with numpy : 0.02684783935546875 nb_pixel_total : 11638 time to create 1 rle with old method : 0.018642425537109375 length of segment : 122 time for calcul the mask position with numpy : 0.025501728057861328 nb_pixel_total : 48232 time to create 1 rle with old method : 0.05940890312194824 length of segment : 437 time for calcul the mask position with numpy : 0.010185718536376953 nb_pixel_total : 8985 time to create 1 rle with old method : 0.02407217025756836 length of segment : 166 time for calcul the mask position with numpy : 0.11878728866577148 nb_pixel_total : 63178 time to create 1 rle with old method : 0.11375045776367188 length of segment : 273 time for calcul the mask position with numpy : 0.018033266067504883 nb_pixel_total : 30289 time to create 1 rle with old method : 0.03867006301879883 length of segment : 222 time for calcul the mask position with numpy : 0.021756410598754883 nb_pixel_total : 35608 time to create 1 rle with old method : 0.04911446571350098 length of segment : 142 time for calcul the mask position with numpy : 0.004857778549194336 nb_pixel_total : 17675 time to create 1 rle with old method : 0.0225832462310791 length of segment : 205 time for calcul the mask position with numpy : 0.01720571517944336 nb_pixel_total : 9140 time to create 1 rle with old method : 0.014728307723999023 length of segment : 143 time for calcul the mask position with numpy : 0.007302045822143555 nb_pixel_total : 27919 time to create 1 rle with old method : 0.03671455383300781 length of segment : 237 time for calcul the mask position with numpy : 0.06125020980834961 nb_pixel_total : 26722 time to create 1 rle with old method : 0.03359174728393555 length of segment : 345 time for calcul the mask position with numpy : 0.01740288734436035 nb_pixel_total : 14324 time to create 1 rle with old method : 0.021886348724365234 length of segment : 132 time for calcul the mask position with numpy : 0.03740239143371582 nb_pixel_total : 66842 time to create 1 rle with old method : 0.08606791496276855 length of segment : 249 time for calcul the mask position with numpy : 0.00917959213256836 nb_pixel_total : 11800 time to create 1 rle with old method : 0.017996549606323242 length of segment : 96 time for calcul the mask position with numpy : 0.004470348358154297 nb_pixel_total : 27129 time to create 1 rle with old method : 0.0348658561706543 length of segment : 142 time for calcul the mask position with numpy : 0.010796308517456055 nb_pixel_total : 10708 time to create 1 rle with old method : 0.016784191131591797 length of segment : 84 time for calcul the mask position with numpy : 0.005291938781738281 nb_pixel_total : 5033 time to create 1 rle with old method : 0.006867647171020508 length of segment : 121 time for calcul the mask position with numpy : 0.008401870727539062 nb_pixel_total : 9280 time to create 1 rle with old method : 0.015203714370727539 length of segment : 346 time for calcul the mask position with numpy : 0.005965232849121094 nb_pixel_total : 42071 time to create 1 rle with old method : 0.047997474670410156 length of segment : 293 time for calcul the mask position with numpy : 0.005006074905395508 nb_pixel_total : 6603 time to create 1 rle with old method : 0.009682178497314453 length of segment : 105 time for calcul the mask position with numpy : 0.0009131431579589844 nb_pixel_total : 12251 time to create 1 rle with old method : 0.014490365982055664 length of segment : 150 time for calcul the mask position with numpy : 0.01206064224243164 nb_pixel_total : 15010 time to create 1 rle with old method : 0.02083134651184082 length of segment : 181 time for calcul the mask position with numpy : 0.013027191162109375 nb_pixel_total : 25076 time to create 1 rle with old method : 0.03054499626159668 length of segment : 214 time for calcul the mask position with numpy : 0.002591848373413086 nb_pixel_total : 14819 time to create 1 rle with old method : 0.017940998077392578 length of segment : 145 time for calcul the mask position with numpy : 0.005990028381347656 nb_pixel_total : 11035 time to create 1 rle with old method : 0.015449285507202148 length of segment : 139 time for calcul the mask position with numpy : 0.02595353126525879 nb_pixel_total : 19811 time to create 1 rle with old method : 0.026565074920654297 length of segment : 182 time for calcul the mask position with numpy : 0.019183874130249023 nb_pixel_total : 9270 time to create 1 rle with old method : 0.01487421989440918 length of segment : 109 time for calcul the mask position with numpy : 0.005044698715209961 nb_pixel_total : 14351 time to create 1 rle with old method : 0.021814823150634766 length of segment : 175 time for calcul the mask position with numpy : 0.005445957183837891 nb_pixel_total : 27825 time to create 1 rle with old method : 0.031525373458862305 length of segment : 344 time for calcul the mask position with numpy : 0.02228236198425293 nb_pixel_total : 44772 time to create 1 rle with old method : 0.061235666275024414 length of segment : 617 time for calcul the mask position with numpy : 0.021799564361572266 nb_pixel_total : 13814 time to create 1 rle with old method : 0.02090597152709961 length of segment : 189 time for calcul the mask position with numpy : 0.009981393814086914 nb_pixel_total : 19793 time to create 1 rle with old method : 0.0273892879486084 length of segment : 203 time for calcul the mask position with numpy : 0.03670978546142578 nb_pixel_total : 17366 time to create 1 rle with old method : 0.023904085159301758 length of segment : 162 time for calcul the mask position with numpy : 0.009606361389160156 nb_pixel_total : 17249 time to create 1 rle with old method : 0.022608518600463867 length of segment : 125 time for calcul the mask position with numpy : 0.004973173141479492 nb_pixel_total : 42913 time to create 1 rle with old method : 0.04884624481201172 length of segment : 280 time for calcul the mask position with numpy : 0.004947185516357422 nb_pixel_total : 31685 time to create 1 rle with old method : 0.03611636161804199 length of segment : 328 time for calcul the mask position with numpy : 0.059145212173461914 nb_pixel_total : 68564 time to create 1 rle with old method : 0.07883524894714355 length of segment : 272 time for calcul the mask position with numpy : 0.00353240966796875 nb_pixel_total : 24210 time to create 1 rle with old method : 0.028206586837768555 length of segment : 216 time for calcul the mask position with numpy : 0.00026297569274902344 nb_pixel_total : 5896 time to create 1 rle with old method : 0.009369850158691406 length of segment : 128 time for calcul the mask position with numpy : 0.00987696647644043 nb_pixel_total : 23239 time to create 1 rle with old method : 0.031117916107177734 length of segment : 195 time for calcul the mask position with numpy : 0.0029621124267578125 nb_pixel_total : 17570 time to create 1 rle with old method : 0.02014017105102539 length of segment : 160 time for calcul the mask position with numpy : 0.0031480789184570312 nb_pixel_total : 21396 time to create 1 rle with old method : 0.024602890014648438 length of segment : 206 time for calcul the mask position with numpy : 0.006889820098876953 nb_pixel_total : 10978 time to create 1 rle with old method : 0.01527094841003418 length of segment : 120 time for calcul the mask position with numpy : 0.10114765167236328 nb_pixel_total : 70458 time to create 1 rle with old method : 0.0819859504699707 length of segment : 462 time for calcul the mask position with numpy : 0.008486747741699219 nb_pixel_total : 10829 time to create 1 rle with old method : 0.012763261795043945 length of segment : 115 time for calcul the mask position with numpy : 0.003632783889770508 nb_pixel_total : 21295 time to create 1 rle with old method : 0.025063276290893555 length of segment : 167 time for calcul the mask position with numpy : 0.0062749385833740234 nb_pixel_total : 14445 time to create 1 rle with old method : 0.020124197006225586 length of segment : 137 time for calcul the mask position with numpy : 0.05644583702087402 nb_pixel_total : 49381 time to create 1 rle with old method : 0.05991101264953613 length of segment : 356 time for calcul the mask position with numpy : 0.030603408813476562 nb_pixel_total : 24886 time to create 1 rle with old method : 0.03230905532836914 length of segment : 372 time for calcul the mask position with numpy : 0.026520729064941406 nb_pixel_total : 19487 time to create 1 rle with old method : 0.026093721389770508 length of segment : 184 time for calcul the mask position with numpy : 0.0009520053863525391 nb_pixel_total : 12296 time to create 1 rle with old method : 0.014903068542480469 length of segment : 158 time for calcul the mask position with numpy : 0.002561330795288086 nb_pixel_total : 23206 time to create 1 rle with old method : 0.027808666229248047 length of segment : 339 time for calcul the mask position with numpy : 0.0006070137023925781 nb_pixel_total : 4796 time to create 1 rle with old method : 0.006007194519042969 length of segment : 71 time for calcul the mask position with numpy : 0.013963699340820312 nb_pixel_total : 114857 time to create 1 rle with old method : 0.15975451469421387 length of segment : 637 time for calcul the mask position with numpy : 0.001796722412109375 nb_pixel_total : 21602 time to create 1 rle with old method : 0.02481555938720703 length of segment : 166 time for calcul the mask position with numpy : 0.0011713504791259766 nb_pixel_total : 14266 time to create 1 rle with old method : 0.017644882202148438 length of segment : 150 time for calcul the mask position with numpy : 0.0024526119232177734 nb_pixel_total : 30565 time to create 1 rle with old method : 0.036182403564453125 length of segment : 205 time for calcul the mask position with numpy : 0.0013959407806396484 nb_pixel_total : 11552 time to create 1 rle with old method : 0.01492929458618164 length of segment : 121 time for calcul the mask position with numpy : 0.0012102127075195312 nb_pixel_total : 20764 time to create 1 rle with old method : 0.02414703369140625 length of segment : 236 time for calcul the mask position with numpy : 0.0026247501373291016 nb_pixel_total : 36542 time to create 1 rle with old method : 0.045789480209350586 length of segment : 283 time for calcul the mask position with numpy : 0.0022361278533935547 nb_pixel_total : 22245 time to create 1 rle with old method : 0.03790760040283203 length of segment : 242 time for calcul the mask position with numpy : 0.0031061172485351562 nb_pixel_total : 34017 time to create 1 rle with old method : 0.053580284118652344 length of segment : 347 time for calcul the mask position with numpy : 0.0010986328125 nb_pixel_total : 11337 time to create 1 rle with old method : 0.01887035369873047 length of segment : 144 time for calcul the mask position with numpy : 0.0008234977722167969 nb_pixel_total : 7547 time to create 1 rle with old method : 0.013545513153076172 length of segment : 94 time for calcul the mask position with numpy : 0.010344982147216797 nb_pixel_total : 47030 time to create 1 rle with old method : 0.06340193748474121 length of segment : 337 time for calcul the mask position with numpy : 0.0005109310150146484 nb_pixel_total : 6804 time to create 1 rle with old method : 0.008625507354736328 length of segment : 76 time for calcul the mask position with numpy : 0.0009436607360839844 nb_pixel_total : 10014 time to create 1 rle with old method : 0.011616706848144531 length of segment : 128 time for calcul the mask position with numpy : 0.0022225379943847656 nb_pixel_total : 21467 time to create 1 rle with old method : 0.02506709098815918 length of segment : 265 time for calcul the mask position with numpy : 0.0033562183380126953 nb_pixel_total : 38252 time to create 1 rle with old method : 0.04485058784484863 length of segment : 291 time for calcul the mask position with numpy : 0.004019498825073242 nb_pixel_total : 45217 time to create 1 rle with old method : 0.05134916305541992 length of segment : 199 time for calcul the mask position with numpy : 0.002393007278442383 nb_pixel_total : 39076 time to create 1 rle with old method : 0.04455256462097168 length of segment : 260 time for calcul the mask position with numpy : 0.0009663105010986328 nb_pixel_total : 18803 time to create 1 rle with old method : 0.02209186553955078 length of segment : 260 time for calcul the mask position with numpy : 0.0015628337860107422 nb_pixel_total : 16518 time to create 1 rle with old method : 0.019891023635864258 length of segment : 184 time for calcul the mask position with numpy : 0.0027527809143066406 nb_pixel_total : 28642 time to create 1 rle with old method : 0.033414602279663086 length of segment : 236 time for calcul the mask position with numpy : 0.003782510757446289 nb_pixel_total : 51262 time to create 1 rle with old method : 0.06009101867675781 length of segment : 290 time for calcul the mask position with numpy : 0.0014462471008300781 nb_pixel_total : 21520 time to create 1 rle with old method : 0.026035070419311523 length of segment : 151 time for calcul the mask position with numpy : 0.0014781951904296875 nb_pixel_total : 16059 time to create 1 rle with old method : 0.020176172256469727 length of segment : 159 time for calcul the mask position with numpy : 0.0011911392211914062 nb_pixel_total : 9540 time to create 1 rle with old method : 0.011555671691894531 length of segment : 111 time for calcul the mask position with numpy : 0.0013592243194580078 nb_pixel_total : 15332 time to create 1 rle with old method : 0.01852893829345703 length of segment : 289 time for calcul the mask position with numpy : 0.003283262252807617 nb_pixel_total : 31106 time to create 1 rle with old method : 0.03652834892272949 length of segment : 307 time for calcul the mask position with numpy : 0.0010118484497070312 nb_pixel_total : 11843 time to create 1 rle with old method : 0.014138221740722656 length of segment : 191 time for calcul the mask position with numpy : 0.002186298370361328 nb_pixel_total : 18949 time to create 1 rle with old method : 0.023352861404418945 length of segment : 219 time for calcul the mask position with numpy : 0.0026366710662841797 nb_pixel_total : 24075 time to create 1 rle with old method : 0.028507232666015625 length of segment : 288 time for calcul the mask position with numpy : 0.0015902519226074219 nb_pixel_total : 17531 time to create 1 rle with old method : 0.02115654945373535 length of segment : 221 time for calcul the mask position with numpy : 0.0010662078857421875 nb_pixel_total : 14743 time to create 1 rle with old method : 0.01813030242919922 length of segment : 173 time for calcul the mask position with numpy : 0.0012896060943603516 nb_pixel_total : 11222 time to create 1 rle with old method : 0.013715505599975586 length of segment : 174 time for calcul the mask position with numpy : 0.006836414337158203 nb_pixel_total : 66172 time to create 1 rle with old method : 0.07549142837524414 length of segment : 323 time for calcul the mask position with numpy : 0.0008687973022460938 nb_pixel_total : 26764 time to create 1 rle with old method : 0.032532691955566406 length of segment : 195 time for calcul the mask position with numpy : 0.0023355484008789062 nb_pixel_total : 32038 time to create 1 rle with old method : 0.039649248123168945 length of segment : 322 time for calcul the mask position with numpy : 0.0012183189392089844 nb_pixel_total : 20760 time to create 1 rle with old method : 0.02472686767578125 length of segment : 108 time for calcul the mask position with numpy : 0.003019571304321289 nb_pixel_total : 18585 time to create 1 rle with old method : 0.022016286849975586 length of segment : 169 time for calcul the mask position with numpy : 0.0036687850952148438 nb_pixel_total : 61848 time to create 1 rle with old method : 0.07213544845581055 length of segment : 599 time for calcul the mask position with numpy : 0.0008699893951416016 nb_pixel_total : 11287 time to create 1 rle with old method : 0.013419151306152344 length of segment : 104 time for calcul the mask position with numpy : 0.001195669174194336 nb_pixel_total : 14599 time to create 1 rle with old method : 0.016900062561035156 length of segment : 153 time for calcul the mask position with numpy : 0.0014684200286865234 nb_pixel_total : 6110 time to create 1 rle with old method : 0.007555723190307617 length of segment : 186 time for calcul the mask position with numpy : 0.0010921955108642578 nb_pixel_total : 14876 time to create 1 rle with old method : 0.017399072647094727 length of segment : 181 time for calcul the mask position with numpy : 0.0008170604705810547 nb_pixel_total : 7872 time to create 1 rle with old method : 0.009400367736816406 length of segment : 124 time for calcul the mask position with numpy : 0.0025773048400878906 nb_pixel_total : 37090 time to create 1 rle with old method : 0.04327082633972168 length of segment : 338 time for calcul the mask position with numpy : 0.0012180805206298828 nb_pixel_total : 15174 time to create 1 rle with old method : 0.01790761947631836 length of segment : 174 time for calcul the mask position with numpy : 0.0040531158447265625 nb_pixel_total : 37362 time to create 1 rle with old method : 0.04439377784729004 length of segment : 256 time for calcul the mask position with numpy : 0.0022809505462646484 nb_pixel_total : 23875 time to create 1 rle with old method : 0.027644872665405273 length of segment : 204 time for calcul the mask position with numpy : 0.003091096878051758 nb_pixel_total : 36504 time to create 1 rle with old method : 0.04205441474914551 length of segment : 266 time for calcul the mask position with numpy : 0.005950927734375 nb_pixel_total : 66887 time to create 1 rle with old method : 0.07873964309692383 length of segment : 342 time for calcul the mask position with numpy : 0.0026772022247314453 nb_pixel_total : 28677 time to create 1 rle with old method : 0.03348565101623535 length of segment : 155 time for calcul the mask position with numpy : 0.0029582977294921875 nb_pixel_total : 36255 time to create 1 rle with old method : 0.042496442794799805 length of segment : 269 time for calcul the mask position with numpy : 0.0022301673889160156 nb_pixel_total : 20592 time to create 1 rle with old method : 0.023977041244506836 length of segment : 240 time for calcul the mask position with numpy : 0.006733417510986328 nb_pixel_total : 85081 time to create 1 rle with old method : 0.10203289985656738 length of segment : 358 time for calcul the mask position with numpy : 0.003695249557495117 nb_pixel_total : 36618 time to create 1 rle with old method : 0.04204607009887695 length of segment : 328 time for calcul the mask position with numpy : 0.00205230712890625 nb_pixel_total : 28182 time to create 1 rle with old method : 0.03281426429748535 length of segment : 268 time for calcul the mask position with numpy : 0.004483461380004883 nb_pixel_total : 55298 time to create 1 rle with old method : 0.07575535774230957 length of segment : 217 time for calcul the mask position with numpy : 0.0060787200927734375 nb_pixel_total : 51081 time to create 1 rle with old method : 0.0601961612701416 length of segment : 373 time for calcul the mask position with numpy : 0.0007729530334472656 nb_pixel_total : 9827 time to create 1 rle with old method : 0.01172947883605957 length of segment : 90 time for calcul the mask position with numpy : 0.0019178390502929688 nb_pixel_total : 14967 time to create 1 rle with old method : 0.017853260040283203 length of segment : 420 time for calcul the mask position with numpy : 0.004545927047729492 nb_pixel_total : 42535 time to create 1 rle with old method : 0.050092220306396484 length of segment : 304 time for calcul the mask position with numpy : 0.0014696121215820312 nb_pixel_total : 11986 time to create 1 rle with old method : 0.01398468017578125 length of segment : 130 time for calcul the mask position with numpy : 0.0018706321716308594 nb_pixel_total : 18200 time to create 1 rle with old method : 0.021582365036010742 length of segment : 204 time for calcul the mask position with numpy : 0.0035588741302490234 nb_pixel_total : 27862 time to create 1 rle with old method : 0.03275918960571289 length of segment : 232 time for calcul the mask position with numpy : 0.005675315856933594 nb_pixel_total : 64498 time to create 1 rle with old method : 0.07436394691467285 length of segment : 377 time for calcul the mask position with numpy : 0.001890420913696289 nb_pixel_total : 21686 time to create 1 rle with old method : 0.025281667709350586 length of segment : 173 time for calcul the mask position with numpy : 0.0003540515899658203 nb_pixel_total : 5983 time to create 1 rle with old method : 0.0071980953216552734 length of segment : 159 time for calcul the mask position with numpy : 0.0006287097930908203 nb_pixel_total : 8480 time to create 1 rle with old method : 0.010130882263183594 length of segment : 88 time for calcul the mask position with numpy : 0.00415492057800293 nb_pixel_total : 39377 time to create 1 rle with old method : 0.04527163505554199 length of segment : 308 time for calcul the mask position with numpy : 0.004385471343994141 nb_pixel_total : 39144 time to create 1 rle with old method : 0.045693159103393555 length of segment : 304 time for calcul the mask position with numpy : 0.0037560462951660156 nb_pixel_total : 18817 time to create 1 rle with old method : 0.022550344467163086 length of segment : 166 time for calcul the mask position with numpy : 0.0035223960876464844 nb_pixel_total : 26096 time to create 1 rle with old method : 0.0302884578704834 length of segment : 202 time for calcul the mask position with numpy : 0.0007832050323486328 nb_pixel_total : 8141 time to create 1 rle with old method : 0.009566545486450195 length of segment : 173 time for calcul the mask position with numpy : 0.0016505718231201172 nb_pixel_total : 24621 time to create 1 rle with old method : 0.028848648071289062 length of segment : 187 time for calcul the mask position with numpy : 0.0029146671295166016 nb_pixel_total : 34406 time to create 1 rle with old method : 0.03962445259094238 length of segment : 290 time for calcul the mask position with numpy : 0.0009019374847412109 nb_pixel_total : 19288 time to create 1 rle with old method : 0.022539377212524414 length of segment : 277 time for calcul the mask position with numpy : 0.0036764144897460938 nb_pixel_total : 51287 time to create 1 rle with old method : 0.05971884727478027 length of segment : 333 time for calcul the mask position with numpy : 0.00048065185546875 nb_pixel_total : 2905 time to create 1 rle with