2022/11/01 15:44:49 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 830108406 GPU 0: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/cache/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 GCC: gcc (GCC) 5.4.0 PyTorch: 1.9.0+cu111 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 - CuDNN 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.10.0+cu111 OpenCV: 4.6.0 MMEngine: 0.2.0 Runtime environment: cudnn_benchmark: True mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: slurm Distributed training: True GPU number: 1 ------------------------------------------------------------ 2022/11/01 15:44:49 - mmengine - INFO - Config: file_client_args = dict(backend='disk') mask_rcnn = dict( type='MaskRCNN', data_preprocessor=dict( type='DetDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], bgr_to_rgb=True, pad_mask=False, pad_size_divisor=32), backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=True), norm_eval=True, style='pytorch', init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=5), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', scales=[4], ratios=[0.17, 0.44, 1.13, 2.9, 7.46], strides=[4, 8, 16, 32, 64]), bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0]), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), roi_head=dict( type='StandardRoIHead', bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=dict( type='Shared2FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=1, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.1, 0.1, 0.2, 0.2]), reg_class_agnostic=False, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), mask_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), mask_head=dict( type='FCNMaskHead', num_convs=4, in_channels=256, conv_out_channels=256, num_classes=1, loss_mask=dict( type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))), train_cfg=dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.3, min_pos_iou=0.3, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=256, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=False), allowed_border=-1, pos_weight=-1, debug=False), rpn_proposal=dict( nms_pre=2000, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0.5, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, pos_weight=-1, debug=False)), test_cfg=dict( rpn=dict( nms_pre=1000, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100, mask_thr_binary=0.5)), _scope_='mmdet') model = dict( type='MMDetWrapper', text_repr_type='poly', cfg=dict( type='MaskRCNN', data_preprocessor=dict( type='DetDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], bgr_to_rgb=True, pad_mask=False, pad_size_divisor=32), backbone=dict( _scope_='mmocr', type='CLIPResNet', init_cfg=dict( type='Pretrained', checkpoint= 'r50_oclip.pth' )), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=5), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', scales=[4], ratios=[0.17, 0.44, 1.13, 2.9, 7.46], strides=[4, 8, 16, 32, 64]), bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0]), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), roi_head=dict( type='StandardRoIHead', bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict( type='RoIAlign', output_size=7, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=dict( type='Shared2FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=1, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.1, 0.1, 0.2, 0.2]), reg_class_agnostic=False, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), mask_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict( type='RoIAlign', output_size=14, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), mask_head=dict( type='FCNMaskHead', num_convs=4, in_channels=256, conv_out_channels=256, num_classes=1, loss_mask=dict( type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))), train_cfg=dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.3, min_pos_iou=0.3, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=256, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=False), allowed_border=-1, pos_weight=-1, debug=False), rpn_proposal=dict( nms_pre=2000, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0.5, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, pos_weight=-1, debug=False)), test_cfg=dict( rpn=dict( nms_pre=1000, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100, mask_thr_binary=0.5)), _scope_='mmdet')) train_pipeline = [ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.12549019607843137, saturation=0.5, contrast=0.5), dict( type='RandomResize', scale=(640, 640), ratio_range=(1.0, 4.125), keep_ratio=True), dict(type='RandomFlip', prob=0.5), dict(type='TextDetRandomCrop', target_size=(640, 640)), dict(type='MMOCR2MMDet', poly2mask=True), dict( type='mmdet.PackDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'flip', 'scale_factor', 'flip_direction')) ] test_pipeline = [ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), color_type='color_ignore_orientation'), dict(type='Resize', scale=(1920, 1920), keep_ratio=True), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] ctw_det_data_root = 'data/det/ctw1500' ctw_det_train = dict( type='OCRDataset', data_root='data/det/ctw1500', ann_file='instances_training.json', data_prefix=dict(img_path='imgs/'), filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.12549019607843137, saturation=0.5, contrast=0.5), dict( type='RandomResize', scale=(640, 640), ratio_range=(1.0, 4.125), keep_ratio=True), dict(type='RandomFlip', prob=0.5), dict(type='TextDetRandomCrop', target_size=(640, 640)), dict(type='MMOCR2MMDet', poly2mask=True), dict( type='mmdet.PackDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'flip', 'scale_factor', 'flip_direction')) ]) ctw_det_test = dict( type='OCRDataset', data_root='data/det/ctw1500', ann_file='instances_test.json', data_prefix=dict(img_path='imgs/'), test_mode=True, pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), color_type='color_ignore_orientation'), dict(type='Resize', scale=(1600, 1600), keep_ratio=True), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ]) default_scope = 'mmocr' env_cfg = dict( cudnn_benchmark=True, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) randomness = dict(seed=None) default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=5), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=20, out_dir='sproject:s3://oclip'), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffer=dict(type='SyncBuffersHook'), visualization=dict( type='VisualizationHook', interval=1, enable=False, show=False, draw_gt=False, draw_pred=False)) log_level = 'INFO' log_processor = dict(type='LogProcessor', window_size=10, by_epoch=True) load_from = None resume = True val_evaluator = dict(type='HmeanIOUMetric') test_evaluator = dict(type='HmeanIOUMetric') vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='TextDetLocalVisualizer', name='visualizer', vis_backends=[dict(type='LocalVisBackend')]) optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)) train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=160, val_interval=20) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict(type='LinearLR', end=500, start_factor=0.001, by_epoch=False), dict(type='MultiStepLR', milestones=[80, 128], end=160) ] ctw_test_pipeline = [ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), color_type='color_ignore_orientation'), dict(type='Resize', scale=(1600, 1600), keep_ratio=True), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] train_dataloader = dict( batch_size=8, num_workers=4, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/det/ctw1500', ann_file='instances_training.json', data_prefix=dict(img_path='imgs/'), filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel'), color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.12549019607843137, saturation=0.5, contrast=0.5), dict( type='RandomResize', scale=(640, 640), ratio_range=(1.0, 4.125), keep_ratio=True), dict(type='RandomFlip', prob=0.5), dict(type='TextDetRandomCrop', target_size=(640, 640)), dict(type='MMOCR2MMDet', poly2mask=True), dict( type='mmdet.PackDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'flip', 'scale_factor', 'flip_direction')) ])) val_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/det/ctw1500', ann_file='instances_test.json', data_prefix=dict(img_path='imgs/'), test_mode=True, pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel'), color_type='color_ignore_orientation'), dict(type='Resize', scale=(1600, 1600), keep_ratio=True), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) test_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/det/ctw1500', ann_file='instances_test.json', data_prefix=dict(img_path='imgs/'), test_mode=True, pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel'), color_type='color_ignore_orientation'), dict(type='Resize', scale=(1600, 1600), keep_ratio=True), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) auto_scale_lr = dict(base_batch_size=8) launcher = 'slurm' work_dir = './work_dirs/mask-rcnn_resnet50-oclip_fpn_160e_ctw1500' Name of parameter - Initialization information wrapped_model.backbone.stem.0.weight - torch.Size([32, 3, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.stem.1.weight - torch.Size([32]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.stem.1.bias - torch.Size([32]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.stem.3.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.stem.4.weight - torch.Size([32]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.stem.4.bias - torch.Size([32]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.stem.6.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.stem.7.weight - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.stem.7.bias - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.downsample.1.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.downsample.2.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.0.downsample.2.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.bn3.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.bn3.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.downsample.1.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.downsample.2.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.0.downsample.2.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.bn3.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.1.bn3.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.bn3.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.2.bn3.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.bn3.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer2.3.bn3.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.bn3.weight - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.bn3.bias - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.downsample.1.weight - torch.Size([1024, 512, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.downsample.2.weight - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.0.downsample.2.bias - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.bn3.weight - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.1.bn3.bias - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.bn3.weight - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.2.bn3.bias - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.bn3.weight - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.3.bn3.bias - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.bn1.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.bn1.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.bn2.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.bn2.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.bn3.weight - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.4.bn3.bias - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.bn1.