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 : 3276679 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 : ['2708834'] with mtr_portfolio_ids : ['21906642'] and first list_photo_ids : [] new path : /proc/3276679/ 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 , BFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 11 ; length of list_pids : 11 ; length of list_args : 11 time to download the photos : 1.8238301277160645 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 13:00:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 4621 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-31 13:00:32.845892: 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 13:00:32.871287: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-31 13:00:32.873492: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f7c7c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-31 13:00:32.873551: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-31 13:00:32.877385: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-31 13:00:33.148258: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x4061970 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-31 13:00:33.148321: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-31 13:00:33.149588: 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 13:00:33.150034: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 13:00:33.153222: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 13:00:33.156424: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 13:00:33.156785: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 13:00:33.159349: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 13:00:33.160592: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 13:00:33.165711: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 13:00:33.166978: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 13:00:33.167057: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 13:00:33.167701: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-31 13:00:33.167721: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-31 13:00:33.167731: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-31 13:00:33.168833: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4169 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 13:00:33.444746: 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 13:00:33.444853: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 13:00:33.444874: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 13:00:33.444893: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 13:00:33.444910: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 13:00:33.444928: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 13:00:33.444945: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 13:00:33.444963: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 13:00:33.446193: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 13:00:33.447517: 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 13:00:33.447603: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 13:00:33.447623: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 13:00:33.447641: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 13:00:33.447658: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 13:00:33.447676: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 13:00:33.447693: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 13:00:33.447711: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 13:00:33.448885: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 13:00:33.448926: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-31 13:00:33.448938: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-31 13:00:33.448948: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-31 13:00:33.450172: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4169 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 13:00:46.007674: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 13:00:46.125137: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_NOT_INITIALIZED 2025-03-31 13:00:46.126449: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_NOT_INITIALIZED 2025-03-31 13:00:46.135019: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 13:00:46.149356: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2025-03-31 13:00:46.153544: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2025-03-31 13:00:47.232799: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2025-03-31 13:00:47.237144: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2025-03-31 13:00:50.583272: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.405612: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-03-31 13:00:51.483159: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.483250: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.484399: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.484428: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.491058: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.491084: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.491739: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.491768: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.536567: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.536604: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.537218: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.537233: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.537851: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.537866: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.538473: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.538487: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.546887: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.546971: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 417.62MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.547940: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.547958: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 417.62MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-31 13:00:51.583078: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.584217: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.585294: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.586347: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.591050: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.592149: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.593206: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.594258: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.596896: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.596923: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-03-31 13:00:51.606194: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.607317: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.617115: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.618135: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.619149: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.620124: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.621103: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-31 13:00:51.622068: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.57G (3836608512 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 11 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 error in detect the image : temp/1743418828_3276679_1348990554_a06d0f00552012f8267fc89b808346cb.jpg 2 root error(s) found. (0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[node conv1/convolution (defined at /usr/local/lib/python3.8/dist-packages/keras/backend/tensorflow_backend.py:3007) ]] [[mrcnn_detection/map/while/body/_1/GatherV2_1/_82]] (1) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[node conv1/convolution (defined at /usr/local/lib/python3.8/dist-packages/keras/backend/tensorflow_backend.py:3007) ]] 0 successful operations. 0 derived errors ignored. [Op:__inference_keras_scratch_graph_13584] Function call stack: keras_scratch_graph -> keras_scratch_graph 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 error in detect the image : temp/1743418828_3276679_1348990549_2c8f475ea76bbc3fffcecb5038245fa0.jpg 2 root error(s) found. (0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[node conv1/convolution (defined at /usr/local/lib/python3.8/dist-packages/keras/backend/tensorflow_backend.py:3007) ]] [[mrcnn_detection/map/while/body/_1/GatherV2_1/_82]] (1) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[node conv1/convolution (defined at /usr/local/lib/python3.8/dist-packages/keras/backend/tensorflow_backend.py:3007) ]] 0 successful operations. 0 derived errors ignored. [Op:__inference_keras_scratch_graph_13584] Function call stack: keras_scratch_graph -> keras_scratch_graph 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 : 45 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 56 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 50 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 44 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 85 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 : 78 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 : 71 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 : 64 Detection mask done ! Trying to reset tf kernel 3277359 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 3424 tf kernel not reseted sub process len(results) : 9 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 9 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 : 4621 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 : 0.06269502639770508 nb_pixel_total : 33479 time to create 1 rle with old method : 0.04067254066467285 length of segment : 261 time for calcul the mask position with numpy : 0.0016155242919921875 nb_pixel_total : 26751 time to create 1 rle with old method : 0.028533458709716797 length of segment : 178 time for calcul the mask position with numpy : 0.06778526306152344 nb_pixel_total : 395014 time to create 1 rle with new method : 0.040857553482055664 length of segment : 1016 time for calcul the mask position with numpy : 0.013509988784790039 nb_pixel_total : 64858 time to create 1 rle with old method : 0.07891011238098145 length of segment : 277 time for calcul the mask position with numpy : 0.03675103187561035 nb_pixel_total : 116687 time to create 1 rle with old method : 0.13696980476379395 length of segment : 481 time for calcul the mask position with numpy : 0.011325597763061523 nb_pixel_total : 7836 time to create 1 rle with old method : 0.011737346649169922 length of segment : 99 time for calcul the mask position with numpy : 0.005990266799926758 nb_pixel_total : 87087 time to create 1 rle with old method : 0.13111019134521484 length of segment : 362 time for calcul the mask position with numpy : 0.01032876968383789 nb_pixel_total : 9066 time to create 1 rle with old method : 0.013381242752075195 length of segment : 119 time for calcul the mask position with numpy : 0.025191783905029297 nb_pixel_total : 200557 time to create 1 rle with new method : 0.011907815933227539 length of segment : 621 time for calcul the mask position with numpy : 0.027978181838989258 nb_pixel_total : 93080 time to create 1 rle with old method : 0.12152218818664551 length of segment : 424 time for calcul the mask position with numpy : 0.0024471282958984375 nb_pixel_total : 19452 time to create 1 rle with old method : 0.02304697036743164 length of segment : 193 time for calcul the mask position with numpy : 0.0005369186401367188 nb_pixel_total : 15913 time to create 1 rle with old method : 0.018513917922973633 length of segment : 266 time for calcul the mask position with numpy : 0.0046041011810302734 nb_pixel_total : 43903 time to create 1 rle with old method : 0.06592345237731934 length of segment : 467 time for calcul the mask position with numpy : 0.004206418991088867 nb_pixel_total : 62875 time to create 1 rle with old method : 0.07313203811645508 length of segment : 359 time for calcul the mask position with numpy : 0.0017621517181396484 nb_pixel_total : 38481 time to create 1 rle with old method : 0.04346108436584473 length of segment : 306 time for calcul the mask position with numpy : 0.028090953826904297 nb_pixel_total : 120220 time to create 1 rle with old method : 0.1502513885498047 length of segment : 933 time for calcul the mask position with numpy : 0.0009913444519042969 nb_pixel_total : 33464 time to create 1 rle with old method : 0.03923749923706055 length of segment : 213 time for calcul the mask position with numpy : 0.012777328491210938 nb_pixel_total : 56271 time to create 1 rle with old method : 0.07326960563659668 length of segment : 309 time for calcul the mask position with numpy : 0.0013151168823242188 nb_pixel_total : 22937 time to create 1 rle with old method : 0.02657794952392578 length of segment : 311 time for calcul the mask position with numpy : 0.008675575256347656 nb_pixel_total : 211452 time to create 1 rle with new method : 0.012434244155883789 length of segment : 738 time for calcul the mask position with numpy : 0.0014803409576416016 nb_pixel_total : 6330 time to create 1 rle with old method : 0.007780313491821289 length of segment : 119 time for calcul the mask position with numpy : 0.0030574798583984375 nb_pixel_total : 39806 time to create 1 rle with old method : 0.04764819145202637 length of segment : 240 time for calcul the mask position with numpy : 0.329315185546875 nb_pixel_total : 823490 time to create 1 rle with new method : 0.4154074192047119 length of segment : 867 time for calcul the mask position with numpy : 0.007962226867675781 nb_pixel_total : 13579 time to create 1 rle with old method : 0.018316984176635742 length of segment : 97 time for calcul the mask position with numpy : 0.003110647201538086 nb_pixel_total : 4987 time to create 1 rle with old method : 0.0058705806732177734 length of segment : 78 time for calcul the mask position with numpy : 0.07941842079162598 nb_pixel_total : 199382 time to create 1 rle with new method : 0.008943319320678711 length of segment : 418 time for calcul the mask position with numpy : 0.02227616310119629 nb_pixel_total : 37539 time to create 1 rle with old method : 0.05184054374694824 length of segment : 248 time for calcul the mask position with numpy : 0.007242679595947266 nb_pixel_total : 10955 time to create 1 rle with old method : 0.014311552047729492 length of segment : 170 time for calcul the mask position with numpy : 0.006044626235961914 nb_pixel_total : 10508 time to create 1 rle with old method : 0.014677762985229492 length of segment : 109 time for calcul the mask position with numpy : 0.012902259826660156 nb_pixel_total : 28250 time to create 1 rle with old method : 0.03661227226257324 length of segment : 194 time for calcul the mask position with numpy : 0.1244666576385498 nb_pixel_total : 456939 time to create 1 rle with new method : 0.026447772979736328 length of segment : 792 time for calcul the mask position with numpy : 0.0018672943115234375 nb_pixel_total : 18864 time to create 1 rle with old method : 0.030594587326049805 length of segment : 221 time for calcul the mask position with numpy : 0.007092714309692383 nb_pixel_total : 39217 time to create 1 rle with old method : 0.05540347099304199 length of segment : 170 time for calcul the mask position with numpy : 0.022444725036621094 nb_pixel_total : 16891 time to create 1 rle with old method : 0.02579808235168457 length of segment : 225 time for calcul the mask position with numpy : 0.006093502044677734 nb_pixel_total : 10266 time to create 1 rle with old method : 0.015633821487426758 length of segment : 75 time for calcul the mask position with numpy : 0.011846542358398438 nb_pixel_total : 44678 time to create 1 rle with old method : 0.061908721923828125 length of segment : 315 time for calcul the mask position with numpy : 0.012066841125488281 nb_pixel_total : 43424 time to create 1 rle with old method : 0.055983543395996094 length of segment : 319 time for calcul the mask position with numpy : 0.07971453666687012 nb_pixel_total : 527318 time to create 1 rle with new method : 0.0394442081451416 length of segment : 847 time for calcul the mask position with numpy : 0.03917431831359863 nb_pixel_total : 142490 time to create 1 rle with old method : 0.19293546676635742 length of segment : 684 time for calcul the mask position with numpy : 0.004240512847900391 nb_pixel_total : 34226 time to create 1 rle with old method : 0.042142629623413086 length of segment : 308 time for calcul the mask position with numpy : 0.0038824081420898438 nb_pixel_total : 20499 time to create 1 rle with old method : 0.027547359466552734 length of segment : 227 time for calcul the mask position with numpy : 0.01862335205078125 nb_pixel_total : 109300 time to create 1 rle with old method : 0.12599420547485352 length of segment : 492 time for calcul the mask position with numpy : 0.002588987350463867 nb_pixel_total : 4097 time to create 1 rle with old method : 0.004923343658447266 length of segment : 98 time for calcul the mask position with numpy : 0.0040929317474365234 nb_pixel_total : 19421 time to create 1 rle with old method : 0.023215532302856445 length of segment : 128 time for calcul the mask position with numpy : 0.0015950202941894531 nb_pixel_total : 6030 time to create 1 rle with old method : 0.009089946746826172 length of segment : 86 time for calcul the mask position with numpy : 0.0030813217163085938 nb_pixel_total : 109432 time to create 1 rle with old method : 0.12636423110961914 length of segment : 540 time for calcul the mask position with numpy : 0.002022981643676758 nb_pixel_total : 6204 time to create 1 rle with old method : 0.011850833892822266 length of segment : 101 time for calcul the mask position with numpy : 0.004441022872924805 nb_pixel_total : 31902 time to create 1 rle with old method : 0.03676748275756836 length of segment : 285 time for calcul the mask position with numpy : 0.0026803016662597656 nb_pixel_total : 7816 time to create 1 rle with old method : 0.01122593879699707 length of segment : 115 time for calcul the mask position with numpy : 0.008290290832519531 nb_pixel_total : 84669 time to create 1 rle with old method : 0.09878420829772949 length of segment : 385 time for calcul the mask position with numpy : 0.036116600036621094 nb_pixel_total : 72674 time to create 1 rle with old method : 0.08678483963012695 length of segment : 375 time for calcul the mask position with numpy : 0.03557395935058594 nb_pixel_total : 31782 time to create 1 rle with old method : 0.04233217239379883 length of segment : 249 time for calcul the mask position with numpy : 0.0038199424743652344 nb_pixel_total : 20356 time to create 1 rle with old method : 0.032955169677734375 length of segment : 202 time for calcul the mask position with numpy : 0.00022125244140625 nb_pixel_total : 9248 time to create 1 rle with old method : 0.010904550552368164 length of segment : 108 time for calcul the mask position with numpy : 0.0007474422454833984 nb_pixel_total : 11733 time to create 1 rle with old method : 0.01366424560546875 length of segment : 168 time for calcul the mask position with numpy : 0.002095460891723633 nb_pixel_total : 5619 time to create 1 rle with old method : 0.006726264953613281 length of segment : 74 time for calcul the mask position with numpy : 0.13424181938171387 nb_pixel_total : 232576 time to create 1 rle with new method : 0.015570402145385742 length of segment : 485 time for calcul the mask position with numpy : 0.042199134826660156 nb_pixel_total : 47108 time to create 1 rle with old method : 0.059755563735961914 length of segment : 352 time for calcul the mask position with numpy : 0.006941318511962891 nb_pixel_total : 26972 time to create 1 rle with old method : 0.035019636154174805 length of segment : 594 time for calcul the mask position with numpy : 0.0018606185913085938 nb_pixel_total : 11283 time to create 1 rle with old method : 0.014021873474121094 length of segment : 355 time for calcul the mask position with numpy : 0.08579421043395996 nb_pixel_total : 318703 time to create 1 rle with new method : 0.030147314071655273 length of segment : 703 time for calcul the mask position with numpy : 0.034026384353637695 nb_pixel_total : 55595 time to create 1 rle with old method : 0.06763958930969238 length of segment : 244 time for calcul the mask position with numpy : 0.0003044605255126953 nb_pixel_total : 9299 time to create 1 rle with old method : 0.015259027481079102 length of segment : 191 time for calcul the mask position with numpy : 0.0008487701416015625 nb_pixel_total : 12163 time to create 1 rle with old method : 0.014219045639038086 length of segment : 187 time for calcul the mask position with numpy : 0.008361577987670898 nb_pixel_total : 6308 time to create 1 rle with old method : 0.00959920883178711 length of segment : 115 time for calcul the mask position with numpy : 0.0027816295623779297 nb_pixel_total : 27510 time to create 1 rle with old method : 0.03352046012878418 length of segment : 143 time for calcul the mask position with numpy : 0.00018525123596191406 nb_pixel_total : 4829 time to create 1 rle with old method : 0.006949663162231445 length of segment : 94 time for calcul the mask position with numpy : 0.0015215873718261719 nb_pixel_total : 8284 time to create 1 rle with old method : 0.010107755661010742 length of segment : 94 time for calcul the mask position with numpy : 0.0004284381866455078 nb_pixel_total : 11926 time to create 1 rle with old method : 0.01532125473022461 length of segment : 244 time for calcul the mask position with numpy : 0.003731250762939453 nb_pixel_total : 40724 time to create 1 rle with old method : 0.04796028137207031 length of segment : 287 time for calcul the mask position with numpy : 0.0595240592956543 nb_pixel_total : 52122 time to create 1 rle with old method : 0.07272887229919434 length of segment : 239 time for calcul the mask position with numpy : 0.0059316158294677734 nb_pixel_total : 19604 time to create 1 rle with old method : 0.025542736053466797 length of segment : 119 time for calcul the mask position with numpy : 0.24090790748596191 nb_pixel_total : 297280 time to create 1 rle with new method : 0.030694961547851562 length of segment : 1197 time for calcul the mask position with numpy : 0.017003536224365234 nb_pixel_total : 82265 time to create 1 rle with old method : 0.10289955139160156 length of segment : 348 time for calcul the mask position with numpy : 0.005417346954345703 nb_pixel_total : 95678 time to create 1 rle with old method : 0.1041264533996582 length of segment : 479 time for calcul the mask position with numpy : 0.017444372177124023 nb_pixel_total : 67160 time to create 1 rle with old method : 0.08556318283081055 length of segment : 454 time for calcul the mask position with numpy : 0.010437250137329102 nb_pixel_total : 69904 time to create 1 rle with old method : 0.08111262321472168 length of segment : 235 time for calcul the mask position with numpy : 0.009631872177124023 nb_pixel_total : 108263 time to create 1 rle with old method : 0.12729382514953613 