old method : 0.0035638809204101562 length of segment : 77 time for calcul the mask position with numpy : 0.001451730728149414 nb_pixel_total : 16384 time to create 1 rle with old method : 0.019422054290771484 length of segment : 147 time for calcul the mask position with numpy : 0.0009174346923828125 nb_pixel_total : 10504 time to create 1 rle with old method : 0.012822151184082031 length of segment : 113 time for calcul the mask position with numpy : 0.0011363029479980469 nb_pixel_total : 7019 time to create 1 rle with old method : 0.008439779281616211 length of segment : 241 time for calcul the mask position with numpy : 0.0012726783752441406 nb_pixel_total : 13838 time to create 1 rle with old method : 0.023003578186035156 length of segment : 125 time for calcul the mask position with numpy : 0.0011620521545410156 nb_pixel_total : 10551 time to create 1 rle with old method : 0.01786947250366211 length of segment : 114 time for calcul the mask position with numpy : 0.0015811920166015625 nb_pixel_total : 16317 time to create 1 rle with old method : 0.01919698715209961 length of segment : 200 time for calcul the mask position with numpy : 0.0014488697052001953 nb_pixel_total : 12797 time to create 1 rle with old method : 0.014810562133789062 length of segment : 223 time for calcul the mask position with numpy : 0.0063970088958740234 nb_pixel_total : 72631 time to create 1 rle with old method : 0.08542466163635254 length of segment : 342 time for calcul the mask position with numpy : 0.0016164779663085938 nb_pixel_total : 15622 time to create 1 rle with old method : 0.01842331886291504 length of segment : 171 time for calcul the mask position with numpy : 0.0018470287322998047 nb_pixel_total : 20664 time to create 1 rle with old method : 0.0246431827545166 length of segment : 192 time for calcul the mask position with numpy : 0.002653360366821289 nb_pixel_total : 34382 time to create 1 rle with old method : 0.04111146926879883 length of segment : 251 time for calcul the mask position with numpy : 0.00270843505859375 nb_pixel_total : 43665 time to create 1 rle with old method : 0.0518648624420166 length of segment : 298 time for calcul the mask position with numpy : 0.0005385875701904297 nb_pixel_total : 8739 time to create 1 rle with old method : 0.01047968864440918 length of segment : 106 time for calcul the mask position with numpy : 0.0015194416046142578 nb_pixel_total : 14758 time to create 1 rle with old method : 0.017474651336669922 length of segment : 201 time for calcul the mask position with numpy : 0.004128932952880859 nb_pixel_total : 36327 time to create 1 rle with old method : 0.04589080810546875 length of segment : 269 time for calcul the mask position with numpy : 0.0030460357666015625 nb_pixel_total : 42175 time to create 1 rle with old method : 0.04938650131225586 length of segment : 261 time for calcul the mask position with numpy : 0.0030846595764160156 nb_pixel_total : 34897 time to create 1 rle with old method : 0.04380321502685547 length of segment : 157 time for calcul the mask position with numpy : 0.0015926361083984375 nb_pixel_total : 8616 time to create 1 rle with old method : 0.011087179183959961 length of segment : 113 time for calcul the mask position with numpy : 0.0015842914581298828 nb_pixel_total : 17708 time to create 1 rle with old method : 0.022179126739501953 length of segment : 85 time for calcul the mask position with numpy : 0.0003151893615722656 nb_pixel_total : 2466 time to create 1 rle with old method : 0.0030059814453125 length of segment : 66 time for calcul the mask position with numpy : 0.0009562969207763672 nb_pixel_total : 14225 time to create 1 rle with old method : 0.016623258590698242 length of segment : 125 time for calcul the mask position with numpy : 0.00061798095703125 nb_pixel_total : 14096 time to create 1 rle with old method : 0.01638054847717285 length of segment : 153 time spent for convertir_results : 36.79160785675049 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 368 chid ids of type : 3594 Number RLEs to save : 81617 save missing photos in datou_result : time spend for datou_step_exec : 221.09475111961365 time spend to save output : 9.02678370475769 total time spend for step 1 : 230.12153482437134 step2:crop_condition Mon Mar 31 22:54:21 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 10 ! batch 1 Loaded 368 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ begin to crop the class : papier param for this class : {'min_score': 0.7} filtre for class : papier hashtag_id of this class : 492668766 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 286 About to insert : list_path_to_insert length 286 new photo from crops ! About to upload 286 photos upload in portfolio : 3736932 init cache_photo without model_param we have 286 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743454506_1501023 we have uploaded 286 photos in the portfolio 3736932 time of upload the photos Elapsed time : 87.7597644329071 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.7} filtre for class : carton hashtag_id of this class : 492774966 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 55 About to insert : list_path_to_insert length 55 new photo from crops ! About to upload 55 photos upload in portfolio : 3736932 init cache_photo without model_param we have 55 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743454605_1501023 we have uploaded 55 photos in the portfolio 3736932 time of upload the photos Elapsed time : 20.90856122970581 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/1743454627_1501023 we have uploaded 1 photos in the portfolio 3736932 time of upload the photos Elapsed time : 0.6364743709564209 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 ! map_result returned by crop_photo_return_map_crop : length : 12 About to insert : list_path_to_insert length 12 new photo from crops ! About to upload 12 photos upload in portfolio : 3736932 init cache_photo without model_param we have 12 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743454633_1501023 we have uploaded 12 photos in the portfolio 3736932 time of upload the photos Elapsed time : 3.7498950958251953 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 ! map_result returned by crop_photo_return_map_crop : length : 5 About to insert : list_path_to_insert length 5 new photo from crops ! About to upload 5 photos upload in portfolio : 3736932 init cache_photo without model_param we have 5 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743454639_1501023 we have uploaded 5 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.6038672924041748 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.7} filtre for class : pehd hashtag_id of this class : 628944319 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3736932 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743454642_1501023 we have uploaded 3 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.2149558067321777 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.7} filtre for class : pet_fonce hashtag_id of this class : 2107755900 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 6 About to insert : list_path_to_insert length 6 new photo from crops ! About to upload 6 photos upload in portfolio : 3736932 init cache_photo without model_param we have 6 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743454647_1501023 we have uploaded 6 photos in the portfolio 3736932 time of upload the photos Elapsed time : 2.1478471755981445 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 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1349085160, 1349085142, 1349085138, 1349085131, 1349085127, 1348950350, 1348949687, 1348949682, 1348949676, 1348949672] Looping around the photos to save general results len do output : 368 /1349115302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115305Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115309Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115321Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115394Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115398Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115399Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115401Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115405Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115406Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115407Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115409Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115410Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115413Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115414Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115415Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115417Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115418Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115419Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115421Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115422Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115423Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115425Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115427Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115428Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115460Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115473Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115656Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349115984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1349116158Didn'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, '2710822') ('3318', '21925661', '1349085160', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085142', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085138', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085131', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085127', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348950350', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949687', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949682', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949676', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949672', None, None, None, None, None, '2710822') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1114 time used for this insertion : 0.05692577362060547 save_final save missing photos in datou_result : time spend for datou_step_exec : 188.70601415634155 time spend to save output : 0.4171574115753174 total time spend for step 2 : 189.12317156791687 step3:rle_unique_nms_with_priority Mon Mar 31 22:57:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 368 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 30 nb_hashtags : 4 time to prepare the origin masks : 4.043526887893677 time for calcul the mask position with numpy : 0.4724128246307373 nb_pixel_total : 5663546 time to create 1 rle with new method : 0.715965747833252 time for calcul the mask position with numpy : 0.029726743698120117 nb_pixel_total : 28035 time to create 1 rle with old method : 0.03146028518676758 time for calcul the mask position with numpy : 0.030059337615966797 nb_pixel_total : 80454 time to create 1 rle with old method : 0.10392189025878906 time for calcul the mask position with numpy : 0.03688383102416992 nb_pixel_total : 242009 time to create 1 rle with new method : 1.1920998096466064 time for calcul the mask position with numpy : 0.030495405197143555 nb_pixel_total : 6427 time to create 1 rle with old method : 0.009564876556396484 time for calcul the mask position with numpy : 0.04121804237365723 nb_pixel_total : 21197 time to create 1 rle with old method : 0.039882659912109375 time for calcul the mask position with numpy : 0.03244376182556152 nb_pixel_total : 203233 time to create 1 rle with new method : 0.6971790790557861 time for calcul the mask position with numpy : 0.030057907104492188 nb_pixel_total : 61316 time to create 1 rle with old method : 0.06857013702392578 time for calcul the mask position with numpy : 0.02960944175720215 nb_pixel_total : 90627 time to create 1 rle with old method : 0.1173715591430664 time for calcul the mask position with numpy : 0.029170751571655273 nb_pixel_total : 6109 time to create 1 rle with old method : 0.007012128829956055 time for calcul the mask position with numpy : 0.02921152114868164 nb_pixel_total : 18445 time to create 1 rle with old method : 0.020633697509765625 time for calcul the mask position with numpy : 0.029052734375 nb_pixel_total : 4414 time to create 1 rle with old method : 0.007424831390380859 time for calcul the mask position with numpy : 0.03600287437438965 nb_pixel_total : 132677 time to create 1 rle with old method : 0.17084026336669922 time for calcul the mask position with numpy : 0.028931140899658203 nb_pixel_total : 33424 time to create 1 rle with old method : 0.03740525245666504 time for calcul the mask position with numpy : 0.028795719146728516 nb_pixel_total : 15974 time to create 1 rle with old method : 0.01793074607849121 time for calcul the mask position with numpy : 0.028789043426513672 nb_pixel_total : 31494 time to create 1 rle with old method : 0.035462379455566406 time for calcul the mask position with numpy : 0.028886079788208008 nb_pixel_total : 24219 time to create 1 rle with old method : 0.027235984802246094 time for calcul the mask position with numpy : 0.028806209564208984 nb_pixel_total : 4299 time to create 1 rle with old method : 0.004898548126220703 time for calcul the mask position with numpy : 0.028877973556518555 nb_pixel_total : 50206 time to create 1 rle with old method : 0.05658292770385742 time for calcul the mask position with numpy : 0.028881072998046875 nb_pixel_total : 10101 time to create 1 rle with old method : 0.01151275634765625 time for calcul the mask position with numpy : 0.028961896896362305 nb_pixel_total : 12785 time to create 1 rle with old method : 0.01502847671508789 time for calcul the mask position with numpy : 0.030506372451782227 nb_pixel_total : 11038 time to create 1 rle with old method : 0.01240229606628418 time for calcul the mask position with numpy : 0.029303550720214844 nb_pixel_total : 76173 time to create 1 rle with old method : 0.08467864990234375 time for calcul the mask position with numpy : 0.02893996238708496 nb_pixel_total : 5031 time to create 1 rle with old method : 0.005755901336669922 time for calcul the mask position with numpy : 0.028819799423217773 nb_pixel_total : 30008 time to create 1 rle with old method : 0.03418421745300293 time for calcul the mask position with numpy : 0.02967977523803711 nb_pixel_total : 56701 time to create 1 rle with old method : 0.0634315013885498 time for calcul the mask position with numpy : 0.028836488723754883 nb_pixel_total : 20977 time to create 1 rle with old method : 0.023573875427246094 time for calcul the mask position with numpy : 0.02883291244506836 nb_pixel_total : 10509 time to create 1 rle with old method : 0.011944293975830078 time for calcul the mask position with numpy : 0.02927565574645996 nb_pixel_total : 55142 time to create 1 rle with old method : 0.06342673301696777 time for calcul the mask position with numpy : 0.029161453247070312 nb_pixel_total : 30539 time to create 1 rle with old method : 0.040758371353149414 time for calcul the mask position with numpy : 0.02901434898376465 nb_pixel_total : 13131 time to create 1 rle with old method : 0.014831304550170898 create new chi : 5.210386753082275 time to delete rle : 0.01966071128845215 batch 1 Loaded 61 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 18179 TO DO : save crop sub photo not yet done ! save time : 1.33660888671875 nb_obj : 40 nb_hashtags : 6 time to prepare the origin masks : 3.8372795581817627 time for calcul the mask position with numpy : 0.42873120307922363 nb_pixel_total : 6086352 time to create 1 rle with new method : 0.5979595184326172 time for calcul the mask position with numpy : 0.030896902084350586 nb_pixel_total : 20156 time to create 1 rle with old method : 0.025887727737426758 time for calcul the mask position with numpy : 0.031092405319213867 nb_pixel_total : 34038 time to create 1 rle with old method : 0.03985953330993652 time for calcul the mask position with numpy : 0.03273606300354004 nb_pixel_total : 14914 time to create 1 rle with old method : 0.017256975173950195 time for calcul the mask position with numpy : 0.029412031173706055 nb_pixel_total : 35486 time to create 1 rle with old method : 0.03990674018859863 time for calcul the mask position with numpy : 0.029001712799072266 nb_pixel_total : 33331 time to create 1 rle with old method : 0.037538766860961914 time for calcul the mask position with numpy : 0.029148340225219727 nb_pixel_total : 8275 time to create 1 rle with old method : 0.009566068649291992 time for calcul the mask position with numpy : 0.028928041458129883 nb_pixel_total : 16117 time to create 1 rle with old method : 0.019724607467651367 time for calcul the mask position with numpy : 0.029097557067871094 nb_pixel_total : 14743 time to create 1 rle with old method : 0.01691579818725586 time for calcul the mask position with numpy : 0.029312849044799805 nb_pixel_total : 10781 time to create 1 rle with old method : 0.01226353645324707 time for calcul the mask position with numpy : 0.031275272369384766 nb_pixel_total : 12330 time to create 1 rle with old method : 0.02336716651916504 time for calcul the mask position with numpy : 0.03696942329406738 nb_pixel_total : 12371 time to create 1 rle with old method : 0.016909122467041016 time for calcul the mask position with numpy : 0.04983067512512207 nb_pixel_total : 18436 time to create 1 rle with old method : 0.021561145782470703 time for calcul the mask position with numpy : 0.03526782989501953 nb_pixel_total : 37362 time to create 1 rle with old method : 0.047882080078125 time for calcul the mask position with numpy : 0.04135608673095703 nb_pixel_total : 6846 time to create 1 rle with old method : 0.007982254028320312 time for calcul the mask position with numpy : 0.02910900115966797 nb_pixel_total : 58620 time to create 1 rle with old method : 0.06865859031677246 time for calcul the mask position with numpy : 0.029143333435058594 nb_pixel_total : 14225 time to create 1 rle with old method : 0.01627969741821289 time for calcul the mask position with numpy : 0.0363612174987793 nb_pixel_total : 38879 time to create 1 rle with old method : 0.04400229454040527 time for calcul the mask position with numpy : 0.028975248336791992 nb_pixel_total : 12692 time to create 1 rle with old method : 0.014420747756958008 time for calcul the mask position with numpy : 0.029117345809936523 nb_pixel_total : 14674 time to create 1 rle with old method : 0.016511201858520508 time for calcul the mask position with numpy : 0.029071569442749023 nb_pixel_total : 9896 time to create 1 rle with old method : 0.011496782302856445 time for calcul the mask position with numpy : 0.029250621795654297 nb_pixel_total : 99618 time to create 1 rle with old method : 0.11109375953674316 time for calcul the mask position with numpy : 0.029167652130126953 nb_pixel_total : 23955 time to create 1 rle with old method : 0.027797698974609375 time for calcul the mask position with numpy : 0.030849218368530273 nb_pixel_total : 18140 time to create 1 rle with old method : 0.029124021530151367 time for calcul the mask position with numpy : 0.032979726791381836 nb_pixel_total : 31032 time to create 1 rle with old method : 0.03879117965698242 time for calcul the mask position with numpy : 0.03346586227416992 nb_pixel_total : 20041 time to create 1 rle with old method : 0.022855043411254883 time for calcul the mask position with numpy : 0.029782533645629883 nb_pixel_total : 32646 time to create 1 rle with old method : 0.03649544715881348 time for calcul the mask position with numpy : 0.029510974884033203 nb_pixel_total : 12622 time to create 1 rle with old method : 0.014203071594238281 time for calcul the mask position with numpy : 0.029531240463256836 nb_pixel_total : 21547 time to create 1 rle with old method : 0.024071216583251953 time for calcul the mask position with numpy : 0.029948949813842773 nb_pixel_total : 15386 time to create 1 rle with old method : 0.017572402954101562 time for calcul the mask position with numpy : 0.029642105102539062 nb_pixel_total : 20596 time to create 1 rle with old method : 0.026954174041748047 time for calcul the mask position with numpy : 0.028258085250854492 nb_pixel_total : 9919 time to create 1 rle with old method : 0.011073112487792969 time for calcul the mask position with numpy : 0.02898097038269043 nb_pixel_total : 15127 time to create 1 rle with old method : 0.0170285701751709 time for calcul the mask position with numpy : 0.029154539108276367 nb_pixel_total : 10772 time to create 1 rle with old method : 0.013060569763183594 time for calcul the mask position with numpy : 0.02852630615234375 nb_pixel_total : 13301 time to create 1 rle with old method : 0.01465463638305664 time for calcul the mask position with numpy : 0.028539657592773438 nb_pixel_total : 47067 time to create 1 rle with old method : 0.05275082588195801 time for calcul the mask position with numpy : 0.030544042587280273 nb_pixel_total : 92352 time to create 1 rle with old method : 0.1382291316986084 time for calcul the mask position with numpy : 0.030787229537963867 nb_pixel_total : 18860 time to create 1 rle with old method : 0.02397441864013672 time for calcul the mask position with numpy : 0.0312347412109375 nb_pixel_total : 4791 time to create 1 rle with old method : 0.006224870681762695 time for calcul the mask position with numpy : 0.031041860580444336 nb_pixel_total : 441 time to create 1 rle with old method : 0.0006246566772460938 time for calcul the mask position with numpy : 0.030257463455200195 nb_pixel_total : 31503 time to create 1 rle with old method : 0.03526902198791504 create new chi : 3.4864566326141357 time to delete rle : 0.0039942264556884766 batch 1 Loaded 81 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 18008 TO DO : save crop sub photo not yet done ! save time : 1.152252435684204 nb_obj : 35 nb_hashtags : 5 time to prepare the origin masks : 3.8189709186553955 time for calcul the mask position with numpy : 0.29287171363830566 nb_pixel_total : 6050586 time to create 1 rle with new method : 0.762603759765625 time for calcul the mask position with numpy : 0.03138399124145508 nb_pixel_total : 27031 time to create 1 rle with old method : 0.030886173248291016 time for calcul the mask position with numpy : 0.02919602394104004 nb_pixel_total : 37463 time to create 1 rle with old method : 