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.bn1.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.bn2.weight - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.bn2.bias - torch.Size([256]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.bn3.weight - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer3.5.bn3.bias - torch.Size([1024]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.bn1.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.bn1.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.bn2.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.bn2.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.bn3.weight - torch.Size([2048]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.bn3.bias - torch.Size([2048]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.downsample.1.weight - torch.Size([2048, 1024, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.downsample.2.weight - torch.Size([2048]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.0.downsample.2.bias - torch.Size([2048]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.bn1.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.bn1.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.bn2.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.bn2.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.bn3.weight - torch.Size([2048]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.1.bn3.bias - torch.Size([2048]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.bn1.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.bn1.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.bn2.weight - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.bn2.bias - torch.Size([512]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.bn3.weight - torch.Size([2048]): PretrainedInit: load from r50_oclip.pth wrapped_model.backbone.layer4.2.bn3.bias - torch.Size([2048]): PretrainedInit: load from r50_oclip.pth wrapped_model.neck.lateral_convs.0.conv.weight - torch.Size([256, 256, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.neck.lateral_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.neck.lateral_convs.1.conv.weight - torch.Size([256, 512, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.neck.lateral_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.neck.lateral_convs.2.conv.weight - torch.Size([256, 1024, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.neck.lateral_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.neck.lateral_convs.3.conv.weight - torch.Size([256, 2048, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.neck.lateral_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.neck.fpn_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.neck.fpn_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.neck.fpn_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.neck.fpn_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.neck.fpn_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.neck.fpn_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.neck.fpn_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.neck.fpn_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.rpn_head.rpn_conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 wrapped_model.rpn_head.rpn_conv.bias - torch.Size([256]): NormalInit: mean=0, std=0.01, bias=0 wrapped_model.rpn_head.rpn_cls.weight - torch.Size([5, 256, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 wrapped_model.rpn_head.rpn_cls.bias - torch.Size([5]): NormalInit: mean=0, std=0.01, bias=0 wrapped_model.rpn_head.rpn_reg.weight - torch.Size([20, 256, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 wrapped_model.rpn_head.rpn_reg.bias - torch.Size([20]): NormalInit: mean=0, std=0.01, bias=0 wrapped_model.roi_head.bbox_head.fc_cls.weight - torch.Size([2, 1024]): NormalInit: mean=0, std=0.01, bias=0 wrapped_model.roi_head.bbox_head.fc_cls.bias - torch.Size([2]): NormalInit: mean=0, std=0.01, bias=0 wrapped_model.roi_head.bbox_head.fc_reg.weight - torch.Size([4, 1024]): NormalInit: mean=0, std=0.001, bias=0 wrapped_model.roi_head.bbox_head.fc_reg.bias - torch.Size([4]): NormalInit: mean=0, std=0.001, bias=0 wrapped_model.roi_head.bbox_head.shared_fcs.0.weight - torch.Size([1024, 12544]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.roi_head.bbox_head.shared_fcs.0.bias - torch.Size([1024]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.roi_head.bbox_head.shared_fcs.1.weight - torch.Size([1024, 1024]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.roi_head.bbox_head.shared_fcs.1.bias - torch.Size([1024]): XavierInit: gain=1, distribution=uniform, bias=0 wrapped_model.roi_head.mask_head.convs.0.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule wrapped_model.roi_head.mask_head.convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.roi_head.mask_head.convs.1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule wrapped_model.roi_head.mask_head.convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.roi_head.mask_head.convs.2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule wrapped_model.roi_head.mask_head.convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.roi_head.mask_head.convs.3.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule wrapped_model.roi_head.mask_head.convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MMDetWrapper wrapped_model.roi_head.mask_head.upsample.weight - torch.Size([256, 256, 2, 2]): Initialized by user-defined `init_weights` in FCNMaskHead wrapped_model.roi_head.mask_head.upsample.bias - torch.Size([256]): Initialized by user-defined `init_weights` in FCNMaskHead wrapped_model.roi_head.mask_head.conv_logits.weight - torch.Size([1, 256, 1, 1]): Initialized by user-defined `init_weights` in FCNMaskHead wrapped_model.roi_head.mask_head.conv_logits.bias - torch.Size([1]): Initialized by user-defined `init_weights` in FCNMaskHead 2022/11/01 15:46:37 - mmengine - INFO - Auto resumed from the latest checkpoint sproject:s3://oclip/mask-rcnn_resnet50-oclip_fpn_160e_ctw1500/epoch_140.pth. 2022/11/01 15:46:38 - mmengine - INFO - Load checkpoint from sproject:s3://oclip/mask-rcnn_resnet50-oclip_fpn_160e_ctw1500/epoch_140.pth 2022/11/01 15:46:38 - mmengine - INFO - resumed epoch: 140, iter: 17500 2022/11/01 15:46:38 - mmengine - INFO - Checkpoints will be saved to sproject:s3://oclip/mask-rcnn_resnet50-oclip_fpn_160e_ctw1500. 2022/11/01 15:48:09 - mmengine - INFO - Epoch(train) [141][5/125] lr: 2.0000e-04 eta: 0:19:44 time: 9.3105 data_time: 7.9806 memory: 41868 loss: 0.4119 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0119 loss_cls: 0.0810 acc: 96.5576 loss_bbox: 0.1125 loss_mask: 0.1993 2022/11/01 15:48:12 - mmengine - INFO - Epoch(train) [141][10/125] lr: 2.0000e-04 eta: 6:28:29 time: 9.3614 data_time: 7.9922 memory: 11487 loss: 0.4074 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0098 loss_cls: 0.0792 acc: 96.4111 loss_bbox: 0.1211 loss_mask: 0.1899 2022/11/01 15:48:14 - mmengine - INFO - Epoch(train) [141][15/125] lr: 2.0000e-04 eta: 6:28:29 time: 0.5190 data_time: 0.0549 memory: 10427 loss: 0.4381 loss_rpn_cls: 0.0075 loss_rpn_bbox: 0.0089 loss_cls: 0.0897 acc: 97.3145 loss_bbox: 0.1387 loss_mask: 0.1932 2022/11/01 15:48:17 - mmengine - INFO - Epoch(train) [141][20/125] lr: 2.0000e-04 eta: 3:24:28 time: 0.5328 data_time: 0.0845 memory: 10253 loss: 0.4099 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0108 loss_cls: 0.0829 acc: 95.8252 loss_bbox: 0.1248 loss_mask: 0.1833 2022/11/01 15:48:20 - mmengine - INFO - Epoch(train) [141][25/125] lr: 2.0000e-04 eta: 3:24:28 time: 0.5426 data_time: 0.0917 memory: 10511 loss: 0.3924 loss_rpn_cls: 0.0087 loss_rpn_bbox: 0.0132 loss_cls: 0.0762 acc: 96.5820 loss_bbox: 0.1189 loss_mask: 0.1754 2022/11/01 15:48:22 - mmengine - INFO - Epoch(train) [141][30/125] lr: 2.0000e-04 eta: 2:22:54 time: 0.5196 data_time: 0.0877 memory: 9903 loss: 0.3985 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0108 loss_cls: 0.0731 acc: 97.3145 loss_bbox: 0.1149 loss_mask: 0.1912 2022/11/01 15:48:25 - mmengine - INFO - Epoch(train) [141][35/125] lr: 2.0000e-04 eta: 2:22:54 time: 0.5101 data_time: 0.0821 memory: 10307 loss: 0.4239 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0091 loss_cls: 0.0814 acc: 95.1660 loss_bbox: 0.1222 loss_mask: 0.2033 2022/11/01 15:48:28 - mmengine - INFO - Epoch(train) [141][40/125] lr: 2.0000e-04 eta: 1:52:03 time: 0.5187 data_time: 0.0711 memory: 10024 loss: 0.4336 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0093 loss_cls: 0.0855 acc: 97.9736 loss_bbox: 0.1274 loss_mask: 0.2034 2022/11/01 15:48:30 - mmengine - INFO - Epoch(train) [141][45/125] lr: 2.0000e-04 eta: 1:52:03 time: 0.5472 data_time: 0.0912 memory: 11502 loss: 0.4479 loss_rpn_cls: 0.0099 loss_rpn_bbox: 0.0115 loss_cls: 0.0859 acc: 94.2871 loss_bbox: 0.1313 loss_mask: 0.2093 2022/11/01 15:48:33 - mmengine - INFO - Epoch(train) [141][50/125] lr: 2.0000e-04 eta: 1:34:05 time: 0.5889 data_time: 0.1092 memory: 11372 loss: 0.4900 loss_rpn_cls: 0.0111 loss_rpn_bbox: 0.0137 loss_cls: 0.1024 acc: 93.1641 loss_bbox: 0.1554 loss_mask: 0.2073 2022/11/01 15:48:36 - mmengine - INFO - Epoch(train) [141][55/125] lr: 2.0000e-04 eta: 1:34:05 time: 0.5872 data_time: 0.1056 memory: 10543 loss: 0.4793 loss_rpn_cls: 0.0099 loss_rpn_bbox: 0.0126 loss_cls: 0.1053 acc: 97.1924 loss_bbox: 0.1550 loss_mask: 0.1964 2022/11/01 15:48:39 - mmengine - INFO - Epoch(train) [141][60/125] lr: 2.0000e-04 eta: 1:21:58 time: 0.5727 data_time: 0.1019 memory: 10723 loss: 0.4704 loss_rpn_cls: 0.0125 loss_rpn_bbox: 0.0116 loss_cls: 0.0983 acc: 97.5830 loss_bbox: 0.1425 loss_mask: 0.2055 2022/11/01 15:48:41 - mmengine - INFO - Epoch(train) [141][65/125] lr: 2.0000e-04 eta: 1:21:58 time: 0.5176 data_time: 0.0839 memory: 10206 loss: 0.4248 loss_rpn_cls: 0.0135 loss_rpn_bbox: 0.0100 loss_cls: 0.0820 acc: 97.4609 loss_bbox: 0.1243 loss_mask: 0.1950 2022/11/01 15:48:44 - mmengine - INFO - Epoch(train) [141][70/125] lr: 2.0000e-04 eta: 1:12:39 time: 0.4645 data_time: 0.0682 memory: 9826 loss: 0.3964 loss_rpn_cls: 0.0091 loss_rpn_bbox: 0.0088 loss_cls: 0.0721 acc: 97.0459 loss_bbox: 0.1107 loss_mask: 0.1956 2022/11/01 15:48:46 - mmengine - INFO - Epoch(train) [141][75/125] lr: 2.0000e-04 eta: 1:12:39 time: 0.4940 data_time: 0.0739 memory: 10567 loss: 0.4252 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0090 loss_cls: 0.0803 acc: 96.9482 loss_bbox: 0.1211 loss_mask: 0.2077 2022/11/01 15:48:49 - mmengine - INFO - Epoch(train) [141][80/125] lr: 2.0000e-04 eta: 1:05:51 time: 0.5043 data_time: 0.0684 memory: 10202 loss: 0.4384 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0116 loss_cls: 0.0842 acc: 97.1436 loss_bbox: 0.1341 loss_mask: 0.1999 2022/11/01 15:48:51 - mmengine - INFO - Epoch(train) [141][85/125] lr: 2.0000e-04 eta: 1:05:51 time: 0.5026 data_time: 0.0716 memory: 10012 loss: 0.4270 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0119 loss_cls: 0.0833 acc: 95.1904 loss_bbox: 0.1280 loss_mask: 0.1946 2022/11/01 15:48:54 - mmengine - INFO - Epoch(train) [141][90/125] lr: 2.0000e-04 eta: 1:00:32 time: 0.5019 data_time: 0.0758 memory: 10177 loss: 0.4317 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0099 loss_cls: 0.0880 acc: 95.3369 loss_bbox: 0.1252 loss_mask: 0.1989 2022/11/01 15:48:56 - mmengine - INFO - Epoch(train) [141][95/125] lr: 2.0000e-04 eta: 1:00:32 time: 0.4573 data_time: 0.0559 memory: 9789 loss: 0.4113 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0084 loss_cls: 0.0848 acc: 97.5342 loss_bbox: 0.1206 loss_mask: 0.1894 2022/11/01 15:48:59 - mmengine - INFO - Epoch(train) [141][100/125] lr: 2.0000e-04 eta: 0:56:07 time: 0.4643 data_time: 0.0713 memory: 10015 loss: 0.3780 loss_rpn_cls: 0.0055 loss_rpn_bbox: 0.0080 loss_cls: 0.0779 acc: 97.4609 loss_bbox: 0.1097 loss_mask: 0.1769 2022/11/01 15:49:01 - mmengine - INFO - Epoch(train) [141][105/125] lr: 2.0000e-04 eta: 0:56:07 time: 0.5151 data_time: 0.0874 memory: 10710 loss: 0.4490 loss_rpn_cls: 0.0090 loss_rpn_bbox: 0.0127 loss_cls: 0.0916 acc: 96.9971 loss_bbox: 0.1386 loss_mask: 0.1971 2022/11/01 15:49:03 - mmengine - INFO - Epoch(train) [141][110/125] lr: 2.0000e-04 eta: 0:52:33 time: 0.4867 data_time: 0.0825 memory: 9805 loss: 0.4654 loss_rpn_cls: 0.0107 loss_rpn_bbox: 0.0135 loss_cls: 0.0918 acc: 95.9717 loss_bbox: 0.1435 loss_mask: 0.2060 2022/11/01 15:49:06 - mmengine - INFO - Epoch(train) [141][115/125] lr: 2.0000e-04 eta: 0:52:33 time: 0.4901 data_time: 0.0916 memory: 9592 loss: 0.4098 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0104 loss_cls: 0.0783 acc: 96.8018 loss_bbox: 0.1214 loss_mask: 0.1915 2022/11/01 15:49:09 - mmengine - INFO - Epoch(train) [141][120/125] lr: 2.0000e-04 eta: 0:49:46 time: 0.5397 data_time: 0.0960 memory: 10190 loss: 0.4064 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0091 loss_cls: 0.0763 acc: 97.2900 loss_bbox: 0.1147 loss_mask: 0.2004 2022/11/01 15:49:11 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:49:11 - mmengine - INFO - Epoch(train) [141][125/125] lr: 2.0000e-04 eta: 0:49:46 time: 0.4744 data_time: 0.0556 memory: 9599 loss: 0.4328 loss_rpn_cls: 0.0056 loss_rpn_bbox: 0.0072 loss_cls: 0.0799 acc: 95.3613 loss_bbox: 0.1198 loss_mask: 0.2203 2022/11/01 15:49:15 - mmengine - INFO - Epoch(train) [142][5/125] lr: 2.0000e-04 eta: 0:49:46 time: 0.6168 data_time: 0.1641 memory: 10664 loss: 0.4553 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0103 loss_cls: 0.0876 acc: 95.5322 loss_bbox: 0.1336 loss_mask: 0.2164 2022/11/01 15:49:17 - mmengine - INFO - Epoch(train) [142][10/125] lr: 2.0000e-04 eta: 0:45:50 time: 0.6449 data_time: 0.1874 memory: 10092 loss: 0.4462 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0107 loss_cls: 0.0837 acc: 97.6562 loss_bbox: 0.1263 loss_mask: 0.2171 2022/11/01 15:49:20 - mmengine - INFO - Epoch(train) [142][15/125] lr: 2.0000e-04 eta: 0:45:50 time: 0.4773 data_time: 0.0761 memory: 10496 loss: 0.4301 loss_rpn_cls: 0.0099 loss_rpn_bbox: 0.0112 loss_cls: 0.0820 acc: 95.5078 loss_bbox: 0.1242 loss_mask: 0.2028 2022/11/01 15:49:23 - mmengine - INFO - Epoch(train) [142][20/125] lr: 2.0000e-04 eta: 0:43:55 time: 0.5264 data_time: 0.1038 memory: 10088 loss: 0.4333 loss_rpn_cls: 0.0108 loss_rpn_bbox: 0.0126 loss_cls: 0.0840 acc: 94.4580 loss_bbox: 0.1291 loss_mask: 0.1968 2022/11/01 15:49:25 - mmengine - INFO - Epoch(train) [142][25/125] lr: 2.0000e-04 eta: 0:43:55 time: 0.5314 data_time: 0.0891 memory: 10659 loss: 0.4351 loss_rpn_cls: 0.0094 loss_rpn_bbox: 0.0104 loss_cls: 0.0869 acc: 95.9229 loss_bbox: 0.1256 loss_mask: 0.2028 2022/11/01 15:49:27 - mmengine - INFO - Epoch(train) [142][30/125] lr: 2.0000e-04 eta: 0:42:10 time: 0.4968 data_time: 0.0628 memory: 10056 loss: 0.4028 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0105 loss_cls: 0.0793 acc: 98.0957 loss_bbox: 0.1165 loss_mask: 0.1888 2022/11/01 15:49:29 - mmengine - INFO - Epoch(train) [142][35/125] lr: 2.0000e-04 eta: 0:42:10 time: 0.4414 data_time: 0.0670 memory: 9570 loss: 0.4153 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0099 loss_cls: 0.0766 acc: 96.8018 loss_bbox: 0.1205 loss_mask: 0.2011 2022/11/01 15:49:32 - mmengine - INFO - Epoch(train) [142][40/125] lr: 2.0000e-04 eta: 0:40:25 time: 0.4156 data_time: 0.0750 memory: 9692 loss: 0.4608 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0109 loss_cls: 0.0852 acc: 96.5088 loss_bbox: 0.1279 loss_mask: 0.2293 2022/11/01 15:49:34 - mmengine - INFO - Epoch(train) [142][45/125] lr: 2.0000e-04 eta: 0:40:25 time: 0.4571 data_time: 0.0769 memory: 10069 loss: 0.4476 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0111 loss_cls: 0.0837 acc: 97.2656 loss_bbox: 0.1190 loss_mask: 0.2250 2022/11/01 15:49:36 - mmengine - INFO - Epoch(train) [142][50/125] lr: 2.0000e-04 eta: 0:39:01 time: 0.4834 data_time: 0.0850 memory: 9830 loss: 0.4354 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0111 loss_cls: 0.0836 acc: 96.1670 loss_bbox: 0.1205 loss_mask: 0.2119 2022/11/01 15:49:39 - mmengine - INFO - Epoch(train) [142][55/125] lr: 2.0000e-04 eta: 0:39:01 time: 0.4525 data_time: 0.0769 memory: 10940 loss: 0.4487 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0104 loss_cls: 0.0853 acc: 96.4844 loss_bbox: 0.1329 loss_mask: 0.2126 2022/11/01 15:49:41 - mmengine - INFO - Epoch(train) [142][60/125] lr: 2.0000e-04 eta: 0:37:40 time: 0.4441 data_time: 0.0552 memory: 10492 loss: 0.4498 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0095 loss_cls: 0.0877 acc: 97.7539 loss_bbox: 0.1392 loss_mask: 0.2062 2022/11/01 15:49:43 - mmengine - INFO - Epoch(train) [142][65/125] lr: 2.0000e-04 eta: 0:37:40 time: 0.4454 data_time: 0.0545 memory: 9972 loss: 0.4282 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0083 loss_cls: 0.0865 acc: 97.3145 loss_bbox: 0.1205 loss_mask: 0.2060 2022/11/01 15:49:46 - mmengine - INFO - Epoch(train) [142][70/125] lr: 2.0000e-04 eta: 0:36:31 time: 0.4691 data_time: 0.0696 memory: 9866 loss: 0.4113 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0069 loss_cls: 0.0804 acc: 97.3633 loss_bbox: 0.1079 loss_mask: 0.2090 2022/11/01 15:49:48 - mmengine - INFO - Epoch(train) [142][75/125] lr: 2.0000e-04 eta: 0:36:31 time: 0.4889 data_time: 0.0818 memory: 10279 loss: 0.4137 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0094 loss_cls: 0.0775 acc: 97.3389 loss_bbox: 0.1233 loss_mask: 0.1973 2022/11/01 15:49:51 - mmengine - INFO - Epoch(train) [142][80/125] lr: 2.0000e-04 eta: 0:35:30 time: 0.4955 data_time: 0.0813 memory: 10047 loss: 0.4498 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0109 loss_cls: 0.0903 acc: 96.3623 loss_bbox: 0.1471 loss_mask: 0.1953 2022/11/01 15:49:53 - mmengine - INFO - Epoch(train) [142][85/125] lr: 2.0000e-04 eta: 0:35:30 time: 0.5023 data_time: 0.0692 memory: 10539 loss: 0.4594 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0099 loss_cls: 0.0919 acc: 97.5342 loss_bbox: 0.1441 loss_mask: 0.2076 2022/11/01 15:49:55 - mmengine - INFO - Epoch(train) [142][90/125] lr: 2.0000e-04 eta: 0:34:33 time: 0.4740 data_time: 0.0513 memory: 9810 loss: 0.4331 loss_rpn_cls: 0.0062 loss_rpn_bbox: 0.0094 loss_cls: 0.0809 acc: 97.1924 loss_bbox: 0.1246 loss_mask: 0.2120 2022/11/01 15:49:58 - mmengine - INFO - Epoch(train) [142][95/125] lr: 2.0000e-04 eta: 0:34:33 time: 0.4892 data_time: 0.0690 memory: 10506 loss: 0.4265 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0094 loss_cls: 0.0850 acc: 96.3867 loss_bbox: 0.1242 loss_mask: 0.2011 2022/11/01 15:50:00 - mmengine - INFO - Epoch(train) [142][100/125] lr: 2.0000e-04 eta: 0:33:42 time: 0.4986 data_time: 0.1183 memory: 9455 loss: 0.4244 loss_rpn_cls: 0.0053 loss_rpn_bbox: 0.0081 loss_cls: 0.0877 acc: 96.4600 loss_bbox: 0.1280 loss_mask: 0.1953 2022/11/01 15:50:03 - mmengine - INFO - Epoch(train) [142][105/125] lr: 2.0000e-04 eta: 0:33:42 time: 0.5470 data_time: 0.1214 memory: 11274 loss: 0.4813 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0146 loss_cls: 0.1015 acc: 96.2891 loss_bbox: 0.1584 loss_mask: 0.1997 2022/11/01 15:50:06 - mmengine - INFO - Epoch(train) [142][110/125] lr: 2.0000e-04 eta: 0:32:58 time: 0.5248 data_time: 0.0795 memory: 9983 loss: 0.4591 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0146 loss_cls: 0.0940 acc: 97.5586 loss_bbox: 0.1472 loss_mask: 0.1944 2022/11/01 15:50:08 - mmengine - INFO - Epoch(train) [142][115/125] lr: 2.0000e-04 eta: 0:32:58 time: 0.4712 data_time: 0.0829 memory: 10618 loss: 0.4128 loss_rpn_cls: 0.0106 loss_rpn_bbox: 0.0081 loss_cls: 0.0776 acc: 95.6543 loss_bbox: 0.1198 loss_mask: 0.1967 2022/11/01 15:50:11 - mmengine - INFO - Epoch(train) [142][120/125] lr: 2.0000e-04 eta: 0:32:17 time: 0.5238 data_time: 0.1136 memory: 10576 loss: 0.4895 loss_rpn_cls: 0.0154 loss_rpn_bbox: 0.0128 loss_cls: 0.0951 acc: 96.4111 loss_bbox: 0.1523 loss_mask: 0.2138 2022/11/01 15:50:12 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:50:12 - mmengine - INFO - Epoch(train) [142][125/125] lr: 2.0000e-04 eta: 0:32:17 time: 0.4378 data_time: 0.0716 memory: 9590 loss: 0.4865 loss_rpn_cls: 0.0134 loss_rpn_bbox: 0.0146 loss_cls: 0.0954 acc: 97.0459 loss_bbox: 0.1501 loss_mask: 0.2129 2022/11/01 15:50:16 - mmengine - INFO - Epoch(train) [143][5/125] lr: 2.0000e-04 eta: 0:32:17 time: 0.5166 data_time: 0.1467 memory: 10100 loss: 0.4441 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0124 loss_cls: 0.0884 acc: 95.4590 loss_bbox: 0.1334 loss_mask: 0.2013 2022/11/01 15:50:18 - mmengine - INFO - Epoch(train) [143][10/125] lr: 2.0000e-04 eta: 0:31:06 time: 0.6083 data_time: 0.1723 memory: 10826 loss: 0.4168 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0109 loss_cls: 0.0840 acc: 97.4121 loss_bbox: 0.1284 loss_mask: 0.1852 2022/11/01 15:50:21 - mmengine - INFO - Epoch(train) [143][15/125] lr: 2.0000e-04 eta: 0:31:06 time: 0.4885 data_time: 0.0729 memory: 10473 loss: 0.4050 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0093 loss_cls: 0.0788 acc: 97.3145 loss_bbox: 0.1230 loss_mask: 0.1864 2022/11/01 15:50:23 - mmengine - INFO - Epoch(train) [143][20/125] lr: 2.0000e-04 eta: 0:30:29 time: 0.4860 data_time: 0.1029 memory: 9967 loss: 0.4401 loss_rpn_cls: 0.0065 loss_rpn_bbox: 0.0097 loss_cls: 0.0865 acc: 95.4834 loss_bbox: 0.1275 loss_mask: 0.2099 2022/11/01 15:50:26 - mmengine - INFO - Epoch(train) [143][25/125] lr: 2.0000e-04 eta: 0:30:29 time: 0.4913 data_time: 0.0960 memory: 10144 loss: 0.4295 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0099 loss_cls: 0.0841 acc: 98.3643 loss_bbox: 0.1232 loss_mask: 0.2049 2022/11/01 15:50:28 - mmengine - INFO - Epoch(train) [143][30/125] lr: 2.0000e-04 eta: 0:29:56 time: 0.5063 data_time: 0.0795 memory: 10312 loss: 0.4267 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0094 loss_cls: 0.0855 acc: 93.2129 loss_bbox: 0.1271 loss_mask: 0.1959 2022/11/01 15:50:31 - mmengine - INFO - Epoch(train) [143][35/125] lr: 2.0000e-04 eta: 0:29:56 time: 0.5378 data_time: 0.0862 memory: 10641 loss: 0.4648 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0100 loss_cls: 0.0944 acc: 95.6543 loss_bbox: 0.1463 loss_mask: 0.2047 2022/11/01 15:50:33 - mmengine - INFO - Epoch(train) [143][40/125] lr: 2.0000e-04 eta: 0:29:23 time: 0.4877 data_time: 0.0739 memory: 10120 loss: 0.4462 loss_rpn_cls: 0.0085 loss_rpn_bbox: 0.0093 loss_cls: 0.0820 acc: 97.7783 loss_bbox: 0.1351 loss_mask: 0.2114 2022/11/01 15:50:36 - mmengine - INFO - Epoch(train) [143][45/125] lr: 2.0000e-04 eta: 0:29:23 time: 0.4410 data_time: 0.0822 memory: 9976 loss: 0.4208 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0074 loss_cls: 0.0775 acc: 96.9238 loss_bbox: 0.1164 loss_mask: 0.2124 2022/11/01 15:50:38 - mmengine - INFO - Epoch(train) [143][50/125] lr: 2.0000e-04 eta: 0:28:50 time: 0.4563 data_time: 0.0873 memory: 10414 loss: 0.4244 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0093 loss_cls: 0.0851 acc: 96.7041 loss_bbox: 0.1169 loss_mask: 0.2063 2022/11/01 15:50:40 - mmengine - INFO - Epoch(train) [143][55/125] lr: 2.0000e-04 eta: 0:28:50 time: 0.4569 data_time: 0.0726 memory: 10242 loss: 0.4032 loss_rpn_cls: 0.0060 loss_rpn_bbox: 0.0099 loss_cls: 0.0792 acc: 97.8516 loss_bbox: 0.1150 loss_mask: 0.1932 2022/11/01 15:50:42 - mmengine - INFO - Epoch(train) [143][60/125] lr: 2.0000e-04 eta: 0:28:16 time: 0.4142 data_time: 0.0577 memory: 9890 loss: 0.4035 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0093 loss_cls: 0.0752 acc: 97.8760 loss_bbox: 0.1172 loss_mask: 0.1951 2022/11/01 15:50:44 - mmengine - INFO - Epoch(train) [143][65/125] lr: 2.0000e-04 eta: 0:28:16 time: 0.3809 data_time: 0.0577 memory: 9802 loss: 0.4173 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0103 loss_cls: 0.0766 acc: 98.0469 loss_bbox: 0.1215 loss_mask: 0.2013 2022/11/01 15:50:46 - mmengine - INFO - Epoch(train) [143][70/125] lr: 