length of segment : 849 time for calcul the mask position with numpy : 0.0060656070709228516 nb_pixel_total : 25935 time to create 1 rle with old method : 0.03349757194519043 length of segment : 183 time for calcul the mask position with numpy : 0.021381378173828125 nb_pixel_total : 7980 time to create 1 rle with old method : 0.014755964279174805 length of segment : 162 time for calcul the mask position with numpy : 0.0037598609924316406 nb_pixel_total : 34166 time to create 1 rle with old method : 0.04169011116027832 length of segment : 240 time for calcul the mask position with numpy : 0.018924951553344727 nb_pixel_total : 12897 time to create 1 rle with old method : 0.01782679557800293 length of segment : 239 time for calcul the mask position with numpy : 0.012391328811645508 nb_pixel_total : 13657 time to create 1 rle with old method : 0.02073979377746582 length of segment : 159 time for calcul the mask position with numpy : 0.02437448501586914 nb_pixel_total : 49221 time to create 1 rle with old method : 0.05968117713928223 length of segment : 221 time for calcul the mask position with numpy : 0.0619664192199707 nb_pixel_total : 71180 time to create 1 rle with old method : 0.08582496643066406 length of segment : 388 time for calcul the mask position with numpy : 0.0009608268737792969 nb_pixel_total : 25589 time to create 1 rle with old method : 0.04474020004272461 length of segment : 164 time for calcul the mask position with numpy : 0.00140380859375 nb_pixel_total : 15531 time to create 1 rle with old method : 0.01842665672302246 length of segment : 197 time for calcul the mask position with numpy : 0.012552738189697266 nb_pixel_total : 21986 time to create 1 rle with old method : 0.04119467735290527 length of segment : 228 time for calcul the mask position with numpy : 0.0002894401550292969 nb_pixel_total : 6326 time to create 1 rle with old method : 0.010638952255249023 length of segment : 130 time for calcul the mask position with numpy : 0.0059854984283447266 nb_pixel_total : 10186 time to create 1 rle with old method : 0.014772176742553711 length of segment : 238 time for calcul the mask position with numpy : 0.00025534629821777344 nb_pixel_total : 8012 time to create 1 rle with old method : 0.010115385055541992 length of segment : 117 time for calcul the mask position with numpy : 0.014091014862060547 nb_pixel_total : 37618 time to create 1 rle with old method : 0.05116558074951172 length of segment : 240 time for calcul the mask position with numpy : 0.0006949901580810547 nb_pixel_total : 21610 time to create 1 rle with old method : 0.02537059783935547 length of segment : 164 time for calcul the mask position with numpy : 0.13087844848632812 nb_pixel_total : 317065 time to create 1 rle with new method : 0.0304563045501709 length of segment : 731 time for calcul the mask position with numpy : 0.0019385814666748047 nb_pixel_total : 16278 time to create 1 rle with old method : 0.018587827682495117 length of segment : 127 time for calcul the mask position with numpy : 0.023148775100708008 nb_pixel_total : 132029 time to create 1 rle with old method : 0.1656324863433838 length of segment : 524 time for calcul the mask position with numpy : 0.0007607936859130859 nb_pixel_total : 36383 time to create 1 rle with old method : 0.04198050498962402 length of segment : 233 time for calcul the mask position with numpy : 0.0004093647003173828 nb_pixel_total : 19929 time to create 1 rle with old method : 0.023213863372802734 length of segment : 337 time for calcul the mask position with numpy : 0.001291036605834961 nb_pixel_total : 17828 time to create 1 rle with old method : 0.021254777908325195 length of segment : 126 time for calcul the mask position with numpy : 0.06798863410949707 nb_pixel_total : 159182 time to create 1 rle with new method : 0.01194000244140625 length of segment : 517 time for calcul the mask position with numpy : 0.004117727279663086 nb_pixel_total : 65183 time to create 1 rle with old method : 0.0758821964263916 length of segment : 330 time for calcul the mask position with numpy : 0.13361740112304688 nb_pixel_total : 233940 time to create 1 rle with new method : 0.01669931411743164 length of segment : 587 time for calcul the mask position with numpy : 0.06322264671325684 nb_pixel_total : 63499 time to create 1 rle with old method : 0.08874845504760742 length of segment : 322 time for calcul the mask position with numpy : 0.002625703811645508 nb_pixel_total : 32144 time to create 1 rle with old method : 0.03737950325012207 length of segment : 291 time for calcul the mask position with numpy : 0.011595964431762695 nb_pixel_total : 8802 time to create 1 rle with old method : 0.015675067901611328 length of segment : 71 time for calcul the mask position with numpy : 0.0050525665283203125 nb_pixel_total : 62063 time to create 1 rle with old method : 0.09634017944335938 length of segment : 349 time for calcul the mask position with numpy : 0.0897061824798584 nb_pixel_total : 96469 time to create 1 rle with old method : 0.11121606826782227 length of segment : 342 time for calcul the mask position with numpy : 0.0034415721893310547 nb_pixel_total : 32056 time to create 1 rle with old method : 0.04073643684387207 length of segment : 174 time for calcul the mask position with numpy : 0.021044015884399414 nb_pixel_total : 14402 time to create 1 rle with old method : 0.020498275756835938 length of segment : 152 time for calcul the mask position with numpy : 0.0035772323608398438 nb_pixel_total : 25516 time to create 1 rle with old method : 0.03393673896789551 length of segment : 330 time for calcul the mask position with numpy : 0.021310806274414062 nb_pixel_total : 109886 time to create 1 rle with old method : 0.13160109519958496 length of segment : 474 time for calcul the mask position with numpy : 0.00881648063659668 nb_pixel_total : 17813 time to create 1 rle with old method : 0.025289058685302734 length of segment : 181 time for calcul the mask position with numpy : 0.0009853839874267578 nb_pixel_total : 12821 time to create 1 rle with old method : 0.015568256378173828 length of segment : 222 time for calcul the mask position with numpy : 0.03162741661071777 nb_pixel_total : 71685 time to create 1 rle with old method : 0.08511900901794434 length of segment : 234 time for calcul the mask position with numpy : 0.010262727737426758 nb_pixel_total : 22520 time to create 1 rle with old method : 0.028641939163208008 length of segment : 224 time for calcul the mask position with numpy : 0.0006556510925292969 nb_pixel_total : 8254 time to create 1 rle with old method : 0.009839534759521484 length of segment : 119 time for calcul the mask position with numpy : 0.03667330741882324 nb_pixel_total : 31104 time to create 1 rle with old method : 0.040277957916259766 length of segment : 211 time for calcul the mask position with numpy : 0.00543975830078125 nb_pixel_total : 16707 time to create 1 rle with old method : 0.025328397750854492 length of segment : 198 time for calcul the mask position with numpy : 0.016228914260864258 nb_pixel_total : 60061 time to create 1 rle with old method : 0.08316159248352051 length of segment : 457 time for calcul the mask position with numpy : 0.014974832534790039 nb_pixel_total : 21069 time to create 1 rle with old method : 0.029963254928588867 length of segment : 116 time for calcul the mask position with numpy : 0.009330272674560547 nb_pixel_total : 28060 time to create 1 rle with old method : 0.03390765190124512 length of segment : 224 time for calcul the mask position with numpy : 0.007569313049316406 nb_pixel_total : 28800 time to create 1 rle with old method : 0.03539466857910156 length of segment : 219 time for calcul the mask position with numpy : 0.007432699203491211 nb_pixel_total : 47800 time to create 1 rle with old method : 0.05872058868408203 length of segment : 396 time for calcul the mask position with numpy : 0.010774850845336914 nb_pixel_total : 60809 time to create 1 rle with old method : 0.07230949401855469 length of segment : 282 time for calcul the mask position with numpy : 0.041033267974853516 nb_pixel_total : 95683 time to create 1 rle with old method : 0.10973191261291504 length of segment : 330 time for calcul the mask position with numpy : 0.03134512901306152 nb_pixel_total : 71776 time to create 1 rle with old method : 0.08252739906311035 length of segment : 255 time for calcul the mask position with numpy : 0.0037703514099121094 nb_pixel_total : 34317 time to create 1 rle with old method : 0.03965163230895996 length of segment : 188 time for calcul the mask position with numpy : 0.00040030479431152344 nb_pixel_total : 9799 time to create 1 rle with old method : 0.011752843856811523 length of segment : 197 time for calcul the mask position with numpy : 0.004476070404052734 nb_pixel_total : 73962 time to create 1 rle with old method : 0.0828695297241211 length of segment : 528 time for calcul the mask position with numpy : 0.0022542476654052734 nb_pixel_total : 39035 time to create 1 rle with old method : 0.044406890869140625 length of segment : 207 time for calcul the mask position with numpy : 0.0016818046569824219 nb_pixel_total : 25256 time to create 1 rle with old method : 0.04133200645446777 length of segment : 204 time for calcul the mask position with numpy : 0.00077056884765625 nb_pixel_total : 9870 time to create 1 rle with old method : 0.01184988021850586 length of segment : 97 time for calcul the mask position with numpy : 0.0229794979095459 nb_pixel_total : 35088 time to create 1 rle with old method : 0.04681992530822754 length of segment : 200 time for calcul the mask position with numpy : 0.001443624496459961 nb_pixel_total : 11166 time to create 1 rle with old method : 0.013129711151123047 length of segment : 84 time for calcul the mask position with numpy : 0.00791168212890625 nb_pixel_total : 18679 time to create 1 rle with old method : 0.024214506149291992 length of segment : 155 time for calcul the mask position with numpy : 0.0009295940399169922 nb_pixel_total : 8448 time to create 1 rle with old method : 0.01049184799194336 length of segment : 106 time for calcul the mask position with numpy : 0.0020186901092529297 nb_pixel_total : 23756 time to create 1 rle with old method : 0.027788639068603516 length of segment : 188 time for calcul the mask position with numpy : 0.003011941909790039 nb_pixel_total : 21988 time to create 1 rle with old method : 0.02573370933532715 length of segment : 114 time for calcul the mask position with numpy : 0.005500078201293945 nb_pixel_total : 16169 time to create 1 rle with old method : 0.02195000648498535 length of segment : 278 time for calcul the mask position with numpy : 0.0007491111755371094 nb_pixel_total : 39443 time to create 1 rle with old method : 0.044214725494384766 length of segment : 177 time for calcul the mask position with numpy : 0.00611424446105957 nb_pixel_total : 15328 time to create 1 rle with old method : 0.02771592140197754 length of segment : 144 time for calcul the mask position with numpy : 0.041207075119018555 nb_pixel_total : 95104 time to create 1 rle with old method : 0.10935091972351074 length of segment : 317 time for calcul the mask position with numpy : 0.018932819366455078 nb_pixel_total : 106455 time to create 1 rle with old method : 0.1259608268737793 length of segment : 289 time for calcul the mask position with numpy : 0.0031425952911376953 nb_pixel_total : 29261 time to create 1 rle with old method : 0.034256696701049805 length of segment : 315 time for calcul the mask position with numpy : 0.0064547061920166016 nb_pixel_total : 89676 time to create 1 rle with old method : 0.10266423225402832 length of segment : 401 time for calcul the mask position with numpy : 0.0015096664428710938 nb_pixel_total : 21949 time to create 1 rle with old method : 0.026393890380859375 length of segment : 214 time for calcul the mask position with numpy : 0.0014090538024902344 nb_pixel_total : 16136 time to create 1 rle with old method : 0.01894211769104004 length of segment : 211 time for calcul the mask position with numpy : 0.0013227462768554688 nb_pixel_total : 16931 time to create 1 rle with old method : 0.019685983657836914 length of segment : 194 time for calcul the mask position with numpy : 0.0006511211395263672 nb_pixel_total : 9476 time to create 1 rle with old method : 0.01153874397277832 length of segment : 115 time for calcul the mask position with numpy : 0.027231454849243164 nb_pixel_total : 297714 time to create 1 rle with new method : 0.03438305854797363 length of segment : 955 time for calcul the mask position with numpy : 0.0010907649993896484 nb_pixel_total : 43178 time to create 1 rle with old method : 0.04749488830566406 length of segment : 410 time for calcul the mask position with numpy : 0.0028159618377685547 nb_pixel_total : 38140 time to create 1 rle with old method : 0.04437541961669922 length of segment : 268 time for calcul the mask position with numpy : 0.006033658981323242 nb_pixel_total : 76379 time to create 1 rle with old method : 0.08716225624084473 length of segment : 329 time for calcul the mask position with numpy : 0.002325773239135742 nb_pixel_total : 25287 time to create 1 rle with old method : 0.02964472770690918 length of segment : 244 time for calcul the mask position with numpy : 0.0010421276092529297 nb_pixel_total : 12348 time to create 1 rle with old method : 0.014551162719726562 length of segment : 149 time for calcul the mask position with numpy : 0.002337217330932617 nb_pixel_total : 32616 time to create 1 rle with old method : 0.037790775299072266 length of segment : 233 time for calcul the mask position with numpy : 0.0013840198516845703 nb_pixel_total : 14379 time to create 1 rle with old method : 0.017096757888793945 length of segment : 198 time for calcul the mask position with numpy : 0.0017008781433105469 nb_pixel_total : 27604 time to create 1 rle with old method : 0.03403615951538086 length of segment : 143 time for calcul the mask position with numpy : 0.015163898468017578 nb_pixel_total : 177142 time to create 1 rle with new method : 0.019107580184936523 length of segment : 437 time for calcul the mask position with numpy : 0.0019273757934570312 nb_pixel_total : 17807 time to create 1 rle with old method : 0.021786928176879883 length of segment : 330 time for calcul the mask position with numpy : 0.0030684471130371094 nb_pixel_total : 38730 time to create 1 rle with old method : 0.044077396392822266 length of segment : 296 time for calcul the mask position with numpy : 0.0011522769927978516 nb_pixel_total : 20506 time to create 1 rle with old method : 0.02453780174255371 length of segment : 196 time for calcul the mask position with numpy : 0.0012323856353759766 nb_pixel_total : 14771 time to create 1 rle with old method : 0.01784801483154297 length of segment : 139 time for calcul the mask position with numpy : 0.0032083988189697266 nb_pixel_total : 37516 time to create 1 rle with old method : 0.04724431037902832 length of segment : 191 time for calcul the mask position with numpy : 0.0008876323699951172 nb_pixel_total : 12308 time to create 1 rle with old method : 0.014843225479125977 length of segment : 107 time for calcul the mask position with numpy : 0.0016322135925292969 nb_pixel_total : 18028 time to create 1 rle with old method : 0.021692752838134766 length of segment : 339 time for calcul the mask position with numpy : 0.001169443130493164 nb_pixel_total : 17036 time to create 1 rle with old method : 0.021022796630859375 length of segment : 219 time for calcul the mask position with numpy : 0.0106658935546875 nb_pixel_total : 169918 time to create 1 rle with new method : 0.01063394546508789 length of segment : 728 time for calcul the mask position with numpy : 0.002812623977661133 nb_pixel_total : 28575 time to create 1 rle with old method : 0.035314321517944336 length of segment : 270 time for calcul the mask position with numpy : 0.0005919933319091797 nb_pixel_total : 8714 time to create 1 rle with old method : 0.010494709014892578 length of segment : 78 time for calcul the mask position with numpy : 0.0006985664367675781 nb_pixel_total : 8502 time to create 1 rle with old method : 0.010121583938598633 length of segment : 174 time for calcul the mask position with numpy : 0.006669044494628906 nb_pixel_total : 103620 time to create 1 rle with old method : 0.14053010940551758 length of segment : 447 time for calcul the mask position with numpy : 0.0022737979888916016 nb_pixel_total : 36318 time to create 1 rle with old method : 0.041349172592163086 length of segment : 354 time for calcul the mask position with numpy : 0.0021369457244873047 nb_pixel_total : 28134 time to create 1 rle with old method : 0.0322268009185791 length of segment : 116 time for calcul the mask position with numpy : 0.0007710456848144531 nb_pixel_total : 7879 time to create 1 rle with old method : 0.009336709976196289 length of segment : 113 time for calcul the mask position with numpy : 0.002942323684692383 nb_pixel_total : 38395 time to create 1 rle with old method : 0.043654680252075195 length of segment : 249 time for calcul the mask position with numpy : 0.016747474670410156 nb_pixel_total : 193403 time to create 1 rle with new method : 0.022140026092529297 length of segment : 821 time for calcul the mask position with numpy : 0.009045839309692383 nb_pixel_total : 121292 time to create 1 rle with old method : 0.1383519172668457 length of segment : 613 time for calcul the mask position with numpy : 0.0010602474212646484 nb_pixel_total : 13518 time to create 1 rle with old method : 0.015566110610961914 length of segment : 143 time for calcul the mask position with numpy : 0.003642559051513672 nb_pixel_total : 36618 time to create 1 rle with old method : 0.042711734771728516 length of segment : 395 time for calcul the mask position with numpy : 0.000997781753540039 nb_pixel_total : 8844 time to create 1 rle with old method : 0.010367393493652344 length of segment : 135 time for calcul the mask position with numpy : 0.004147052764892578 nb_pixel_total : 40347 time to create 1 rle with old method : 0.04721546173095703 length of segment : 259 time for calcul the mask position with numpy : 0.0010929107666015625 nb_pixel_total : 12216 time to create 1 rle with old method : 0.014638662338256836 length of segment : 117 time for calcul the mask position with numpy : 0.00043511390686035156 nb_pixel_total : 5558 time to create 1 rle with old method : 0.0066416263580322266 length of segment : 108 time for calcul the mask position with numpy : 0.0013477802276611328 nb_pixel_total : 20818 time to create 1 rle with old method : 0.02461981773376465 length of segment : 228 time for calcul the mask position with numpy : 0.0015223026275634766 nb_pixel_total : 26747 time to create 1 rle with old method : 0.03178668022155762 length of segment : 181 time for calcul the mask position with numpy : 0.0015273094177246094 nb_pixel_total : 19939 time to create 1 rle with old method : 0.02401447296142578 length of segment : 161 time for calcul the mask position with numpy : 0.012253999710083008 nb_pixel_total : 169397 time to create 1 rle with new method : 0.012900829315185547 length of segment : 645 time for calcul the mask position with numpy : 0.0004947185516357422 nb_pixel_total : 6711 time to create 1 rle with old method : 0.0082855224609375 length of segment : 64 time for calcul the mask position with numpy : 0.00022268295288085938 nb_pixel_total : 5266 time to create 1 rle with old method : 0.006577491760253906 length of segment : 112 time for calcul the mask position with numpy : 0.0013523101806640625 nb_pixel_total : 14909 time to create 1 rle with old method : 0.018086910247802734 length of segment : 132 time for calcul the mask position with numpy : 0.028483867645263672 nb_pixel_total : 498055 time to create 1 rle with new method : 0.046506404876708984 length of segment : 567 time for calcul the mask position with numpy : 0.0009989738464355469 nb_pixel_total : 11108 time to create 1 rle with old method : 0.013713598251342773 length of segment : 171 time for calcul the mask position with numpy : 0.00617527961730957 nb_pixel_total : 89906 time to create 1 rle with old method : 0.09987854957580566 length of segment : 424 time for calcul the mask position with numpy : 0.0022656917572021484 nb_pixel_total : 45708 time to create 1 rle with old method : 0.052555084228515625 length of segment : 151 time for calcul the mask position with numpy : 0.0007097721099853516 nb_pixel_total : 11517 time to create 1 rle with old method : 0.013697385787963867 length of segment : 122 time for calcul the mask position with numpy : 0.0005404949188232422 nb_pixel_total : 6526 time to create 1 rle with old method : 0.007891416549682617 length of segment : 120 time for calcul the mask position with numpy : 0.01394033432006836 nb_pixel_total : 133051 time to create 1 rle with old method : 0.17384743690490723 length of segment : 855 time for calcul the mask position with numpy : 0.0014622211456298828 nb_pixel_total : 23116 time to create 1 rle with old method : 0.026071548461914062 length of segment : 181 time for calcul the mask position with numpy : 0.0005362033843994141 nb_pixel_total : 8974 time to create 1 rle with old method : 0.010439872741699219 length of segment : 140 time for calcul the mask position with numpy : 0.0012335777282714844 nb_pixel_total : 11046 time to create 1 rle with old method : 0.012988090515136719 length of segment : 170 time for calcul the mask position with numpy : 0.0006477832794189453 nb_pixel_total : 27952 time to create 1 rle with old method : 0.0327606201171875 length of segment : 307 time for calcul the mask position with numpy : 0.0008838176727294922 nb_pixel_total : 11997 time to create 1 rle with old method : 0.015861988067626953 length of segment : 117 time for calcul the mask position with numpy : 0.0004982948303222656 nb_pixel_total : 9538 time to create 1 rle with old method : 0.011532783508300781 length of segment : 68 time for calcul the mask position with numpy : 0.014923572540283203 nb_pixel_total : 269566 time to create 1 rle with new method : 0.018777847290039062 length of segment : 783 time for calcul the mask position with numpy : 0.0033004283905029297 nb_pixel_total : 45481 time to create 1 rle with old method : 0.05158686637878418 length of segment : 405 time for calcul the mask position with numpy : 0.0014634132385253906 nb_pixel_total : 21531 time to create 1 rle with old method : 0.024927854537963867 length of segment : 313 time for calcul the mask position with numpy : 0.00060272216796875 nb_pixel_total : 23572 time to create 1 rle with old method : 0.02680182456970215 length of segment : 334 time for calcul the mask position with numpy : 0.001931905746459961 nb_pixel_total : 33371 time to create 1 rle with old method : 0.03844428062438965 length of segment : 162 time for calcul the mask position with numpy : 0.0014853477478027344 nb_pixel_total : 9871 time to create 1 rle with old method : 0.011746883392333984 length of segment : 