0.05244016647338867 time for calcul the mask position with numpy : 0.03314471244812012 nb_pixel_total : 7782 time to create 1 rle with old method : 0.012489080429077148 time for calcul the mask position with numpy : 0.032946109771728516 nb_pixel_total : 18668 time to create 1 rle with old method : 0.02130722999572754 time for calcul the mask position with numpy : 0.028975963592529297 nb_pixel_total : 35997 time to create 1 rle with old method : 0.04156064987182617 time for calcul the mask position with numpy : 0.028857707977294922 nb_pixel_total : 8217 time to create 1 rle with old method : 0.00957036018371582 time for calcul the mask position with numpy : 0.029015541076660156 nb_pixel_total : 39770 time to create 1 rle with old method : 0.045687198638916016 time for calcul the mask position with numpy : 0.029021024703979492 nb_pixel_total : 58657 time to create 1 rle with old method : 0.07334184646606445 time for calcul the mask position with numpy : 0.029302120208740234 nb_pixel_total : 25571 time to create 1 rle with old method : 0.029098987579345703 time for calcul the mask position with numpy : 0.029162168502807617 nb_pixel_total : 11550 time to create 1 rle with old method : 0.013290166854858398 time for calcul the mask position with numpy : 0.02917003631591797 nb_pixel_total : 4229 time to create 1 rle with old method : 0.004957675933837891 time for calcul the mask position with numpy : 0.029146194458007812 nb_pixel_total : 23660 time to create 1 rle with old method : 0.02730727195739746 time for calcul the mask position with numpy : 0.029196739196777344 nb_pixel_total : 49860 time to create 1 rle with old method : 0.055969953536987305 time for calcul the mask position with numpy : 0.031984806060791016 nb_pixel_total : 25094 time to create 1 rle with old method : 0.03315877914428711 time for calcul the mask position with numpy : 0.03358149528503418 nb_pixel_total : 43222 time to create 1 rle with old method : 0.05274009704589844 time for calcul the mask position with numpy : 0.029164791107177734 nb_pixel_total : 10288 time to create 1 rle with old method : 0.011878490447998047 time for calcul the mask position with numpy : 0.029083728790283203 nb_pixel_total : 17485 time to create 1 rle with old method : 0.019924402236938477 time for calcul the mask position with numpy : 0.028917789459228516 nb_pixel_total : 48912 time to create 1 rle with old method : 0.054433584213256836 time for calcul the mask position with numpy : 0.029244184494018555 nb_pixel_total : 11363 time to create 1 rle with old method : 0.012990236282348633 time for calcul the mask position with numpy : 0.029356956481933594 nb_pixel_total : 20082 time to create 1 rle with old method : 0.023018836975097656 time for calcul the mask position with numpy : 0.02950882911682129 nb_pixel_total : 25615 time to create 1 rle with old method : 0.03281378746032715 time for calcul the mask position with numpy : 0.028857707977294922 nb_pixel_total : 30861 time to create 1 rle with old method : 0.03472709655761719 time for calcul the mask position with numpy : 0.029176950454711914 nb_pixel_total : 11523 time to create 1 rle with old method : 0.013279199600219727 time for calcul the mask position with numpy : 0.029387235641479492 nb_pixel_total : 34092 time to create 1 rle with old method : 0.03888869285583496 time for calcul the mask position with numpy : 0.029178380966186523 nb_pixel_total : 18519 time to create 1 rle with old method : 0.020863056182861328 time for calcul the mask position with numpy : 0.02911853790283203 nb_pixel_total : 43278 time to create 1 rle with old method : 0.049118995666503906 time for calcul the mask position with numpy : 0.029523849487304688 nb_pixel_total : 31224 time to create 1 rle with old method : 0.03501391410827637 time for calcul the mask position with numpy : 0.030771493911743164 nb_pixel_total : 11566 time to create 1 rle with old method : 0.013324737548828125 time for calcul the mask position with numpy : 0.03054952621459961 nb_pixel_total : 34274 time to create 1 rle with old method : 0.04628252983093262 time for calcul the mask position with numpy : 0.03342175483703613 nb_pixel_total : 30842 time to create 1 rle with old method : 0.0428318977355957 time for calcul the mask position with numpy : 0.029525279998779297 nb_pixel_total : 2850 time to create 1 rle with old method : 0.004258155822753906 time for calcul the mask position with numpy : 0.030377864837646484 nb_pixel_total : 14119 time to create 1 rle with old method : 0.016251564025878906 time for calcul the mask position with numpy : 0.030315160751342773 nb_pixel_total : 44537 time to create 1 rle with old method : 0.05056309700012207 time for calcul the mask position with numpy : 0.029700756072998047 nb_pixel_total : 10269 time to create 1 rle with old method : 0.012147188186645508 time for calcul the mask position with numpy : 0.0330653190612793 nb_pixel_total : 131184 time to create 1 rle with old method : 0.18562006950378418 create new chi : 3.367846965789795 time to delete rle : 0.002611398696899414 batch 1 Loaded 71 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 17959 TO DO : save crop sub photo not yet done ! save time : 1.1526288986206055 nb_obj : 49 nb_hashtags : 3 time to prepare the origin masks : 4.086865186691284 time for calcul the mask position with numpy : 0.4499061107635498 nb_pixel_total : 5555612 time to create 1 rle with new method : 0.5833587646484375 time for calcul the mask position with numpy : 0.03187084197998047 nb_pixel_total : 21068 time to create 1 rle with old method : 0.024717092514038086 time for calcul the mask position with numpy : 0.03214764595031738 nb_pixel_total : 14201 time to create 1 rle with old method : 0.017121315002441406 time for calcul the mask position with numpy : 0.031519412994384766 nb_pixel_total : 26997 time to create 1 rle with old method : 0.034982919692993164 time for calcul the mask position with numpy : 0.03195691108703613 nb_pixel_total : 38913 time to create 1 rle with old method : 0.05052375793457031 time for calcul the mask position with numpy : 0.03569293022155762 nb_pixel_total : 17030 time to create 1 rle with old method : 0.020055770874023438 time for calcul the mask position with numpy : 0.030322551727294922 nb_pixel_total : 3288 time to create 1 rle with old method : 0.004576921463012695 time for calcul the mask position with numpy : 0.030187368392944336 nb_pixel_total : 44178 time to create 1 rle with old method : 0.05731201171875 time for calcul the mask position with numpy : 0.033850908279418945 nb_pixel_total : 5672 time to create 1 rle with old method : 0.0064928531646728516 time for calcul the mask position with numpy : 0.030050992965698242 nb_pixel_total : 10519 time to create 1 rle with old method : 0.012131929397583008 time for calcul the mask position with numpy : 0.029723167419433594 nb_pixel_total : 8422 time to create 1 rle with old method : 0.009604454040527344 time for calcul the mask position with numpy : 0.02918100357055664 nb_pixel_total : 32526 time to create 1 rle with old method : 0.036974430084228516 time for calcul the mask position with numpy : 0.03182625770568848 nb_pixel_total : 29982 time to create 1 rle with old method : 0.03412032127380371 time for calcul the mask position with numpy : 0.030145883560180664 nb_pixel_total : 18410 time to create 1 rle with old method : 0.02081775665283203 time for calcul the mask position with numpy : 0.02962183952331543 nb_pixel_total : 13744 time to create 1 rle with old method : 0.01586461067199707 time for calcul the mask position with numpy : 0.029871225357055664 nb_pixel_total : 8396 time to create 1 rle with old method : 0.009641170501708984 time for calcul the mask position with numpy : 0.02944493293762207 nb_pixel_total : 11462 time to create 1 rle with old method : 0.01486063003540039 time for calcul the mask position with numpy : 0.029412031173706055 nb_pixel_total : 27957 time to create 1 rle with old method : 0.032361745834350586 time for calcul the mask position with numpy : 0.029940128326416016 nb_pixel_total : 14333 time to create 1 rle with old method : 0.01918935775756836 time for calcul the mask position with numpy : 0.0357968807220459 nb_pixel_total : 30569 time to create 1 rle with old method : 0.04425549507141113 time for calcul the mask position with numpy : 0.031909942626953125 nb_pixel_total : 12254 time to create 1 rle with old method : 0.015016794204711914 time for calcul the mask position with numpy : 0.03143429756164551 nb_pixel_total : 58148 time to create 1 rle with old method : 0.08565711975097656 time for calcul the mask position with numpy : 0.02959132194519043 nb_pixel_total : 44795 time to create 1 rle with old method : 0.0527033805847168 time for calcul the mask position with numpy : 0.02993011474609375 nb_pixel_total : 21784 time to create 1 rle with old method : 0.025699377059936523 time for calcul the mask position with numpy : 0.039229631423950195 nb_pixel_total : 115886 time to create 1 rle with old method : 0.1724853515625 time for calcul the mask position with numpy : 0.033341169357299805 nb_pixel_total : 14075 time to create 1 rle with old method : 0.02286076545715332 time for calcul the mask position with numpy : 0.02976393699645996 nb_pixel_total : 13017 time to create 1 rle with old method : 0.014703750610351562 time for calcul the mask position with numpy : 0.02919626235961914 nb_pixel_total : 15692 time to create 1 rle with old method : 0.01798534393310547 time for calcul the mask position with numpy : 0.029694080352783203 nb_pixel_total : 95398 time to create 1 rle with old method : 0.10714864730834961 time for calcul the mask position with numpy : 0.03011608123779297 nb_pixel_total : 25935 time to create 1 rle with old method : 0.029096126556396484 time for calcul the mask position with numpy : 0.03095269203186035 nb_pixel_total : 18716 time to create 1 rle with old method : 0.021993160247802734 time for calcul the mask position with numpy : 0.030321598052978516 nb_pixel_total : 15967 time to create 1 rle with old method : 0.01808023452758789 time for calcul the mask position with numpy : 0.029712438583374023 nb_pixel_total : 51532 time to create 1 rle with old method : 0.06194925308227539 time for calcul the mask position with numpy : 0.029352188110351562 nb_pixel_total : 34369 time to create 1 rle with old method : 0.038883209228515625 time for calcul the mask position with numpy : 0.03486347198486328 nb_pixel_total : 13335 time to create 1 rle with old method : 0.01525259017944336 time for calcul the mask position with numpy : 0.034859657287597656 nb_pixel_total : 81595 time to create 1 rle with old method : 0.12980961799621582 time for calcul the mask position with numpy : 0.036019086837768555 nb_pixel_total : 4251 time to create 1 rle with old method : 0.006155967712402344 time for calcul the mask position with numpy : 0.032759904861450195 nb_pixel_total : 28401 time to create 1 rle with old method : 0.03261399269104004 time for calcul the mask position with numpy : 0.029336929321289062 nb_pixel_total : 22069 time to create 1 rle with old method : 0.025763273239135742 time for calcul the mask position with numpy : 0.029431819915771484 nb_pixel_total : 52010 time to create 1 rle with old method : 0.059580087661743164 time for calcul the mask position with numpy : 0.03178095817565918 nb_pixel_total : 167107 time to create 1 rle with new method : 1.1492962837219238 time for calcul the mask position with numpy : 0.031531333923339844 nb_pixel_total : 39105 time to create 1 rle with old method : 0.04624366760253906 time for calcul the mask position with numpy : 0.029937744140625 nb_pixel_total : 27926 time to create 1 rle with old method : 0.03152728080749512 time for calcul the mask position with numpy : 0.029830217361450195 nb_pixel_total : 29068 time to create 1 rle with old method : 0.03267621994018555 time for calcul the mask position with numpy : 0.02976369857788086 nb_pixel_total : 55063 time to create 1 rle with old method : 0.08034920692443848 time for calcul the mask position with numpy : 0.03441619873046875 nb_pixel_total : 17257 time to create 1 rle with old method : 0.02265477180480957 time for calcul the mask position with numpy : 0.02965235710144043 nb_pixel_total : 15089 time to create 1 rle with old method : 0.019335031509399414 time for calcul the mask position with numpy : 0.030643224716186523 nb_pixel_total : 15788 time to create 1 rle with old method : 0.020189762115478516 time for calcul the mask position with numpy : 0.030635833740234375 nb_pixel_total : 7688 time to create 1 rle with old method : 0.009690046310424805 time for calcul the mask position with numpy : 0.03050541877746582 nb_pixel_total : 3641 time to create 1 rle with old method : 0.004664182662963867 create new chi : 5.4697043895721436 time to delete rle : 0.004903316497802734 batch 1 Loaded 99 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 23144 TO DO : save crop sub photo not yet done ! save time : 1.4608805179595947 nb_obj : 33 nb_hashtags : 4 time to prepare the origin masks : 3.9522573947906494 time for calcul the mask position with numpy : 0.4556107521057129 nb_pixel_total : 6169061 time to create 1 rle with new method : 0.6322343349456787 time for calcul the mask position with numpy : 0.029509782791137695 nb_pixel_total : 40516 time to create 1 rle with old method : 0.053235769271850586 time for calcul the mask position with numpy : 0.02916741371154785 nb_pixel_total : 131495 time to create 1 rle with old method : 0.145249605178833 time for calcul the mask position with numpy : 0.029210567474365234 nb_pixel_total : 12839 time to create 1 rle with old method : 0.014447450637817383 time for calcul the mask position with numpy : 0.031417131423950195 nb_pixel_total : 9602 time to create 1 rle with old method : 0.011054277420043945 time for calcul the mask position with numpy : 0.02939438819885254 nb_pixel_total : 13248 time to create 1 rle with old method : 0.015049934387207031 time for calcul the mask position with numpy : 0.0294797420501709 nb_pixel_total : 14850 time to create 1 rle with old method : 0.016774892807006836 time for calcul the mask position with numpy : 0.02896738052368164 nb_pixel_total : 29003 time to create 1 rle with old method : 0.03651738166809082 time for calcul the mask position with numpy : 0.032863616943359375 nb_pixel_total : 2240 time to create 1 rle with old method : 0.0036661624908447266 time for calcul the mask position with numpy : 0.032834529876708984 nb_pixel_total : 25924 time to create 1 rle with old method : 0.03034687042236328 time for calcul the mask position with numpy : 0.029748916625976562 nb_pixel_total : 13376 time to create 1 rle with old method : 0.01796722412109375 time for calcul the mask position with numpy : 0.02964162826538086 nb_pixel_total : 6226 time to create 1 rle with old method : 0.007096767425537109 time for calcul the mask position with numpy : 0.03275275230407715 nb_pixel_total : 12781 time to create 1 rle with old method : 0.014467716217041016 time for calcul the mask position with numpy : 0.029627323150634766 nb_pixel_total : 31254 time to create 1 rle with old method : 0.03519773483276367 time for calcul the mask position with numpy : 0.029680967330932617 nb_pixel_total : 4321 time to create 1 rle with old method : 0.005014896392822266 time for calcul the mask position with numpy : 0.03822779655456543 nb_pixel_total : 10979 time to create 1 rle with old method : 0.012490034103393555 time for calcul the mask position with numpy : 0.029227018356323242 nb_pixel_total : 61267 time to create 1 rle with old method : 0.07122063636779785 time for calcul the mask position with numpy : 0.03258013725280762 nb_pixel_total : 9818 time to create 1 rle with old method : 0.01137232780456543 time for calcul the mask position with numpy : 0.039789438247680664 nb_pixel_total : 8770 time to create 1 rle with old method : 0.010790109634399414 time for calcul the mask position with numpy : 0.02996373176574707 nb_pixel_total : 27269 time to create 1 rle with old method : 0.032759904861450195 time for calcul the mask position with numpy : 0.029397249221801758 nb_pixel_total : 16559 time to create 1 rle with old method : 0.019116878509521484 time for calcul the mask position with numpy : 0.029951095581054688 nb_pixel_total : 35832 time to create 1 rle with old method : 0.04091811180114746 time for calcul the mask position with numpy : 0.03154444694519043 nb_pixel_total : 69996 time to create 1 rle with old method : 0.08709907531738281 time for calcul the mask position with numpy : 0.03591299057006836 nb_pixel_total : 18341 time to create 1 rle with old method : 0.035712480545043945 time for calcul the mask position with numpy : 0.03643393516540527 nb_pixel_total : 8515 time to create 1 rle with old method : 0.0166471004486084 time for calcul the mask position with numpy : 0.035629987716674805 nb_pixel_total : 34684 time to create 1 rle with old method : 0.03990769386291504 time for calcul the mask position with numpy : 0.03023815155029297 nb_pixel_total : 22016 time to create 1 rle with old method : 0.026666641235351562 time for calcul the mask position with numpy : 0.029764890670776367 nb_pixel_total : 9288 time to create 1 rle with old method : 0.010807991027832031 time for calcul the mask position with numpy : 0.029688596725463867 nb_pixel_total : 106 time to create 1 rle with old method : 0.0003292560577392578 time for calcul the mask position with numpy : 0.029952049255371094 nb_pixel_total : 57243 time to create 1 rle with old method : 0.08070063591003418 time for calcul the mask position with numpy : 0.03344082832336426 nb_pixel_total : 51164 time to create 1 rle with old method : 0.056882381439208984 time for calcul the mask position with numpy : 0.029485464096069336 nb_pixel_total : 60470 time to create 1 rle with old method : 0.09148526191711426 time for calcul the mask position with numpy : 0.031714677810668945 nb_pixel_total : 19889 time to create 1 rle with old method : 0.023014545440673828 time for calcul the mask position with numpy : 0.030811309814453125 nb_pixel_total : 11298 time to create 1 rle with old method : 0.013875007629394531 create new chi : 3.2547214031219482 time to delete rle : 0.002973318099975586 batch 1 Loaded 67 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 15617 TO DO : save crop sub photo not yet done ! save time : 1.052445888519287 nb_obj : 12 nb_hashtags : 3 time to prepare the origin masks : 3.9593722820281982 time for calcul the mask position with numpy : 0.6627490520477295 nb_pixel_total : 6772720 time to create 1 rle with new method : 0.9857056140899658 time for calcul the mask position with numpy : 0.03619551658630371 nb_pixel_total : 15670 time to create 1 rle with old method : 0.017740964889526367 time for calcul the mask position with numpy : 0.035745859146118164 nb_pixel_total : 19174 time to create 1 rle with old method : 0.021988868713378906 time for calcul the mask position with numpy : 0.02341628074645996 nb_pixel_total : 13477 time to create 1 rle with old method : 0.015204191207885742 time for calcul the mask position with numpy : 0.022263765335083008 nb_pixel_total : 21091 time to create 1 rle with old method : 0.023651123046875 time for calcul the mask position with numpy : 0.02271437644958496 nb_pixel_total : 17125 time to create 1 rle with old method : 0.01940298080444336 time for calcul the mask position with numpy : 0.021328210830688477 nb_pixel_total : 7807 time to create 1 rle with old method : 0.008765935897827148 time for calcul the mask position with numpy : 0.02162003517150879 nb_pixel_total : 52134 time to create 1 rle with old method : 0.06042218208312988 time for calcul the mask position with numpy : 0.024802207946777344 nb_pixel_total : 43843 time to create 1 rle with old method : 0.04913806915283203 time for calcul the mask position with numpy : 0.022467374801635742 nb_pixel_total : 29429 time to create 1 rle with old method : 0.03304481506347656 time for calcul the mask position with numpy : 0.022922515869140625 nb_pixel_total : 12745 time to create 1 rle with old method : 0.014311790466308594 time for calcul the mask position with numpy : 0.022179841995239258 nb_pixel_total : 21545 time to create 1 rle with old method : 0.02413201332092285 time for calcul the mask position with numpy : 0.021524906158447266 nb_pixel_total : 23480 time to create 1 rle with old method : 0.026074886322021484 create new chi : 2.29628324508667 time to delete rle : 0.00104522705078125 batch 1 Loaded 25 chid ids of type : 3594 +++++++++++++Number RLEs to save : 6452 TO DO : save crop sub photo not yet done ! save time : 0.44820618629455566 nb_obj : 9 nb_hashtags : 3 time to prepare the origin masks : 3.4354028701782227 time for calcul the mask position with numpy : 0.25992321968078613 nb_pixel_total : 6717254 time to create 1 rle with new method : 0.70387864112854 time for calcul the mask position with numpy : 0.03721499443054199 nb_pixel_total : 13171 time to create 1 rle with old method : 0.018637657165527344 time for calcul the mask position with numpy : 0.02331852912902832 nb_pixel_total : 12131 time to create 1 rle with old method : 0.013720035552978516 time for calcul the mask position with numpy : 0.021221637725830078 nb_pixel_total : 18568 time to create 1 rle with old method : 0.020977020263671875 time for calcul the mask position with numpy : 0.021470069885253906 nb_pixel_total : 48173 time to create 1 rle with old method : 0.055927276611328125 time for calcul the mask position with numpy : 0.022119998931884766 nb_pixel_total : 147345 time to create 1 rle with old method : 0.16564059257507324 time for calcul the mask position with numpy : 0.037175893783569336 nb_pixel_total : 24649 time to create 1 rle with old method : 0.027483701705932617 time for calcul the mask position with numpy : 0.03515982627868652 nb_pixel_total : 11613 time to create 1 rle with old method : 0.01300811767578125 time for calcul the mask position with numpy : 0.038631439208984375 nb_pixel_total : 16853 time to create 1 rle with old method : 0.0189511775970459 time for calcul the mask position with numpy : 0.03504633903503418 nb_pixel_total : 40483 time to create 1 rle with old method : 0.04519152641296387 create new chi : 1.6627984046936035 time to delete rle : 0.0013298988342285156 batch 1 Loaded 19 chid ids of type : 3594 +++++++++++++++Number RLEs to save : 6480 TO DO : save crop sub photo not yet done ! save time : 0.6906948089599609 nb_obj : 57 nb_hashtags : 2 time to prepare the origin masks : 4.216943025588989 time for calcul the mask position with numpy : 0.2808694839477539 nb_pixel_total : 5730026 time to create 1 rle with new method : 0.33728837966918945 time for calcul the mask position with numpy : 0.029330730438232422 nb_pixel_total : 17675 time to create 1 rle with old method : 0.019898653030395508 time for calcul the mask position with numpy : 0.0291750431060791 nb_pixel_total : 17570 time to create 1 rle with old method : 0.019702911376953125 time for calcul the mask position with numpy : 0.029132843017578125 nb_pixel_total : 9280 time to create 1 rle with old method : 0.01065206527709961 time for calcul the mask position with numpy : 0.029053211212158203 nb_pixel_total : 23239 time to create 1 rle with old method : 0.02607417106628418 time for calcul the mask position with numpy : 0.02927231788635254 nb_pixel_total : 30289 time to create 1 rle with old method : 0.034003257751464844 time for calcul the mask position with numpy : 0.029321908950805664 nb_pixel_total : 19793 time to create 1 rle with old method : 0.02209782600402832 time for calcul the mask position with numpy : 0.029844045639038086 nb_pixel_total : 20674 time to create 1 rle with old method : 0.02326512336730957 time for calcul the mask position with numpy : 0.02901911735534668 nb_pixel_total : 19118 time to create 1 rle with old method : 0.02157735824584961 time for calcul the mask position with numpy : 0.029097557067871094 nb_pixel_total : 7759 time to create 1 rle with old method : 0.008895635604858398 time for calcul the mask position with numpy : 0.02911376953125 nb_pixel_total : 37503 time to create 1 rle with old method : 0.04210090637207031 time for calcul the mask position with numpy : 0.02897500991821289 nb_pixel_total : 27825 time to create 1 rle with old method : 0.03106069564819336 time for calcul the mask position with numpy : 0.02899479866027832 nb_pixel_total : 42071 time to create 1 rle with old method : 0.04721474647521973 time for calcul the mask position with numpy : 0.030593156814575195 nb_pixel_total : 5896 time to create 1 rle with old method : 0.006735563278198242 time for calcul the mask position with numpy : 0.028916358947753906 nb_pixel_total : 42913 time to create 1 rle with old method : 0.047844886779785156 time for calcul the mask position with numpy : 0.02900075912475586 nb_pixel_total : 24210 time to create 1 rle with old method : 0.028313398361206055 time for calcul the mask position with numpy : 0.030407190322875977 nb_pixel_total : 31685 time to create 1 rle with old method : 0.035021305084228516 time for calcul the mask position with numpy : 0.029463529586791992 nb_pixel_total : 21295 time to create 1 rle with old method : 0.024010896682739258 time for calcul the mask position with numpy : 0.029275894165039062 nb_pixel_total : 12251 time to create 1 rle with old method : 0.01392364501953125 time for calcul the mask position with numpy : 0.029011011123657227 nb_pixel_total : 14819 time to create 1 rle with old method : 0.017995834350585938 time for calcul the mask position with numpy : 0.028891324996948242 nb_pixel_total : 48232 time to create 1 rle with old method : 0.0541994571685791 time for calcul the mask position with numpy : 0.02933669090270996 nb_pixel_total : 27129 time to create 1 rle with old method : 0.03173065185546875 time for calcul the mask position with numpy : 0.02901911735534668 nb_pixel_total : 25076 time to create 1 rle with old method : 0.0281219482421875 time for calcul the mask position with numpy : 0.03396773338317871 nb_pixel_total : 27919 time to create 1 rle with old method : 0.03144645690917969 time for calcul the mask position with numpy : 0.029109954833984375 nb_pixel_total : 21187 time to create 1 rle with old method : 0.023735761642456055 time for calcul the mask position with numpy : 0.02902984619140625 nb_pixel_total : 10978 time to create 1 rle with old method : 0.012374639511108398 time for calcul the mask position with numpy : 0.02892470359802246 nb_pixel_total : 24886 time to create 1 rle with old method : 0.027991533279418945 time for calcul the mask position with numpy : 0.0294034481048584 nb_pixel_total : 68564 time to create 1 rle with old method : 0.07681536674499512 time for calcul the mask position with numpy : 0.03221583366394043 nb_pixel_total : 35608 time to create 1 rle with old method : 0.052770376205444336 time for calcul the mask position with numpy : 0.03374767303466797 nb_pixel_total : 19487 time to create 1 rle with old method : 0.02483391761779785 time for calcul the mask position with numpy : 0.030385255813598633 nb_pixel_total : 10829 time to create 1 rle with old method : 0.013328075408935547 time for calcul the mask position with numpy : 0.02999734878540039 nb_pixel_total : 17366 time to create 1 rle with old method : 0.021513700485229492 time for calcul the mask position with numpy : 0.03021717071533203 nb_pixel_total : 70458 time to create 1 rle with old method : 0.08536458015441895 time for calcul the mask position with numpy : 0.030588150024414062 nb_pixel_total : 13567 time to create 1 rle with old method : 0.015500307083129883 time for calcul the mask position with numpy : 0.029294729232788086 nb_pixel_total : 23473 time to create 1 rle with old method : 0.02655172348022461 time for calcul the mask position with numpy : 0.02917623519897461 nb_pixel_total : 20164 time to create 1 rle with old method : 0.022710800170898438 time for calcul the mask position with numpy : 0.029021501541137695 nb_pixel_total : 11638 time to create 1 rle with old method : 0.013269662857055664 time for calcul the mask position with numpy : 0.03057861328125 nb_pixel_total : 14324 time to create 1 rle with old method : 0.016029834747314453 time for calcul the mask position with numpy : 0.029273033142089844 nb_pixel_total : 49381 time to create 1 rle with old method : 0.054940223693847656 time for calcul the mask position with numpy : 0.029339075088500977 nb_pixel_total : 26721 time to create 1 rle with old method : 0.030989408493041992 time for calcul the mask position with numpy : 0.029493093490600586 nb_pixel_total : 26722 time to create 1 rle with old method : 0.030333280563354492 time for calcul the mask position with numpy : 0.029940366744995117 nb_pixel_total : 63178 time to create 1 rle with old method : 0.07048869132995605 time for calcul the mask position with numpy : 0.029351234436035156 nb_pixel_total : 19811 time to create 1 rle with old method : 0.022513866424560547 time for calcul the mask position with numpy : 0.028931856155395508 nb_pixel_total : 13813 time to create 1 rle with old method : 0.015676498413085938 time for calcul the mask position with numpy : 0.02933502197265625 nb_pixel_total : 9140 time to create 1 rle with old method : 0.010411500930786133 time for calcul the mask position with numpy : 0.02947092056274414 nb_pixel_total : 9270 time to create 1 rle with old method : 0.01047658920288086 time for calcul the mask position with numpy : 0.03173685073852539 nb_pixel_total : 5931 time to create 1 rle with old method : 0.006784200668334961 time for calcul the mask position with numpy : 0.029186248779296875 nb_pixel_total : 17249 time to create 1 rle with old method : 0.019602060317993164 time for calcul the mask position with numpy : 0.029664039611816406 nb_pixel_total : 14351 time to create 1 rle with old method : 0.016251325607299805 time for calcul the mask position with numpy : 0.02907276153564453 nb_pixel_total : 10581 time to create 1 rle with old method : 0.011972427368164062 time for calcul the mask position with numpy : 0.029518842697143555 nb_pixel_total : 12335 time to create 1 rle with old method : 0.013873577117919922 time for calcul the mask position with numpy : 0.029308795928955078 nb_pixel_total : 6603 time to create 1 rle with old method : 0.0074083805084228516 time for calcul the mask position with numpy : 0.029631376266479492 nb_pixel_total : 15010 time to create 1 rle with old method : 0.016829490661621094 time for calcul the mask position with numpy : 0.02982616424560547 nb_pixel_total : 66842 time to create 1 rle with old method : 0.07623553276062012 time for calcul the mask position with numpy : 0.02947831153869629 nb_pixel_total : 11800 time to create 1 rle with old method : 0.013379573822021484 time for calcul the mask position with numpy : 0.029720544815063477 nb_pixel_total : 8985 time to create 1 rle with old method : 0.010239839553833008 time for calcul the mask position with numpy : 0.02933335304260254 nb_pixel_total : 5033 time to create 1 rle with old method : 0.005803346633911133 time for calcul the mask position with numpy : 0.029724836349487305 nb_pixel_total : 10708 time to create 1 rle with old method : 0.01226353645324707 create new chi : 4.023956060409546 time to delete rle : 0.00503230094909668 batch 1 Loaded 115 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 26472 TO DO : save crop sub photo not yet done ! save time : 2.636714220046997 nb_obj : 47 nb_hashtags : 5 time to prepare the origin masks : 4.117985725402832 time for calcul the mask position with numpy : 0.6529030799865723 nb_pixel_total : 5889066 time to create 1 rle with new method : 0.623781681060791 time for calcul the mask position with numpy : 0.029993295669555664 nb_pixel_total : 12296 time to create 1 rle with old method : 0.015605926513671875 time for calcul the mask position with numpy : 0.03190016746520996 nb_pixel_total : 4796 time to create 1 rle with old method : 0.005450725555419922 time for calcul the mask position with numpy : 0.029778003692626953 nb_pixel_total : 24075 time to create 1 rle with old method : 0.027049779891967773 time for calcul the mask position with numpy : 0.029522418975830078 nb_pixel_total : 15332 time to create 1 rle with old method : 0.018358945846557617 time for calcul the mask position with numpy : 0.029203176498413086 nb_pixel_total : 10014 time to create 1 rle with old method : 0.011484622955322266 time for calcul the mask position with numpy : 0.02972269058227539 nb_pixel_total : 11219 time to create 1 rle with old method : 0.012746334075927734 time for calcul the mask position with numpy : 0.03056192398071289 nb_pixel_total : 21602 time to create 1 rle with old method : 0.02438211441040039 time for calcul the mask position with numpy : 0.030057907104492188 nb_pixel_total : 114857 time to create 1 rle with old method : 0.12818026542663574 time for calcul the mask position with numpy : 0.029549598693847656 nb_pixel_total : 16059 time to create 1 rle with old method : 0.0180966854095459 time for calcul the mask position with numpy : 0.029232501983642578 nb_pixel_total : 7872 time to create 1 rle with old method : 0.008943796157836914 time for calcul the mask position with numpy : 0.029185056686401367 nb_pixel_total : 16518 time to create 1 rle with old method : 0.018625259399414062 time for calcul the mask position with numpy : 0.033479928970336914 nb_pixel_total : 51262 time to create 1 rle with old method : 0.058054447174072266 time for calcul the mask position with numpy : 0.0293121337890625 nb_pixel_total : 6110 time to create 1 rle with old method : 0.007092714309692383 time for calcul the mask position with numpy : 0.03049921989440918 nb_pixel_total : 26764 time to create 1 rle with old method : 0.031610965728759766 time for calcul the mask position with numpy : 0.029318571090698242 nb_pixel_total : 21520 time to create 1 rle with old method : 0.02430438995361328 time for calcul the mask position with numpy : 0.029103517532348633 nb_pixel_total : 32038 time to create 1 rle with old method : 0.035932302474975586 time for calcul the mask position with numpy : 0.030817747116088867 nb_pixel_total : 14266 time to create 1 rle with old method : 0.01605844497680664 time for calcul the mask position with numpy : 0.028455734252929688 nb_pixel_total : 18803 time to create 1 rle with old method : 0.021924257278442383 time for calcul the mask position with numpy : 0.03308534622192383 nb_pixel_total : 14599 time to create 1 rle with old method : 0.016559839248657227 time for calcul the mask position with numpy : 0.029124021530151367 nb_pixel_total : 14876 time to create 1 rle with old method : 0.017917156219482422 time for calcul the mask position with numpy : 0.02973484992980957 nb_pixel_total : 47030 time to create 1 rle with old method : 0.05498218536376953 time for calcul the mask position with numpy : 0.029321908950805664 nb_pixel_total : 34017 time to create 1 rle with old method : 0.0381011962890625 time for calcul the mask position with numpy : 0.029034137725830078 nb_pixel_total : 11843 time to create 1 rle with old method : 0.013114213943481445 time for calcul the mask position with numpy : 0.028670549392700195 nb_pixel_total : 36542 time to create 1 rle with old method : 0.040975332260131836 time for calcul the mask position with numpy : 0.031079769134521484 nb_pixel_total : 28642 time to create 1 rle with old method : 0.03285717964172363 time for calcul the mask position with numpy : 0.03166985511779785 nb_pixel_total : 61848 time to create 1 rle with old method : 0.06900405883789062 time for calcul the mask position with numpy : 0.029113054275512695 nb_pixel_total : 14743 time to create 1 rle with old method : 0.016548871994018555 time for calcul the mask position with numpy : 0.02918696403503418 nb_pixel_total : 39076 time to create 1 rle with old method : 0.043901920318603516 time for calcul the mask position with numpy : 0.03299975395202637 nb_pixel_total : 30565 time to create 1 rle with old method : 0.03671455383300781 time for calcul the mask position with numpy : 0.028945207595825195 nb_pixel_total : 66172 time to create 1 rle with old method : 0.0794527530670166 time for calcul the mask position with numpy : 0.029818296432495117 nb_pixel_total : 21467 time to create 1 rle with old method : 0.02569103240966797 time for calcul the mask position with numpy : 0.030099153518676758 nb_pixel_total : 31106 time to create 1 rle with old method : 0.03760337829589844 time for calcul the mask position with numpy : 0.029453516006469727 nb_pixel_total : 18949 time to create 1 rle with old method : 0.022927045822143555 time for calcul the mask position with numpy : 0.029979228973388672 nb_pixel_total : 11552 time to create 1 rle with old method : 0.014107465744018555 time for calcul the mask position with numpy : 0.029819965362548828 nb_pixel_total : 11337 time to create 1 rle with old method : 0.016546964645385742 time for calcul the mask position with numpy : 0.040837764739990234 nb_pixel_total : 18585 time to create 1 rle with old method : 0.020818471908569336 time for calcul the mask position with numpy : 0.02858281135559082 nb_pixel_total : 9540 time to create 1 rle with old method : 0.010744571685791016 time for calcul the mask position with numpy : 0.028643369674682617 nb_pixel_total : 17531 time to create 1 rle with old method : 0.019252538681030273 time for calcul the mask position with numpy : 0.02883172035217285 nb_pixel_total : 38252 time to create 1 rle with old method : 0.04222822189331055 time for calcul the mask position with numpy : 0.02863764762878418 nb_pixel_total : 23206 time to create 1 rle with old method : 0.025696277618408203 time for calcul the mask position with numpy : 0.028682947158813477 nb_pixel_total : 20433 time to create 1 rle with old method : 0.02292776107788086 time for calcul the mask position with numpy : 0.028501033782958984 nb_pixel_total : 11287 time to create 1 rle with old method : 0.012540102005004883 time for calcul the mask position with numpy : 0.029319286346435547 nb_pixel_total : 22245 time to create 1 rle with old method : 0.025446176528930664 time for calcul the mask position with numpy : 0.029460430145263672 nb_pixel_total : 6804 time to create 1 rle with old method : 0.0076978206634521484 time for calcul the mask position with numpy : 0.02895069122314453 nb_pixel_total : 45217 time to create 1 rle with old method : 0.04967474937438965 time for calcul the mask position with numpy : 0.028006315231323242 nb_pixel_total : 7547 time to create 1 rle with old method : 0.008154869079589844 time for calcul the mask position with numpy : 0.028647422790527344 nb_pixel_total : 20760 time to create 1 rle with old method : 0.023427486419677734 create new chi : 4.054667234420776 time to delete rle : 0.0038089752197265625 batch 1 Loaded 95 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 23035 TO DO : save crop sub photo not yet done ! save time : 3.291674852371216 nb_obj : 56 nb_hashtags : 5 time to prepare the origin masks : 4.009292840957642 time for calcul the mask position with numpy : 0.5912301540374756 nb_pixel_total : 5553374 time to create 1 rle with new method : 0.6853194236755371 time for calcul the mask position with numpy : 0.02891397476196289 nb_pixel_total : 7019 time to create 1 rle with old method : 0.008065938949584961 time for calcul the mask position with numpy : 0.028994321823120117 nb_pixel_total : 13838 time to create 1 rle with old method : 0.015607833862304688 time for calcul the mask position with numpy : 0.029163599014282227 nb_pixel_total : 8480 time to create 1 rle with old method : 0.009627819061279297 time for calcul the mask position with numpy : 0.02922224998474121 nb_pixel_total : 37090 time to create 1 rle with old method : 0.04160356521606445 time for calcul the mask position with numpy : 0.031114816665649414 nb_pixel_total : 14225 time to create 1 rle with old method : 0.01693558692932129 time for calcul the mask position with numpy : 0.031036376953125 nb_pixel_total : 8327 time to create 1 rle with old method : 0.010385274887084961 time for calcul the mask position with numpy : 0.031000614166259766 nb_pixel_total : 27862 time to create 1 rle with old method : 0.031641244888305664 time for calcul the mask position with numpy : 0.029251575469970703 nb_pixel_total : 66887 time to create 1 rle with old method : 0.07520604133605957 time for calcul the mask position with numpy : 0.02927088737487793 nb_pixel_total : 18817 time to create 1 rle with old method : 0.021175861358642578 time for calcul the mask position with numpy : 0.029547929763793945 nb_pixel_total : 15174 time to create 1 rle with old method : 0.01730823516845703 time for calcul the mask position with numpy : 0.029521942138671875 nb_pixel_total : 33815 time to create 1 rle with old method : 0.03835773468017578 time for calcul the mask position with numpy : 0.02956986427307129 nb_pixel_total : 18200 time to create 1 rle with old method : 0.020770549774169922 time for calcul the mask position with numpy : 0.02944040298461914 nb_pixel_total : 72631 time to create 1 rle with old method : 0.08131122589111328 time for calcul the mask position with numpy : 0.029085874557495117 nb_pixel_total : 42175 time to create 1 rle with old method : 0.046957969665527344 time for calcul the mask position with numpy : 0.029176712036132812 nb_pixel_total : 39377 time to create 1 rle with old method : 0.04383420944213867 time for calcul the mask position with numpy : 0.029270172119140625 nb_pixel_total : 24621 time to create 1 rle with old method : 0.03450441360473633 time for calcul the mask position with numpy : 0.032622337341308594 nb_pixel_total : 14967 time to create 1 rle with old method : 0.020526647567749023 time for calcul the mask position with numpy : 0.03212690353393555 nb_pixel_total : 20592 time to create 1 rle with old method : 0.029803991317749023 time for calcul the mask position with numpy : 0.0310518741607666 nb_pixel_total : 43665 time to create 1 rle with old method : 0.04938387870788574 time for calcul the mask position with numpy : 0.029224872589111328 nb_pixel_total : 39144 time to create 1 rle with old method : 0.043624162673950195 time for calcul the mask position with numpy : 0.02904224395751953 nb_pixel_total : 15622 time to create 1 rle with old method : 0.017621994018554688 time for calcul the mask position with numpy : 0.029098033905029297 nb_pixel_total : 36327 time to create 1 rle with old method : 0.040480613708496094 time for calcul the mask position with numpy : 0.029593706130981445 nb_pixel_total : 85081 time to create 1 rle with old method : 0.10720229148864746 time for calcul the mask position with numpy : 0.03247404098510742 nb_pixel_total : 64498 time to create 1 rle with old method : 0.12659907341003418 time for calcul the mask position with numpy : 0.02926921844482422 nb_pixel_total : 36618 time to create 1 rle with old method : 0.04126739501953125 time for calcul the mask position with numpy : 0.029124736785888672 nb_pixel_total : 36255 time to create 1 rle with old method : 0.040552616119384766 time for calcul the mask position with numpy : 0.029230356216430664 nb_pixel_total : 55298 time to create 1 rle with old method : 0.06201934814453125 time for calcul the mask position with numpy : 0.0291292667388916 nb_pixel_total : 36504 time to create 1 rle with old method : 0.04132270812988281 time for calcul the mask position with numpy : 0.030841350555419922 nb_pixel_total : 12797 time to create 1 rle with old method : 0.014430999755859375 time for calcul the mask position with numpy : 0.031023263931274414 nb_pixel_total : 34406 time to create 1 rle with old method : 0.038640499114990234 time for calcul the mask position with numpy : 0.0316162109375 nb_pixel_total : 21686 time to create 1 rle with old method : 0.02461409568786621 time for calcul the mask position with numpy : 0.02925872802734375 nb_pixel_total : 11986 time to create 1 rle with old method : 0.015377283096313477 time for calcul the mask position with numpy : 0.029189109802246094 nb_pixel_total : 20664 time to create 1 rle with old method : 0.027705669403076172 time for calcul the mask position with numpy : 0.031237363815307617 nb_pixel_total : 51081 time to create 1 rle with old method : 0.0758218765258789 time for calcul the mask position with numpy : 0.03351235389709473 nb_pixel_total : 14758 time to create 1 rle with old method : 0.02747321128845215 time for calcul the mask position with numpy : 0.035634756088256836 nb_pixel_total : 2466 time to create 1 rle with old method : 0.004477262496948242 time for calcul the mask position with numpy : 0.03630208969116211 nb_pixel_total : 10213 time to create 1 rle with old method : 0.019002437591552734 time for calcul the mask position with numpy : 0.03204798698425293 nb_pixel_total : 51287 time to create 1 rle with old method : 0.06116843223571777 time for calcul the mask position with numpy : 0.03224468231201172 nb_pixel_total : 37362 time to create 1 rle with old method : 0.041962385177612305 time for calcul the mask position with numpy : 0.02933955192565918 nb_pixel_total : 16384 time to create 1 rle with old method : 0.018564701080322266 