2.0000e-04 eta: 0:27:43 time: 0.4139 data_time: 0.0675 memory: 10140 loss: 0.4134 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0091 loss_cls: 0.0766 acc: 98.3398 loss_bbox: 0.1194 loss_mask: 0.2006 2022/11/01 15:50:49 - mmengine - INFO - Epoch(train) [143][75/125] lr: 2.0000e-04 eta: 0:27:43 time: 0.4576 data_time: 0.0749 memory: 10298 loss: 0.4445 loss_rpn_cls: 0.0085 loss_rpn_bbox: 0.0109 loss_cls: 0.0906 acc: 97.2168 loss_bbox: 0.1309 loss_mask: 0.2036 2022/11/01 15:50:51 - mmengine - INFO - Epoch(train) [143][80/125] lr: 2.0000e-04 eta: 0:27:15 time: 0.4507 data_time: 0.0666 memory: 10372 loss: 0.4561 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0124 loss_cls: 0.0923 acc: 97.3145 loss_bbox: 0.1323 loss_mask: 0.2120 2022/11/01 15:50:53 - mmengine - INFO - Epoch(train) [143][85/125] lr: 2.0000e-04 eta: 0:27:15 time: 0.4531 data_time: 0.0680 memory: 10302 loss: 0.4365 loss_rpn_cls: 0.0102 loss_rpn_bbox: 0.0116 loss_cls: 0.0802 acc: 96.1426 loss_bbox: 0.1259 loss_mask: 0.2085 2022/11/01 15:50:55 - mmengine - INFO - Epoch(train) [143][90/125] lr: 2.0000e-04 eta: 0:26:48 time: 0.4490 data_time: 0.0849 memory: 9729 loss: 0.4036 loss_rpn_cls: 0.0104 loss_rpn_bbox: 0.0088 loss_cls: 0.0719 acc: 97.2412 loss_bbox: 0.1166 loss_mask: 0.1958 2022/11/01 15:50:57 - mmengine - INFO - Epoch(train) [143][95/125] lr: 2.0000e-04 eta: 0:26:48 time: 0.4008 data_time: 0.0805 memory: 9514 loss: 0.4035 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0100 loss_cls: 0.0736 acc: 97.4365 loss_bbox: 0.1176 loss_mask: 0.1946 2022/11/01 15:50:59 - mmengine - INFO - Epoch(train) [143][100/125] lr: 2.0000e-04 eta: 0:26:19 time: 0.3817 data_time: 0.0652 memory: 9583 loss: 0.4161 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0133 loss_cls: 0.0764 acc: 96.8506 loss_bbox: 0.1232 loss_mask: 0.1948 2022/11/01 15:51:02 - mmengine - INFO - Epoch(train) [143][105/125] lr: 2.0000e-04 eta: 0:26:19 time: 0.4500 data_time: 0.0720 memory: 10132 loss: 0.4133 loss_rpn_cls: 0.0087 loss_rpn_bbox: 0.0141 loss_cls: 0.0752 acc: 97.8516 loss_bbox: 0.1201 loss_mask: 0.1951 2022/11/01 15:51:04 - mmengine - INFO - Epoch(train) [143][110/125] lr: 2.0000e-04 eta: 0:25:57 time: 0.4913 data_time: 0.0898 memory: 9987 loss: 0.4485 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0135 loss_cls: 0.0878 acc: 97.3877 loss_bbox: 0.1308 loss_mask: 0.2067 2022/11/01 15:51:06 - mmengine - INFO - Epoch(train) [143][115/125] lr: 2.0000e-04 eta: 0:25:57 time: 0.4394 data_time: 0.0703 memory: 10080 loss: 0.4474 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0119 loss_cls: 0.0915 acc: 95.1660 loss_bbox: 0.1321 loss_mask: 0.2026 2022/11/01 15:51:08 - mmengine - INFO - Epoch(train) [143][120/125] lr: 2.0000e-04 eta: 0:25:32 time: 0.4199 data_time: 0.0588 memory: 9681 loss: 0.3967 loss_rpn_cls: 0.0065 loss_rpn_bbox: 0.0094 loss_cls: 0.0784 acc: 97.0459 loss_bbox: 0.1129 loss_mask: 0.1895 2022/11/01 15:51:10 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:51:10 - mmengine - INFO - Epoch(train) [143][125/125] lr: 2.0000e-04 eta: 0:25:32 time: 0.4039 data_time: 0.0459 memory: 10468 loss: 0.4105 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0103 loss_cls: 0.0811 acc: 96.7773 loss_bbox: 0.1172 loss_mask: 0.1937 2022/11/01 15:51:13 - mmengine - INFO - Epoch(train) [144][5/125] lr: 2.0000e-04 eta: 0:25:32 time: 0.5163 data_time: 0.1663 memory: 9263 loss: 0.4416 loss_rpn_cls: 0.0106 loss_rpn_bbox: 0.0120 loss_cls: 0.0894 acc: 97.9736 loss_bbox: 0.1216 loss_mask: 0.2081 2022/11/01 15:51:16 - mmengine - INFO - Epoch(train) [144][10/125] lr: 2.0000e-04 eta: 0:24:52 time: 0.5588 data_time: 0.2009 memory: 9996 loss: 0.4174 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0096 loss_cls: 0.0814 acc: 98.2666 loss_bbox: 0.1063 loss_mask: 0.2121 2022/11/01 15:51:17 - mmengine - INFO - Epoch(train) [144][15/125] lr: 2.0000e-04 eta: 0:24:52 time: 0.4142 data_time: 0.0668 memory: 9502 loss: 0.4044 loss_rpn_cls: 0.0062 loss_rpn_bbox: 0.0081 loss_cls: 0.0760 acc: 97.5342 loss_bbox: 0.1096 loss_mask: 0.2045 2022/11/01 15:51:19 - mmengine - INFO - Epoch(train) [144][20/125] lr: 2.0000e-04 eta: 0:24:27 time: 0.3604 data_time: 0.0466 memory: 9486 loss: 0.4095 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0100 loss_cls: 0.0761 acc: 96.8750 loss_bbox: 0.1186 loss_mask: 0.1989 2022/11/01 15:51:21 - mmengine - INFO - Epoch(train) [144][25/125] lr: 2.0000e-04 eta: 0:24:27 time: 0.3805 data_time: 0.0545 memory: 9745 loss: 0.4154 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0116 loss_cls: 0.0775 acc: 96.1914 loss_bbox: 0.1248 loss_mask: 0.1948 2022/11/01 15:51:23 - mmengine - INFO - Epoch(train) [144][30/125] lr: 2.0000e-04 eta: 0:24:06 time: 0.4228 data_time: 0.0917 memory: 9492 loss: 0.4182 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0111 loss_cls: 0.0811 acc: 95.6543 loss_bbox: 0.1208 loss_mask: 0.1970 2022/11/01 15:51:25 - mmengine - INFO - Epoch(train) [144][35/125] lr: 2.0000e-04 eta: 0:24:06 time: 0.4253 data_time: 0.0854 memory: 10157 loss: 0.4181 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0123 loss_cls: 0.0813 acc: 96.1182 loss_bbox: 0.1245 loss_mask: 0.1919 2022/11/01 15:51:28 - mmengine - INFO - Epoch(train) [144][40/125] lr: 2.0000e-04 eta: 0:23:45 time: 0.4167 data_time: 0.0714 memory: 9894 loss: 0.4018 loss_rpn_cls: 0.0065 loss_rpn_bbox: 0.0106 loss_cls: 0.0766 acc: 97.2412 loss_bbox: 0.1234 loss_mask: 0.1846 2022/11/01 15:51:30 - mmengine - INFO - Epoch(train) [144][45/125] lr: 2.0000e-04 eta: 0:23:45 time: 0.4475 data_time: 0.0881 memory: 10217 loss: 0.4018 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0083 loss_cls: 0.0806 acc: 97.3145 loss_bbox: 0.1248 loss_mask: 0.1810 2022/11/01 15:51:32 - mmengine - INFO - Epoch(train) [144][50/125] lr: 2.0000e-04 eta: 0:23:27 time: 0.4517 data_time: 0.0908 memory: 9924 loss: 0.4357 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0097 loss_cls: 0.0909 acc: 95.9961 loss_bbox: 0.1368 loss_mask: 0.1902 2022/11/01 15:51:34 - mmengine - INFO - Epoch(train) [144][55/125] lr: 2.0000e-04 eta: 0:23:27 time: 0.4170 data_time: 0.0876 memory: 9676 loss: 0.4381 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0108 loss_cls: 0.0874 acc: 97.1191 loss_bbox: 0.1308 loss_mask: 0.2003 2022/11/01 15:51:36 - mmengine - INFO - Epoch(train) [144][60/125] lr: 2.0000e-04 eta: 0:23:08 time: 0.4155 data_time: 0.0866 memory: 9514 loss: 0.3986 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0092 loss_cls: 0.0738 acc: 96.3867 loss_bbox: 0.1068 loss_mask: 0.1995 2022/11/01 15:51:39 - mmengine - INFO - Epoch(train) [144][65/125] lr: 2.0000e-04 eta: 0:23:08 time: 0.4436 data_time: 0.0804 memory: 9963 loss: 0.3991 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0091 loss_cls: 0.0769 acc: 97.5098 loss_bbox: 0.1074 loss_mask: 0.1974 2022/11/01 15:51:41 - mmengine - INFO - Epoch(train) [144][70/125] lr: 2.0000e-04 eta: 0:22:50 time: 0.4376 data_time: 0.0661 memory: 9393 loss: 0.4198 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0107 loss_cls: 0.0829 acc: 97.5586 loss_bbox: 0.1167 loss_mask: 0.2014 2022/11/01 15:51:43 - mmengine - INFO - Epoch(train) [144][75/125] lr: 2.0000e-04 eta: 0:22:50 time: 0.4567 data_time: 0.0661 memory: 10594 loss: 0.4017 loss_rpn_cls: 0.0075 loss_rpn_bbox: 0.0099 loss_cls: 0.0740 acc: 97.4854 loss_bbox: 0.1055 loss_mask: 0.2048 2022/11/01 15:51:45 - mmengine - INFO - Epoch(train) [144][80/125] lr: 2.0000e-04 eta: 0:22:34 time: 0.4587 data_time: 0.0452 memory: 9955 loss: 0.4313 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0104 loss_cls: 0.0812 acc: 95.8740 loss_bbox: 0.1286 loss_mask: 0.2033 2022/11/01 15:51:48 - mmengine - INFO - Epoch(train) [144][85/125] lr: 2.0000e-04 eta: 0:22:34 time: 0.4408 data_time: 0.0535 memory: 10225 loss: 0.4544 loss_rpn_cls: 0.0106 loss_rpn_bbox: 0.0133 loss_cls: 0.0948 acc: 94.6289 loss_bbox: 0.1424 loss_mask: 0.1933 2022/11/01 15:51:49 - mmengine - INFO - Epoch(train) [144][90/125] lr: 2.0000e-04 eta: 0:22:17 time: 0.4184 data_time: 0.0510 memory: 10193 loss: 0.4254 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0102 loss_cls: 0.0833 acc: 97.8516 loss_bbox: 0.1264 loss_mask: 0.1974 2022/11/01 15:51:52 - mmengine - INFO - Epoch(train) [144][95/125] lr: 2.0000e-04 eta: 0:22:17 time: 0.4522 data_time: 0.0983 memory: 9518 loss: 0.4435 loss_rpn_cls: 0.0046 loss_rpn_bbox: 0.0076 loss_cls: 0.0831 acc: 96.8506 loss_bbox: 0.1291 loss_mask: 0.2191 2022/11/01 15:51:55 - mmengine - INFO - Epoch(train) [144][100/125] lr: 2.0000e-04 eta: 0:22:06 time: 0.5460 data_time: 0.1623 memory: 10394 loss: 0.4376 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0092 loss_cls: 0.0873 acc: 96.8750 loss_bbox: 0.1284 loss_mask: 0.2042 2022/11/01 15:51:57 - mmengine - INFO - Epoch(train) [144][105/125] lr: 2.0000e-04 eta: 0:22:06 time: 0.4809 data_time: 0.0800 memory: 10459 loss: 0.4235 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0104 loss_cls: 0.0825 acc: 95.4834 loss_bbox: 0.1278 loss_mask: 0.1936 2022/11/01 15:51:59 - mmengine - INFO - Epoch(train) [144][110/125] lr: 2.0000e-04 eta: 0:21:49 time: 0.4075 data_time: 0.0253 memory: 9628 loss: 0.4424 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0120 loss_cls: 0.0874 acc: 96.7041 loss_bbox: 0.1322 loss_mask: 0.2037 2022/11/01 15:52:02 - mmengine - INFO - Epoch(train) [144][115/125] lr: 2.0000e-04 eta: 0:21:49 time: 0.4772 data_time: 0.0657 memory: 11015 loss: 0.4439 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0119 loss_cls: 0.0877 acc: 97.4365 loss_bbox: 0.1409 loss_mask: 0.1962 2022/11/01 15:52:04 - mmengine - INFO - Epoch(train) [144][120/125] lr: 2.0000e-04 eta: 0:21:37 time: 0.5282 data_time: 0.0799 memory: 10404 loss: 0.4612 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0114 loss_cls: 0.0924 acc: 94.8486 loss_bbox: 0.1492 loss_mask: 0.2002 2022/11/01 15:52:06 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:52:06 - mmengine - INFO - Epoch(train) [144][125/125] lr: 2.0000e-04 eta: 0:21:37 time: 0.4696 data_time: 0.0535 memory: 10552 loss: 0.4799 loss_rpn_cls: 0.0102 loss_rpn_bbox: 0.0132 loss_cls: 0.0989 acc: 97.1191 loss_bbox: 0.1469 loss_mask: 0.2107 2022/11/01 15:52:10 - mmengine - INFO - Epoch(train) [145][5/125] lr: 2.0000e-04 eta: 0:21:37 time: 0.5656 data_time: 0.1924 memory: 9293 loss: 0.4142 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0099 loss_cls: 0.0814 acc: 97.8760 loss_bbox: 0.1242 loss_mask: 0.1914 2022/11/01 15:52:14 - mmengine - INFO - Epoch(train) [145][10/125] lr: 2.0000e-04 eta: 0:21:20 time: 0.7706 data_time: 0.3824 memory: 10580 loss: 0.4149 loss_rpn_cls: 0.0062 loss_rpn_bbox: 0.0092 loss_cls: 0.0839 acc: 97.2168 loss_bbox: 0.1274 loss_mask: 0.1883 2022/11/01 15:52:16 - mmengine - INFO - Epoch(train) [145][15/125] lr: 2.0000e-04 eta: 0:21:20 time: 0.6079 data_time: 0.2325 memory: 9746 loss: 0.4734 loss_rpn_cls: 0.0102 loss_rpn_bbox: 0.0120 loss_cls: 0.0982 acc: 95.9473 loss_bbox: 0.1458 loss_mask: 0.2073 2022/11/01 15:52:18 - mmengine - INFO - Epoch(train) [145][20/125] lr: 2.0000e-04 eta: 0:21:05 time: 0.4169 data_time: 0.0464 memory: 10637 loss: 0.4588 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0107 loss_cls: 0.0935 acc: 97.8516 loss_bbox: 0.1405 loss_mask: 0.2053 2022/11/01 15:52:20 - mmengine - INFO - Epoch(train) [145][25/125] lr: 2.0000e-04 eta: 0:21:05 time: 0.4490 data_time: 0.0613 memory: 9286 loss: 0.4176 loss_rpn_cls: 0.0090 loss_rpn_bbox: 0.0089 loss_cls: 0.0818 acc: 97.0703 loss_bbox: 0.1217 loss_mask: 0.1962 2022/11/01 15:52:23 - mmengine - INFO - Epoch(train) [145][30/125] lr: 2.0000e-04 eta: 0:20:51 time: 0.4397 data_time: 0.0670 memory: 10381 loss: 0.4181 loss_rpn_cls: 0.0108 loss_rpn_bbox: 0.0083 loss_cls: 0.0785 acc: 97.6074 loss_bbox: 0.1165 loss_mask: 0.2040 2022/11/01 15:52:25 - mmengine - INFO - Epoch(train) [145][35/125] lr: 2.0000e-04 eta: 0:20:51 time: 0.4275 