290 time for calcul the mask position with numpy : 0.0005099773406982422 nb_pixel_total : 9572 time to create 1 rle with old method : 0.011309146881103516 length of segment : 89 time for calcul the mask position with numpy : 0.0001773834228515625 nb_pixel_total : 6528 time to create 1 rle with old method : 0.007904529571533203 length of segment : 72 time for calcul the mask position with numpy : 0.0010678768157958984 nb_pixel_total : 15883 time to create 1 rle with old method : 0.018332242965698242 length of segment : 121 time for calcul the mask position with numpy : 0.0009169578552246094 nb_pixel_total : 17464 time to create 1 rle with old method : 0.020976781845092773 length of segment : 118 time for calcul the mask position with numpy : 0.0010609626770019531 nb_pixel_total : 19853 time to create 1 rle with old method : 0.022885560989379883 length of segment : 171 time for calcul the mask position with numpy : 0.0013210773468017578 nb_pixel_total : 23668 time to create 1 rle with old method : 0.02737283706665039 length of segment : 318 time for calcul the mask position with numpy : 0.0053942203521728516 nb_pixel_total : 95232 time to create 1 rle with old method : 0.10767793655395508 length of segment : 392 time for calcul the mask position with numpy : 0.0005273818969726562 nb_pixel_total : 14659 time to create 1 rle with old method : 0.017513036727905273 length of segment : 138 time for calcul the mask position with numpy : 0.0016636848449707031 nb_pixel_total : 26365 time to create 1 rle with old method : 0.029486417770385742 length of segment : 300 time for calcul the mask position with numpy : 0.005288839340209961 nb_pixel_total : 95095 time to create 1 rle with old method : 0.10626626014709473 length of segment : 362 time for calcul the mask position with numpy : 0.001756429672241211 nb_pixel_total : 31249 time to create 1 rle with old method : 0.036530494689941406 length of segment : 221 time for calcul the mask position with numpy : 0.010999441146850586 nb_pixel_total : 135616 time to create 1 rle with old method : 0.1539626121520996 length of segment : 510 time for calcul the mask position with numpy : 0.02139568328857422 nb_pixel_total : 462372 time to create 1 rle with new method : 0.04104924201965332 length of segment : 688 time for calcul the mask position with numpy : 0.0008897781372070312 nb_pixel_total : 11418 time to create 1 rle with old method : 0.013396024703979492 length of segment : 169 time for calcul the mask position with numpy : 0.0006310939788818359 nb_pixel_total : 11419 time to create 1 rle with old method : 0.013578653335571289 length of segment : 118 time for calcul the mask position with numpy : 0.0040531158447265625 nb_pixel_total : 73739 time to create 1 rle with old method : 0.08459734916687012 length of segment : 458 time for calcul the mask position with numpy : 0.0020074844360351562 nb_pixel_total : 45920 time to create 1 rle with old method : 0.052458763122558594 length of segment : 152 time for calcul the mask position with numpy : 0.000728607177734375 nb_pixel_total : 25417 time to create 1 rle with old method : 0.0290067195892334 length of segment : 194 time for calcul the mask position with numpy : 0.0007748603820800781 nb_pixel_total : 29074 time to create 1 rle with old method : 0.03573894500732422 length of segment : 207 time for calcul the mask position with numpy : 0.0012097358703613281 nb_pixel_total : 21463 time to create 1 rle with old method : 0.024411439895629883 length of segment : 159 time for calcul the mask position with numpy : 0.0024111270904541016 nb_pixel_total : 23799 time to create 1 rle with old method : 0.027146339416503906 length of segment : 269 time for calcul the mask position with numpy : 0.00016760826110839844 nb_pixel_total : 6906 time to create 1 rle with old method : 0.008130550384521484 length of segment : 66 time for calcul the mask position with numpy : 0.0007381439208984375 nb_pixel_total : 11068 time to create 1 rle with old method : 0.012825489044189453 length of segment : 112 time for calcul the mask position with numpy : 0.005009174346923828 nb_pixel_total : 98817 time to create 1 rle with old method : 0.10854959487915039 length of segment : 451 time for calcul the mask position with numpy : 0.0005927085876464844 nb_pixel_total : 9565 time to create 1 rle with old method : 0.011932849884033203 length of segment : 68 time for calcul the mask position with numpy : 0.009577512741088867 nb_pixel_total : 122672 time to create 1 rle with old method : 0.1425943374633789 length of segment : 407 time for calcul the mask position with numpy : 0.012192726135253906 nb_pixel_total : 202370 time to create 1 rle with new method : 0.01554107666015625 length of segment : 795 time for calcul the mask position with numpy : 0.0011811256408691406 nb_pixel_total : 13874 time to create 1 rle with old method : 0.01693868637084961 length of segment : 194 time for calcul the mask position with numpy : 0.0007364749908447266 nb_pixel_total : 9237 time to create 1 rle with old method : 0.011016130447387695 length of segment : 132 time for calcul the mask position with numpy : 0.0011210441589355469 nb_pixel_total : 18008 time to create 1 rle with old method : 0.021065950393676758 length of segment : 126 time for calcul the mask position with numpy : 0.0015690326690673828 nb_pixel_total : 19435 time to create 1 rle with old method : 0.022432565689086914 length of segment : 196 time for calcul the mask position with numpy : 0.001295328140258789 nb_pixel_total : 11657 time to create 1 rle with old method : 0.013398885726928711 length of segment : 206 time for calcul the mask position with numpy : 0.0012331008911132812 nb_pixel_total : 17637 time to create 1 rle with old method : 0.020520687103271484 length of segment : 277 time for calcul the mask position with numpy : 0.0013093948364257812 nb_pixel_total : 32905 time to create 1 rle with old method : 0.038057804107666016 length of segment : 207 time for calcul the mask position with numpy : 0.008257150650024414 nb_pixel_total : 188929 time to create 1 rle with new method : 0.010033369064331055 length of segment : 459 time for calcul the mask position with numpy : 0.0011343955993652344 nb_pixel_total : 20225 time to create 1 rle with old method : 0.02919936180114746 length of segment : 161 time for calcul the mask position with numpy : 0.0004527568817138672 nb_pixel_total : 5567 time to create 1 rle with old method : 0.009386062622070312 length of segment : 80 time for calcul the mask position with numpy : 0.0011363029479980469 nb_pixel_total : 16516 time to create 1 rle with old method : 0.02093672752380371 length of segment : 120 time for calcul the mask position with numpy : 0.0011610984802246094 nb_pixel_total : 17816 time to create 1 rle with old method : 0.021214962005615234 length of segment : 128 time for calcul the mask position with numpy : 0.0024919509887695312 nb_pixel_total : 36762 time to create 1 rle with old method : 0.04283261299133301 length of segment : 323 time for calcul the mask position with numpy : 0.002856016159057617 nb_pixel_total : 61024 time to create 1 rle with old method : 0.07086014747619629 length of segment : 354 time for calcul the mask position with numpy : 0.0005927085876464844 nb_pixel_total : 9194 time to create 1 rle with old method : 0.010993242263793945 length of segment : 112 time for calcul the mask position with numpy : 0.022190332412719727 nb_pixel_total : 504788 time to create 1 rle with new method : 0.04425621032714844 length of segment : 574 time for calcul the mask position with numpy : 0.0006794929504394531 nb_pixel_total : 8490 time to create 1 rle with old method : 0.009927749633789062 length of segment : 161 time for calcul the mask position with numpy : 0.0014188289642333984 nb_pixel_total : 21244 time to create 1 rle with old method : 0.024982213973999023 length of segment : 176 time for calcul the mask position with numpy : 0.0008177757263183594 nb_pixel_total : 14957 time to create 1 rle with old method : 0.01873469352722168 length of segment : 113 time for calcul the mask position with numpy : 0.0013551712036132812 nb_pixel_total : 25344 time to create 1 rle with old method : 0.029050588607788086 length of segment : 160 time for calcul the mask position with numpy : 0.0057218074798583984 nb_pixel_total : 99102 time to create 1 rle with old method : 0.1364736557006836 length of segment : 488 time for calcul the mask position with numpy : 0.0008218288421630859 nb_pixel_total : 11140 time to create 1 rle with old method : 0.012961387634277344 length of segment : 113 time for calcul the mask position with numpy : 0.0006916522979736328 nb_pixel_total : 9073 time to create 1 rle with old method : 0.010729312896728516 length of segment : 140 time for calcul the mask position with numpy : 0.009473562240600586 nb_pixel_total : 172560 time to create 1 rle with new method : 0.012269020080566406 length of segment : 817 time for calcul the mask position with numpy : 0.0008254051208496094 nb_pixel_total : 11542 time to create 1 rle with old method : 0.013953447341918945 length of segment : 102 time for calcul the mask position with numpy : 0.0006182193756103516 nb_pixel_total : 8873 time to create 1 rle with old method : 0.010697603225708008 length of segment : 86 time for calcul the mask position with numpy : 0.00045013427734375 nb_pixel_total : 16273 time to create 1 rle with old method : 0.019228696823120117 length of segment : 136 time for calcul the mask position with numpy : 0.006119966506958008 nb_pixel_total : 158702 time to create 1 rle with new method : 0.006521463394165039 length of segment : 445 time for calcul the mask position with numpy : 0.0014171600341796875 nb_pixel_total : 35297 time to create 1 rle with old method : 0.04047656059265137 length of segment : 134 time for calcul the mask position with numpy : 0.00023412704467773438 nb_pixel_total : 10930 time to create 1 rle with old method : 0.012691736221313477 length of segment : 127 time for calcul the mask position with numpy : 0.004073143005371094 nb_pixel_total : 62868 time to create 1 rle with old method : 0.07127618789672852 length of segment : 691 time for calcul the mask position with numpy : 0.0017726421356201172 nb_pixel_total : 37028 time to create 1 rle with old method : 0.04195523262023926 length of segment : 232 time for calcul the mask position with numpy : 0.009830951690673828 nb_pixel_total : 249102 time to create 1 rle with new method : 0.012067794799804688 length of segment : 639 time for calcul the mask position with numpy : 0.0005578994750976562 nb_pixel_total : 11006 time to create 1 rle with old method : 0.013043642044067383 length of segment : 110 time for calcul the mask position with numpy : 0.001537322998046875 nb_pixel_total : 48814 time to create 1 rle with old method : 0.054372310638427734 length of segment : 275 time for calcul the mask position with numpy : 0.0005950927734375 nb_pixel_total : 19322 time to create 1 rle with old method : 0.02176666259765625 length of segment : 174 time for calcul the mask position with numpy : 0.0015869140625 nb_pixel_total : 22190 time to create 1 rle with old method : 0.024157047271728516 length of segment : 295 time for calcul the mask position with numpy : 0.0015914440155029297 nb_pixel_total : 36288 time to create 1 rle with old method : 0.040628671646118164 length of segment : 255 time for calcul the mask position with numpy : 0.0008511543273925781 nb_pixel_total : 14143 time to create 1 rle with old method : 0.01625370979309082 length of segment : 260 time for calcul the mask position with numpy : 0.0008077621459960938 nb_pixel_total : 8663 time to create 1 rle with old method : 0.010301589965820312 length of segment : 124 time for calcul the mask position with numpy : 0.0007359981536865234 nb_pixel_total : 12921 time to create 1 rle with old method : 0.014908552169799805 length of segment : 184 time for calcul the mask position with numpy : 0.0003895759582519531 nb_pixel_total : 6072 time to create 1 rle with old method : 0.0070192813873291016 length of segment : 74 time for calcul the mask position with numpy : 0.0003268718719482422 nb_pixel_total : 10122 time to create 1 rle with old method : 0.011786460876464844 length of segment : 72 time for calcul the mask position with numpy : 0.0007033348083496094 nb_pixel_total : 32874 time to create 1 rle with old method : 0.03718447685241699 length of segment : 175 time for calcul the mask position with numpy : 0.0020644664764404297 nb_pixel_total : 53968 time to create 1 rle with old method : 0.05854463577270508 length of segment : 365 time for calcul the mask position with numpy : 0.001682281494140625 nb_pixel_total : 26123 time to create 1 rle with old method : 0.029702186584472656 length of segment : 262 time for calcul the mask position with numpy : 0.0010728836059570312 nb_pixel_total : 21381 time to create 1 rle with old method : 0.025032997131347656 length of segment : 199 time for calcul the mask position with numpy : 0.0019385814666748047 nb_pixel_total : 38011 time to create 1 rle with old method : 0.04342079162597656 length of segment : 326 time for calcul the mask position with numpy : 0.002092599868774414 nb_pixel_total : 24177 time to create 1 rle with old method : 0.028395652770996094 length of segment : 297 time spent for convertir_results : 28.70167112350464 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 286 chid ids of type : 3594 Number RLEs to save : 80235 save missing photos in datou_result : time spend for datou_step_exec : 163.34912586212158 time spend to save output : 5.531387567520142 total time spend for step 1 : 168.88051342964172 step2:crop_condition Mon Mar 31 13:03:18 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 11 ! batch 1 Loaded 286 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 ! map_result returned by crop_photo_return_map_crop : length : 168 About to insert : list_path_to_insert length 168 new photo from crops ! About to upload 168 photos upload in portfolio : 3736932 init cache_photo without model_param we have 168 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743419042_3276679 we have uploaded 168 photos in the portfolio 3736932 time of upload the photos Elapsed time : 45.544132471084595 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.7} filtre for class : carton hashtag_id of this class : 492774966 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 73 About to insert : list_path_to_insert length 73 new photo from crops ! About to upload 73 photos upload in portfolio : 3736932 init cache_photo without model_param we have 73 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743419114_3276679 we have uploaded 73 photos in the portfolio 3736932 time of upload the photos Elapsed time : 21.447835445404053 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.7} filtre for class : metal hashtag_id of this class : 492628673 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 3736932 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743419137_3276679 we have uploaded 4 photos in the portfolio 3736932 time of upload the photos Elapsed time : 1.693467617034912 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.7} filtre for class : pet_clair hashtag_id of this class : 2107755846 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 22 About to insert : list_path_to_insert length 22 new photo from crops ! About to upload 22 photos upload in portfolio : 3736932 init cache_photo without model_param we have 22 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743419150_3276679 we have uploaded 22 photos in the portfolio 3736932 time of upload the photos Elapsed time : 9.46142029762268 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.7} filtre for class : autre hashtag_id of this class : 494826614 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 9 About to insert : list_path_to_insert length 9 new photo from crops ! About to upload 9 photos upload in portfolio : 3736932 init cache_photo without model_param we have 9 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743419163_3276679 we have uploaded 9 photos in the portfolio 3736932 time of upload the photos Elapsed time : 3.5374977588653564 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.7} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.7} filtre for class : pet_fonce hashtag_id of this class : 2107755900 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! 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 : 10 About to insert : list_path_to_insert length 10 new photo from crops ! About to upload 10 photos upload in portfolio : 3736932 init cache_photo without model_param we have 10 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1743419171_3276679 we have uploaded 10 photos in the portfolio 3736932 time of upload the photos Elapsed time : 3.2367279529571533 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 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1348990554, 1348990549, 1348990539, 1348990537, 1348990534, 1348990500, 1348990497, 1348990491, 1348990489, 1348990485, 1348990483] Looping around the photos to save general results len do output : 286 /1348997850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348997999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998219Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998221Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998223Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998226Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998236Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998238Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998297Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998298Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998300Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1348998305Didn'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, '2708834') ('3318', '21906642', '1348990554', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990549', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990539', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990537', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990534', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990500', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990497', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990491', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990489', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990485', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990483', None, None, None, None, None, '2708834') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 869 time used for this insertion : 0.6953568458557129 save_final save missing photos in datou_result : time spend for datou_step_exec : 175.5960533618927 time spend to save output : 0.7026228904724121 total time spend for step 2 : 176.2986762523651 step3:rle_unique_nms_with_priority Mon Mar 31 13:06:15 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 286 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ No data in photo_id : 1348990554 No data in photo_id : 1348990549 nb_obj : 22 nb_hashtags : 4 time to prepare the origin masks : 9.381863832473755 time for calcul the mask position with numpy : 0.3682432174682617 nb_pixel_total : 5361578 time to create 1 rle with new method : 0.7509729862213135 time for calcul the mask position with numpy : 0.027150392532348633 nb_pixel_total : 39806 time to create 1 rle with old method : 0.0627894401550293 time for calcul the mask position with numpy : 0.037554025650024414 nb_pixel_total : 6330 time to create 1 rle with old method : 0.014335870742797852 time for calcul the mask position with numpy : 0.03147292137145996 nb_pixel_total : 211452 time to create 1 rle with new method : 0.8005516529083252 time for calcul the mask position with numpy : 0.028597593307495117 nb_pixel_total : 6080 time to create 1 rle with old method : 0.00992131233215332 time for calcul the mask position with numpy : 0.027781009674072266 nb_pixel_total : 56271 time to create 1 rle with old method : 0.08912396430969238 time for calcul the mask position with numpy : 0.02696394920349121 nb_pixel_total : 33464 time to create 1 rle with old method : 0.052997589111328125 time for calcul the mask position with numpy : 0.030611276626586914 nb_pixel_total : 120220 time to create 1 rle with old method : 0.19063448905944824 time for calcul the mask position with numpy : 0.028717994689941406 nb_pixel_total : 38481 time to create 1 rle with old method : 0.04786539077758789 time for calcul the mask position with numpy : 0.02244734764099121 nb_pixel_total : 62875 time to create 1 rle with old method : 0.09520220756530762 time for calcul the mask position with numpy : 0.022577524185180664 nb_pixel_total : 43903 time to create 1 rle with old method : 0.05010199546813965 time for calcul the mask position with numpy : 0.022666215896606445 nb_pixel_total : 15913 time to create 1 rle with old method : 0.01831197738647461 time for calcul the mask position with numpy : 0.022722721099853516 nb_pixel_total : 19452 time to create 1 rle with old method : 0.022472858428955078 time for calcul the mask position with numpy : 0.02738046646118164 nb_pixel_total : 93080 time to create 1 rle with old method : 0.11775469779968262 time for calcul the mask position with numpy : 0.025168895721435547 nb_pixel_total : 200557 time to create 1 rle with new method : 1.1026692390441895 time for calcul the mask position with numpy : 0.026226282119750977 nb_pixel_total : 9066 time to create 1 rle with old method : 0.014568328857421875 time for calcul the mask position with numpy : 0.023893117904663086 nb_pixel_total : 87087 time to create 1 rle with old method : 0.11383581161499023 time for calcul the mask position with numpy : 0.025137901306152344 nb_pixel_total : 7836 time to create 1 rle with old method : 0.012620925903320312 time for calcul the mask position with numpy : 0.025236129760742188 nb_pixel_total : 116687 time to create 1 rle with old method : 0.1306467056274414 time for calcul the mask position with numpy : 0.02236175537109375 nb_pixel_total : 64858 time to create 1 rle with old method : 0.07381033897399902 time for calcul the mask position with numpy : 0.025674819946289062 nb_pixel_total : 395014 time to create 1 rle with new method : 0.3349599838256836 time for calcul the mask position with numpy : 0.023305416107177734 nb_pixel_total : 26751 time to create 1 rle with old method : 0.030535459518432617 time for calcul the mask position with numpy : 0.02276158332824707 nb_pixel_total : 33479 time to create 1 rle with old method : 0.03925013542175293 create new chi : 5.243316173553467 time to delete rle : 0.03654885292053223 batch 1 Loaded 45 chid ids of type : 3594 ++++++++++++++++++++++++++++++++Number RLEs to save : 18442 TO DO : save crop sub photo not yet done ! save time : 1.105417013168335 nb_obj : 24 nb_hashtags : 5 time to prepare the origin masks : 8.75068974494934 time for calcul the mask position with numpy : 0.3413505554199219 nb_pixel_total : 4429007 time to create 1 rle with new method : 0.5551407337188721 time for calcul the mask position with numpy : 0.03423047065734863 nb_pixel_total : 3359 time to create 1 rle with old method : 0.004126071929931641 time for calcul the mask position with numpy : 0.03467154502868652 nb_pixel_total : 6030 time to create 1 rle with old method : 0.006930351257324219 time for calcul the mask position with numpy : 0.03435659408569336 nb_pixel_total : 19421 time to create 1 rle with old method : 0.021956682205200195 time for calcul the mask position with numpy : 0.022681474685668945 nb_pixel_total : 4097 time to create 1 rle with old method : 0.004750251770019531 time for calcul the mask position with numpy : 0.022031307220458984 nb_pixel_total : 104824 time to create 1 rle with old method : 0.11507177352905273 time for calcul the mask position with numpy : 0.02053213119506836 nb_pixel_total : 20499 time to create 1 rle with old method : 0.023035049438476562 time for calcul the mask position with numpy : 0.030055761337280273 nb_pixel_total : 34226 time to create 1 rle with old method : 0.05455732345581055 time for calcul the mask position with numpy : 0.03629112243652344 nb_pixel_total : 142490 time to create 1 rle with old method : 0.15804481506347656 time for calcul the mask position with numpy : 0.038575172424316406 nb_pixel_total : 527318 time to create 1 rle with new method : 0.6646091938018799 time for calcul the mask position with numpy : 0.03380465507507324 nb_pixel_total : 43424 time to create 1 rle with old method : 0.047593116760253906 time for calcul the mask position with numpy : 0.03216266632080078 nb_pixel_total : 44678 time to create 1 rle with old method : 0.0493016242980957 time for calcul the mask position with numpy : 0.03382253646850586 nb_pixel_total : 10266 time to create 1 rle with old method : 0.011834144592285156 time for calcul the mask position with numpy : 0.03434109687805176 nb_pixel_total : 16891 time to create 1 rle with old method : 0.018700122833251953 time for calcul the mask position with numpy : 0.03425025939941406 nb_pixel_total : 39217 time to create 1 rle with old method : 0.042527198791503906 time for calcul the mask position with numpy : 0.029521465301513672 nb_pixel_total : 18864 time to create 1 rle with old method : 0.02079010009765625 time for calcul the mask position with numpy : 0.02394890785217285 nb_pixel_total : 456939 time to create 1 rle with new method : 0.4765348434448242 time for calcul the mask position with numpy : 0.021813154220581055 nb_pixel_total : 28250 time to create 1 rle with old method : 0.03047657012939453 time for calcul the mask position with numpy : 0.02093219757080078 nb_pixel_total : 10508 time to create 1 rle with old method : 0.011373043060302734 time for calcul the mask position with numpy : 0.021402835845947266 nb_pixel_total : 10955 time to create 1 rle with old method : 0.012268781661987305 time for calcul the mask position with numpy : 0.0211637020111084 nb_pixel_total : 37539 time to create 1 rle with old method : 0.03899359703063965 time for calcul the mask position with numpy : 0.020553112030029297 nb_pixel_total : 199382 time to create 1 rle with new method : 0.6095833778381348 time for calcul the mask position with numpy : 0.0252530574798584 nb_pixel_total : 4987 time to create 1 rle with old method : 0.005622386932373047 time for calcul the mask position with numpy : 0.021709918975830078 nb_pixel_total : 13579 time to create 1 rle with old method : 0.014615297317504883 time for calcul the mask position with numpy : 0.027175188064575195 nb_pixel_total : 823490 time to create 1 rle with new method : 0.6411447525024414 create new chi : 4.78328013420105 time to delete rle : 0.003983736038208008 batch 1 Loaded 49 chid ids of type : 3594 ++++++++++++++++++++++++++++++Number RLEs to save : 16616 TO DO : save crop sub photo not yet done ! save time : 1.3522841930389404 nb_obj : 23 nb_hashtags : 3 time to prepare the origin masks : 8.434579849243164 time for calcul the mask position with numpy : 0.5043618679046631 nb_pixel_total : 6003501 time to create 1 rle with new method : 0.6091375350952148 time for calcul the mask position with numpy : 0.03447914123535156 nb_pixel_total : 9286 time to create 1 rle with old method : 0.010470390319824219 time for calcul the mask position with numpy : 0.03642845153808594 nb_pixel_total : 8284 time to create 1 rle with old method : 0.00932931900024414 time for calcul the mask position with numpy : 0.024408817291259766 nb_pixel_total : 570 time to create 1 rle with old method : 0.0006735324859619141 time for calcul the mask position with numpy : 0.021170854568481445 nb_pixel_total : 27510 time to create 1 rle with old method : 0.02971172332763672 time for calcul the mask position with numpy : 0.021028757095336914 nb_pixel_total : 6308 time to create 1 rle with old method : 0.0068171024322509766 time for calcul the mask position with numpy : 0.02069711685180664 nb_pixel_total : 12162 time to create 1 rle with old method : 0.013469696044921875 time for calcul the mask position with numpy : 0.020305156707763672 nb_pixel_total : 8379 time to create 1 rle with old method : 0.009353876113891602 time for calcul the mask position with numpy : 0.021750211715698242 nb_pixel_total : 55595 time to create 1 rle with old method : 0.060750722885131836 time for calcul the mask position with numpy : 0.024417400360107422 nb_pixel_total : 318703 time to create 1 rle with new method : 0.5548450946807861 time for calcul the mask position with numpy : 0.02129364013671875 nb_pixel_total : 11283 time to create 1 rle with old method : 0.012579917907714844 time for calcul the mask position with numpy : 0.019861221313476562 nb_pixel_total : 26972 time to create 1 rle with old method : 0.029044151306152344 time for calcul the mask position with numpy : 0.021254539489746094 nb_pixel_total : 47108 time to create 1 rle with old method : 0.052501678466796875 time for calcul the mask position with numpy : 0.0238189697265625 nb_pixel_total : 232576 time to create 1 rle with new method : 0.7376501560211182 time for calcul the mask position with numpy : 0.0223696231842041 nb_pixel_total : 5619 time to create 1 rle with old method : 0.006357431411743164 time for calcul the mask position with numpy : 0.023554086685180664 nb_pixel_total : 11733 time to create 1 rle with old method : 0.01900196075439453 time for calcul the mask position with numpy : 0.023620128631591797 nb_pixel_total : 9248 time to create 1 rle with old method : 0.014596939086914062 time for calcul the mask position with numpy : 0.021512508392333984 nb_pixel_total : 20356 time to create 1 rle with old method : 0.022305727005004883 time for calcul the mask position with numpy : 0.021723508834838867 nb_pixel_total : 31782 time to create 1 rle with old method : 0.03531932830810547 time for calcul the mask position with numpy : 0.022547483444213867 nb_pixel_total : 72674 time to create 1 rle with old method : 0.0852365493774414 time for calcul the mask position with numpy : 0.023825883865356445 nb_pixel_total : 84669 time to create 1 rle with old method : 0.09384489059448242 time for calcul the mask position with numpy : 0.021175861358642578 nb_pixel_total : 7816 time to create 1 rle with old method : 0.008997440338134766 time for calcul the mask position with numpy : 0.022025108337402344 nb_pixel_total : 31902 time to create 1 rle with old method : 0.03533434867858887 time for calcul the mask position with numpy : 0.020877599716186523 nb_pixel_total : 6204 time to create 1 rle with old method : 0.007029056549072266 create new chi : 3.5857491493225098 time to delete rle : 0.003458261489868164 batch 1 Loaded 47 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++Number RLEs to save : 13609 TO DO : save crop sub photo not yet done ! save time : 0.8414249420166016 nb_obj : 29 nb_hashtags : 3 time to prepare the origin masks : 4.056873798370361 time for calcul the mask position with numpy : 0.5037939548492432 nb_pixel_total : 5379753 time to create 1 rle with new method : 0.7186763286590576 time for calcul the mask position with numpy : 0.029029130935668945 nb_pixel_total : 10186 time to create 1 rle with old method : 0.011694669723510742 time for calcul the mask position with numpy : 0.02908635139465332 nb_pixel_total : 34166 time to create 1 rle with old method : 0.037828922271728516 time for calcul the mask position with numpy : 0.0285341739654541 nb_pixel_total : 6326 time to create 1 rle with old method : 0.00716853141784668 time for calcul the mask position with numpy : 0.028940677642822266 nb_pixel_total : 25589 time to create 1 rle with old method : 0.028572559356689453 time for calcul the mask position with numpy : 0.02889084815979004 nb_pixel_total : 95678 time to create 1 rle with old method : 0.10541629791259766 time for calcul the mask position with numpy : 0.02859044075012207 nb_pixel_total : 15531 time to create 1 rle with old method : 0.01778697967529297 time for calcul the mask position with numpy : 0.0317835807800293 nb_pixel_total : 297280 time to create 1 rle with new method : 0.41038036346435547 time for calcul the mask position with numpy : 0.028760433197021484 nb_pixel_total : 16278 time to create 1 rle with old method : 0.017978906631469727 time for calcul the mask position with numpy : 0.02894282341003418 nb_pixel_total : 6898 time to create 1 rle with old method : 0.007875204086303711 time for calcul the mask position with numpy : 0.03137660026550293 nb_pixel_total : 19604 time to create 1 rle with old method : 0.023799419403076172 time for calcul the mask position with numpy : 0.02861499786376953 nb_pixel_total : 25935 time to create 1 rle with old method : 0.028821706771850586 time for calcul the mask position with numpy : 0.028512954711914062 nb_pixel_total : 71180 time to create 1 rle with old method : 0.07776284217834473 time for calcul the mask position with numpy : 0.028842687606811523 nb_pixel_total : 52122 time to create 1 rle with old method : 0.05770611763000488 time for calcul the mask position with numpy : 0.029004573822021484 nb_pixel_total : 21986 time to create 1 rle with old method : 0.024347543716430664 time for calcul the mask position with numpy : 0.029072046279907227 nb_pixel_total : 82259 time to create 1 rle with old method : 0.09114289283752441 time for calcul the mask position with numpy : 0.029628992080688477 nb_pixel_total : 132029 time to create 1 rle with old method : 0.14414191246032715 time for calcul the mask position with numpy : 0.028244495391845703 nb_pixel_total : 13657 time to create 1 rle with old method : 0.014620780944824219 time for calcul the mask position with numpy : 0.027492284774780273 nb_pixel_total : 49221 time to create 1 rle with old method : 0.052449941635131836 time for calcul the mask position with numpy : 0.029664993286132812 nb_pixel_total : 317065 time to create 1 rle with new method : 0.7488894462585449 time for calcul the mask position with numpy : 0.027292251586914062 nb_pixel_total : 12897 time to create 1 rle with old method : 0.014204740524291992 time for calcul the mask position with numpy : 0.027709007263183594 nb_pixel_total : 7980 time to create 1 rle with old method : 0.008643388748168945 time for calcul the mask position with numpy : 0.027400970458984375 nb_pixel_total : 37618 time to create 1 rle with old method : 0.040025949478149414 time for calcul the mask position with numpy : 0.02705526351928711 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006954669952392578 time for calcul the mask position with numpy : 0.02735733985900879 nb_pixel_total : 67160 time to create 1 rle with old method : 0.07026171684265137 time for calcul the mask position with numpy : 0.028073549270629883 nb_pixel_total : 14662 time to create 1 rle with old method : 0.015993833541870117 time for calcul the mask position with numpy : 0.029665708541870117 nb_pixel_total : 108263 time to create 1 rle with old method : 0.11674785614013672 time for calcul the mask position with numpy : 0.028790712356567383 nb_pixel_total : 40724 time to create 1 rle with old method : 0.04493093490600586 time for calcul the mask position with numpy : 0.02890157699584961 nb_pixel_total : 69904 time to create 1 rle with old method : 0.07675313949584961 time for calcul the mask position with numpy : 0.028412580490112305 nb_pixel_total : 17828 time to create 1 rle with old method : 0.02008843421936035 create new chi : 4.460117816925049 time to delete rle : 0.002853870391845703 batch 1 Loaded 60 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 19762 TO DO : save crop sub photo not yet done ! save time : 1.1620173454284668 nb_obj : 44 nb_hashtags : 5 time to prepare the origin masks : 4.349868059158325 time for calcul the mask position with numpy : 0.3888850212097168 nb_pixel_total : 5039532 time to create 1 rle with new method : 0.8010013103485107 time for calcul the mask position with numpy : 0.028377294540405273 nb_pixel_total : 34317 time to create 1 rle with old method : 0.03720450401306152 time for calcul the mask position with numpy : 0.028447628021240234 nb_pixel_total : 11166 time to create 1 rle with old method : 0.012511253356933594 time for calcul the mask position with numpy : 0.028809309005737305 nb_pixel_total : 159182 time to create 1 rle with new method : 0.600059986114502 time for calcul the mask position with numpy : 0.028202533721923828 nb_pixel_total : 9799 time to create 1 rle with old method : 0.010896444320678711 time for calcul the mask position with numpy : 0.028714895248413086 nb_pixel_total : 230418 time to create 1 rle with new method : 0.3980751037597656 time for calcul the mask position with numpy : 0.03302311897277832 nb_pixel_total : 23756 time to create 1 rle with old method : 0.03553152084350586 time for calcul the mask position with numpy : 0.028645753860473633 nb_pixel_total : 95104 time to create 1 rle with old method : 0.10399436950683594 time for calcul the mask position with numpy : 0.02808237075805664 nb_pixel_total : 63499 time to create 1 rle with old method : 0.0697779655456543 time for calcul the mask position with numpy : 0.028422832489013672 nb_pixel_total : 22520 time to create 1 rle with old method : 0.024288177490234375 time for calcul the mask position with numpy : 0.028494596481323242 nb_pixel_total : 96469 time to create 1 rle with old method : 0.10480594635009766 time for calcul the mask position with numpy : 0.02879190444946289 nb_pixel_total : 71685 time to create 1 rle with old method : 0.0773007869720459 time for calcul the mask position with numpy : 0.027737140655517578 nb_pixel_total : 16707 time to create 1 rle with old method : 0.01852583885192871 time for calcul the mask position with numpy : 0.02819967269897461 nb_pixel_total : 47800 time to create 1 rle with old method : 0.05222892761230469 time for calcul the mask position with numpy : 0.0281984806060791 nb_pixel_total : 17809 time to create 1 rle with old method : 0.01963329315185547 time for calcul the mask position with numpy : 0.027849435806274414 nb_pixel_total : 28060 time to create 1 rle with old method : 0.031134605407714844 time for calcul the mask position with numpy : 0.02899909019470215 nb_pixel_total : 28800 time to create 1 rle with old method : 0.03325772285461426 time for calcul the mask position with numpy : 0.030623197555541992 nb_pixel_total : 71776 time to create 1 rle with old method : 0.08216261863708496 time for calcul the mask position with numpy : 0.02914905548095703 nb_pixel_total : 31104 time to create 1 rle with old method : 0.034807443618774414 time for calcul the mask position with numpy : 0.03010082244873047 nb_pixel_total : 95683 time to create 1 rle with old method : 0.11949658393859863 time for calcul the mask position with numpy : 0.030005216598510742 nb_pixel_total : 8802 time to create 1 rle with old method : 0.009993791580200195 time for calcul the mask position with numpy : 0.03347134590148926 nb_pixel_total : 14402 time to create 1 rle with old method : 0.016335487365722656 time for calcul the mask position with numpy : 0.029202699661254883 nb_pixel_total : 35088 time to create 1 rle with old method : 0.03933405876159668 time for calcul the mask position with numpy : 0.029394149780273438 nb_pixel_total : 5493 time to create 1 rle with old method : 0.00644993782043457 time for calcul the mask position with numpy : 0.028399229049682617 nb_pixel_total : 15328 time to create 1 rle with old method : 0.016948699951171875 time for calcul the mask position with numpy : 0.02827000617980957 nb_pixel_total : 18679 time to create 1 rle with old method : 0.02030181884765625 time for calcul the mask position with numpy : 0.028522491455078125 nb_pixel_total : 109886 time to create 1 rle with old method : 0.12179231643676758 time for calcul the mask position with numpy : 0.028795719146728516 nb_pixel_total : 46837 time to create 1 rle with old method : 0.06370043754577637 time for calcul the mask position with numpy : 0.03341937065124512 nb_pixel_total : 12821 time to create 1 rle with old method : 0.018428802490234375 time for calcul the mask position with numpy : 0.03125357627868652 nb_pixel_total : 25516 time to create 1 rle with old method : 0.04185843467712402 time for calcul the mask position with numpy : 0.032061100006103516 nb_pixel_total : 65183 time to create 1 rle with old method : 0.07262921333312988 time for calcul the mask position with numpy : 0.029440879821777344 nb_pixel_total : 32056 time to create 1 rle with old method : 0.03588461875915527 time for calcul the mask position with numpy : 0.02919936180114746 nb_pixel_total : 32144 time to create 1 rle with old method : 0.036277055740356445 time for calcul the mask position with numpy : 0.029303312301635742 nb_pixel_total : 39035 time to create 1 rle with old method : 0.04391336441040039 time for calcul the mask position with numpy : 0.028886795043945312 nb_pixel_total : 73962 time to create 1 rle with old method : 0.08527684211730957 time for calcul the mask position with numpy : 0.028692007064819336 nb_pixel_total : 62063 time to create 1 rle with old method : 0.09024548530578613 time for calcul the mask position with numpy : 0.037824392318725586 nb_pixel_total : 9870 time to create 1 rle with old method : 0.01383519172668457 time for calcul the mask position with numpy : 0.028967618942260742 nb_pixel_total : 25256 time to create 1 rle with old method : 0.028589963912963867 time for calcul the mask position with numpy : 0.029187679290771484 nb_pixel_total : 8254 time to create 1 rle with old method : 0.009319543838500977 time for calcul the mask position with numpy : 0.029331445693969727 nb_pixel_total : 106455 time to create 1 rle with old method : 0.1168370246887207 time for calcul the mask position with numpy : 0.02834630012512207 nb_pixel_total : 16169 time to create 1 rle with old method : 0.0177309513092041 time for calcul the mask position with numpy : 0.028712034225463867 nb_pixel_total : 60809 time to create 1 rle with old method : 0.06645989418029785 time for calcul the mask position with numpy : 0.027582406997680664 nb_pixel_total : 8448 time to create 1 rle with old method : 0.008961200714111328 time for calcul the mask position with numpy : 0.027472972869873047 nb_pixel_total : 1429 time to create 1 rle with old method : 0.0022530555725097656 time for calcul the mask position with numpy : 0.02821063995361328 nb_pixel_total : 21069 time to create 1 rle with old method : 0.023387670516967773 create new chi : 5.440812110900879 time to delete rle : 0.003267526626586914 batch 1 Loaded 89 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 23682 TO DO : save crop sub photo not yet done ! save time : 1.651902198791504 nb_obj : 48 nb_hashtags : 5 time to prepare the origin masks : 4.3529369831085205 time for calcul the mask position with numpy : 0.7550888061523438 nb_pixel_total : 5026872 time to create 1 rle with new method : 0.5763769149780273 time for calcul the mask position with numpy : 0.028477191925048828 nb_pixel_total : 6711 time to create 1 rle with old method : 0.01104736328125 time for calcul the mask position with numpy : 0.03281521797180176 nb_pixel_total : 17036 time to create 1 rle with old method : 0.02718186378479004 time for calcul the mask position with numpy : 0.0303041934967041 nb_pixel_total : 8714 time to create 1 rle with old method : 0.009518146514892578 time for calcul the mask position with numpy : 0.02835869789123535 nb_pixel_total : 27604 time to create 1 rle with old method : 0.030272960662841797 time for calcul the mask position with numpy : 0.02942204475402832 nb_pixel_total : 29261 time to create 1 rle with old method : 0.032073259353637695 time for calcul the mask position with numpy : 0.02995586395263672 nb_pixel_total : 293304 time to create 1 rle with new method : 0.8421885967254639 time for calcul the mask position with numpy : 0.030412673950195312 nb_pixel_total : 17807 time to create 1 rle with old method : 0.02046513557434082 time for calcul the mask position with numpy : 0.030481815338134766 nb_pixel_total : 193403 time to create 1 rle with new method : 0.5514650344848633 time for calcul the mask position with numpy : 0.02863788604736328 nb_pixel_total : 18028 time to create 1 rle with old method : 0.020018339157104492 time for calcul the mask position with numpy : 0.02851414680480957 nb_pixel_total : 8844 time to create 1 rle with old method : 0.00993800163269043 time for calcul the mask position with numpy : 0.029430389404296875 nb_pixel_total : 89676 time to create 1 rle with old method : 0.09917068481445312 time for calcul the mask position with numpy : 0.028605937957763672 nb_pixel_total : 8502 time to create 1 rle with old method : 0.009635686874389648 time for calcul the mask position with numpy : 0.0284578800201416 nb_pixel_total : 10073 time to create 1 rle with old method : 0.011352062225341797 time for calcul the mask position with numpy : 0.03075122833251953 nb_pixel_total : 14909 time to create 1 rle with old method : 0.01676201820373535 time for calcul the mask position with numpy : 0.027855873107910156 nb_pixel_total : 20414 time to create 1 rle with old method : 0.021930456161499023 time for calcul the mask position with numpy : 0.02715778350830078 nb_pixel_total : 36618 time to create 1 rle with old method : 0.03973960876464844 time for calcul the mask position with numpy : 0.02929544448852539 nb_pixel_total : 169918 time to create 1 rle with new method : 0.7856085300445557 time for calcul the mask position with numpy : 0.02914142608642578 nb_pixel_total : 25287 time to create 1 rle with old method : 0.028561115264892578 time for calcul the mask position with numpy : 0.0289766788482666 nb_pixel_total : 4448 time to create 1 rle with old method : 0.005323648452758789 time for calcul the mask position with numpy : 0.02892923355102539 nb_pixel_total : 12308 time to create 1 rle with old method : 0.013938188552856445 time for calcul the mask position with numpy : 0.029570579528808594 nb_pixel_total : 177142 time to create 1 rle with new method : 0.5735046863555908 time for calcul