time for calcul the mask position with numpy : 0.02908015251159668 nb_pixel_total : 8141 time to create 1 rle with old method : 0.009232044219970703 time for calcul the mask position with numpy : 0.029283523559570312 nb_pixel_total : 28677 time to create 1 rle with old method : 0.03833627700805664 time for calcul the mask position with numpy : 0.02915191650390625 nb_pixel_total : 4234 time to create 1 rle with old method : 0.004963874816894531 time for calcul the mask position with numpy : 0.029366493225097656 nb_pixel_total : 42535 time to create 1 rle with old method : 0.0513300895690918 time for calcul the mask position with numpy : 0.0293729305267334 nb_pixel_total : 26096 time to create 1 rle with old method : 0.04221653938293457 time for calcul the mask position with numpy : 0.0323026180267334 nb_pixel_total : 28182 time to create 1 rle with old method : 0.03331875801086426 time for calcul the mask position with numpy : 0.036615610122680664 nb_pixel_total : 10165 time to create 1 rle with old method : 0.012135744094848633 time for calcul the mask position with numpy : 0.029745817184448242 nb_pixel_total : 2905 time to create 1 rle with old method : 0.0033457279205322266 time for calcul the mask position with numpy : 0.030755281448364258 nb_pixel_total : 5941 time to create 1 rle with old method : 0.0067157745361328125 time for calcul the mask position with numpy : 0.03019237518310547 nb_pixel_total : 8616 time to create 1 rle with old method : 0.009864091873168945 time for calcul the mask position with numpy : 0.029530763626098633 nb_pixel_total : 23875 time to create 1 rle with old method : 0.02740764617919922 time for calcul the mask position with numpy : 0.030488014221191406 nb_pixel_total : 16317 time to create 1 rle with old method : 0.019499540328979492 time for calcul the mask position with numpy : 0.0290834903717041 nb_pixel_total : 34897 time to create 1 rle with old method : 0.03998088836669922 time for calcul the mask position with numpy : 0.03217673301696777 nb_pixel_total : 10551 time to create 1 rle with old method : 0.014816761016845703 time for calcul the mask position with numpy : 0.029192209243774414 nb_pixel_total : 9827 time to create 1 rle with old method : 0.011022090911865234 time for calcul the mask position with numpy : 0.02863907814025879 nb_pixel_total : 17708 time to create 1 rle with old method : 0.019651174545288086 create new chi : 4.862462997436523 time to delete rle : 0.004201650619506836 batch 1 Loaded 113 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 26117 TO DO : save crop sub photo not yet done ! save time : 2.06807017326355 map_output_result : {1349085160: (0.0, 'Should be the crop_list due to order', 0), 1349085142: (0.0, 'Should be the crop_list due to order', 0), 1349085138: (0.0, 'Should be the crop_list due to order', 0), 1349085131: (0.0, 'Should be the crop_list due to order', 0), 1349085127: (0.0, 'Should be the crop_list due to order', 0), 1348950350: (0.0, 'Should be the crop_list due to order', 0), 1348949687: (0.0, 'Should be the crop_list due to order', 0), 1348949682: (0.0, 'Should be the crop_list due to order', 0), 1348949676: (0.0, 'Should be the crop_list due to order', 0), 1348949672: (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 [1349085160, 1349085142, 1349085138, 1349085131, 1349085127, 1348950350, 1348949687, 1348949682, 1348949676, 1348949672] Looping around the photos to save general results len do output : 10 /1349085160.Didn't retrieve data . /1349085142.Didn't retrieve data . /1349085138.Didn't retrieve data . /1349085131.Didn't retrieve data . /1349085127.Didn't retrieve data . /1348950350.Didn't retrieve data . /1348949687.Didn't retrieve data . /1348949682.Didn't retrieve data . /1348949676.Didn't retrieve data . /1348949672.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, '2710822') ('3318', '21925661', '1349085160', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085142', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085138', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085131', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085127', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348950350', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949687', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949682', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949676', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949672', None, None, None, None, None, '2710822') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 30 time used for this insertion : 0.01393437385559082 save_final save missing photos in datou_result : time spend for datou_step_exec : 93.91442775726318 time spend to save output : 0.014436721801757812 total time spend for step 3 : 93.92886447906494 step4:ventilate_hashtags_in_portfolio Mon Mar 31 22:59:04 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 : 21925661 get user id for portfolio 21925661 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`=21925661 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('mal_croppe','papier','pet_fonce','autre','flou','background','environnement','metal','pet_clair','pehd','carton')) 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`=21925661 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('mal_croppe','papier','pet_fonce','autre','flou','background','environnement','metal','pet_clair','pehd','carton')) 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`=21925661 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('mal_croppe','papier','pet_fonce','autre','flou','background','environnement','metal','pet_clair','pehd','carton')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://www.fotonower.com/velours/21927023,21927024,21927025,21927026,21927027,21927028,21927029,21927030,21927031,21927032,21927033?tags=mal_croppe,papier,pet_fonce,autre,flou,background,environnement,metal,pet_clair,pehd,carton Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1349085160, 1349085142, 1349085138, 1349085131, 1349085127, 1348950350, 1348949687, 1348949682, 1348949676, 1348949672] Looping around the photos to save general results len do output : 1 /21925661. 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, '2710822') ('3318', '21925661', '1349085160', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085142', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085138', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085131', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085127', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348950350', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949687', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949682', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949676', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949672', None, None, None, None, None, '2710822') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 11 time used for this insertion : 0.013696432113647461 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.7062387466430664 time spend to save output : 0.014017105102539062 total time spend for step 4 : 1.7202558517456055 step5:final Mon Mar 31 22:59:06 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 : {1349085160: ('0.14630428184005087',), 1349085142: ('0.14630428184005087',), 1349085138: ('0.14630428184005087',), 1349085131: ('0.14630428184005087',), 1349085127: ('0.14630428184005087',), 1348950350: ('0.14630428184005087',), 1348949687: ('0.14630428184005087',), 1348949682: ('0.14630428184005087',), 1348949676: ('0.14630428184005087',), 1348949672: ('0.14630428184005087',)} new output for save of step final : {1349085160: ('0.14630428184005087',), 1349085142: ('0.14630428184005087',), 1349085138: ('0.14630428184005087',), 1349085131: ('0.14630428184005087',), 1349085127: ('0.14630428184005087',), 1348950350: ('0.14630428184005087',), 1348949687: ('0.14630428184005087',), 1348949682: ('0.14630428184005087',), 1348949676: ('0.14630428184005087',), 1348949672: ('0.14630428184005087',)} [1349085160, 1349085142, 1349085138, 1349085131, 1349085127, 1348950350, 1348949687, 1348949682, 1348949676, 1348949672] Looping around the photos to save general results len do output : 10 /1349085160.Didn't retrieve data . /1349085142.Didn't retrieve data . /1349085138.Didn't retrieve data . /1349085131.Didn't retrieve data . /1349085127.Didn't retrieve data . /1348950350.Didn't retrieve data . /1348949687.Didn't retrieve data . /1348949682.Didn't retrieve data . /1348949676.Didn't retrieve data . /1348949672.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, '2710822') ('3318', '21925661', '1349085160', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085142', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085138', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085131', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085127', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348950350', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949687', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949682', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949676', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949672', None, None, None, None, None, '2710822') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 30 time used for this insertion : 0.014477252960205078 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.13437747955322266 time spend to save output : 0.015283823013305664 total time spend for step 5 : 0.14966130256652832 step6:blur_detection Mon Mar 31 22:59:06 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/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8.jpg resize: (2160, 3264) 1349085160 -3.7521919632588103 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8.jpg resize: (2160, 3264) 1349085142 -3.315705711673113 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700.jpg resize: (2160, 3264) 1349085138 -4.327169341799626 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989.jpg resize: (2160, 3264) 1349085131 -3.267217606692126 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51.jpg resize: (2160, 3264) 1349085127 -3.71642920845779 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283.jpg resize: (2160, 3264) 1348950350 -0.5940600124790875 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce.jpg resize: (2160, 3264) 1348949687 -2.5896591169763483 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1.jpg resize: (2160, 3264) 1348949682 -5.942095960750408 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627.jpg resize: (2160, 3264) 1348949676 -4.183820105760761 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22.jpg resize: (2160, 3264) 1348949672 -3.4861684865469154 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771684_0.png resize: (112, 69) 1349115302 -0.49362732264009457 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771706_0.png resize: (216, 95) 1349115304 -4.482017588407129 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771690_0.png resize: (279, 149) 1349115305 -2.1799072267773703 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771705_0.png resize: (500, 419) 1349115306 -2.45971226658154 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771707_0.png resize: (165, 116) 1349115308 -2.2764043593768797 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771688_0.png resize: (338, 257) 1349115309 -2.2043092637417527 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771696_0.png resize: (200, 379) 1349115310 -3.554369354525658 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771708_0.png resize: (149, 170) 1349115312 -3.1185206984096094 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771683_0.png resize: (105, 184) 1349115313 -3.3413048933451397 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771689_0.png resize: (169, 112) 1349115314 -2.598732334459943 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771700_0.png resize: (222, 96) 1349115316 -2.2548909669356196 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771687_0.png resize: (215, 182) 1349115318 -3.69695211893377 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771694_0.png resize: (162, 214) 1349115319 -2.9297059275189685 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771681_0.png resize: (185, 196) 1349115321 -0.6640358240980415 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771686_0.png resize: (247, 501) 1349115322 -3.8302029709926892 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771709_0.png resize: (645, 506) 1349115323 -3.1219544053838946 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771703_0.png resize: (464, 577) 1349115325 -4.349768595621834 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771682_0.png resize: (462, 232) 1349115326 -1.4040106533929577 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771692_0.png resize: (202, 152) 1349115327 -3.1708056366901585 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771693_0.png resize: (290, 353) 1349115329 -3.3299323089284116 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771698_0.png resize: (294, 296) 1349115331 -1.9485423183935726 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771710_0.png resize: (215, 113) 1349115332 -1.8799554968164067 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771742_0.png resize: (163, 87) 1349115335 -2.2057543262909394 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771719_0.png resize: (98, 168) 1349115336 -2.6185937494854916 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771714_0.png resize: (114, 234) 1349115337 -1.2635206588172117 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771713_0.png resize: (381, 394) 1349115339 -2.4719032894519826 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771718_0.png resize: (165, 98) 1349115340 -1.1503414144689714 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771727_0.png resize: (148, 172) 1349115341 -2.1511045995848392 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771735_0.png resize: (186, 205) 1349115343 -2.090674157787813 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771747_0.png resize: (131, 144) 1349115344 -2.289423860428944 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771712_0.png resize: (129, 129) 1349115345 -2.145589737404132 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771717_0.png resize: (233, 228) 1349115347 -1.8764063983166863 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771716_0.png resize: (187, 171) 1349115348 -2.3000229332640294 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771723_0.png resize: (448, 395) 1349115349 -2.017998989924215 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771728_0.png resize: (85, 113) 1349115351 -0.649905401125074 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771733_0.png resize: (66, 94) 1349115352 -0.5354148479662129 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771743_0.png resize: (199, 141) 1349115354 -1.637209896494986 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771724_0.png resize: (205, 127) 1349115355 -1.8417335153011178 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771737_0.png resize: (264, 193) 1349115356 -0.5966695431579797 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771741_0.png resize: (306, 236) 1349115358 -2.99150510516905 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771731_0.png resize: (256, 137) 1349115359 -1.3433708790115626 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771726_0.png resize: (163, 170) 1349115360 -1.3217821008374158 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771730_0.png resize: (131, 156) 1349115362 -3.470616448915459 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771720_0.png resize: (123, 206) 1349115363 -2.8811225623950336 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771738_0.png resize: (265, 165) 1349115364 -2.5847640122599183 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771736_0.png resize: (161, 162) 1349115366 -3.447489302794546 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771715_0.png resize: (128, 182) 1349115367 -2.002846244742674 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771745_0.png resize: (273, 255) 1349115369 -2.6215980517192965 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771732_0.png resize: (94, 189) 1349115370 -3.15349738082881 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771729_0.png resize: (125, 238) 1349115371 -3.103075635625859 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771762_0.png resize: (333, 233) 1349115373 -2.7550394847937523 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771772_0.png resize: (224, 174) 1349115374 -1.6086509784604637 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771756_0.png resize: (102, 150) 1349115375 -1.4059475965625143 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771783_0.png resize: (186, 263) 1349115377 -2.255361127165461 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771757_0.png resize: (227, 448) 1349115379 -2.5478359163623887 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771784_0.png resize: (122, 92) 1349115380 -2.562494450589537 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771776_0.png resize: (216, 299) 1349115382 -3.198369482808841 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771759_0.png resize: (118, 135) 1349115383 -1.7395103321188827 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771750_0.png resize: (182, 212) 1349115384 -2.3889290722119148 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771766_0.png resize: (181, 220) 1349115386 -2.699677346719024 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771761_0.png resize: (197, 157) 1349115387 -3.0326161934450395 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771758_0.png resize: (255, 178) 1349115389 -3.684167890501851 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771773_0.png resize: (267, 91) 1349115390 -2.7266205434110296 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771775_0.png resize: (93, 146) 1349115391 -2.9991274708454667 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771765_0.png resize: (324, 146) 1349115393 -3.159826872803563 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771753_0.png resize: (139, 117) 1349115394 -2.242704078478616 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771768_0.png resize: (279, 299) 1349115395 -2.3742613478232975 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771771_0.png resize: (194, 128) 1349115397 -2.571077947999488 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771752_0.png resize: (359, 258) 1349115398 -2.522973496984853 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771769_0.png resize: (478, 585) 1349115399 -2.226974390906655 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771779_0.png resize: (102, 120) 1349115401 0.37088203785987367 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771767_0.png resize: (247, 249) 1349115402 -1.8030719150914694 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771782_0.png resize: (87, 124) 1349115403 -0.7844737267826744 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771755_0.png resize: (249, 231) 1349115405 -2.5583879866728085 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771763_0.png resize: (235, 221) 1349115406 -3.2963132448611767 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771799_0.png resize: (208, 191) 1349115407 -1.8941364948151844 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771803_0.png resize: (177, 46) 1349115409 -4.05322537884066 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771822_0.png resize: (393, 211) 1349115410 -1.451450029786507 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771801_0.png resize: (238, 215) 1349115411 -2.665980428404251 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771807_0.png resize: (346, 271) 1349115413 -2.1269166610335892 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771800_0.png resize: (150, 176) 1349115414 -2.392289384170547 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771790_0.png resize: (217, 139) 1349115415 -1.1039539860393974 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771816_0.png resize: (78, 151) 1349115417 -2.1599531434044286 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771831_0.png resize: (131, 152) 1349115418 -1.3242560031291373 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771792_0.png resize: (143, 115) 1349115419 -1.5131684743464129 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771809_0.png resize: (107, 66) 1349115421 -0.5075731445688202 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771789_0.png resize: (169, 253) 1349115422 -1.7778920206584916 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771797_0.png resize: (122, 139) 1349115423 -2.1964190216017743 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771829_0.png resize: (175, 193) 1349115425 0.16035657562025468 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771813_0.png resize: (125, 88) 1349115427 -0.8204611052806489 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771794_0.png resize: (258, 247) 1349115428 -0.6386416975159201 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771795_0.png resize: (238, 149) 1349115430 -2.8826609796379827 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771802_0.png resize: (139, 115) 1349115431 3.911029279203628 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771832_0.png resize: (55, 94) 1349115432 -0.5544784927999273 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771808_0.png resize: (177, 222) 1349115434 -1.3881932276696214 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771793_0.png resize: (199, 238) 1349115435 -0.6092210840134429 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771833_0.png resize: (206, 186) 1349115436 4.858637460033698 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771818_0.png resize: (183, 93) 1349115438 -0.8762417479347677 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771820_0.png resize: (260, 207) 1349115439 -2.382164189143756 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771815_0.png resize: (134, 170) 1349115440 -2.5194464240911456 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771811_0.png resize: (155, 156) 1349115442 -0.5133823536835241 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771798_0.png resize: (227, 171) 1349115443 -0.9484533053706944 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771812_0.png resize: (234, 127) 1349115446 -2.219233931715062 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771810_0.png resize: (310, 410) 1349115447 -1.7967306049443779 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771788_0.png resize: (205, 100) 1349115448 -2.868234155464934 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771785_0.png resize: (320, 262) 1349115450 -1.4489705814222813 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771787_0.png resize: (197, 276) 1349115451 0.17764424368081452 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771821_0.png resize: (573, 455) 1349115452 -3.2601526120731696 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771786_0.png resize: (171, 137) 1349115454 -1.9375059193745356 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771828_0.png resize: (155, 135) 1349115455 -0.998994208544067 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771827_0.png resize: (174, 236) 1349115456 -3.086824804707345 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771819_0.png resize: (165, 390) 1349115459 -2.9595441303496024 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771817_0.png resize: (174, 119) 1349115460 -0.029470167034995033 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771805_0.png resize: (143, 141) 1349115461 -3.5770003500614718 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771791_0.png resize: (241, 85) 1349115463 -2.0937552489942655 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771839_0.png resize: (187, 170) 1349115464 -1.667806135979901 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771836_0.png resize: (213, 213) 1349115465 -1.9312294771953256 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771847_0.png resize: (196, 195) 1349115467 -2.125983792158201 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771855_0.png resize: (100, 182) 1349115468 -3.052525987657167 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771838_0.png resize: (65, 83) 1349115469 -0.6042494785811275 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771865_0.png resize: (107, 146) 1349115471 -1.4503832154175833 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771854_0.png resize: (193, 420) 1349115472 -2.5504469384969193 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771851_0.png resize: (182, 243) 1349115473 -1.8751896036470719 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771835_0.png resize: (169, 281) 1349115475 -5.476073823674775 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771859_0.png resize: (163, 90) 1349115476 -3.068559868682054 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771849_0.png resize: (300, 178) 1349115478 -2.9903546724721415 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771858_0.png resize: (118, 139) 1349115479 -3.5882619517067513 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771862_0.png resize: (67, 113) 1349115480 1.3324257865325755 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771837_0.png resize: (217, 161) 1349115482 -1.5646526008790749 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771845_0.png resize: (184, 158) 1349115483 -3.274611447057465 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771844_0.png resize: (195, 116) 1349115484 -1.644691987322145 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771843_0.png resize: (215, 338) 1349115486 -2.709990273562817 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771842_0.png resize: (81, 135) 1349115487 -3.115821147552772 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771852_0.png resize: (270, 171) 1349115488 -2.4144277556611744 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771850_0.png resize: (168, 120) 1349115490 -2.3840517901492633 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771860_0.png resize: (275, 343) 1349115492 -3.311241606032625 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771834_0.png resize: (341, 245) 1349115493 -1.875403237469465 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771853_0.png resize: (500, 368) 1349115495 -3.151369188060653 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771841_0.png resize: (98, 172) 1349115496 -0.37129858557916234 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771856_0.png resize: (202, 87) 1349115497 -1.9845796692387774 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771866_0.png resize: (321, 356) 1349115499 -2.295704398133737 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771863_0.png resize: (361, 318) 1349115500 -2.1278608316394343 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771840_0.png resize: (113, 113) 1349115502 -0.49701261915876627 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771878_0.png resize: (138, 130) 1349115503 0.8652296390089682 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771869_0.png resize: (138, 131) 1349115504 -1.3723720956631316 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771872_0.png resize: (289, 235) 1349115506 -2.247455942671209 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771875_0.png resize: (152, 232) 1349115507 -0.22758307787823304 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771874_0.png resize: (196, 136) 1349115509 -2.8225554995783124 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771876_0.png resize: (137, 123) 1349115510 0.5421816775270317 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771867_0.png resize: (237, 184) 1349115511 0.11495857273835411 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771881_0.png resize: (100, 172) 1349115513 -1.598849149645804 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771885_0.png resize: (121, 206) 1349115514 -2.5181457285882636 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771884_0.png resize: (280, 285) 1349115515 -2.403397788820154 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771879_0.png resize: (347, 317) 1349115517 -1.0553076802219439 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771886_0.png resize: (99, 146) 1349115518 -1.6253826170019716 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771882_0.png resize: (260, 161) 1349115519 -1.9663928648695856 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771896_0.png resize: (118, 127) 1349115521 -1.6925012753190918 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771931_0.png resize: (250, 359) 1349115522 -1.7433124959946802 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771914_0.png resize: (105, 82) 1349115523 -1.3685383936780444 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771902_0.png resize: (187, 127) 1349115525 -2.856844486462376 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771890_0.png resize: (321, 173) 1349115526 -3.0025521789188696 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771891_0.png resize: (179, 219) 1349115527 -3.732745698095818 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771913_0.png resize: (286, 295) 1349115529 -3.1720296139177577 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771905_0.png resize: (345, 158) 1349115530 -3.3930526362925306 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771937_0.png resize: (118, 159) 1349115531 -1.2717942632888743 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771933_0.png resize: (128, 60) 1349115533 -2.778768026471478 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771906_0.png resize: (129, 150) 1349115534 -3.5669359076164424 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771924_0.png resize: (428, 211) 1349115535 -4.204499007372023 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771941_0.png resize: (137, 148) 1349115538 -1.885291949977392 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771923_0.png resize: (322, 155) 1349115539 -3.7786999299916015 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771935_0.png resize: (158, 141) 1349115540 -3.3591046101856996 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771920_0.png resize: (181, 154) 1349115542 -3.7690035333150504 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771889_0.png resize: (208, 76) 1349115543 -1.1269282510320386 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771894_0.png resize: (300, 175) 1349115544 -3.049028272997939 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771903_0.png resize: (143, 78) 1349115546 -2.4907454505371533 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771919_0.png resize: (119, 183) 1349115547 -2.5715488923030416 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771888_0.png resize: (99, 113) 1349115548 -2.8667848564045064 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771907_0.png resize: (235, 347) 1349115550 -3.8154749776337393 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771917_0.png resize: (214, 189) 1349115551 -3.9196084197994434 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771928_0.png resize: (112, 214) 1349115553 -3.0797489176846575 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771897_0.png resize: (402, 189) 1349115555 -3.1440079848558256 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771936_0.png resize: (206, 166) 1349115556 -2.2719143487328113 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771915_0.png resize: (150, 137) 1349115557 -0.1387413088242356 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771909_0.png resize: (136, 272) 1349115559 -1.0994786481366512 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771929_0.png resize: (257, 242) 1349115560 -4.733829612322892 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771895_0.png resize: (124, 111) 1349115561 -2.5742535092993046 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771918_0.png resize: (145, 176) 1349115563 -0.6895057562158534 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771904_0.png resize: (172, 300) 1349115564 -3.66141252464533 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771930_0.png resize: (294, 267) 1349115565 -2.482695545981246 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771939_0.png resize: (92, 192) 1349115567 -4.676979269531209 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771911_0.png resize: (114, 83) 1349115568 -4.255905974594247 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771908_0.png resize: (96, 158) 1349115569 -3.8779178796099676 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771943_0.png resize: (339, 125) 1349115571 -3.4572839274878397 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771932_0.png resize: (182, 199) 1349115572 -3.381657106919977 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771898_0.png resize: (166, 125) 1349115573 -3.129111740499202 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771934_0.png resize: (181, 175) 1349115575 -4.3343497329355065 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771916_0.png resize: (181, 140) 1349115576 -3.2662486264677684 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771912_0.png resize: (226, 83) 1349115577 -3.401390662496325 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771892_0.png resize: (185, 212) 1349115579 -3.945635356706414 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771910_0.png resize: (81, 182) 1349115580 -2.5906961341611474 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771921_0.png resize: (108, 111) 1349115581 -2.827659539688314 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771925_0.png resize: (154, 127) 1349115583 -3.538688132091917 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771926_0.png resize: (195, 134) 1349115584 -3.740546932668044 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771963_0.png resize: (291, 213) 1349115585 -1.685219081908673 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771977_0.png resize: (290, 132) 1349115587 -2.672070465430733 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771987_0.png resize: (98, 150) 1349115588 -1.083040114144934 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771958_0.png resize: (92, 104) 1349115590 -0.885840127715721 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771969_0.png resize: (227, 362) 1349115591 -2.9107209134260685 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771962_0.png resize: (248, 170) 1349115592 -2.5051150512789766 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771956_0.png resize: (276, 214) 1349115594 -2.270254410135762 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771984_0.png resize: (108, 226) 1349115595 -0.522026105406367 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771955_0.png resize: (175, 189) 1349115596 -2.697707807849611 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771970_0.png resize: (146, 230) 1349115598 -3.400453160939344 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771965_0.png resize: (233, 247) 1349115600 -3.6817959095518593 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771949_0.png resize: (147, 202) 1349115601 -1.4601382845936761 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771946_0.png resize: (232, 153) 1349115603 -3.280521868097403 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771953_0.png resize: (216, 125) 1349115604 -2.0503276366714727 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771964_0.png resize: (193, 388) 1349115605 -2.2393440836064515 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771991_0.png resize: (96, 119) 1349115608 -2.3931903883212167 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771983_0.png resize: (246, 198) 1349115609 -3.3160562347695386 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771961_0.png resize: (128, 107) 1349115610 -1.4701841572842294 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771981_0.png resize: (296, 408) 1349115612 -2.5367590265871276 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771988_0.png resize: (152, 128) 1349115613 -1.7985515170095336 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771950_0.png resize: (145, 121) 1349115614 -1.4251710065404841 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771985_0.png resize: (149, 212) 1349115616 -1.7418119411199084 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771990_0.png resize: (154, 150) 1349115617 -2.8427982552744986 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771975_0.png resize: (191, 111) 1349115618 -3.5025818568754503 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771979_0.png resize: (144, 141) 1349115620 -3.0101573878452133 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771966_0.png resize: (259, 114) 1349115621 -1.7986898572420824 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771959_0.png resize: (332, 397) 1349115622 -1.3163567992535987 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771986_0.png resize: (331, 306) 1349115624 -3.8174754278377927 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771971_0.png resize: (158, 189) 1349115625 -2.4939078882185117 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771948_0.png resize: (616, 307) 1349115626 -2.7371441009598954 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771951_0.png resize: (205, 232) 1349115628 -2.8489724358812407 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771980_0.png resize: (171, 130) 1349115629 -2.9811485396739847 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771974_0.png resize: (293, 199) 1349115630 -3.26739510009521 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771957_0.png resize: (143, 104) 1349115632 -0.9629744574335004 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771978_0.png resize: (168, 171) 1349115633 -2.8506599248113287 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771976_0.png resize: (205, 174) 1349115634 -2.262026989986227 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771968_0.png resize: (235, 207) 1349115636 -3.920725926058166 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771945_0.png resize: (157, 110) 1349115637 -2.983260330314773 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772040_0.png resize: (230, 249) 1349115638 -2.11274782166943 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772045_0.png resize: (66, 48) 1349115640 2.088627576353438 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771992_0.png resize: (337, 138) 1349115641 -0.6831486582641463 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772009_0.png resize: (130, 178) 1349115643 -2.6686635980981555 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772032_0.png resize: (203, 91) 1349115644 -2.729437104367066 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772023_0.png resize: (277, 104) 1349115645 -2.0447631097702668 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772013_0.png resize: (172, 263) 1349115647 -2.3051996259280614 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772005_0.png resize: (350, 250) 1349115648 -2.2103876586665696 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772010_0.png resize: (166, 224) 1349115650 -2.4848309011332534 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772022_0.png resize: (316, 198) 1349115652 -2.112337846333554 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772024_0.png resize: (327, 236) 1349115653 -2.0702889702577543 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772020_0.png resize: (137, 89) 1349115654 -3.3172997285817374 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771995_0.png resize: (202, 195) 1349115656 -2.7107758269357687 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771999_0.png resize: (269, 185) 1349115657 -1.812167113307756 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771994_0.png resize: (240, 231) 1349115658 -2.9224717128189432 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772014_0.png resize: (147, 70) 1349115660 -3.6230660396100873 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772003_0.png resize: (264, 154) 1349115662 -2.8528675828844476 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772036_0.png resize: (206, 325) 1349115663 -1.7970484960584208 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772039_0.png resize: (116, 205) 1349115665 -3.611578780382403 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772008_0.png resize: (226, 319) 1349115666 -2.6546232404987546 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772047_0.png resize: (152, 126) 1349115667 -2.0733801180318627 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771993_0.png resize: (174, 138) 1349115669 -2.03196783435117 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772044_0.png resize: (83, 331) 1349115670 -2.728377228710459 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772001_0.png resize: (316, 366) 1349115671 -2.599492516476851 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772043_0.png resize: (109, 222) 1349115673 -3.3695778112058856 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772030_0.png resize: (97, 207) 1349115674 -2.6028525973314585 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772027_0.png resize: (109, 165) 1349115675 -2.1228428544144413 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772006_0.png resize: (90, 131) 1349115677 -2.386461144100036 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772037_0.png resize: (296, 188) 1349115678 -1.1576498827258244 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772026_0.png resize: (144, 174) 1349115679 -2.389446822193738 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771997_0.png resize: (341, 286) 1349115681 -0.960921348311467 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772025_0.png resize: (76, 60) 1349115682 -2.169363447752114 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772031_0.png resize: (147, 227) 1349115683 -2.3160221250352553 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772015_0.png resize: (86, 108) 1349115685 1.067063562381402 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771998_0.png resize: (155, 291) 1349115686 -2.8000934830785114 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772028_0.png resize: (132, 123) 1349115687 -3.2717491870577624 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772042_0.png resize: (142, 329) 1349115689 -2.8493806067370215 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772038_0.png resize: (100, 125) 1349115690 -3.609411824521205 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772021_0.png resize: (187, 191) 1349115691 -1.7358314442370208 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772016_0.png resize: (308, 223) 1349115693 -2.854825965183655 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772018_0.png resize: (166, 153) 1349115694 -2.7064172536840427 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772004_0.png resize: (194, 393) 1349115695 -4.256120566827151 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772007_0.png resize: (319, 127) 1349115697 -3.1009043942602887 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772019_0.png resize: (223, 228) 1349115698 -2.392624927815507 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772000_0.png resize: (240, 117) 1349115699 -2.280008414270886 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771697_0.png resize: (136, 145) 1349115894 -2.3863093736635443 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771699_0.png resize: (165, 519) 1349115895 -2.069991180854396 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771702_0.png resize: (76, 72) 1349115896 -0.9764981312499917 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771685_0.png resize: (155, 292) 1349115898 -0.7829155703276132 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771695_0.png resize: (140, 168) 1349115899 -2.270972628313001 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771680_0.png resize: (125, 321) 1349115900 -2.388184345831463 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771704_0.png resize: (119, 153) 1349115902 -1.9712595784288394 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771721_0.png resize: (89, 209) 1349115903 -0.6602564846526727 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771711_0.png resize: (218, 268) 1349115904 -1.5219493535954742 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771740_0.png resize: (124, 232) 1349115906 -2.4518981250447505 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771739_0.png resize: (122, 173) 1349115907 -1.216066310097068 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771760_0.png resize: (125, 237) 1349115908 -2.8185119622812684 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771754_0.png resize: (125, 