data_time: 0.0515 memory: 9622 loss: 0.4470 loss_rpn_cls: 0.0091 loss_rpn_bbox: 0.0105 loss_cls: 0.0861 acc: 97.3389 loss_bbox: 0.1324 loss_mask: 0.2089 2022/11/01 15:52:27 - mmengine - INFO - Epoch(train) [145][40/125] lr: 2.0000e-04 eta: 0:20:37 time: 0.4166 data_time: 0.0473 memory: 9700 loss: 0.4192 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0091 loss_cls: 0.0831 acc: 97.0703 loss_bbox: 0.1260 loss_mask: 0.1937 2022/11/01 15:52:30 - mmengine - INFO - Epoch(train) [145][45/125] lr: 2.0000e-04 eta: 0:20:37 time: 0.4914 data_time: 0.0626 memory: 10937 loss: 0.4357 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0114 loss_cls: 0.0922 acc: 95.3613 loss_bbox: 0.1382 loss_mask: 0.1870 2022/11/01 15:52:32 - mmengine - INFO - Epoch(train) [145][50/125] lr: 2.0000e-04 eta: 0:20:26 time: 0.4985 data_time: 0.0687 memory: 9338 loss: 0.4398 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0125 loss_cls: 0.0852 acc: 97.4365 loss_bbox: 0.1330 loss_mask: 0.2004 2022/11/01 15:52:34 - mmengine - INFO - Epoch(train) [145][55/125] lr: 2.0000e-04 eta: 0:20:26 time: 0.3989 data_time: 0.0620 memory: 9498 loss: 0.3950 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0083 loss_cls: 0.0692 acc: 97.3389 loss_bbox: 0.1098 loss_mask: 0.1995 2022/11/01 15:52:36 - mmengine - INFO - Epoch(train) [145][60/125] lr: 2.0000e-04 eta: 0:20:12 time: 0.4217 data_time: 0.0841 memory: 9470 loss: 0.3809 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0084 loss_cls: 0.0663 acc: 97.9492 loss_bbox: 0.1030 loss_mask: 0.1969 2022/11/01 15:52:38 - mmengine - INFO - Epoch(train) [145][65/125] lr: 2.0000e-04 eta: 0:20:12 time: 0.4728 data_time: 0.0885 memory: 10590 loss: 0.4092 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0099 loss_cls: 0.0785 acc: 95.2881 loss_bbox: 0.1183 loss_mask: 0.1949 2022/11/01 15:52:41 - mmengine - INFO - Epoch(train) [145][70/125] lr: 2.0000e-04 eta: 0:20:01 time: 0.4705 data_time: 0.0880 memory: 9609 loss: 0.4468 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0124 loss_cls: 0.0955 acc: 96.6797 loss_bbox: 0.1400 loss_mask: 0.1901 2022/11/01 15:52:43 - mmengine - INFO - Epoch(train) [145][75/125] lr: 2.0000e-04 eta: 0:20:01 time: 0.4466 data_time: 0.0982 memory: 10190 loss: 0.4325 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0118 loss_cls: 0.0876 acc: 97.3877 loss_bbox: 0.1302 loss_mask: 0.1960 2022/11/01 15:52:45 - mmengine - INFO - Epoch(train) [145][80/125] lr: 2.0000e-04 eta: 0:19:49 time: 0.4494 data_time: 0.0954 memory: 10330 loss: 0.4346 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0112 loss_cls: 0.0850 acc: 96.8018 loss_bbox: 0.1286 loss_mask: 0.2016 2022/11/01 15:52:47 - mmengine - INFO - Epoch(train) [145][85/125] lr: 2.0000e-04 eta: 0:19:49 time: 0.4219 data_time: 0.0764 memory: 9437 loss: 0.4641 loss_rpn_cls: 0.0091 loss_rpn_bbox: 0.0131 loss_cls: 0.0948 acc: 95.7764 loss_bbox: 0.1401 loss_mask: 0.2071 2022/11/01 15:52:50 - mmengine - INFO - Epoch(train) [145][90/125] lr: 2.0000e-04 eta: 0:19:37 time: 0.4426 data_time: 0.0836 memory: 10148 loss: 0.4487 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0110 loss_cls: 0.0898 acc: 96.5576 loss_bbox: 0.1333 loss_mask: 0.2068 2022/11/01 15:52:52 - mmengine - INFO - Epoch(train) [145][95/125] lr: 2.0000e-04 eta: 0:19:37 time: 0.4612 data_time: 0.0868 memory: 9951 loss: 0.4318 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0078 loss_cls: 0.0812 acc: 96.1914 loss_bbox: 0.1218 loss_mask: 0.2128 2022/11/01 15:52:54 - mmengine - INFO - Epoch(train) [145][100/125] lr: 2.0000e-04 eta: 0:19:24 time: 0.4034 data_time: 0.0708 memory: 9632 loss: 0.4231 loss_rpn_cls: 0.0090 loss_rpn_bbox: 0.0085 loss_cls: 0.0828 acc: 97.3145 loss_bbox: 0.1173 loss_mask: 0.2055 2022/11/01 15:52:56 - mmengine - INFO - Epoch(train) [145][105/125] lr: 2.0000e-04 eta: 0:19:24 time: 0.4106 data_time: 0.0724 memory: 10386 loss: 0.4145 loss_rpn_cls: 0.0096 loss_rpn_bbox: 0.0101 loss_cls: 0.0852 acc: 97.5342 loss_bbox: 0.1193 loss_mask: 0.1903 2022/11/01 15:52:58 - mmengine - INFO - Epoch(train) [145][110/125] lr: 2.0000e-04 eta: 0:19:12 time: 0.4325 data_time: 0.0785 memory: 9482 loss: 0.4096 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0088 loss_cls: 0.0816 acc: 96.1426 loss_bbox: 0.1211 loss_mask: 0.1910 2022/11/01 15:53:01 - mmengine - INFO - Epoch(train) [145][115/125] lr: 2.0000e-04 eta: 0:19:12 time: 0.4834 data_time: 0.1040 memory: 10465 loss: 0.4322 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0115 loss_cls: 0.0863 acc: 96.7041 loss_bbox: 0.1306 loss_mask: 0.1967 2022/11/01 15:53:03 - mmengine - INFO - Epoch(train) [145][120/125] lr: 2.0000e-04 eta: 0:19:02 time: 0.4785 data_time: 0.0901 memory: 10432 loss: 0.4530 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0126 loss_cls: 0.0924 acc: 97.6562 loss_bbox: 0.1404 loss_mask: 0.1993 2022/11/01 15:53:04 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:53:04 - mmengine - INFO - Epoch(train) [145][125/125] lr: 2.0000e-04 eta: 0:19:02 time: 0.3763 data_time: 0.0422 memory: 9319 loss: 0.4104 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0089 loss_cls: 0.0780 acc: 97.8271 loss_bbox: 0.1208 loss_mask: 0.1955 2022/11/01 15:53:08 - mmengine - INFO - Epoch(train) [146][5/125] lr: 2.0000e-04 eta: 0:19:02 time: 0.4943 data_time: 0.1787 memory: 9755 loss: 0.4065 loss_rpn_cls: 0.0065 loss_rpn_bbox: 0.0093 loss_cls: 0.0751 acc: 97.7783 loss_bbox: 0.1187 loss_mask: 0.1969 2022/11/01 15:53:10 - mmengine - INFO - Epoch(train) [146][10/125] lr: 2.0000e-04 eta: 0:18:42 time: 0.5466 data_time: 0.1944 memory: 9762 loss: 0.4260 loss_rpn_cls: 0.0063 loss_rpn_bbox: 0.0088 loss_cls: 0.0791 acc: 97.4609 loss_bbox: 0.1239 loss_mask: 0.2078 2022/11/01 15:53:12 - mmengine - INFO - Epoch(train) [146][15/125] lr: 2.0000e-04 eta: 0:18:42 time: 0.4491 data_time: 0.0539 memory: 11153 loss: 0.4536 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0113 loss_cls: 0.0880 acc: 93.5303 loss_bbox: 0.1320 loss_mask: 0.2132 2022/11/01 15:53:14 - mmengine - INFO - Epoch(train) [146][20/125] lr: 2.0000e-04 eta: 0:18:32 time: 0.4436 data_time: 0.0614 memory: 10321 loss: 0.4422 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0145 loss_cls: 0.0866 acc: 97.5586 loss_bbox: 0.1351 loss_mask: 0.1975 2022/11/01 15:53:16 - mmengine - INFO - Epoch(train) [146][25/125] lr: 2.0000e-04 eta: 0:18:32 time: 0.4169 data_time: 0.0737 memory: 9619 loss: 0.4029 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0115 loss_cls: 0.0748 acc: 98.0225 loss_bbox: 0.1169 loss_mask: 0.1937 2022/11/01 15:53:18 - mmengine - INFO - Epoch(train) [146][30/125] lr: 2.0000e-04 eta: 0:18:20 time: 0.4138 data_time: 0.0713 memory: 9608 loss: 0.3911 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0100 loss_cls: 0.0755 acc: 99.0723 loss_bbox: 0.1109 loss_mask: 0.1881 2022/11/01 15:53:20 - mmengine - INFO - Epoch(train) [146][35/125] lr: 2.0000e-04 eta: 0:18:20 time: 0.4081 data_time: 0.0560 memory: 9540 loss: 0.4085 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0098 loss_cls: 0.0817 acc: 96.0205 loss_bbox: 0.1186 loss_mask: 0.1914 2022/11/01 15:53:22 - mmengine - INFO - Epoch(train) [146][40/125] lr: 2.0000e-04 eta: 0:18:09 time: 0.3940 data_time: 0.0373 memory: 9959 loss: 0.4559 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0090 loss_cls: 0.0923 acc: 96.3379 loss_bbox: 0.1313 loss_mask: 0.2152 2022/11/01 15:53:25 - mmengine - INFO - Epoch(train) [146][45/125] lr: 2.0000e-04 eta: 0:18:09 time: 0.4229 data_time: 0.0587 memory: 9612 loss: 0.4566 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0101 loss_cls: 0.0900 acc: 95.4346 loss_bbox: 0.1340 loss_mask: 0.2154 2022/11/01 15:53:27 - mmengine - INFO - Epoch(train) [146][50/125] lr: 2.0000e-04 eta: 0:18:01 time: 0.5132 data_time: 0.1223 memory: 10348 loss: 0.4733 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0118 loss_cls: 0.0958 acc: 97.3633 loss_bbox: 0.1423 loss_mask: 0.2158 2022/11/01 15:53:30 - mmengine - INFO - Epoch(train) [146][55/125] lr: 2.0000e-04 eta: 0:18:01 time: 0.4919 data_time: 0.1022 memory: 10245 loss: 0.4775 loss_rpn_cls: 0.0125 loss_rpn_bbox: 0.0130 loss_cls: 0.0968 acc: 96.2158 loss_bbox: 0.1457 loss_mask: 0.2094 2022/11/01 15:53:31 - mmengine - INFO - Epoch(train) [146][60/125] lr: 2.0000e-04 eta: 0:17:49 time: 0.3888 data_time: 0.0430 memory: 9559 loss: 0.4178 loss_rpn_cls: 0.0110 loss_rpn_bbox: 0.0101 loss_cls: 0.0765 acc: 97.6074 loss_bbox: 0.1198 loss_mask: 0.2005 2022/11/01 15:53:34 - mmengine - INFO - Epoch(train) [146][65/125] lr: 2.0000e-04 eta: 0:17:49 time: 0.3977 data_time: 0.0342 memory: 10548 loss: 0.4057 loss_rpn_cls: 0.0120 loss_rpn_bbox: 0.0086 loss_cls: 0.0723 acc: 96.4355 loss_bbox: 0.1066 loss_mask: 0.2062 2022/11/01 15:53:37 - mmengine - INFO - Epoch(train) [146][70/125] lr: 2.0000e-04 eta: 0:17:42 time: 0.5242 data_time: 0.1651 memory: 9403 loss: 0.4245 loss_rpn_cls: 0.0117 loss_rpn_bbox: 0.0101 loss_cls: 0.0792 acc: 97.3877 loss_bbox: 0.1147 loss_mask: 0.2089 2022/11/01 15:53:39 - mmengine - INFO - Epoch(train) [146][75/125] lr: 2.0000e-04 eta: 0:17:42 time: 0.5192 data_time: 0.1553 memory: 10377 loss: 0.4406 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0106 loss_cls: 0.0859 acc: 96.5576 loss_bbox: 0.1263 loss_mask: 0.2107 2022/11/01 15:53:41 - mmengine - INFO - Epoch(train) [146][80/125] lr: 2.0000e-04 eta: 0:17:31 time: 0.3987 data_time: 0.0316 memory: 9612 loss: 0.4604 loss_rpn_cls: 0.0087 loss_rpn_bbox: 0.0122 loss_cls: 0.0935 acc: 96.7529 loss_bbox: 0.1369 loss_mask: 0.2090 2022/11/01 15:53:43 - mmengine - INFO - Epoch(train) [146][85/125] lr: 2.0000e-04 eta: 0:17:31 time: 0.4139 data_time: 0.0855 memory: 9923 loss: 0.4139 loss_rpn_cls: 0.0091 loss_rpn_bbox: 0.0106 loss_cls: 0.0821 acc: 97.8516 loss_bbox: 0.1204 loss_mask: 0.1917 2022/11/01 15:53:45 - mmengine - INFO - Epoch(train) [146][90/125] lr: 2.0000e-04 eta: 0:17:22 time: 0.4348 data_time: 0.0823 memory: 10608 loss: 0.4259 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0108 loss_cls: 0.0844 acc: 95.7031 loss_bbox: 0.1270 loss_mask: 0.1949 2022/11/01 15:53:47 - mmengine - INFO - Epoch(train) [146][95/125] lr: 2.0000e-04 eta: 0:17:22 time: 0.3955 data_time: 0.0496 memory: 9524 loss: 0.4566 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0120 loss_cls: 0.0914 acc: 97.3633 loss_bbox: 0.1429 loss_mask: 0.2028 2022/11/01 15:53:49 - mmengine - INFO - Epoch(train) [146][100/125] lr: 2.0000e-04 eta: 0:17:11 time: 0.3821 data_time: 0.0482 memory: 10060 loss: 0.4179 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0121 loss_cls: 0.0777 acc: 97.7051 loss_bbox: 0.1228 loss_mask: 0.1982 2022/11/01 15:53:51 - mmengine - INFO - Epoch(train) [146][105/125] lr: 2.0000e-04 eta: 0:17:11 time: 0.4027 data_time: 0.0535 memory: 9341 loss: 0.3667 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0103 loss_cls: 0.0613 acc: 98.2178 loss_bbox: 0.0954 loss_mask: 0.1924 2022/11/01 15:53:53 - mmengine - INFO - Epoch(train) [146][110/125] lr: 2.0000e-04 eta: 0:17:01 time: 0.4137 data_time: 0.0556 memory: 9732 loss: 0.3687 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0080 loss_cls: 0.0647 acc: 96.9727 loss_bbox: 0.1006 loss_mask: 0.1889 2022/11/01 15:53:55 - mmengine - INFO - Epoch(train) [146][115/125] lr: 2.0000e-04 eta: 0:17:01 time: 0.4235 data_time: 0.0563 memory: 10441 loss: 0.4463 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0109 loss_cls: 0.0837 acc: 95.7764 loss_bbox: 0.1348 loss_mask: 0.2077 2022/11/01 15:53:57 - mmengine - INFO - Epoch(train) [146][120/125] lr: 2.0000e-04 eta: 0:16:51 time: 0.3944 data_time: 0.0592 memory: 9583 loss: 0.4463 loss_rpn_cls: 0.0100 loss_rpn_bbox: 0.0115 loss_cls: 0.0844 acc: 98.0957 loss_bbox: 0.1334 loss_mask: 0.2070 2022/11/01 15:53:59 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:53:59 - mmengine - INFO - Epoch(train) [146][125/125] lr: 2.0000e-04 eta: 0:16:51 time: 0.3750 data_time: 