the mask position with numpy : 0.028853654861450195 nb_pixel_total : 16136 time to create 1 rle with old method : 0.017881155014038086 time for calcul the mask position with numpy : 0.028345346450805664 nb_pixel_total : 3818 time to create 1 rle with old method : 0.00418400764465332 time for calcul the mask position with numpy : 0.02885150909423828 nb_pixel_total : 103620 time to create 1 rle with old method : 0.14052605628967285 time for calcul the mask position with numpy : 0.029200315475463867 nb_pixel_total : 37516 time to create 1 rle with old method : 0.04152274131774902 time for calcul the mask position with numpy : 0.028207063674926758 nb_pixel_total : 32616 time to create 1 rle with old method : 0.03583860397338867 time for calcul the mask position with numpy : 0.028692960739135742 nb_pixel_total : 19939 time to create 1 rle with old method : 0.022328853607177734 time for calcul the mask position with numpy : 0.02811598777770996 nb_pixel_total : 36318 time to create 1 rle with old method : 0.03994107246398926 time for calcul the mask position with numpy : 0.02838754653930664 nb_pixel_total : 14379 time to create 1 rle with old method : 0.015976667404174805 time for calcul the mask position with numpy : 0.028898239135742188 nb_pixel_total : 121292 time to create 1 rle with old method : 0.1341872215270996 time for calcul the mask position with numpy : 0.028749704360961914 nb_pixel_total : 28575 time to create 1 rle with old method : 0.03200960159301758 time for calcul the mask position with numpy : 0.028393983840942383 nb_pixel_total : 28134 time to create 1 rle with old method : 0.03071451187133789 time for calcul the mask position with numpy : 0.028568506240844727 nb_pixel_total : 76379 time to create 1 rle with old method : 0.08530855178833008 time for calcul the mask position with numpy : 0.028757810592651367 nb_pixel_total : 21949 time to create 1 rle with old method : 0.02529168128967285 time for calcul the mask position with numpy : 0.02901458740234375 nb_pixel_total : 38711 time to create 1 rle with old method : 0.04398155212402344 time for calcul the mask position with numpy : 0.03070521354675293 nb_pixel_total : 16931 time to create 1 rle with old method : 0.018947839736938477 time for calcul the mask position with numpy : 0.028995990753173828 nb_pixel_total : 12159 time to create 1 rle with old method : 0.013658523559570312 time for calcul the mask position with numpy : 0.028722286224365234 nb_pixel_total : 38395 time to create 1 rle with old method : 0.04150843620300293 time for calcul the mask position with numpy : 0.028312206268310547 nb_pixel_total : 12348 time to create 1 rle with old method : 0.013855457305908203 time for calcul the mask position with numpy : 0.029282808303833008 nb_pixel_total : 26747 time to create 1 rle with old method : 0.03147530555725098 time for calcul the mask position with numpy : 0.029699087142944336 nb_pixel_total : 20818 time to create 1 rle with old method : 0.022929668426513672 time for calcul the mask position with numpy : 0.02831411361694336 nb_pixel_total : 7879 time to create 1 rle with old method : 0.008596181869506836 time for calcul the mask position with numpy : 0.029099464416503906 nb_pixel_total : 38140 time to create 1 rle with old method : 0.04226541519165039 time for calcul the mask position with numpy : 0.028984546661376953 nb_pixel_total : 13518 time to create 1 rle with old method : 0.014984607696533203 time for calcul the mask position with numpy : 0.028919458389282227 nb_pixel_total : 14771 time to create 1 rle with old method : 0.016527652740478516 time for calcul the mask position with numpy : 0.02887701988220215 nb_pixel_total : 9476 time to create 1 rle with old method : 0.010562419891357422 time for calcul the mask position with numpy : 0.029086828231811523 nb_pixel_total : 37239 time to create 1 rle with old method : 0.041770219802856445 time for calcul the mask position with numpy : 0.029003381729125977 nb_pixel_total : 5558 time to create 1 rle with old method : 0.006348609924316406 create new chi : 6.974261999130249 time to delete rle : 0.0049669742584228516 batch 1 Loaded 97 chid ids of type : 3594 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 26706 TO DO : save crop sub photo not yet done ! save time : 2.0057153701782227 nb_obj : 31 nb_hashtags : 5 time to prepare the origin masks : 4.199188470840454 time for calcul the mask position with numpy : 0.17595863342285156 nb_pixel_total : 5268929 time to create 1 rle with new method : 0.9277427196502686 time for calcul the mask position with numpy : 0.03076624870300293 nb_pixel_total : 45708 time to create 1 rle with old method : 0.05318427085876465 time for calcul the mask position with numpy : 0.030601024627685547 nb_pixel_total : 15883 time to create 1 rle with old method : 0.018588542938232422 time for calcul the mask position with numpy : 0.03049755096435547 nb_pixel_total : 269566 time to create 1 rle with new method : 0.8420605659484863 time for calcul the mask position with numpy : 0.02916574478149414 nb_pixel_total : 14659 time to create 1 rle with old method : 0.01639866828918457 time for calcul the mask position with numpy : 0.029279232025146484 nb_pixel_total : 33371 time to create 1 rle with old method : 0.036028146743774414 time for calcul the mask position with numpy : 0.029110193252563477 nb_pixel_total : 9572 time to create 1 rle with old method : 0.010731697082519531 time for calcul the mask position with numpy : 0.029282093048095703 nb_pixel_total : 95095 time to create 1 rle with old method : 0.10440731048583984 time for calcul the mask position with numpy : 0.02907729148864746 nb_pixel_total : 11517 time to create 1 rle with old method : 0.013031244277954102 time for calcul the mask position with numpy : 0.029056549072265625 nb_pixel_total : 19853 time to create 1 rle with old method : 0.022328853607177734 time for calcul the mask position with numpy : 0.02898120880126953 nb_pixel_total : 11108 time to create 1 rle with old method : 0.012463569641113281 time for calcul the mask position with numpy : 0.02915787696838379 nb_pixel_total : 11046 time to create 1 rle with old method : 0.012410402297973633 time for calcul the mask position with numpy : 0.0291900634765625 nb_pixel_total : 11997 time to create 1 rle with old method : 0.013507366180419922 time for calcul the mask position with numpy : 0.02912116050720215 nb_pixel_total : 9871 time to create 1 rle with old method : 0.011324405670166016 time for calcul the mask position with numpy : 0.029710054397583008 nb_pixel_total : 133051 time to create 1 rle with old method : 0.14924001693725586 time for calcul the mask position with numpy : 0.029665470123291016 nb_pixel_total : 95232 time to create 1 rle with old method : 0.10660147666931152 time for calcul the mask position with numpy : 0.028902053833007812 nb_pixel_total : 26365 time to create 1 rle with old method : 0.028750896453857422 time for calcul the mask position with numpy : 0.027573347091674805 nb_pixel_total : 8974 time to create 1 rle with old method : 0.009536266326904297 time for calcul the mask position with numpy : 0.02741098403930664 nb_pixel_total : 6526 time to create 1 rle with old method : 0.00732421875 time for calcul the mask position with numpy : 0.027822494506835938 nb_pixel_total : 23668 time to create 1 rle with old method : 0.025818586349487305 time for calcul the mask position with numpy : 0.02854633331298828 nb_pixel_total : 31249 time to create 1 rle with old method : 0.034206390380859375 time for calcul the mask position with numpy : 0.02774333953857422 nb_pixel_total : 21531 time to create 1 rle with old method : 0.023097515106201172 time for calcul the mask position with numpy : 0.027587413787841797 nb_pixel_total : 17464 time to create 1 rle with old method : 0.018914222717285156 time for calcul the mask position with numpy : 0.028996944427490234 nb_pixel_total : 135616 time to create 1 rle with old method : 0.14856457710266113 time for calcul the mask position with numpy : 0.031033992767333984 nb_pixel_total : 498055 time to create 1 rle with new method : 1.1312177181243896 time for calcul the mask position with numpy : 0.0293729305267334 nb_pixel_total : 89906 time to create 1 rle with old method : 0.09810376167297363 time for calcul the mask position with numpy : 0.028116464614868164 nb_pixel_total : 23116 time to create 1 rle with old method : 0.02549433708190918 time for calcul the mask position with numpy : 0.028486013412475586 nb_pixel_total : 45481 time to create 1 rle with old method : 0.049819231033325195 time for calcul the mask position with numpy : 0.027944087982177734 nb_pixel_total : 26193 time to create 1 rle with old method : 0.029091596603393555 time for calcul the mask position with numpy : 0.0290374755859375 nb_pixel_total : 23572 time to create 1 rle with old method : 0.02642035484313965 time for calcul the mask position with numpy : 0.02864217758178711 nb_pixel_total : 6528 time to create 1 rle with old method : 0.007531404495239258 time for calcul the mask position with numpy : 0.029630422592163086 nb_pixel_total : 9538 time to create 1 rle with old method : 0.010922431945800781 create new chi : 5.1821324825286865 time to delete rle : 0.003603219985961914 batch 1 Loaded 63 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 19105 TO DO : save crop sub photo not yet done ! save time : 1.4304275512695312 nb_obj : 30 nb_hashtags : 5 time to prepare the origin masks : 4.116704940795898 time for calcul the mask position with numpy : 0.6193554401397705 nb_pixel_total : 5416174 time to create 1 rle with new method : 1.0732812881469727 time for calcul the mask position with numpy : 0.029914379119873047 nb_pixel_total : 45920 time to create 1 rle with old method : 0.05178499221801758 time for calcul the mask position with numpy : 0.029754161834716797 nb_pixel_total : 16516 time to create 1 rle with old method : 0.02272319793701172 time for calcul the mask position with numpy : 0.030634403228759766 nb_pixel_total : 18008 time to create 1 rle with old method : 0.020552635192871094 time for calcul the mask position with numpy : 0.033577919006347656 nb_pixel_total : 98817 time to create 1 rle with old method : 0.11407208442687988 time for calcul the mask position with numpy : 0.02951955795288086 nb_pixel_total : 11419 time to create 1 rle with old method : 0.012978553771972656 time for calcul the mask position with numpy : 0.02876114845275879 nb_pixel_total : 11418 time to create 1 rle with old method : 0.01250457763671875 time for calcul the mask position with numpy : 0.028707504272460938 nb_pixel_total : 11657 time to create 1 rle with old method : 0.014078140258789062 time for calcul the mask position with numpy : 0.028882265090942383 nb_pixel_total : 11068 time to create 1 rle with old method : 0.012359857559204102 time for calcul the mask position with numpy : 0.028743982315063477 nb_pixel_total : 17637 time to create 1 rle with old method : 0.019550323486328125 time for calcul the mask position with numpy : 0.02853226661682129 nb_pixel_total : 9237 time to create 1 rle with old method : 0.010219812393188477 time for calcul the mask position with numpy : 0.03213763236999512 nb_pixel_total : 188929 time to create 1 rle with new method : 0.6519064903259277 time for calcul the mask position with numpy : 0.02891254425048828 nb_pixel_total : 20225 time to create 1 rle with old method : 0.022591829299926758 time for calcul the mask position with numpy : 0.02985692024230957 nb_pixel_total : 202370 time to create 1 rle with new method : 0.8418829441070557 time for calcul the mask position with numpy : 0.029024839401245117 nb_pixel_total : 61024 time to create 1 rle with old method : 0.06755256652832031 time for calcul the mask position with numpy : 0.028636693954467773 nb_pixel_total : 9194 time to create 1 rle with old method : 0.010096073150634766 time for calcul the mask position with numpy : 0.02873992919921875 nb_pixel_total : 5567 time to create 1 rle with old method : 0.006165266036987305 time for calcul the mask position with numpy : 0.028947830200195312 nb_pixel_total : 13874 time to create 1 rle with old method : 0.015794038772583008 time for calcul the mask position with numpy : 0.02980518341064453 nb_pixel_total : 36762 time to create 1 rle with old method : 0.040277719497680664 time for calcul the mask position with numpy : 0.0290069580078125 nb_pixel_total : 17816 time to create 1 rle with old method : 0.01992654800415039 time for calcul the mask position with numpy : 0.029433727264404297 nb_pixel_total : 19435 time to create 1 rle with old method : 0.02188897132873535 time for calcul the mask position with numpy : 0.030300617218017578 nb_pixel_total : 122672 time to create 1 rle with old method : 0.1376502513885498 time for calcul the mask position with numpy : 0.03977632522583008 nb_pixel_total : 462372 time to create 1 rle with new method : 1.2666757106781006 time for calcul the mask position with numpy : 0.029404163360595703 nb_pixel_total : 32905 time to create 1 rle with old method : 0.03715395927429199 time for calcul the mask position with numpy : 0.02927994728088379 nb_pixel_total : 25344 time to create 1 rle with old method : 0.028172731399536133 time for calcul the mask position with numpy : 0.029936552047729492 nb_pixel_total : 73739 time to create 1 rle with old method : 0.09242844581604004 time for calcul the mask position with numpy : 0.03339672088623047 nb_pixel_total : 21463 time to create 1 rle with old method : 0.027040719985961914 time for calcul the mask position with numpy : 0.031011343002319336 nb_pixel_total : 28408 time to create 1 rle with old method : 0.03510308265686035 time for calcul the mask position with numpy : 0.03823995590209961 nb_pixel_total : 23799 time to create 1 rle with old method : 0.03754162788391113 time for calcul the mask position with numpy : 0.03589200973510742 nb_pixel_total : 6906 time to create 1 rle with old method : 0.007878780364990234 time for calcul the mask position with numpy : 0.030873775482177734 nb_pixel_total : 9565 time to create 1 rle with old method : 0.010894536972045898 create new chi : 6.388425350189209 time to delete rle : 0.002888917922973633 batch 1 Loaded 61 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 16817 TO DO : save crop sub photo not yet done ! save time : 1.072547435760498 nb_obj : 34 nb_hashtags : 5 time to prepare the origin masks : 4.251177549362183 time for calcul the mask position with numpy : 0.8548135757446289 nb_pixel_total : 5210835 time to create 1 rle with new method : 1.0016160011291504 time for calcul the mask position with numpy : 0.03137993812561035 nb_pixel_total : 35297 time to create 1 rle with old method : 0.039653778076171875 time for calcul the mask position with numpy : 0.029876708984375 nb_pixel_total : 11542 time to create 1 rle with old method : 0.012982606887817383 time for calcul the mask position with numpy : 0.02858901023864746 nb_pixel_total : 6072 time to create 1 rle with old method : 0.007015228271484375 time for calcul the mask position with numpy : 0.0292818546295166 nb_pixel_total : 19322 time to create 1 rle with old method : 0.021981477737426758 time for calcul the mask position with numpy : 0.030579090118408203 nb_pixel_total : 249102 time to create 1 rle with new method : 1.2181503772735596 time for calcul the mask position with numpy : 0.029641389846801758 nb_pixel_total : 8873 time to create 1 rle with old method : 0.01182866096496582 time for calcul the mask position with numpy : 0.02952742576599121 nb_pixel_total : 11006 time to create 1 rle with old method : 0.012706518173217773 time for calcul the mask position with numpy : 0.029349565505981445 nb_pixel_total : 8490 time to create 1 rle with old method : 0.009752273559570312 time for calcul the mask position with numpy : 0.030004262924194336 nb_pixel_total : 53968 time to create 1 rle with old method : 0.061309099197387695 time for calcul the mask position with numpy : 0.029358863830566406 nb_pixel_total : 9073 time to create 1 rle with old method : 0.010342836380004883 time for calcul the mask position with numpy : 0.0294034481048584 nb_pixel_total : 23911 time to create 1 rle with old method : 0.02736043930053711 time for calcul the mask position with numpy : 0.02944636344909668 nb_pixel_total : 11140 time to create 1 rle with old method : 0.012578248977661133 time for calcul the mask position with numpy : 0.028856515884399414 nb_pixel_total : 8663 time to create 1 rle with old method : 0.009915828704833984 time for calcul the mask position with numpy : 0.028919219970703125 nb_pixel_total : 21244 time to create 1 rle with old method : 0.023930788040161133 time for calcul the mask position with numpy : 0.02984309196472168 nb_pixel_total : 172560 time to create 1 rle with new method : 1.725083827972412 time for calcul the mask position with numpy : 0.03054642677307129 nb_pixel_total : 158702 time to create 1 rle with new method : 0.704521894454956 time for calcul the mask position with numpy : 0.029132366180419922 nb_pixel_total : 62868 time to create 1 rle with old method : 0.07088184356689453 time for calcul the mask position with numpy : 0.029102325439453125 nb_pixel_total : 22190 time to create 1 rle with old method : 0.026025056838989258 time for calcul the mask position with numpy : 0.032613515853881836 nb_pixel_total : 38011 time to create 1 rle with old method : 0.04268622398376465 time for calcul the mask position with numpy : 0.029007673263549805 nb_pixel_total : 36288 time to create 1 rle with old method : 0.04050564765930176 time for calcul the mask position with numpy : 0.028844356536865234 nb_pixel_total : 26123 time to create 1 rle with old method : 0.029322147369384766 time for calcul the mask position with numpy : 0.029049158096313477 nb_pixel_total : 37028 time to create 1 rle with old method : 0.04224371910095215 time for calcul the mask position with numpy : 0.029102325439453125 nb_pixel_total : 21381 time to create 1 rle with old method : 0.024480342864990234 time for calcul the mask position with numpy : 0.030267715454101562 nb_pixel_total : 12921 time to create 1 rle with old method : 0.01523137092590332 time for calcul the mask position with numpy : 0.033876657485961914 nb_pixel_total : 504788 time to create 1 rle with new method : 0.5586869716644287 time for calcul the mask position with numpy : 0.02984476089477539 nb_pixel_total : 32874 time to create 1 rle with old method : 0.037003517150878906 time for calcul the mask position with numpy : 0.03626060485839844 nb_pixel_total : 14143 time to create 1 rle with old method : 0.016058921813964844 time for calcul the mask position with numpy : 0.03041529655456543 nb_pixel_total : 99102 time to create 1 rle with old method : 0.11101770401000977 time for calcul the mask position with numpy : 0.0300595760345459 nb_pixel_total : 25344 time to create 1 rle with old method : 0.028861522674560547 time for calcul the mask position with numpy : 0.029642581939697266 nb_pixel_total : 14957 time to create 1 rle with old method : 0.017206192016601562 time for calcul the mask position with numpy : 0.029810190200805664 nb_pixel_total : 48814 time to create 1 rle with old method : 0.053882598876953125 time for calcul the mask position with numpy : 0.028885602951049805 nb_pixel_total : 12556 time to create 1 rle with old method : 0.01428532600402832 time for calcul the mask position with numpy : 0.028635740280151367 nb_pixel_total : 10930 time to create 1 rle with old method : 0.012562751770019531 time for calcul the mask position with numpy : 0.029103994369506836 nb_pixel_total : 10122 time to create 1 rle with old method : 0.012944459915161133 create new chi : 8.07416844367981 time to delete rle : 0.003366231918334961 batch 1 Loaded 69 chid ids of type : 3594 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 19600 TO DO : save crop sub photo not yet done ! save time : 1.2691247463226318 map_output_result : {1348990554: (0.0, 'Should be the crop_list due to order', 0.0), 1348990549: (0.0, 'Should be the crop_list due to order', 0.0), 1348990539: (0.0, 'Should be the crop_list due to order', 0), 1348990537: (0.0, 'Should be the crop_list due to order', 0), 1348990534: (0.0, 'Should be the crop_list due to order', 0), 1348990500: (0.0, 'Should be the crop_list due to order', 0), 1348990497: (0.0, 'Should be the crop_list due to order', 0), 1348990491: (0.0, 'Should be the crop_list due to order', 0), 1348990489: (0.0, 'Should be the crop_list due to order', 0), 1348990485: (0.0, 'Should be the crop_list due to order', 0), 1348990483: (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 [1348990554, 1348990549, 1348990539, 1348990537, 1348990534, 1348990500, 1348990497, 1348990491, 1348990489, 1348990485, 1348990483] Looping around the photos to save general results len do output : 11 /1348990554.Didn't retrieve data . /1348990549.Didn't retrieve data . /1348990539.Didn't retrieve data . /1348990537.Didn't retrieve data . /1348990534.Didn't retrieve data . /1348990500.Didn't retrieve data . /1348990497.Didn't retrieve data . /1348990491.Didn't retrieve data . /1348990489.Didn't retrieve data . /1348990485.Didn't retrieve data . /1348990483.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, '2708834') ('3318', '21906642', '1348990554', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990549', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990539', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990537', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990534', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990500', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990497', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990491', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990489', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990485', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990483', None, None, None, None, None, '2708834') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 33 time used for this insertion : 0.013947248458862305 save_final save missing photos in datou_result : time spend for datou_step_exec : 115.39319896697998 time spend to save output : 0.01452326774597168 total time spend for step 3 : 115.40772223472595 step4:ventilate_hashtags_in_portfolio Mon Mar 31 13:08:10 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 : 21906642 get user id for portfolio 21906642 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 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('metal','background','pet_fonce','carton','environnement','flou','papier','pehd','autre','pet_clair','mal_croppe')) 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`=21906642 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('metal','background','pet_fonce','carton','environnement','flou','papier','pehd','autre','pet_clair','mal_croppe')) AND mptpi.`min_score`=0.5 To do 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`=21906642 AND mptpi.