250) 1349115910 0.2599342218597591 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771764_0.png resize: (163, 224) 1349115911 -2.667423892760678 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771778_0.png resize: (126, 151) 1349115912 -3.8576255411021934 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771770_0.png resize: (317, 343) 1349115914 -1.987932591496065 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771781_0.png resize: (183, 228) 1349115915 -2.462438327026928 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771777_0.png resize: (280, 186) 1349115916 -1.8427199323027772 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771823_0.png resize: (107, 107) 1349115919 -1.0360429941363998 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771826_0.png resize: (98, 184) 1349115920 -1.5961427872166127 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771814_0.png resize: (191, 175) 1349115921 -1.2478240751633594 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771825_0.png resize: (261, 393) 1349115923 -3.18059868130509 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771824_0.png resize: (301, 415) 1349115924 -1.9821377178088548 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771804_0.png resize: (162, 191) 1349115925 -0.8428176946372872 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771806_0.png resize: (279, 610) 1349115927 -1.5484250506864699 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771857_0.png resize: (154, 217) 1349115928 -1.7667804010588715 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771864_0.png resize: (107, 138) 1349115929 -1.6473962145703327 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771846_0.png resize: (143, 302) 1349115931 -2.6827146866245823 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771873_0.png resize: (62, 150) 1349115932 -0.7444895944183055 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771868_0.png resize: (164, 167) 1349115933 -1.4897951540346084 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771870_0.png resize: (171, 212) 1349115935 -1.3819064337541025 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771887_0.png resize: (124, 162) 1349115936 -3.3952792100076064 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771880_0.png resize: (136, 142) 1349115938 0.20581865842108257 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771900_0.png resize: (220, 222) 1349115939 -2.1826329909264355 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771938_0.png resize: (432, 232) 1349115941 -3.2446009684259023 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771927_0.png resize: (162, 183) 1349115943 -4.5991993266689475 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771944_0.png resize: (184, 196) 1349115944 -3.149281426827779 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771899_0.png resize: (272, 289) 1349115945 -2.778886406815781 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771901_0.png resize: (140, 297) 1349115947 1.2826460191756153 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771942_0.png resize: (313, 264) 1349115948 -3.9953541963522086 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771893_0.png resize: (136, 278) 1349115949 -2.257545730845305 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771940_0.png resize: (144, 231) 1349115951 -4.434974938174376 treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771922_0.png resize: (174, 111) 1349115952 -1.5323404485388321 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771972_0.png resize: (110, 142) 1349115953 -2.3949117619145985 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771954_0.png resize: (204, 254) 1349115955 -1.8212591530766595 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771952_0.png resize: (121, 152) 1349115956 -2.376481768068515 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771982_0.png resize: (183, 186) 1349115958 -2.694670777868373 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771973_0.png resize: (198, 145) 1349115959 -4.56304843168168 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771947_0.png resize: (71, 106) 1349115960 -2.200464653921977 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772017_0.png resize: (219, 315) 1349115962 -2.7954037990334406 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772034_0.png resize: (156, 172) 1349115963 -2.1109306532563785 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772002_0.png resize: (328, 187) 1349115964 -1.1801761234220156 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772035_0.png resize: (156, 236) 1349115966 -3.377269840111445 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771996_0.png resize: (263, 192) 1349115967 -2.8617402113703463 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772011_0.png resize: (232, 270) 1349115968 -1.4291437841806658 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771774_0.png resize: (110, 142) 1349115984 -4.305578266621725 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771691_0.png resize: (476, 199) 1349116047 -2.7184273383677695 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771746_0.png resize: (189, 247) 1349116049 -2.559440194127914 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771734_0.png resize: (357, 208) 1349116050 -2.412897437336353 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771751_0.png resize: (384, 199) 1349116051 -3.4711017814769143 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771830_0.png resize: (261, 308) 1349116053 -2.196589436777517 treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771796_0.png resize: (491, 250) 1349116054 -3.0111572785818894 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771877_0.png resize: (140, 202) 1349116055 -1.2036412672873948 treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771871_0.png resize: (134, 390) 1349116057 -1.4011932563985325 treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771883_0.png resize: (493, 471) 1349116058 -1.1991448335008248 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771967_0.png resize: (181, 127) 1349116060 -1.071633866081811 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772012_0.png resize: (330, 277) 1349116063 -2.3209944473929176 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772033_0.png resize: (340, 308) 1349116064 -1.9680823383698611 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771725_0.png resize: (156, 123) 1349116085 -1.352979288024793 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771848_0.png resize: (121, 95) 1349116087 -1.8150320079701912 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771960_0.png resize: (76, 115) 1349116088 -0.3145964161475938 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772046_0.png resize: (120, 150) 1349116089 -2.253557432420338 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772029_0.png resize: (125, 166) 1349116091 -3.623281705821838 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771744_0.png resize: (132, 123) 1349116111 -1.5035581422498538 treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771780_0.png resize: (125, 245) 1349116112 -1.088069099917694 treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772041_0.png resize: (261, 230) 1349116114 -1.896533682313552 treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771701_0.png resize: (284, 147) 1349116152 -2.6714279369395393 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771748_0.png resize: (133, 116) 1349116153 -0.9887645845896182 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771722_0.png resize: (171, 246) 1349116154 -3.1880554858346457 treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771749_0.png resize: (277, 222) 1349116156 -3.2275128050490234 treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771861_0.png resize: (134, 197) 1349116157 -3.744035136729631 treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771989_0.png resize: (134, 119) 1349116158 -2.4797832279055565 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 : 378 time used for this insertion : 0.03457331657409668 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 378 time used for this insertion : 0.07374119758605957 save missing photos in datou_result : time spend for datou_step_exec : 39.95143747329712 time spend to save output : 0.12489819526672363 total time spend for step 6 : 40.07633566856384 step7:brightness Mon Mar 31 22:59:46 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/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8.jpg treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8.jpg treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700.jpg treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989.jpg treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51.jpg treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283.jpg treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce.jpg treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1.jpg treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627.jpg treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22.jpg treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771684_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771706_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771690_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771705_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771707_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771688_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771696_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771708_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771683_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771689_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771700_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771687_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771694_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771681_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771686_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771709_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771703_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771682_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771692_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771693_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771698_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771710_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771742_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771719_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771714_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771713_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771718_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771727_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771735_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771747_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771712_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771717_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771716_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771723_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771728_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771733_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771743_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771724_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771737_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771741_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771731_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771726_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771730_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771720_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771738_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771736_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771715_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771745_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771732_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771729_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771762_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771772_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771756_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771783_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771757_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771784_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771776_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771759_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771750_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771766_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771761_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771758_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771773_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771775_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771765_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771753_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771768_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771771_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771752_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771769_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771779_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771767_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771782_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771755_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771763_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771799_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771803_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771822_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771801_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771807_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771800_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771790_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771816_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771831_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771792_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771809_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771789_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771797_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771829_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771813_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771794_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771795_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771802_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771832_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771808_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771793_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771833_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771818_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771820_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771815_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771811_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771798_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771812_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771810_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771788_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771785_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771787_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771821_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771786_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771828_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771827_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771819_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771817_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771805_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771791_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771839_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771836_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771847_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771855_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771838_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771865_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771854_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771851_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771835_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771859_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771849_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771858_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771862_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771837_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771845_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771844_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771843_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771842_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771852_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771850_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771860_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771834_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771853_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771841_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771856_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771866_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771863_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771840_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771878_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771869_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771872_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771875_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771874_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771876_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771867_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771881_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771885_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771884_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771879_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771886_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771882_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771896_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771931_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771914_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771902_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771890_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771891_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771913_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771905_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771937_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771933_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771906_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771924_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771941_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771923_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771935_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771920_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771889_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771894_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771903_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771919_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771888_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771907_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771917_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771928_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771897_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771936_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771915_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771909_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771929_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771895_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771918_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771904_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771930_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771939_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771911_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771908_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771943_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771932_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771898_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771934_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771916_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771912_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771892_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771910_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771921_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771925_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771926_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771963_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771977_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771987_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771958_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771969_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771962_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771956_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771984_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771955_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771970_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771965_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771949_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771946_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771953_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771964_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771991_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771983_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771961_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771981_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771988_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771950_