0.0435 memory: 9842 loss: 0.4263 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0117 loss_cls: 0.0809 acc: 97.8027 loss_bbox: 0.1109 loss_mask: 0.2156 2022/11/01 15:54:02 - mmengine - INFO - Epoch(train) [147][5/125] lr: 2.0000e-04 eta: 0:16:51 time: 0.5424 data_time: 0.1900 memory: 9579 loss: 0.4365 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0107 loss_cls: 0.0822 acc: 97.6807 loss_bbox: 0.1161 loss_mask: 0.2208 2022/11/01 15:54:05 - mmengine - INFO - Epoch(train) [147][10/125] lr: 2.0000e-04 eta: 0:16:36 time: 0.5866 data_time: 0.2574 memory: 9411 loss: 0.4020 loss_rpn_cls: 0.0075 loss_rpn_bbox: 0.0100 loss_cls: 0.0758 acc: 97.1436 loss_bbox: 0.1200 loss_mask: 0.1887 2022/11/01 15:54:07 - mmengine - INFO - Epoch(train) [147][15/125] lr: 2.0000e-04 eta: 0:16:36 time: 0.4501 data_time: 0.1064 memory: 10857 loss: 0.3996 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0130 loss_cls: 0.0780 acc: 96.1182 loss_bbox: 0.1215 loss_mask: 0.1802 2022/11/01 15:54:09 - mmengine - INFO - Epoch(train) [147][20/125] lr: 2.0000e-04 eta: 0:16:27 time: 0.4385 data_time: 0.0538 memory: 10362 loss: 0.4558 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0132 loss_cls: 0.0925 acc: 94.8730 loss_bbox: 0.1400 loss_mask: 0.2008 2022/11/01 15:54:11 - mmengine - INFO - Epoch(train) [147][25/125] lr: 2.0000e-04 eta: 0:16:27 time: 0.4445 data_time: 0.0523 memory: 10678 loss: 0.4487 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0133 loss_cls: 0.0891 acc: 97.8271 loss_bbox: 0.1440 loss_mask: 0.1937 2022/11/01 15:54:13 - mmengine - INFO - Epoch(train) [147][30/125] lr: 2.0000e-04 eta: 0:16:18 time: 0.4021 data_time: 0.0429 memory: 9556 loss: 0.3817 loss_rpn_cls: 0.0047 loss_rpn_bbox: 0.0110 loss_cls: 0.0715 acc: 96.9482 loss_bbox: 0.1248 loss_mask: 0.1696 2022/11/01 15:54:15 - mmengine - INFO - Epoch(train) [147][35/125] lr: 2.0000e-04 eta: 0:16:18 time: 0.4069 data_time: 0.0560 memory: 9446 loss: 0.3618 loss_rpn_cls: 0.0049 loss_rpn_bbox: 0.0073 loss_cls: 0.0697 acc: 98.5840 loss_bbox: 0.1099 loss_mask: 0.1701 2022/11/01 15:54:17 - mmengine - INFO - Epoch(train) [147][40/125] lr: 2.0000e-04 eta: 0:16:09 time: 0.4180 data_time: 0.0744 memory: 9727 loss: 0.4004 loss_rpn_cls: 0.0060 loss_rpn_bbox: 0.0081 loss_cls: 0.0801 acc: 95.1904 loss_bbox: 0.1167 loss_mask: 0.1895 2022/11/01 15:54:20 - mmengine - INFO - Epoch(train) [147][45/125] lr: 2.0000e-04 eta: 0:16:09 time: 0.4435 data_time: 0.0762 memory: 10779 loss: 0.4327 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0098 loss_cls: 0.0855 acc: 97.3145 loss_bbox: 0.1335 loss_mask: 0.1960 2022/11/01 15:54:22 - mmengine - INFO - Epoch(train) [147][50/125] lr: 2.0000e-04 eta: 0:16:01 time: 0.4710 data_time: 0.0703 memory: 9821 loss: 0.4160 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0088 loss_cls: 0.0836 acc: 97.5830 loss_bbox: 0.1263 loss_mask: 0.1890 2022/11/01 15:54:24 - mmengine - INFO - Epoch(train) [147][55/125] lr: 2.0000e-04 eta: 0:16:01 time: 0.4454 data_time: 0.0678 memory: 10275 loss: 0.4151 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0097 loss_cls: 0.0807 acc: 96.9971 loss_bbox: 0.1204 loss_mask: 0.1966 2022/11/01 15:54:26 - mmengine - INFO - Epoch(train) [147][60/125] lr: 2.0000e-04 eta: 0:15:52 time: 0.4278 data_time: 0.0704 memory: 9808 loss: 0.4435 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0114 loss_cls: 0.0876 acc: 96.9482 loss_bbox: 0.1325 loss_mask: 0.2022 2022/11/01 15:54:28 - mmengine - INFO - Epoch(train) [147][65/125] lr: 2.0000e-04 eta: 0:15:52 time: 0.4247 data_time: 0.0773 memory: 9651 loss: 0.4344 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0098 loss_cls: 0.0873 acc: 97.4609 loss_bbox: 0.1280 loss_mask: 0.2004 2022/11/01 15:54:31 - mmengine - INFO - Epoch(train) [147][70/125] lr: 2.0000e-04 eta: 0:15:44 time: 0.4295 data_time: 0.0809 memory: 9524 loss: 0.4409 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0085 loss_cls: 0.0870 acc: 96.0205 loss_bbox: 0.1318 loss_mask: 0.2054 2022/11/01 15:54:33 - mmengine - INFO - Epoch(train) [147][75/125] lr: 2.0000e-04 eta: 0:15:44 time: 0.4563 data_time: 0.0989 memory: 10293 loss: 0.4481 loss_rpn_cls: 0.0091 loss_rpn_bbox: 0.0093 loss_cls: 0.0897 acc: 98.3154 loss_bbox: 0.1282 loss_mask: 0.2118 2022/11/01 15:54:35 - mmengine - INFO - Epoch(train) [147][80/125] lr: 2.0000e-04 eta: 0:15:36 time: 0.4369 data_time: 0.0863 memory: 9620 loss: 0.4609 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0099 loss_cls: 0.0940 acc: 95.0928 loss_bbox: 0.1359 loss_mask: 0.2127 2022/11/01 15:54:37 - mmengine - INFO - Epoch(train) [147][85/125] lr: 2.0000e-04 eta: 0:15:36 time: 0.4175 data_time: 0.0508 memory: 10270 loss: 0.4815 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0091 loss_cls: 0.0986 acc: 95.8252 loss_bbox: 0.1489 loss_mask: 0.2177 2022/11/01 15:54:40 - mmengine - INFO - Epoch(train) [147][90/125] lr: 2.0000e-04 eta: 0:15:29 time: 0.4843 data_time: 0.0532 memory: 10913 loss: 0.4815 loss_rpn_cls: 0.0091 loss_rpn_bbox: 0.0110 loss_cls: 0.0983 acc: 96.6553 loss_bbox: 0.1502 loss_mask: 0.2130 2022/11/01 15:54:43 - mmengine - INFO - Epoch(train) [147][95/125] lr: 2.0000e-04 eta: 0:15:29 time: 0.5473 data_time: 0.1416 memory: 10119 loss: 0.4489 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0110 loss_cls: 0.0890 acc: 96.7773 loss_bbox: 0.1444 loss_mask: 0.1956 2022/11/01 15:54:44 - mmengine - INFO - Epoch(train) [147][100/125] lr: 2.0000e-04 eta: 0:15:21 time: 0.4579 data_time: 0.1251 memory: 9501 loss: 0.4089 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0077 loss_cls: 0.0785 acc: 95.9229 loss_bbox: 0.1241 loss_mask: 0.1922 2022/11/01 15:54:47 - mmengine - INFO - Epoch(train) [147][105/125] lr: 2.0000e-04 eta: 0:15:21 time: 0.3887 data_time: 0.0364 memory: 10622 loss: 0.4192 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0081 loss_cls: 0.0823 acc: 98.0469 loss_bbox: 0.1208 loss_mask: 0.2003 2022/11/01 15:54:49 - mmengine - INFO - Epoch(train) [147][110/125] lr: 2.0000e-04 eta: 0:15:13 time: 0.4111 data_time: 0.0540 memory: 9559 loss: 0.4172 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0101 loss_cls: 0.0785 acc: 97.6807 loss_bbox: 0.1213 loss_mask: 0.2001 2022/11/01 15:54:51 - mmengine - INFO - Epoch(train) [147][115/125] lr: 2.0000e-04 eta: 0:15:13 time: 0.4278 data_time: 0.0864 memory: 9821 loss: 0.4478 loss_rpn_cls: 0.0098 loss_rpn_bbox: 0.0133 loss_cls: 0.0843 acc: 95.1904 loss_bbox: 0.1302 loss_mask: 0.2102 2022/11/01 15:54:53 - mmengine - INFO - Epoch(train) [147][120/125] lr: 2.0000e-04 eta: 0:15:04 time: 0.4091 data_time: 0.0755 memory: 9260 loss: 0.4542 loss_rpn_cls: 0.0100 loss_rpn_bbox: 0.0142 loss_cls: 0.0861 acc: 97.1680 loss_bbox: 0.1269 loss_mask: 0.2170 2022/11/01 15:54:55 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:54:55 - mmengine - INFO - Epoch(train) [147][125/125] lr: 2.0000e-04 eta: 0:15:04 time: 0.3839 data_time: 0.0410 memory: 10408 loss: 0.4355 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0125 loss_cls: 0.0819 acc: 97.5830 loss_bbox: 0.1228 loss_mask: 0.2113 2022/11/01 15:54:59 - mmengine - INFO - Epoch(train) [148][5/125] lr: 2.0000e-04 eta: 0:15:04 time: 0.6824 data_time: 0.2826 memory: 10262 loss: 0.4785 loss_rpn_cls: 0.0085 loss_rpn_bbox: 0.0131 loss_cls: 0.0964 acc: 96.9238 loss_bbox: 0.1418 loss_mask: 0.2187 2022/11/01 15:55:02 - mmengine - INFO - Epoch(train) [148][10/125] lr: 2.0000e-04 eta: 0:14:54 time: 0.7346 data_time: 0.3372 memory: 10423 loss: 0.4442 loss_rpn_cls: 0.0113 loss_rpn_bbox: 0.0119 loss_cls: 0.0881 acc: 96.0205 loss_bbox: 0.1227 loss_mask: 0.2103 2022/11/01 15:55:04 - mmengine - INFO - Epoch(train) [148][15/125] lr: 2.0000e-04 eta: 0:14:54 time: 0.4587 data_time: 0.0906 memory: 10654 loss: 0.4305 loss_rpn_cls: 0.0111 loss_rpn_bbox: 0.0106 loss_cls: 0.0852 acc: 96.9238 loss_bbox: 0.1254 loss_mask: 0.1982 2022/11/01 15:55:06 - mmengine - INFO - Epoch(train) [148][20/125] lr: 2.0000e-04 eta: 0:14:46 time: 0.4075 data_time: 0.0429 memory: 10478 loss: 0.4817 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0110 loss_cls: 0.0998 acc: 95.7275 loss_bbox: 0.1484 loss_mask: 0.2129 2022/11/01 15:55:08 - mmengine - INFO - Epoch(train) [148][25/125] lr: 2.0000e-04 eta: 0:14:46 time: 0.4234 data_time: 0.0780 memory: 9644 loss: 0.4581 loss_rpn_cls: 0.0098 loss_rpn_bbox: 0.0109 loss_cls: 0.0918 acc: 97.9736 loss_bbox: 0.1350 loss_mask: 0.2106 2022/11/01 15:55:11 - mmengine - INFO - Epoch(train) [148][30/125] lr: 2.0000e-04 eta: 0:14:39 time: 0.4414 data_time: 0.0892 memory: 10887 loss: 0.4257 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0099 loss_cls: 0.0822 acc: 96.7529 loss_bbox: 0.1295 loss_mask: 0.1958 2022/11/01 15:55:13 - mmengine - INFO - Epoch(train) [148][35/125] lr: 2.0000e-04 eta: 0:14:39 time: 0.4397 data_time: 0.0818 memory: 9665 loss: 0.4280 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0096 loss_cls: 0.0825 acc: 97.7295 loss_bbox: 0.1324 loss_mask: 0.1976 2022/11/01 15:55:15 - mmengine - INFO - Epoch(train) [148][40/125] lr: 2.0000e-04 eta: 0:14:31 time: 0.4311 data_time: 0.0910 memory: 9569 loss: 0.4049 loss_rpn_cls: 0.0054 loss_rpn_bbox: 0.0084 loss_cls: 0.0776 acc: 98.3887 loss_bbox: 0.1236 loss_mask: 0.1898 2022/11/01 15:55:18 - mmengine - INFO - Epoch(train) [148][45/125] lr: 2.0000e-04 eta: 0:14:31 time: 0.5030 data_time: 0.0948 memory: 11168 loss: 0.4356 loss_rpn_cls: 0.0078 loss_rpn_bbox: 0.0113 loss_cls: 0.0888 acc: 96.2646 loss_bbox: 0.1384 loss_mask: 0.1893 2022/11/01 15:55:20 - mmengine - INFO - Epoch(train) [148][50/125] lr: 2.0000e-04 eta: 0:14:25 time: 0.4915 data_time: 0.0773 memory: 9430 loss: 0.4342 loss_rpn_cls: 0.0075 loss_rpn_bbox: 0.0124 loss_cls: 0.0854 acc: 98.3887 loss_bbox: 0.1372 loss_mask: 0.1917 2022/11/01 15:55:22 - mmengine - INFO - Epoch(train) [148][55/125] lr: 2.0000e-04 eta: 0:14:25 time: 0.4472 data_time: 0.0653 memory: 10488 loss: 0.3802 loss_rpn_cls: 0.0048 loss_rpn_bbox: 0.0100 loss_cls: 0.0688 acc: 96.9482 loss_bbox: 0.1187 loss_mask: 0.1779 2022/11/01 15:55:24 - mmengine - INFO - Epoch(train) [148][60/125] lr: 2.0000e-04 eta: 0:14:18 time: 0.4555 data_time: 0.0737 memory: 10354 loss: 0.4111 loss_rpn_cls: 0.0052 loss_rpn_bbox: 0.0098 loss_cls: 0.0812 acc: 96.8262 loss_bbox: 0.1392 loss_mask: 0.1758 2022/11/01 15:55:27 - mmengine - INFO - Epoch(train) [148][65/125] lr: 2.0000e-04 eta: 0:14:18 time: 0.4393 data_time: 0.0819 memory: 10116 loss: 0.4341 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0106 loss_cls: 0.0868 acc: 96.1426 loss_bbox: 0.1417 loss_mask: 0.1876 2022/11/01 15:55:28 - mmengine - INFO - Epoch(train) [148][70/125] lr: 2.0000e-04 eta: 0:14:10 time: 0.4103 data_time: 0.0680 memory: 9546 loss: 0.4311 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0115 loss_cls: 0.0853 acc: 96.1670 loss_bbox: 0.1311 loss_mask: 0.1952 2022/11/01 15:55:30 - mmengine - INFO - Epoch(train) [148][75/125] lr: 2.0000e-04 eta: 0:14:10 time: 0.3730 data_time: 0.0476 memory: 9648 loss: 0.4168 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0089 loss_cls: 0.0804 acc: 97.5342 loss_bbox: 0.1222 loss_mask: 0.1969 2022/11/01 15:55:32 - mmengine - INFO - Epoch(train) [148][80/125] lr: 2.0000e-04 eta: 0:14:02 time: 0.3986 data_time: 0.0628 memory: 10210 loss: 0.4227 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0087 loss_cls: 0.0804 acc: 96.8506 loss_bbox: 0.1249 loss_mask: 0.2003 2022/11/01 15:55:35 - mmengine - INFO - Epoch(train) [148][85/125] lr: 2.0000e-04 eta: 0:14:02 time: 0.4393 data_time: 0.0886 memory: 9648 loss: 0.4528 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0115 loss_cls: 0.0891 acc: 96.6553 loss_bbox: 0.1380 loss_mask: 0.2049 2022/11/01 15:55:37 - mmengine - INFO - Epoch(train) [148][90/125] lr: 2.0000e-04 eta: 0:13:55 time: 0.4292 data_time: 0.0711 memory: 9220 loss: 0.4151 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0100 loss_cls: 0.0761 acc: 98.2666 loss_bbox: 