`type`=3594 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('metal','background','pet_fonce','carton','environnement','flou','papier','pehd','autre','pet_clair','mal_croppe')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://www.fotonower.com/velours/21906876,21906877,21906878,21906879,21906880,21906881,21906882,21906883,21906884,21906885,21906886?tags=metal,background,pet_fonce,carton,environnement,flou,papier,pehd,autre,pet_clair,mal_croppe Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1348990554, 1348990549, 1348990539, 1348990537, 1348990534, 1348990500, 1348990497, 1348990491, 1348990489, 1348990485, 1348990483] Looping around the photos to save general results len do output : 1 /21906642. 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, '2708834') ('3318', '21906642', '1348990554', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990549', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990539', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990537', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990534', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990500', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990497', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990491', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990489', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990485', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990483', None, None, None, None, None, '2708834') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.0137786865234375 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.7899243831634521 time spend to save output : 0.01402592658996582 total time spend for step 4 : 0.803950309753418 step5:final Mon Mar 31 13:08:11 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : {1348990554: ('0.2103858617836865',), 1348990549: ('0.2103858617836865',), 1348990539: ('0.2103858617836865',), 1348990537: ('0.2103858617836865',), 1348990534: ('0.2103858617836865',), 1348990500: ('0.2103858617836865',), 1348990497: ('0.2103858617836865',), 1348990491: ('0.2103858617836865',), 1348990489: ('0.2103858617836865',), 1348990485: ('0.2103858617836865',), 1348990483: ('0.2103858617836865',)} new output for save of step final : {1348990554: ('0.2103858617836865',), 1348990549: ('0.2103858617836865',), 1348990539: ('0.2103858617836865',), 1348990537: ('0.2103858617836865',), 1348990534: ('0.2103858617836865',), 1348990500: ('0.2103858617836865',), 1348990497: ('0.2103858617836865',), 1348990491: ('0.2103858617836865',), 1348990489: ('0.2103858617836865',), 1348990485: ('0.2103858617836865',), 1348990483: ('0.2103858617836865',)} [1348990554, 1348990549, 1348990539, 1348990537, 1348990534, 1348990500, 1348990497, 1348990491, 1348990489, 1348990485, 1348990483] Looping around the photos to save general results len do output : 11 /1348990554.Didn't retrieve data . /1348990549.Didn't retrieve data . /1348990539.Didn't retrieve data . /1348990537.Didn't retrieve data . /1348990534.Didn't retrieve data . /1348990500.Didn't retrieve data . /1348990497.Didn't retrieve data . /1348990491.Didn't retrieve data . /1348990489.Didn't retrieve data . /1348990485.Didn't retrieve data . /1348990483.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, '2708834') ('3318', '21906642', '1348990554', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990549', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990539', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990537', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990534', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990500', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990497', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990491', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990489', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990485', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990483', None, None, None, None, None, '2708834') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 33 time used for this insertion : 0.013204813003540039 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.15568089485168457 time spend to save output : 0.013800621032714844 total time spend for step 5 : 0.16948151588439941 step6:blur_detection Mon Mar 31 13:08:11 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1743418828_3276679_1348990554_a06d0f00552012f8267fc89b808346cb.jpg resize: (2160, 3264) 1348990554 -2.895521610743893 treat image : temp/1743418828_3276679_1348990549_2c8f475ea76bbc3fffcecb5038245fa0.jpg resize: (2160, 3264) 1348990549 -6.850502936631432 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7.jpg resize: (2160, 3264) 1348990539 -2.2137888323413533 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7.jpg resize: (2160, 3264) 1348990537 -1.4589583807610245 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e.jpg resize: (2160, 3264) 1348990534 -4.613687148254605 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412.jpg resize: (2160, 3264) 1348990500 -1.7534022582668907 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1.jpg resize: (2160, 3264) 1348990497 -3.673913890628008 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734.jpg resize: (2160, 3264) 1348990491 -4.423212212338163 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc.jpg resize: (2160, 3264) 1348990489 -6.392847451019325 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49.jpg resize: (2160, 3264) 1348990485 -6.389391067384178 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed.jpg resize: (2160, 3264) 1348990483 -3.879775280536989 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001897_0.png resize: (358, 326) 1348997850 -1.5116198779475254 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001899_0.png resize: (557, 307) 1348997852 -2.7029556378981603 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001887_0.png resize: (252, 407) 1348997853 -2.2304872031271397 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001902_0.png resize: (302, 109) 1348997854 -2.5890716302723837 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001890_0.png resize: (270, 532) 1348997855 -0.42461363665970603 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001894_0.png resize: (193, 180) 1348997857 -1.944916854287906 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001898_0.png resize: (306, 169) 1348997858 0.3016039493220886 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001903_0.png resize: (735, 337) 1348997860 -0.6991776767196417 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001905_0.png resize: (206, 246) 1348997862 -1.464359916391849 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001895_0.png resize: (176, 112) 1348997863 -1.6058476814264764 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001884_0.png resize: (261, 319) 1348997864 -1.4638395947831024 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001889_0.png resize: (86, 134) 1348997865 -1.6125932806841448 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001919_0.png resize: (315, 207) 1348997867 -1.9300870146472926 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001911_0.png resize: (160, 132) 1348997868 -3.0936737574315756 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001907_0.png resize: (96, 178) 1348997869 -1.8969466118938798 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001913_0.png resize: (194, 178) 1348997871 -0.27872664248727536 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001914_0.png resize: (726, 813) 1348997872 -1.7656939844346509 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001927_0.png resize: (111, 276) 1348997873 -1.1834410621749956 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001916_0.png resize: (168, 277) 1348997874 -0.6633241959874038 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001926_0.png resize: (93, 71) 1348997876 -2.063714288334102 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001908_0.png resize: (74, 86) 1348997877 3.0839918430532767 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001906_0.png resize: (859, 1542) 1348997878 -1.4145100014198937 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001915_0.png resize: (236, 279) 1348997880 -2.471540800071131 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001947_0.png resize: (185, 91) 1348997881 -2.9387991316535502 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001933_0.png resize: (381, 301) 1348997882 -3.533937873319821 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001930_0.png resize: (101, 90) 1348997884 -1.6729067769997097 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001937_0.png resize: (108, 111) 1348997885 -3.549080812530045 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001932_0.png resize: (109, 132) 1348997886 -4.005498061203828 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001939_0.png resize: (74, 97) 1348997887 -1.8566853024328824 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001948_0.png resize: (115, 79) 1348997889 -3.151657349567826 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001940_0.png resize: (441, 778) 1348997890 -3.133994983895086 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001942_0.png resize: (440, 115) 1348997891 -3.308598207358999 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001952_0.png resize: (183, 87) 1348997893 -1.529052139951909 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001951_0.png resize: (94, 146) 1348997894 -3.28857131124788 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001943_0.png resize: (298, 156) 1348997895 -3.9197998562703242 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001946_0.png resize: (191, 72) 1348997896 -5.109960225288188 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001938_0.png resize: (163, 121) 1348997898 -3.1743655982178294 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001931_0.png resize: (285, 146) 1348997899 -2.5551604464843107 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001975_0.png resize: (207, 289) 1348997900 -1.7099712737908943 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001953_0.png resize: (275, 195) 1348997902 -0.7273487328513959 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001959_0.png resize: (399, 375) 1348997903 -1.8714971186946958 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001965_0.png resize: (190, 103) 1348997904 -3.050082278766633 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001961_0.png resize: (446, 465) 1348997905 -2.7585766769463778 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001981_0.png resize: (206, 159) 1348997907 -2.938042391541551 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001969_0.png resize: (164, 209) 1348997908 -1.2173649211347037 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001979_0.png resize: (476, 433) 1348997909 -2.618830955580651 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001978_0.png resize: (124, 177) 1348997911 -1.880807294310591 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001957_0.png resize: (339, 399) 1348997912 -2.3658949347243294 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001962_0.png resize: (180, 231) 1348997913 -1.6622634627301471 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001970_0.png resize: (176, 154) 1348997915 -2.472962286291332 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001956_0.png resize: (807, 886) 1348997916 0.6138037998773418 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001982_0.png resize: (116, 279) 1348997918 -2.8629794215465307 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001964_0.png resize: (240, 248) 1348997919 -0.6637733951685878 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001972_0.png resize: (130, 87) 1348997921 -0.5314141145271712 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001958_0.png resize: (375, 439) 1348997922 -1.4059972024909486 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001967_0.png resize: (217, 402) 1348997923 -1.7658985659549784 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001976_0.png resize: (149, 326) 1348997926 0.2012138545395705 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001974_0.png resize: (116, 96) 1348997927 -1.2783007656189236 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001954_0.png resize: (212, 340) 1348997928 -0.9477952408258546 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001955_0.png resize: (118, 221) 1348997929 -3.1923003820441513 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001971_0.png resize: (203, 304) 1348997931 -2.783778049606732 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001966_0.png resize: (158, 103) 1348997932 -1.0482005707398294 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002001_0.png resize: (198, 119) 1348997933 -2.121316641575786 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001995_0.png resize: (179, 143) 1348997935 -2.077446839755839 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002016_0.png resize: (169, 271) 1348997936 -1.2055774965048107 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001990_0.png resize: (277, 460) 1348997937 -1.4956471730646739 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001996_0.png resize: (193, 111) 1348997938 -3.1381149015937146 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002013_0.png resize: (194, 286) 1348997940 -2.294556999017737 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002003_0.png resize: (113, 286) 1348997941 -2.3818383785259925 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002015_0.png resize: (95, 146) 1348997942 -2.269672281844882 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001993_0.png resize: (238, 299) 1348997944 -2.559792143257982 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001988_0.png resize: (70, 166) 1348997945 -2.4669817504964624 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002008_0.png resize: (326, 451) 1348997946 -2.497339932841467 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001986_0.png resize: (290, 311) 1348997947 -1.195065724103573 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001983_0.png resize: (418, 562) 1348997948 -1.1799868535517548 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001985_0.png resize: (584, 725) 1348997949 -2.7553782765777783 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001994_0.png resize: (426, 382) 1348997950 -2.340513964317535 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002004_0.png resize: (224, 201) 1348997951 -1.8209980983538054 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001999_0.png resize: (119, 91) 1348997952 -2.759537251964031 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002007_0.png resize: (256, 295) 1348997953 -2.4390453256990186 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002012_0.png resize: (409, 235) 1348997954 -3.172740314772099 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001998_0.png resize: (217, 143) 1348997955 -1.980889740047599 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002049_0.png resize: (312, 102) 1348997956 -3.2833007426606513 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002030_0.png resize: (211, 127) 1348997957 -3.0215236888069916 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002050_0.png resize: (158, 193) 1348997958 -2.7350769121496294 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002043_0.png resize: (150, 261) 1348997959 -3.789215156667801 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002048_0.png resize: (103, 162) 1348997960 -3.107836660529012 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002039_0.png resize: (232, 199) 1348997961 -3.0029285946110305 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002064_0.png resize: (132, 144) 1348997962 -2.5294565308876567 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002051_0.png resize: (649, 371) 1348997963 -2.3996626006917463 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002028_0.png resize: (374, 310) 1348997964 -0.8568352486044539 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002033_0.png resize: (747, 716) 1348997965 -0.9743514991797981 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002073_0.png resize: (111, 62) 1348997966 -1.5757883411501605 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002062_0.png resize: (135, 152) 1348997967 -1.12655277088499 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002042_0.png resize: (362, 678) 1348997968 -1.838652547290185 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002068_0.png resize: (187, 169) 1348997969 -3.1092470264073535 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002036_0.png resize: (314, 357) 1348997970 -3.485684648975046 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002034_0.png resize: (306, 237) 1348997971 -1.556214226089038 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002052_0.png resize: (266, 161) 1348997972 -3.022084893080074 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002046_0.png resize: (125, 185) 1348997973 -3.7329212023645235 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002045_0.png resize: (195, 192) 1348997974 -0.4669719776068461 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002059_0.png resize: (228, 224) 1348997975 -1.840931452313081 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002040_0.png resize: (155, 142) 1348997976 -3.0093230136073044 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002074_0.png resize: (132, 155) 1348997977 -2.1271342241844287 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002063_0.png resize: (303, 231) 1348997978 -2.8882670484611896 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002061_0.png resize: (542, 338) 1348997979 -4.002224393985205 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002047_0.png resize: (187, 287) 1348997980 -2.4763496464924035 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002035_0.png resize: (195, 294) 1348997981 -2.840049434184861 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002060_0.png resize: (509, 548) 1348997982 -1.1605365586312164 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002029_0.png resize: (214, 135) 1348997983 -3.7368001414957415 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002044_0.png resize: (287, 175) 1348997985 -3.318671316913742 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002031_0.png resize: (192, 132) 1348997986 -4.034873312762489 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002058_0.png resize: (115, 118) 1348997987 -3.3193683571125416 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002032_0.png resize: (115, 100) 1348997988 -2.0112174004773786 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002056_0.png resize: (354, 142) 1348997989 -2.259877817764799 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002038_0.png resize: (139, 130) 1348997990 -2.8597496501714006 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002067_0.png resize: (100, 72) 1348997991 -3.1821960790251587 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002037_0.png resize: (249, 187) 1348997992 -3.5644740588782557 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002027_0.png resize: (315, 192) 1348997993 -3.752527413876099 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002104_0.png resize: (216, 215) 1348997994 -3.588508918658412 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002087_0.png resize: (68, 217) 1348997995 -2.4056441132523165 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002084_0.png resize: (159, 129) 1348997996 -2.8292436951476567 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002077_0.png resize: (369, 379) 1348997997 -3.859831937883817 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002079_0.png resize: (106, 140) 1348997998 -3.5567173682954976 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002085_0.png resize: (211, 198) 1348997999 -4.321841495875204 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002093_0.png resize: (224, 149) 1348998000 -4.194500186921093 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002076_0.png resize: (171, 90) 1348998001 -3.4660875118333125 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002091_0.png resize: (195, 198) 1348998002 -3.9487860842172546 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002086_0.png resize: (113, 191) 1348998003 -4.945157218870869 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002083_0.png resize: (124, 115) 1348998004 -4.792607881863128 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002102_0.png resize: (275, 168) 1348998005 -3.237374702757323 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002099_0.png resize: (184, 211) 1348998006 -5.877762670117475 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002080_0.png resize: (119, 92) 1348998007 -1.045260949037 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002088_0.png resize: (597, 646) 1348998008 -3.0970453766840444 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002090_0.png resize: (221, 171) 1348998009 -3.4984045715013425 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002089_0.png resize: (266, 361) 1348998010 -4.551820059725281 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002082_0.png resize: (154, 196) 1348998011 -4.934644071497178 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002095_0.png resize: (67, 130) 1348998012 -2.4189805708818195 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002118_0.png resize: (67, 215) 1348998013 -2.2944199285679248 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002125_0.png resize: (159, 137) 1348998014 -3.1720793018139104 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002109_0.png resize: (343, 324) 1348998015 -3.7114791331796924 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002108_0.png resize: (106, 139) 1348998016 -3.7070823918296303 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002112_0.png resize: (203, 188) 1348998017 -3.8633676968230137 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002126_0.png resize: (169, 184) 1348998018 -3.860590885187463 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002107_0.png resize: (169, 109) 1348998020 -2.981669519283293 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002116_0.png resize: (107, 171) 1348998021 -4.954267450194771 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002124_0.png resize: (192, 178) 1348998022 -2.4156177759127204 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002133_0.png resize: (295, 278) 1348998023 -4.212367530720245 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002114_0.png resize: (225, 304) 1348998024 -4.345092592986645 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002115_0.png resize: (65, 140) 1348998025 -3.039564729616315 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002113_0.png resize: (155, 180) 1348998026 -4.557700083150072 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002121_0.png resize: (172, 147) 1348998027 -3.327377792246709 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002122_0.png