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771985_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771990_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771975_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771979_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771966_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771959_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771986_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771971_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771948_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771951_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771980_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771974_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771957_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771978_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771976_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771968_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771945_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772040_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772045_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771992_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772009_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772032_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772023_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772013_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772005_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772010_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772022_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772024_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772020_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771995_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771999_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771994_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772014_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772003_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772036_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772039_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772008_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772047_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771993_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772044_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772001_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772043_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772030_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772027_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772006_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772037_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772026_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771997_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772025_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772031_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772015_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771998_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772028_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772042_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772038_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772021_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772016_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772018_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772004_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772007_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772019_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772000_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771697_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771699_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771702_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771685_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771695_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771680_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771704_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771721_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771711_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771740_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771739_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771760_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771754_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771764_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771778_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771770_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771781_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771777_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771823_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771826_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771814_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771825_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771824_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771804_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771806_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771857_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771864_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771846_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771873_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771868_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771870_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771887_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771880_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771900_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771938_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771927_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771944_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771899_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771901_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771942_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771893_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771940_0.png treat image : temp/1743454229_1501023_1348949682_472da3412a15a2847d3ff7650fb6fcc1_rle_crop_3741771922_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771972_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771954_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771952_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771982_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771973_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771947_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772017_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772034_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772002_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772035_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741771996_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772011_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771774_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771691_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771746_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771734_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771751_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771830_0.png treat image : temp/1743454229_1501023_1349085131_fe16f18865ca93352200ea3c8a1dc989_rle_crop_3741771796_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771877_0.png treat image : temp/1743454229_1501023_1348950350_6aa58ca3b018707c34f44b5fdd984283_rle_crop_3741771871_0.png treat image : temp/1743454229_1501023_1348949687_e15f076b6530ee1c5a5cb027ada3d8ce_rle_crop_3741771883_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771967_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772012_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772033_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771725_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771848_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771960_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772046_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772029_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771744_0.png treat image : temp/1743454229_1501023_1349085138_2de561433a794bb135b61d928dac9700_rle_crop_3741771780_0.png treat image : temp/1743454229_1501023_1348949672_7430e486879765db524f4f28814bbe22_rle_crop_3741772041_0.png treat image : temp/1743454229_1501023_1349085160_1e95b7ade02dfa3bcc943d70b608b5b8_rle_crop_3741771701_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771748_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771722_0.png treat image : temp/1743454229_1501023_1349085142_6979c9f9f63b306848392370882ba0f8_rle_crop_3741771749_0.png treat image : temp/1743454229_1501023_1349085127_8ce0cea7184412a6d6f8a51306236d51_rle_crop_3741771861_0.png treat image : temp/1743454229_1501023_1348949676_ce39330cf776b5b22c9819565a543627_rle_crop_3741771989_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 : 378 time used for this insertion : 0.09788179397583008 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 378 time used for this insertion : 0.06906580924987793 save missing photos in datou_result : time spend for datou_step_exec : 10.754130840301514 time spend to save output : 0.1728808879852295 total time spend for step 7 : 10.927011728286743 step8:velours_tree Mon Mar 31 22:59:57 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure 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 : 0.2574489116668701 time spend to save output : 3.600120544433594e-05 total time spend for step 8 : 0.25748491287231445 step9:send_mail_cod Mon Mar 31 22:59:57 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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_P21925661_31-03-2025_22_59_57.pdf 21927023 imagette219270231743454797 21927024 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 .imagette219270241743454797 21927025 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219270251743454798 21927026 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette219270261743454799 21927027 imagette219270271743454799 21927028 imagette219270281743454799 21927030 change filename to text .imagette219270301743454799 21927031 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 .imagette219270311743454799 21927032 change filename to text .change filename to text .change filename to text .imagette219270321743454800 21927033 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 .imagette219270331743454800 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21925661 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21927023,21927024,21927025,21927026,21927027,21927028,21927029,21927030,21927031,21927032,21927033?tags=mal_croppe,papier,pet_fonce,autre,flou,background,environnement,metal,pet_clair,pehd,carton args[1349085160] : ((1349085160, -3.7521919632588103, 492609224), (1349085160, -0.3769983729532026, 496442774), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1349085142] : ((1349085142, -3.315705711673113, 492609224), (1349085142, -0.3786087302920473, 496442774), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1349085138] : ((1349085138, -4.327169341799626, 492609224), (1349085138, -0.0726421736415612, 496442774), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1349085131] : ((1349085131, -3.267217606692126, 492609224), (1349085131, -0.06581406805657292, 2107752395), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1349085127] : ((1349085127, -3.71642920845779, 492609224), (1349085127, -0.2952196512307714, 496442774), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1348950350] : ((1348950350, -0.5940600124790875, 492688767), (1348950350, 0.1702288916703742, 2107752395), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1348949687] : ((1348949687, -2.5896591169763483, 492609224), (1348949687, 0.37649917559800117, 2107752395), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1348949682] : ((1348949682, -5.942095960750408, 492609224), (1348949682, 0.00830603627745699, 2107752395), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1348949676] : ((1348949676, -4.183820105760761, 492609224), (1348949676, -0.07383120801057262, 496442774), '0.14630428184005087') We are sending mail with results at report@fotonower.com args[1348949672] : ((1348949672, -3.4861684865469154, 492609224), (1348949672, -0.2992468359011815, 496442774), '0.14630428184005087') We are sending mail with results at report@fotonower.com refus_total : 0.14630428184005087 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=21925661 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 SELECT photo_id, url FROM MTRBack.photos ph WHERE photo_id IN (1348949672,1348949676,1348949682,1348949687,1348950350,1349085127,1349085131,1349085138,1349085142,1349085160) Found this number of photos: 10 begin to download photo : 1348949672 begin to download photo : 1348949687 begin to download photo : 1349085131 begin to download photo : 1349085160 download finish for photo 1348949687 begin to download photo : 1348950350 download finish for photo 1349085131 begin to download photo : 1349085138 download finish for photo 1348949672 begin to download photo : 1348949676 download finish for photo 1349085138 begin to download photo : 1349085142 download finish for photo 1348950350 begin to download photo : 1349085127 download finish for photo 1349085160 download finish for photo 1349085142 download finish for photo 1348949676 begin to download photo : 1348949682 download finish for photo 1349085127 download finish for photo 1348949682 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21925661_31-03-2025_22_59_57.pdf results_Auto_P21925661_31-03-2025_22_59_57.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21925661_31-03-2025_22_59_57.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','21925661','results_Auto_P21925661_31-03-2025_22_59_57.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21925661_31-03-2025_22_59_57.pdf','pdf','','0.68','0.14630428184005087') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/21925661

https://www.fotonower.com/image?json=false&list_photos_id=1349085160
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1349085142
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1349085138
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1349085131
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1349085127
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348950350
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348949687
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348949682
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348949676
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348949672
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 14.63%
Veuillez trouver les photos des contaminants.

exemples de contaminants: papier: https://www.fotonower.com/view/21927024?limit=200
exemples de contaminants: pet_fonce: https://www.fotonower.com/view/21927025?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/21927026?limit=200
exemples de contaminants: metal: https://www.fotonower.com/view/21927030?limit=200
exemples de contaminants: pet_clair: https://www.fotonower.com/view/21927031?limit=200
exemples de contaminants: pehd: https://www.fotonower.com/view/21927032?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/21927033?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21925661_31-03-2025_22_59_57.pdf.

Lien vers velours :https://www.fotonower.com/velours/21927023,21927024,21927025,21927026,21927027,21927028,21927029,21927030,21927031,21927032,21927033?tags=mal_croppe,papier,pet_fonce,autre,flou,background,environnement,metal,pet_clair,pehd,carton.


L'équipe Fotonower 202 b'' Server: nginx Date: Mon, 31 Mar 2025 21:00:05 GMT Content-Length: 0 Connection: close X-Message-Id: 5Pde4VOLR-u8nJZeuUFr4g 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 [1349085160, 1349085142, 1349085138, 1349085131, 1349085127, 1348950350, 1348949687, 1348949682, 1348949676, 1348949672] 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, '2710822') ('3318', '21925661', '1349085160', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085142', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085138', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085131', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085127', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348950350', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949687', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949682', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949676', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949672', None, None, None, None, None, '2710822') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 10 time used for this insertion : 0.017610549926757812 save_final save missing photos in datou_result : time spend for datou_step_exec : 7.959972620010376 time spend to save output : 0.01785874366760254 total time spend for step 9 : 7.9778313636779785 step10:split_time_score Mon Mar 31 23:00:05 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 ! 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'}] (('07', 10),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 31032025 21925661 Nombre de photos uploadées : 10 / 23040 (0%) 31032025 21925661 Nombre de photos taguées (types de déchets): 0 / 10 (0%) 31032025 21925661 Nombre de photos taguées (volume) : 0 / 10 (0%) elapsed_time : load_data_split_time_score 4.291534423828125e-06 elapsed_time : order_list_meta_photo_and_scores 1.4543533325195312e-05 ?????????? elapsed_time : fill_and_build_computed_from_old_data 0.0005767345428466797 elapsed_time : insert_dashboard_record_day_entry 0.029956340789794922 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 : 0.14630428184005087 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21925661_31-03-2025_22_59_57.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21925661 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`=21925661 AND mptpi.`type`=3594 To do Qualite : 0.14145216719895026 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21925662_31-03-2025_22_51_38.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21925662 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`=21925662 AND mptpi.`type`=3594 To do Qualite : 0.0939584877250109 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21905169_31-03-2025_11_54_31.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21905169 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`=21905169 AND mptpi.`type`=3726 To do Qualite : 0.2533267061721413 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21906639_31-03-2025_13_23_22.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21906639 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`=21906639 AND mptpi.`type`=3594 To do Qualite : 0.2103858617836865 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21906642_31-03-2025_13_09_13.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21906642 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`=21906642 AND mptpi.`type`=3594 To do Qualite : 0.10137259221816262 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21911519_31-03-2025_15_32_52.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21911519 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`=21911519 AND mptpi.`type`=3726 To do Qualite : 0.17051974471791034 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21913880_31-03-2025_16_28_37.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21913880 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`=21913880 AND mptpi.`type`=3594 To do Qualite : 0.2535554108796297 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21917443_31-03-2025_18_19_55.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21917443 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`=21917443 AND mptpi.`type`=3594 To do Qualite : 0.07287105816110555 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21924021_31-03-2025_21_50_54.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21924021 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`=21924021 AND mptpi.`type`=3726 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21926965 order by id desc limit 1 Qualite : 0.2189041275706411 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21925669_31-03-2025_22_45_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21925669 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`=21925669 AND mptpi.`type`=3594 To do Qualite : 0.18545522031874095 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21925670_31-03-2025_22_36_34.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21925670 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`=21925670 AND mptpi.`type`=3594 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'31032025': {'nb_upload': 10, '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 [1349085160, 1349085142, 1349085138, 1349085131, 1349085127, 1348950350, 1348949687, 1348949682, 1348949676, 1348949672] Looping around the photos to save general results len do output : 1 /21925661Didn'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, '2710822') ('3318', '21925661', '1349085160', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085142', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085138', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085131', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1349085127', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348950350', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949687', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949682', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949676', None, None, None, None, None, '2710822') ('3318', None, None, None, None, None, None, None, '2710822') ('3318', '21925661', '1348949672', None, None, None, None, None, '2710822') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 11 time used for this insertion : 0.04955434799194336 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.7098312377929688 time spend to save output : 0.0498347282409668 total time spend for step 10 : 1.7596659660339355 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 10 set_done_treatment 264.37user 134.90system 9:43.33elapsed 68%CPU (0avgtext+0avgdata 5616556maxresident)k 9659992inputs+157560outputs (374595major+24760393minor)pagefaults 0swaps