0.1123 loss_mask: 0.2087 2022/11/01 15:55:39 - mmengine - INFO - Epoch(train) [148][95/125] lr: 2.0000e-04 eta: 0:13:55 time: 0.3842 data_time: 0.0424 memory: 9580 loss: 0.4034 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0074 loss_cls: 0.0756 acc: 97.0947 loss_bbox: 0.1081 loss_mask: 0.2055 2022/11/01 15:55:40 - mmengine - INFO - Epoch(train) [148][100/125] lr: 2.0000e-04 eta: 0:13:46 time: 0.3621 data_time: 0.0455 memory: 9358 loss: 0.4544 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0099 loss_cls: 0.0897 acc: 97.7051 loss_bbox: 0.1315 loss_mask: 0.2162 2022/11/01 15:55:42 - mmengine - INFO - Epoch(train) [148][105/125] lr: 2.0000e-04 eta: 0:13:46 time: 0.3582 data_time: 0.0449 memory: 9553 loss: 0.4404 loss_rpn_cls: 0.0058 loss_rpn_bbox: 0.0106 loss_cls: 0.0834 acc: 97.1924 loss_bbox: 0.1258 loss_mask: 0.2147 2022/11/01 15:55:44 - mmengine - INFO - Epoch(train) [148][110/125] lr: 2.0000e-04 eta: 0:13:38 time: 0.3653 data_time: 0.0521 memory: 9335 loss: 0.4034 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0078 loss_cls: 0.0761 acc: 97.7783 loss_bbox: 0.1143 loss_mask: 0.1986 2022/11/01 15:55:46 - mmengine - INFO - Epoch(train) [148][115/125] lr: 2.0000e-04 eta: 0:13:38 time: 0.3804 data_time: 0.0654 memory: 9496 loss: 0.3982 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0089 loss_cls: 0.0755 acc: 96.6064 loss_bbox: 0.1116 loss_mask: 0.1939 2022/11/01 15:55:48 - mmengine - INFO - Epoch(train) [148][120/125] lr: 2.0000e-04 eta: 0:13:31 time: 0.4046 data_time: 0.0804 memory: 9822 loss: 0.3994 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0120 loss_cls: 0.0773 acc: 95.8740 loss_bbox: 0.1190 loss_mask: 0.1829 2022/11/01 15:55:50 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:55:50 - mmengine - INFO - Epoch(train) [148][125/125] lr: 2.0000e-04 eta: 0:13:31 time: 0.3915 data_time: 0.0544 memory: 10340 loss: 0.4567 loss_rpn_cls: 0.0108 loss_rpn_bbox: 0.0138 loss_cls: 0.0895 acc: 94.6533 loss_bbox: 0.1400 loss_mask: 0.2026 2022/11/01 15:55:54 - mmengine - INFO - Epoch(train) [149][5/125] lr: 2.0000e-04 eta: 0:13:31 time: 0.5701 data_time: 0.2235 memory: 9674 loss: 0.4712 loss_rpn_cls: 0.0098 loss_rpn_bbox: 0.0120 loss_cls: 0.0902 acc: 96.0205 loss_bbox: 0.1411 loss_mask: 0.2180 2022/11/01 15:55:56 - mmengine - INFO - Epoch(train) [149][10/125] lr: 2.0000e-04 eta: 0:13:20 time: 0.6233 data_time: 0.2390 memory: 10626 loss: 0.4309 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0087 loss_cls: 0.0853 acc: 96.6064 loss_bbox: 0.1312 loss_mask: 0.1978 2022/11/01 15:55:58 - mmengine - INFO - Epoch(train) [149][15/125] lr: 2.0000e-04 eta: 0:13:20 time: 0.4326 data_time: 0.0602 memory: 9775 loss: 0.4531 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0132 loss_cls: 0.0939 acc: 96.8994 loss_bbox: 0.1408 loss_mask: 0.1954 2022/11/01 15:56:00 - mmengine - INFO - Epoch(train) [149][20/125] lr: 2.0000e-04 eta: 0:13:13 time: 0.4196 data_time: 0.0519 memory: 11126 loss: 0.4695 loss_rpn_cls: 0.0075 loss_rpn_bbox: 0.0147 loss_cls: 0.0954 acc: 97.5098 loss_bbox: 0.1551 loss_mask: 0.1967 2022/11/01 15:56:02 - mmengine - INFO - Epoch(train) [149][25/125] lr: 2.0000e-04 eta: 0:13:13 time: 0.4162 data_time: 0.0481 memory: 9492 loss: 0.4159 loss_rpn_cls: 0.0057 loss_rpn_bbox: 0.0102 loss_cls: 0.0833 acc: 98.0957 loss_bbox: 0.1314 loss_mask: 0.1851 2022/11/01 15:56:04 - mmengine - INFO - Epoch(train) [149][30/125] lr: 2.0000e-04 eta: 0:13:05 time: 0.3935 data_time: 0.0688 memory: 9812 loss: 0.4326 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0112 loss_cls: 0.0831 acc: 97.0459 loss_bbox: 0.1240 loss_mask: 0.2049 2022/11/01 15:56:06 - mmengine - INFO - Epoch(train) [149][35/125] lr: 2.0000e-04 eta: 0:13:05 time: 0.4141 data_time: 0.0811 memory: 9540 loss: 0.4733 loss_rpn_cls: 0.0109 loss_rpn_bbox: 0.0136 loss_cls: 0.0885 acc: 96.8994 loss_bbox: 0.1372 loss_mask: 0.2231 2022/11/01 15:56:08 - mmengine - INFO - Epoch(train) [149][40/125] lr: 2.0000e-04 eta: 0:12:58 time: 0.3994 data_time: 0.0721 memory: 9433 loss: 0.4270 loss_rpn_cls: 0.0075 loss_rpn_bbox: 0.0128 loss_cls: 0.0799 acc: 96.6064 loss_bbox: 0.1199 loss_mask: 0.2068 2022/11/01 15:56:10 - mmengine - INFO - Epoch(train) [149][45/125] lr: 2.0000e-04 eta: 0:12:58 time: 0.3954 data_time: 0.0624 memory: 9927 loss: 0.4412 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0113 loss_cls: 0.0887 acc: 94.8975 loss_bbox: 0.1287 loss_mask: 0.2041 2022/11/01 15:56:12 - mmengine - INFO - Epoch(train) [149][50/125] lr: 2.0000e-04 eta: 0:12:51 time: 0.4168 data_time: 0.0552 memory: 9733 loss: 0.4864 loss_rpn_cls: 0.0099 loss_rpn_bbox: 0.0122 loss_cls: 0.1020 acc: 95.8008 loss_bbox: 0.1504 loss_mask: 0.2119 2022/11/01 15:56:15 - mmengine - INFO - Epoch(train) [149][55/125] lr: 2.0000e-04 eta: 0:12:51 time: 0.4244 data_time: 0.0536 memory: 9657 loss: 0.4292 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0114 loss_cls: 0.0840 acc: 97.9004 loss_bbox: 0.1299 loss_mask: 0.1962 2022/11/01 15:56:17 - mmengine - INFO - Epoch(train) [149][60/125] lr: 2.0000e-04 eta: 0:12:45 time: 0.4438 data_time: 0.0951 memory: 9289 loss: 0.3760 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0078 loss_cls: 0.0701 acc: 98.0713 loss_bbox: 0.1039 loss_mask: 0.1869 2022/11/01 15:56:19 - mmengine - INFO - Epoch(train) [149][65/125] lr: 2.0000e-04 eta: 0:12:45 time: 0.4147 data_time: 0.0920 memory: 9525 loss: 0.4413 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0074 loss_cls: 0.0919 acc: 96.3623 loss_bbox: 0.1275 loss_mask: 0.2056 2022/11/01 15:56:21 - mmengine - INFO - Epoch(train) [149][70/125] lr: 2.0000e-04 eta: 0:12:38 time: 0.3895 data_time: 0.0708 memory: 9897 loss: 0.4673 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0107 loss_cls: 0.0946 acc: 97.8027 loss_bbox: 0.1431 loss_mask: 0.2102 2022/11/01 15:56:23 - mmengine - INFO - Epoch(train) [149][75/125] lr: 2.0000e-04 eta: 0:12:38 time: 0.3927 data_time: 0.0728 memory: 9782 loss: 0.4356 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0115 loss_cls: 0.0810 acc: 97.6562 loss_bbox: 0.1321 loss_mask: 0.2039 2022/11/01 15:56:25 - mmengine - INFO - Epoch(train) [149][80/125] lr: 2.0000e-04 eta: 0:12:30 time: 0.3793 data_time: 0.0680 memory: 9446 loss: 0.3835 loss_rpn_cls: 0.0052 loss_rpn_bbox: 0.0084 loss_cls: 0.0708 acc: 96.4355 loss_bbox: 0.1099 loss_mask: 0.1892 2022/11/01 15:56:27 - mmengine - INFO - Epoch(train) [149][85/125] lr: 2.0000e-04 eta: 0:12:30 time: 0.3889 data_time: 0.0786 memory: 9687 loss: 0.3767 loss_rpn_cls: 0.0053 loss_rpn_bbox: 0.0079 loss_cls: 0.0690 acc: 96.5576 loss_bbox: 0.1101 loss_mask: 0.1845 2022/11/01 15:56:28 - mmengine - INFO - Epoch(train) [149][90/125] lr: 2.0000e-04 eta: 0:12:23 time: 0.3940 data_time: 0.0548 memory: 10358 loss: 0.4161 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0094 loss_cls: 0.0779 acc: 97.2412 loss_bbox: 0.1299 loss_mask: 0.1921 2022/11/01 15:56:30 - mmengine - INFO - Epoch(train) [149][95/125] lr: 2.0000e-04 eta: 0:12:23 time: 0.3909 data_time: 0.0335 memory: 9632 loss: 0.4048 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0098 loss_cls: 0.0796 acc: 97.4365 loss_bbox: 0.1279 loss_mask: 0.1809 2022/11/01 15:56:33 - mmengine - INFO - Epoch(train) [149][100/125] lr: 2.0000e-04 eta: 0:12:16 time: 0.4097 data_time: 0.0513 memory: 9779 loss: 0.4316 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0094 loss_cls: 0.0901 acc: 96.1914 loss_bbox: 0.1408 loss_mask: 0.1842 2022/11/01 15:56:34 - mmengine - INFO - Epoch(train) [149][105/125] lr: 2.0000e-04 eta: 0:12:16 time: 0.3846 data_time: 0.0456 memory: 9260 loss: 0.4309 loss_rpn_cls: 0.0063 loss_rpn_bbox: 0.0091 loss_cls: 0.0837 acc: 97.5586 loss_bbox: 0.1324 loss_mask: 0.1994 2022/11/01 15:56:36 - mmengine - INFO - Epoch(train) [149][110/125] lr: 2.0000e-04 eta: 0:12:09 time: 0.3647 data_time: 0.0437 memory: 9638 loss: 0.4152 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0104 loss_cls: 0.0773 acc: 97.2412 loss_bbox: 0.1167 loss_mask: 0.2041 2022/11/01 15:56:38 - mmengine - INFO - Epoch(train) [149][115/125] lr: 2.0000e-04 eta: 0:12:09 time: 0.3879 data_time: 0.0483 memory: 9595 loss: 0.4248 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0110 loss_cls: 0.0843 acc: 97.8516 loss_bbox: 0.1215 loss_mask: 0.1991 2022/11/01 15:56:40 - mmengine - INFO - Epoch(train) [149][120/125] lr: 2.0000e-04 eta: 0:12:02 time: 0.4017 data_time: 0.0584 memory: 9897 loss: 0.4365 loss_rpn_cls: 0.0094 loss_rpn_bbox: 0.0123 loss_cls: 0.0891 acc: 95.4346 loss_bbox: 0.1295 loss_mask: 0.1961 2022/11/01 15:56:42 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:56:42 - mmengine - INFO - Epoch(train) [149][125/125] lr: 2.0000e-04 eta: 0:12:02 time: 0.3760 data_time: 0.0511 memory: 9582 loss: 0.4274 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0100 loss_cls: 0.0823 acc: 97.0947 loss_bbox: 0.1210 loss_mask: 0.2068 2022/11/01 15:56:45 - mmengine - INFO - Epoch(train) [150][5/125] lr: 2.0000e-04 eta: 0:12:02 time: 0.4927 data_time: 0.1682 memory: 9501 loss: 0.4102 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0076 loss_cls: 0.0736 acc: 97.1924 loss_bbox: 0.1110 loss_mask: 0.2094 2022/11/01 15:56:47 - mmengine - INFO - Epoch(train) [150][10/125] lr: 2.0000e-04 eta: 0:11:51 time: 0.5196 data_time: 0.1920 memory: 9433 loss: 0.4096 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0095 loss_cls: 0.0761 acc: 97.9248 loss_bbox: 0.1144 loss_mask: 0.1998 2022/11/01 15:56:49 - mmengine - INFO - Epoch(train) [150][15/125] lr: 2.0000e-04 eta: 0:11:51 time: 0.3714 data_time: 0.0469 memory: 9580 loss: 0.4145 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0090 loss_cls: 0.0794 acc: 96.5576 loss_bbox: 0.1185 loss_mask: 0.1996 2022/11/01 15:56:51 - mmengine - INFO - Epoch(train) [150][20/125] lr: 2.0000e-04 eta: 0:11:45 time: 0.4205 data_time: 0.0658 memory: 9449 loss: 0.4415 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0106 loss_cls: 0.0820 acc: 97.2168 loss_bbox: 0.1244 loss_mask: 0.2157 2022/11/01 15:56:54 - mmengine - INFO - Epoch(train) [150][25/125] lr: 2.0000e-04 eta: 0:11:45 time: 0.4731 data_time: 0.1263 memory: 9420 loss: 0.4342 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0111 loss_cls: 0.0799 acc: 96.4111 loss_bbox: 0.1180 loss_mask: 0.2176 2022/11/01 15:56:56 - mmengine - INFO - Epoch(train) [150][30/125] lr: 2.0000e-04 eta: 0:11:39 time: 0.4278 data_time: 0.1047 memory: 9498 loss: 0.4192 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0088 loss_cls: 0.0781 acc: 97.4854 loss_bbox: 0.1179 loss_mask: 0.2085 2022/11/01 15:56:58 - mmengine - INFO - Epoch(train) [150][35/125] lr: 2.0000e-04 eta: 0:11:39 time: 0.4229 data_time: 0.0774 memory: 9690 loss: 0.4029 loss_rpn_cls: 0.0051 loss_rpn_bbox: 0.0091 loss_cls: 0.0749 acc: 95.9229 loss_bbox: 0.1168 loss_mask: 0.1970 2022/11/01 15:57:00 - mmengine - INFO - Epoch(train) [150][40/125] lr: 2.0000e-04 eta: 0:11:33 time: 0.4542 data_time: 0.0826 memory: 11089 loss: 0.4301 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0099 loss_cls: 0.0808 acc: 93.5303 loss_bbox: 0.1310 loss_mask: 0.2002 2022/11/01 15:57:02 - mmengine - INFO - Epoch(train) [150][45/125] lr: 2.0000e-04 eta: 0:11:33 time: 0.4588 data_time: 0.0887 memory: 9776 loss: 0.4752 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0112 loss_cls: 0.0936 acc: 95.7764 loss_bbox: 0.1546 loss_mask: 0.2066 2022/11/01 15:57:04 - mmengine - INFO - Epoch(train) [150][50/125] lr: 2.0000e-04 eta: 0:11:26 time: 0.4202 data_time: 0.0729 memory: 9469 loss: 0.4592 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0117 loss_cls: 0.0960 acc: 96.6064 loss_bbox: 0.1497 loss_mask: 0.1946 2022/11/01 15:57:06 - mmengine - INFO - Epoch(train) [150][55/125] lr: 2.0000e-04 eta: 0:11:26 time: 0.4047 data_time: 0.0584 memory: 9387 loss: 0.4210 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0089 loss_cls: 0.0811 acc: 96.6064 loss_bbox: 0.1247 loss_mask: 