resize: (132, 91) 1348998028 -2.7595695213560214 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002151_0.png resize: (609, 215) 1348998029 -2.594102914022683 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002152_0.png resize: (219, 270) 1348998030 -2.7033574630908284 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002155_0.png resize: (268, 222) 1348998031 -2.573400461454531 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002163_0.png resize: (69, 194) 1348998032 -1.7158634245122857 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002143_0.png resize: (140, 108) 1348998033 -2.2357666171901713 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002141_0.png resize: (476, 424) 1348998034 -2.2889962003646067 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002166_0.png resize: (251, 170) 1348998035 -2.710150196094665 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002154_0.png resize: (99, 139) 1348998036 -2.158088110900918 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002147_0.png resize: (131, 161) 1348998037 -1.665209126558807 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002137_0.png resize: (160, 74) 1348998039 0.21128998064036889 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002142_0.png resize: (113, 168) 1348998040 -2.7600562267673676 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002157_0.png resize: (248, 146) 1348998041 -1.0559013039776537 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002158_0.png resize: (254, 214) 1348998042 -3.5633161020226485 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002159_0.png resize: (188, 116) 1348998043 -4.065725476836304 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002153_0.png resize: (610, 497) 1348998044 -0.41751239315824745 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001896_0.png resize: (307, 293) 1348998153 -3.0179815160063312 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001892_0.png resize: (563, 494) 1348998154 -1.4707750762499623 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001885_0.png resize: (177, 201) 1348998155 -1.0623525208943765 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001891_0.png resize: (121, 100) 1348998156 -0.6132707872574146 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001888_0.png resize: (481, 363) 1348998157 -0.5625384282381529 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001886_0.png resize: (930, 729) 1348998158 0.10712556933826597 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001900_0.png resize: (206, 202) 1348998159 -1.5192825194123811 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001901_0.png resize: (309, 267) 1348998160 -1.013190500029384 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001929_0.png resize: (532, 443) 1348998161 -1.2064670532232704 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001924_0.png resize: (207, 146) 1348998162 -1.5051246857553116 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001918_0.png resize: (62, 198) 1348998163 -0.21795664765214456 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001922_0.png resize: (439, 547) 1348998164 -1.465893423639368 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001910_0.png resize: (211, 286) 1348998165 -1.1950991385458178 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001923_0.png resize: (305, 165) 1348998166 -2.430366623388587 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001934_0.png resize: (361, 307) 1348998168 -2.162244232690053 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001935_0.png resize: (259, 193) 1348998169 -3.2254944028479424 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001944_0.png resize: (688, 736) 1348998170 -3.449673933151276 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001941_0.png resize: (295, 237) 1348998171 -2.4865079283490448 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001950_0.png resize: (92, 71) 1348998172 -2.7296937030730946 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001980_0.png resize: (210, 272) 1348998173 -1.5905143598599647 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001968_0.png resize: (315, 622) 1348998174 -2.070083784865802 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001963_0.png resize: (143, 84) 1348998175 -2.4542046270915088 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001960_0.png resize: (228, 519) 1348998176 -1.4514097174751435 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001973_0.png resize: (141, 162) 1348998177 -2.516936262001515 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002021_0.png resize: (111, 304) 1348998178 -2.4099931176100258 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002010_0.png resize: (188, 277) 1348998179 -1.5645608088480942 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002017_0.png resize: (78, 195) 1348998181 -1.5509083599592233 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002025_0.png resize: (263, 464) 1348998182 -1.194626342862978 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001992_0.png resize: (152, 166) 1348998183 -1.794414379985967 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002022_0.png resize: (278, 93) 1348998184 -2.7094456088475893 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002024_0.png resize: (144, 188) 1348998186 -1.6361424082949165 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001987_0.png resize: (281, 180) 1348998187 -2.113283673357599 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002006_0.png resize: (394, 190) 1348998188 -1.8860708910156034 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002005_0.png resize: (213, 232) 1348998189 -1.8016280710423103 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002019_0.png resize: (105, 111) 1348998190 -3.040643840602695 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002018_0.png resize: (146, 197) 1348998191 -2.388997822934021 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002009_0.png resize: (253, 374) 1348998193 -4.125965603447926 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002071_0.png resize: (629, 375) 1348998194 -1.991112410673045 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002053_0.png resize: (70, 157) 1348998195 -2.777536336152744 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002069_0.png resize: (169, 193) 1348998196 -3.446854159690957 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002054_0.png resize: (129, 86) 1348998197 -3.505029907314922 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002096_0.png resize: (121, 204) 1348998198 -2.039162931766743 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002097_0.png resize: (117, 210) 1348998199 -3.080808625088518 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002075_0.png resize: (550, 1303) 1348998200 -2.757041694696039 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002105_0.png resize: (462, 768) 1348998201 -3.9446568382490113 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002081_0.png resize: (617, 469) 1348998202 -2.5625862012733123 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002094_0.png resize: (76, 148) 1348998203 -5.177156198982885 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002101_0.png resize: (125, 157) 1348998204 -4.606410052261289 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002131_0.png resize: (118, 224) 1348998206 -2.2487272695726146 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002129_0.png resize: (160, 179) 1348998207 -2.856974509680082 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002127_0.png resize: (176, 259) 1348998208 -4.576491607164844 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002132_0.png resize: (119, 213) 1348998209 -3.204819630223267 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002111_0.png resize: (194, 185) 1348998210 -3.293002983556633 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002106_0.png resize: (541, 1278) 1348998211 -2.718788458799602 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002119_0.png resize: (496, 740) 1348998212 -3.1668741566025678 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002120_0.png resize: (631, 513) 1348998213 -4.011505119303508 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002135_0.png resize: (108, 129) 1348998214 -2.618814207356252 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002165_0.png resize: (361, 176) 1348998215 -2.097928624883343 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002140_0.png resize: (160, 256) 1348998216 -2.526779847693332 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002145_0.png resize: (102, 192) 1348998217 -1.7771887816420804 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002138_0.png resize: (176, 180) 1348998218 -2.037638218071625 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002150_0.png resize: (92, 171) 1348998219 -3.4000047206489814 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002160_0.png resize: (124, 149) 1348998220 -3.211465836340525 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002167_0.png resize: (165, 229) 1348998221 -3.2676755032144436 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002148_0.png resize: (444, 477) 1348998222 -1.425948139595358 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002136_0.png resize: (569, 1298) 1348998223 -1.1578124102260439 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002162_0.png resize: (71, 115) 1348998224 -0.9766239996894867 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002168_0.png resize: (275, 244) 1348998225 -3.8067295016896927 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002144_0.png resize: (604, 432) 1348998226 -1.8335751285731925 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002146_0.png resize: (72, 148) 1348998227 -3.0224745242535627 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002156_0.png resize: (155, 180) 1348998228 -3.340684456498317 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002139_0.png resize: (103, 189) 1348998229 -1.9265684227158335 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002161_0.png resize: (135, 142) 1348998230 -0.787376638112012 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002011_0.png resize: (123, 141) 1348998235 -2.9310723121898326 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002098_0.png resize: (171, 155) 1348998236 -5.522511893777845 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002123_0.png resize: (113, 210) 1348998237 -3.1362341049232976 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002164_0.png resize: (159, 269) 1348998238 -4.074856111013389 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001893_0.png resize: (416, 259) 1348998256 -2.669385016814304 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001920_0.png resize: (271, 225) 1348998257 -1.9397834934224996 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001921_0.png resize: (715, 1006) 1348998258 -2.4759133020649253 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001909_0.png resize: (391, 633) 1348998259 -3.0887378359988635 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001912_0.png resize: (97, 137) 1348998260 -2.423208823934681 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001936_0.png resize: (202, 140) 1348998261 -4.519659889693057 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001945_0.png resize: (228, 334) 1348998262 -4.289108101293837 treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001949_0.png resize: (143, 305) 1348998264 -2.3864892379770613 treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001977_0.png resize: (728, 588) 1348998265 -1.5547242821820644 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002014_0.png resize: (191, 173) 1348998266 -2.9556487533552347 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002020_0.png resize: (172, 220) 1348998267 -3.5460783794346384 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002026_0.png resize: (288, 475) 1348998268 -2.3619868639311314 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002000_0.png resize: (204, 235) 1348998269 -3.7949486452470014 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001991_0.png resize: (174, 233) 1348998270 -1.9163451263817262 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001989_0.png resize: (337, 254) 1348998271 -3.0675585271942536 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001997_0.png resize: (231, 374) 1348998272 -3.6691726936620186 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001984_0.png resize: (330, 285) 1348998273 -3.6025985995661287 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002002_0.png resize: (389, 342) 1348998274 -2.1580408424937514 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002041_0.png resize: (135, 263) 1348998275 -3.186726009258404 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002065_0.png resize: (243, 358) 1348998276 -3.321432788960965 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002055_0.png resize: (430, 293) 1348998277 -2.914744525365589 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002169_0.png resize: (221, 286) 1348998278 -2.7785575100974023 treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001904_0.png resize: (119, 65) 1348998282 -0.6985741378065908 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001928_0.png resize: (86, 95) 1348998283 -1.048620937542648 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001917_0.png resize: (225, 156) 1348998284 -2.2801939173480803 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002072_0.png resize: (64, 136) 1348998285 -2.1855102040095553 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002066_0.png resize: (115, 139) 1348998286 -3.5203713099702427 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002103_0.png resize: (317, 414) 1348998287 -4.869940360839355 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002134_0.png resize: (323, 277) 1348998288 -4.285672704908048 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002117_0.png resize: (323, 462) 1348998289 -4.975608930458712 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002130_0.png resize: (77, 87) 1348998290 0.4241186744836279 treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001925_0.png resize: (492, 449) 1348998296 -1.0404956404198134 treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002023_0.png resize: (177, 278) 1348998297 -1.3298687793763844 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002070_0.png resize: (160, 171) 1348998298 -4.810263460116963 treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002057_0.png resize: (104, 377) 1348998299 -2.2603315251820644 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002092_0.png resize: (149, 379) 1348998300 -4.568516269633579 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002078_0.png resize: (149, 396) 1348998301 -1.7327010686473108 treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002100_0.png resize: (389, 337) 1348998302 -4.7713477648462455 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002110_0.png resize: (147, 401) 1348998303 -1.538408261509468 treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002128_0.png resize: (449, 516) 1348998304 -4.8650852053679365 treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002149_0.png resize: (131, 353) 1348998305 -0.5186345825635423 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 : 297 time used for this insertion : 0.02643132209777832 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 297 time used for this insertion : 0.04707503318786621 save missing photos in datou_result : time spend for datou_step_exec : 47.74732232093811 time spend to save output : 0.08067536354064941 total time spend for step 6 : 47.82799768447876 step7:brightness Mon Mar 31 13:08:59 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/1743418828_3276679_1348990554_a06d0f00552012f8267fc89b808346cb.jpg treat image : temp/1743418828_3276679_1348990549_2c8f475ea76bbc3fffcecb5038245fa0.jpg treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7.jpg treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7.jpg treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e.jpg treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412.jpg treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1.jpg treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734.jpg treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc.jpg treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49.jpg treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed.jpg treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001897_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001899_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001887_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001902_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001890_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001894_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001898_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001903_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001905_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001895_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001884_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001889_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001919_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001911_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001907_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001913_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001914_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001927_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001916_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001926_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001908_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001906_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001915_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001947_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001933_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001930_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001937_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001932_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001939_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001948_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001940_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001942_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001952_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001951_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001943_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001946_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001938_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001931_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001975_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001953_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001959_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001965_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001961_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001981_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001969_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001979_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001978_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001957_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001962_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001970_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001956_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001982_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001964_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001972_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001958_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001967_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001976_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001974_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001954_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001955_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001971_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001966_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002001_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001995_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002016_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001990_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001996_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002013_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002003_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002015_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001993_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001988_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002008_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001986_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001983_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001985_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001994_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002004_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001999_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002007_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002012_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001998_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002049_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002030_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002050_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002043_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002048_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002039_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002064_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002051_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002028_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002033_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002073_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002062_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002042_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002068_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002036_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002034_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002052_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002046_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002045_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002059_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002040_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002074_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002063_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002061_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002047_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002035_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002060_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002029_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002044_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002031_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002058_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002032_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002056_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002038_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002067_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002037_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002027_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002104_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002087_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002084_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002077_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002079_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002085_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002093_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002076_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002091_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002086_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002083_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002102_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002099_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002080_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002088_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002090_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002089_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002082_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002095_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002118_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002125_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002109_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002108_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002112_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002126_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002107_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002116_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002124_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002133_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002114_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002115_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002113_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002121_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002122_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002151_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002152_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002155_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002163_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002143_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002141_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002166_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002154_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002147_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002137_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002142_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002157_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002158_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002159_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002153_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001896_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001892_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001885_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001891_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001888_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001886_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001900_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001901_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001929_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001924_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001918_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001922_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001910_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001923_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001934_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001935_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001944_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001941_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001950_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001980_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001968_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001963_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001960_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001973_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002021_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002010_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002017_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002025_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001992_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002022_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002024_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001987_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002006_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002005_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002019_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002018_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002009_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002071_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002053_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002069_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002054_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002096_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002097_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002075_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002105_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002081_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002094_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002101_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002131_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002129_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002127_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002132_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002111_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002106_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002119_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002120_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002135_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002165_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002140_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002145_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002138_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002150_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002160_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002167_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002148_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002136_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002162_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002168_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002144_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002146_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002156_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002139_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002161_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002011_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002098_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002123_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002164_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001893_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001920_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001921_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001909_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001912_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001936_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001945_0.png treat image : temp/1743418828_3276679_1348990534_e6497ce888aa9a502a1ac6e8d36ea99e_rle_crop_3741001949_0.png treat image : temp/1743418828_3276679_1348990500_c280cf2dafd51805f709fa76ad159412_rle_crop_3741001977_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002014_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002020_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002026_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002000_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001991_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001989_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001997_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741001984_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002002_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002041_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002065_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002055_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002169_0.png treat image : temp/1743418828_3276679_1348990539_a203803e8853ba5eca5146b1f16782f7_rle_crop_3741001904_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001928_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001917_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002072_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002066_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002103_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002134_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002117_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002130_0.png treat image : temp/1743418828_3276679_1348990537_10bf83ae3eff34b8b32377edce98abb7_rle_crop_3741001925_0.png treat image : temp/1743418828_3276679_1348990497_0c91ce08c990b4dc468c03d6655ad3c1_rle_crop_3741002023_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002070_0.png treat image : temp/1743418828_3276679_1348990491_7af62e2ea42f6b5eb2be44e3800d9734_rle_crop_3741002057_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002092_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002078_0.png treat image : temp/1743418828_3276679_1348990489_171ab9fac68f2234003a5214126876fc_rle_crop_3741002100_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002110_0.png treat image : temp/1743418828_3276679_1348990485_7cb6035d49e77dec811ac7f0574ddb49_rle_crop_3741002128_0.png treat image : temp/1743418828_3276679_1348990483_a47c23bb0594c8709fd88623819498ed_rle_crop_3741002149_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 : 297 time used for this insertion : 0.19306254386901855 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 297 time used for this insertion : 0.04614973068237305 save missing photos in datou_result : time spend for datou_step_exec : 13.31799840927124 time spend to save output : 0.24518465995788574 total time spend for step 7 : 13.563183069229126 step8:velours_tree Mon Mar 31 13:09:12 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 : 0.4800553321838379 time spend to save output : 3.814697265625e-05 total time spend for step 8 : 0.48009347915649414 step9:send_mail_cod Mon Mar 31 13:09:13 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_P21906642_31-03-2025_13_09_13.pdf 21906876 change filename to text .change filename to text .change filename to text .change filename to text .imagette219068761743419353 21906877 imagette219068771743419353 21906878 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 .imagette219068781743419353 21906879 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 .imagette219068791743419354 21906881 imagette219068811743419356 21906882 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 .imagette219068821743419356 21906883 imagette219068831743419357 21906884 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 .imagette219068841743419357 21906885 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 .imagette219068851743419358 21906886 imagette219068861743419359 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21906642 and hashtag_type = 3594 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21906876,21906877,21906878,21906879,21906880,21906881,21906882,21906883,21906884,21906885,21906886?tags=metal,background,pet_fonce,carton,environnement,flou,papier,pehd,autre,pet_clair,mal_croppe args[1348990554] : ((1348990554, -2.895521610743893, 492609224), (1348990554, -0.04314333542632656, 2107752395), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990549] : ((1348990549, -6.850502936631432, 492609224), (1348990549, -0.25010335924606175, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990539] : ((1348990539, -2.2137888323413533, 492609224), (1348990539, -0.12152050852656021, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990537] : ((1348990537, -1.4589583807610245, 492688767), (1348990537, -0.18346976053556271, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990534] : ((1348990534, -4.613687148254605, 492609224), (1348990534, -0.4992459202673671, 501862349), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990500] : ((1348990500, -1.7534022582668907, 492688767), (1348990500, -0.22892760983571678, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990497] : ((1348990497, -3.673913890628008, 492609224), (1348990497, -0.0976659775463837, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990491] : ((1348990491, -4.423212212338163, 492609224), (1348990491, -0.38221662050331767, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990489] : ((1348990489, -6.392847451019325, 492609224), (1348990489, -0.2654417225381973, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990485] : ((1348990485, -6.389391067384178, 492609224), (1348990485, -0.25701017776498736, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com args[1348990483] : ((1348990483, -3.879775280536989, 492609224), (1348990483, -0.2749059130279966, 496442774), '0.2103858617836865') We are sending mail with results at report@fotonower.com refus_total : 0.2103858617836865 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=21906642 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 SELECT photo_id, url FROM MTRBack.photos ph WHERE photo_id IN (1348990483,1348990500,1348990485,1348990489,1348990491,1348990497,1348990534,1348990537,1348990539,1348990549,1348990554) Found this number of photos: 11 begin to download photo : 1348990483 begin to download photo : 1348990489 begin to download photo : 1348990534 begin to download photo : 1348990549 download finish for photo 1348990483 begin to download photo : 1348990500 download finish for photo 1348990534 begin to download photo : 1348990537 download finish for photo 1348990489 begin to download photo : 1348990491 download finish for photo 1348990549 begin to download photo : 1348990554 download finish for photo 1348990537 begin to download photo : 1348990539 download finish for photo 1348990500 begin to download photo : 1348990485 download finish for photo 1348990491 begin to download photo : 1348990497 download finish for photo 1348990554 download finish for photo 1348990497 download finish for photo 1348990539 download finish for photo 1348990485 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21906642_31-03-2025_13_09_13.pdf results_Auto_P21906642_31-03-2025_13_09_13.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21906642_31-03-2025_13_09_13.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','21906642','results_Auto_P21906642_31-03-2025_13_09_13.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21906642_31-03-2025_13_09_13.pdf','pdf','','1.07','0.2103858617836865') message_in_mail: Bonjour,
Veuillez trouver ci dessous les résultats du service carac on demand pour le portfolio: https://www.fotonower.com/view/21906642

https://www.fotonower.com/image?json=false&list_photos_id=1348990554
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990549
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990539
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990537
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990534
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990500
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990497
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990491
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990489
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990485
Bravo, la photo est bien prise.
https://www.fotonower.com/image?json=false&list_photos_id=1348990483
Bravo, la photo est bien prise.

Dans ces conditions,le taux de refus est: 21.04%
Veuillez trouver les photos des contaminants.

exemples de contaminants: metal: https://www.fotonower.com/view/21906876?limit=200
exemples de contaminants: pet_fonce: https://www.fotonower.com/view/21906878?limit=200
exemples de contaminants: carton: https://www.fotonower.com/view/21906879?limit=200
exemples de contaminants: papier: https://www.fotonower.com/view/21906882?limit=200
exemples de contaminants: autre: https://www.fotonower.com/view/21906884?limit=200
exemples de contaminants: pet_clair: https://www.fotonower.com/view/21906885?limit=200
Veuillez trouver le rapport en pdf:https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21906642_31-03-2025_13_09_13.pdf.

Lien vers velours :https://www.fotonower.com/velours/21906876,21906877,21906878,21906879,21906880,21906881,21906882,21906883,21906884,21906885,21906886?tags=metal,background,pet_fonce,carton,environnement,flou,papier,pehd,autre,pet_clair,mal_croppe.


L'équipe Fotonower 202 b'' Server: nginx Date: Mon, 31 Mar 2025 11:09:23 GMT Content-Length: 0 Connection: close X-Message-Id: 9ghgyVF9Q0OEIz7lX4afOQ 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 [1348990554, 1348990549, 1348990539, 1348990537, 1348990534, 1348990500, 1348990497, 1348990491, 1348990489, 1348990485, 1348990483] 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, '2708834') ('3318', '21906642', '1348990554', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990549', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990539', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990537', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990534', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990500', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990497', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990491', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990489', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990485', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990483', None, None, None, None, None, '2708834') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 11 time used for this insertion : 0.2492837905883789 save_final save missing photos in datou_result : time spend for datou_step_exec : 9.768280982971191 time spend to save output : 0.24953460693359375 total time spend for step 9 : 10.017815589904785 step10:split_time_score Mon Mar 31 13:09:23 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 1 VR 22-3-18 : For now we do not clean correctly the datou structure begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 861, 'mtr_user_id': 31, 'name': 'Rungis_class_dechets_1212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Rungis_Aluminium,Rungis_Carton,Rungis_Papier,Rungis_Plastique_clair,Rungis_Plastique_dur,Rungis_Plastique_fonce,Rungis_Tapis_vide,Rungis_Tetrapak', 'svm_portfolios_learning': '1160730,571842,571844,571839,571933,571840,571841,572307', 'photo_hashtag_type': 999, 'photo_desc_type': 3963, 'type_classification': 'caffe', 'hashtag_id_list': '2107751280,2107750907,2107750908,2107750909,2107750910,2107750911,2107750912,2107750913'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('12', 11),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 31032025 21906642 Nombre de photos uploadées : 11 / 23040 (0%) 31032025 21906642 Nombre de photos taguées (types de déchets): 0 / 11 (0%) 31032025 21906642 Nombre de photos taguées (volume) : 0 / 11 (0%) elapsed_time : load_data_split_time_score 1.9073486328125e-06 elapsed_time : order_list_meta_photo_and_scores 5.9604644775390625e-06 ??????????? elapsed_time : fill_and_build_computed_from_old_data 0.0004780292510986328 elapsed_time : insert_dashboard_record_day_entry 0.02331686019897461 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 : 0.12334489479948355 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P21905150_31-03-2025_11_56_08.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21905150 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`=21905150 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 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21906639 order by id desc limit 1 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 NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'31032025': {'nb_upload': 11, '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 [1348990554, 1348990549, 1348990539, 1348990537, 1348990534, 1348990500, 1348990497, 1348990491, 1348990489, 1348990485, 1348990483] Looping around the photos to save general results len do output : 1 /21906642Didn'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, '2708834') ('3318', '21906642', '1348990554', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990549', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990539', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990537', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990534', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990500', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990497', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990491', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990489', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990485', None, None, None, None, None, '2708834') ('3318', None, None, None, None, None, None, None, '2708834') ('3318', '21906642', '1348990483', None, None, None, None, None, '2708834') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.01349020004272461 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.3325583934783936 time spend to save output : 0.013715982437133789 total time spend for step 10 : 1.3462743759155273 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 11 set_done_treatment 263.14user 159.14system 8:59.74elapsed 78%CPU (0avgtext+0avgdata 5468056maxresident)k 5922104inputs+209480outputs (181243major+22977691minor)pagefaults 0swaps