0.1992 2022/11/01 15:57:09 - mmengine - INFO - Epoch(train) [150][60/125] lr: 2.0000e-04 eta: 0:11:21 time: 0.4689 data_time: 0.0964 memory: 9736 loss: 0.3961 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0089 loss_cls: 0.0692 acc: 98.6572 loss_bbox: 0.1090 loss_mask: 0.2018 2022/11/01 15:57:11 - mmengine - INFO - Epoch(train) [150][65/125] lr: 2.0000e-04 eta: 0:11:21 time: 0.4609 data_time: 0.0855 memory: 10586 loss: 0.4124 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0098 loss_cls: 0.0824 acc: 95.6055 loss_bbox: 0.1216 loss_mask: 0.1910 2022/11/01 15:57:13 - mmengine - INFO - Epoch(train) [150][70/125] lr: 2.0000e-04 eta: 0:11:14 time: 0.4218 data_time: 0.0763 memory: 9870 loss: 0.4179 loss_rpn_cls: 0.0065 loss_rpn_bbox: 0.0086 loss_cls: 0.0859 acc: 96.4600 loss_bbox: 0.1284 loss_mask: 0.1886 2022/11/01 15:57:15 - mmengine - INFO - Epoch(train) [150][75/125] lr: 2.0000e-04 eta: 0:11:14 time: 0.4133 data_time: 0.0704 memory: 9606 loss: 0.3967 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0082 loss_cls: 0.0744 acc: 96.8018 loss_bbox: 0.1219 loss_mask: 0.1862 2022/11/01 15:57:17 - mmengine - INFO - Epoch(train) [150][80/125] lr: 2.0000e-04 eta: 0:11:08 time: 0.3940 data_time: 0.0480 memory: 9411 loss: 0.4029 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0083 loss_cls: 0.0761 acc: 96.0693 loss_bbox: 0.1235 loss_mask: 0.1869 2022/11/01 15:57:19 - mmengine - INFO - Epoch(train) [150][85/125] lr: 2.0000e-04 eta: 0:11:08 time: 0.4167 data_time: 0.0703 memory: 9426 loss: 0.4193 loss_rpn_cls: 0.0105 loss_rpn_bbox: 0.0094 loss_cls: 0.0787 acc: 97.9248 loss_bbox: 0.1262 loss_mask: 0.1944 2022/11/01 15:57:21 - mmengine - INFO - Epoch(train) [150][90/125] lr: 2.0000e-04 eta: 0:11:02 time: 0.4244 data_time: 0.0772 memory: 9436 loss: 0.4184 loss_rpn_cls: 0.0118 loss_rpn_bbox: 0.0104 loss_cls: 0.0798 acc: 95.7764 loss_bbox: 0.1280 loss_mask: 0.1884 2022/11/01 15:57:24 - mmengine - INFO - Epoch(train) [150][95/125] lr: 2.0000e-04 eta: 0:11:02 time: 0.4165 data_time: 0.0802 memory: 9514 loss: 0.4131 loss_rpn_cls: 0.0119 loss_rpn_bbox: 0.0102 loss_cls: 0.0825 acc: 96.5332 loss_bbox: 0.1228 loss_mask: 0.1855 2022/11/01 15:57:26 - mmengine - INFO - Epoch(train) [150][100/125] lr: 2.0000e-04 eta: 0:10:56 time: 0.4150 data_time: 0.0549 memory: 10682 loss: 0.4259 loss_rpn_cls: 0.0112 loss_rpn_bbox: 0.0115 loss_cls: 0.0879 acc: 96.6309 loss_bbox: 0.1261 loss_mask: 0.1891 2022/11/01 15:57:28 - mmengine - INFO - Epoch(train) [150][105/125] lr: 2.0000e-04 eta: 0:10:56 time: 0.3969 data_time: 0.0415 memory: 9502 loss: 0.4297 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0104 loss_cls: 0.0884 acc: 95.5322 loss_bbox: 0.1267 loss_mask: 0.1957 2022/11/01 15:57:31 - mmengine - INFO - Epoch(train) [150][110/125] lr: 2.0000e-04 eta: 0:10:51 time: 0.5476 data_time: 0.2076 memory: 9589 loss: 0.4064 loss_rpn_cls: 0.0052 loss_rpn_bbox: 0.0069 loss_cls: 0.0807 acc: 96.3867 loss_bbox: 0.1188 loss_mask: 0.1948 2022/11/01 15:57:33 - mmengine - INFO - Epoch(train) [150][115/125] lr: 2.0000e-04 eta: 0:10:51 time: 0.5877 data_time: 0.2118 memory: 9417 loss: 0.4209 loss_rpn_cls: 0.0147 loss_rpn_bbox: 0.0103 loss_cls: 0.0809 acc: 96.8994 loss_bbox: 0.1216 loss_mask: 0.1935 2022/11/01 15:57:36 - mmengine - INFO - Epoch(train) [150][120/125] lr: 2.0000e-04 eta: 0:10:45 time: 0.4737 data_time: 0.1141 memory: 9348 loss: 0.4282 loss_rpn_cls: 0.0185 loss_rpn_bbox: 0.0117 loss_cls: 0.0826 acc: 97.3877 loss_bbox: 0.1147 loss_mask: 0.2007 2022/11/01 15:57:38 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:57:38 - mmengine - INFO - Epoch(train) [150][125/125] lr: 2.0000e-04 eta: 0:10:45 time: 0.4198 data_time: 0.0884 memory: 9642 loss: 0.4230 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0098 loss_cls: 0.0860 acc: 95.8252 loss_bbox: 0.1168 loss_mask: 0.2007 2022/11/01 15:57:41 - mmengine - INFO - Epoch(train) [151][5/125] lr: 2.0000e-04 eta: 0:10:45 time: 0.4996 data_time: 0.1648 memory: 9782 loss: 0.4295 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0111 loss_cls: 0.0865 acc: 95.9717 loss_bbox: 0.1249 loss_mask: 0.1998 2022/11/01 15:57:44 - mmengine - INFO - Epoch(train) [151][10/125] lr: 2.0000e-04 eta: 0:10:36 time: 0.6390 data_time: 0.2946 memory: 9521 loss: 0.4300 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0115 loss_cls: 0.0837 acc: 96.1426 loss_bbox: 0.1218 loss_mask: 0.2056 2022/11/01 15:57:46 - mmengine - INFO - Epoch(train) [151][15/125] lr: 2.0000e-04 eta: 0:10:36 time: 0.5073 data_time: 0.1580 memory: 9469 loss: 0.4584 loss_rpn_cls: 0.0102 loss_rpn_bbox: 0.0117 loss_cls: 0.0911 acc: 97.0703 loss_bbox: 0.1278 loss_mask: 0.2176 2022/11/01 15:57:49 - mmengine - INFO - Epoch(train) [151][20/125] lr: 2.0000e-04 eta: 0:10:31 time: 0.4769 data_time: 0.0759 memory: 9878 loss: 0.4267 loss_rpn_cls: 0.0101 loss_rpn_bbox: 0.0102 loss_cls: 0.0844 acc: 97.2168 loss_bbox: 0.1154 loss_mask: 0.2066 2022/11/01 15:57:51 - mmengine - INFO - Epoch(train) [151][25/125] lr: 2.0000e-04 eta: 0:10:31 time: 0.5025 data_time: 0.1000 memory: 9804 loss: 0.4299 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0098 loss_cls: 0.0841 acc: 95.7031 loss_bbox: 0.1216 loss_mask: 0.2058 2022/11/01 15:57:53 - mmengine - INFO - Epoch(train) [151][30/125] lr: 2.0000e-04 eta: 0:10:25 time: 0.4151 data_time: 0.0712 memory: 9642 loss: 0.4644 loss_rpn_cls: 0.0123 loss_rpn_bbox: 0.0112 loss_cls: 0.0872 acc: 95.6787 loss_bbox: 0.1331 loss_mask: 0.2208 2022/11/01 15:57:55 - mmengine - INFO - Epoch(train) [151][35/125] lr: 2.0000e-04 eta: 0:10:25 time: 0.4270 data_time: 0.0794 memory: 9745 loss: 0.4374 loss_rpn_cls: 0.0114 loss_rpn_bbox: 0.0100 loss_cls: 0.0820 acc: 96.9971 loss_bbox: 0.1240 loss_mask: 0.2100 2022/11/01 15:57:57 - mmengine - INFO - Epoch(train) [151][40/125] lr: 2.0000e-04 eta: 0:10:19 time: 0.4532 data_time: 0.1005 memory: 9681 loss: 0.4292 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0088 loss_cls: 0.0871 acc: 95.7275 loss_bbox: 0.1267 loss_mask: 0.1984 2022/11/01 15:57:59 - mmengine - INFO - Epoch(train) [151][45/125] lr: 2.0000e-04 eta: 0:10:19 time: 0.4116 data_time: 0.0773 memory: 9486 loss: 0.4420 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0086 loss_cls: 0.0888 acc: 96.4844 loss_bbox: 0.1324 loss_mask: 0.2032 2022/11/01 15:58:01 - mmengine - INFO - Epoch(train) [151][50/125] lr: 2.0000e-04 eta: 0:10:12 time: 0.3657 data_time: 0.0495 memory: 9433 loss: 0.4250 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0077 loss_cls: 0.0842 acc: 95.9961 loss_bbox: 0.1258 loss_mask: 0.1980 2022/11/01 15:58:03 - mmengine - INFO - Epoch(train) [151][55/125] lr: 2.0000e-04 eta: 0:10:12 time: 0.3912 data_time: 0.0677 memory: 9628 loss: 0.4097 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0096 loss_cls: 0.0815 acc: 96.1182 loss_bbox: 0.1239 loss_mask: 0.1866 2022/11/01 15:58:05 - mmengine - INFO - Epoch(train) [151][60/125] lr: 2.0000e-04 eta: 0:10:06 time: 0.4060 data_time: 0.0817 memory: 9628 loss: 0.4132 loss_rpn_cls: 0.0052 loss_rpn_bbox: 0.0098 loss_cls: 0.0765 acc: 96.9482 loss_bbox: 0.1262 loss_mask: 0.1955 2022/11/01 15:58:07 - mmengine - INFO - Epoch(train) [151][65/125] lr: 2.0000e-04 eta: 0:10:06 time: 0.3951 data_time: 0.0578 memory: 10170 loss: 0.4120 loss_rpn_cls: 0.0055 loss_rpn_bbox: 0.0091 loss_cls: 0.0787 acc: 97.8516 loss_bbox: 0.1220 loss_mask: 0.1967 2022/11/01 15:58:09 - mmengine - INFO - Epoch(train) [151][70/125] lr: 2.0000e-04 eta: 0:10:00 time: 0.4069 data_time: 0.0617 memory: 9759 loss: 0.4103 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0098 loss_cls: 0.0835 acc: 96.1670 loss_bbox: 0.1267 loss_mask: 0.1842 2022/11/01 15:58:11 - mmengine - INFO - Epoch(train) [151][75/125] lr: 2.0000e-04 eta: 0:10:00 time: 0.3909 data_time: 0.0603 memory: 9837 loss: 0.4188 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0119 loss_cls: 0.0838 acc: 96.6797 loss_bbox: 0.1280 loss_mask: 0.1882 2022/11/01 15:58:13 - mmengine - INFO - Epoch(train) [151][80/125] lr: 2.0000e-04 eta: 0:09:54 time: 0.3719 data_time: 0.0391 memory: 9700 loss: 0.4136 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0109 loss_cls: 0.0812 acc: 98.6816 loss_bbox: 0.1205 loss_mask: 0.1929 2022/11/01 15:58:17 - mmengine - INFO - Epoch(train) [151][85/125] lr: 2.0000e-04 eta: 0:09:54 time: 0.5582 data_time: 0.2105 memory: 9743 loss: 0.4167 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0088 loss_cls: 0.0784 acc: 96.0938 loss_bbox: 0.1211 loss_mask: 0.2014 2022/11/01 15:58:19 - mmengine - INFO - Epoch(train) [151][90/125] lr: 2.0000e-04 eta: 0:09:50 time: 0.5797 data_time: 0.2321 memory: 9746 loss: 0.4269 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0118 loss_cls: 0.0798 acc: 95.8252 loss_bbox: 0.1317 loss_mask: 0.1959 2022/11/01 15:58:21 - mmengine - INFO - Epoch(train) [151][95/125] lr: 2.0000e-04 eta: 0:09:50 time: 0.3927 data_time: 0.0546 memory: 9615 loss: 0.4071 loss_rpn_cls: 0.0095 loss_rpn_bbox: 0.0107 loss_cls: 0.0745 acc: 97.6562 loss_bbox: 0.1183 loss_mask: 0.1940 2022/11/01 15:58:23 - mmengine - INFO - Epoch(train) [151][100/125] lr: 2.0000e-04 eta: 0:09:44 time: 0.3882 data_time: 0.0410 memory: 10451 loss: 0.4156 loss_rpn_cls: 0.0090 loss_rpn_bbox: 0.0112 loss_cls: 0.0752 acc: 97.9492 loss_bbox: 0.1199 loss_mask: 0.2002 2022/11/01 15:58:25 - mmengine - INFO - Epoch(train) [151][105/125] lr: 2.0000e-04 eta: 0:09:44 time: 0.4499 data_time: 0.1039 memory: 9184 loss: 0.4173 loss_rpn_cls: 0.0078 loss_rpn_bbox: 0.0109 loss_cls: 0.0783 acc: 96.7041 loss_bbox: 0.1255 loss_mask: 0.1949 2022/11/01 15:58:28 - mmengine - INFO - Epoch(train) [151][110/125] lr: 2.0000e-04 eta: 0:09:38 time: 0.4934 data_time: 0.1190 memory: 9955 loss: 0.4306 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0130 loss_cls: 0.0838 acc: 96.2158 loss_bbox: 0.1322 loss_mask: 0.1945 2022/11/01 15:58:29 - mmengine - INFO - Epoch(train) [151][115/125] lr: 2.0000e-04 eta: 0:09:38 time: 0.4339 data_time: 0.0580 memory: 9467 loss: 0.4142 loss_rpn_cls: 0.0062 loss_rpn_bbox: 0.0119 loss_cls: 0.0784 acc: 97.6318 loss_bbox: 0.1230 loss_mask: 0.1946 2022/11/01 15:58:31 - mmengine - INFO - Epoch(train) [151][120/125] lr: 2.0000e-04 eta: 0:09:32 time: 0.3860 data_time: 0.0369 memory: 10129 loss: 0.4077 loss_rpn_cls: 0.0060 loss_rpn_bbox: 0.0111 loss_cls: 0.0788 acc: 95.8008 loss_bbox: 0.1177 loss_mask: 0.1941 2022/11/01 15:58:33 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:58:33 - mmengine - INFO - Epoch(train) [151][125/125] lr: 2.0000e-04 eta: 0:09:32 time: 0.4022 data_time: 0.0320 memory: 10502 loss: 0.4897 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0146 loss_cls: 0.1011 acc: 94.2383 loss_bbox: 0.1547 loss_mask: 0.2107 2022/11/01 15:58:37 - mmengine - INFO - Epoch(train) [152][5/125] lr: 2.0000e-04 eta: 0:09:32 time: 0.5984 data_time: 0.2396 memory: 9812 loss: 0.4844 loss_rpn_cls: 0.0105 loss_rpn_bbox: 0.0119 loss_cls: 0.0972 acc: 96.7041 loss_bbox: 0.1401 loss_mask: 0.2248 2022/11/01 15:58:40 - mmengine - INFO - Epoch(train) [152][10/125] lr: 2.0000e-04 eta: 0:09:23 time: 0.6056 data_time: 0.2557 memory: 10556 loss: 0.4283 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0102 loss_cls: 0.0830 acc: 97.9492 loss_bbox: 0.1162 loss_mask: 0.2104 2022/11/01 15:58:41 - mmengine - INFO - Epoch(train) [152][15/125] lr: 2.0000e-04 eta: 0:09:23 time: 0.4048 data_time: 0.0686 memory: 9602 loss: 0.4253 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0093 loss_cls: 0.0846 acc: 97.1191 loss_bbox: 0.1240 loss_mask: 0.1993 2022/11/01 15:58:44 - mmengine - INFO - Epoch(train) [152][20/125] lr: 2.0000e-04 eta: 0:09:18 time: 0.4078 data_time: 0.1007 memory: 9463 loss: 0.4236 loss_rpn_cls: 0.0095 loss_rpn_bbox: 0.0097 loss_cls: 0.0820 acc: 96.4355 loss_bbox: 0.1228 loss_mask: 0.1996 2022/11/01 15:58:46 - mmengine - INFO - Epoch(train) [152][25/125] lr: 2.0000e-04 eta: 0:09:18 time: 0.4271 data_time: 0.1066 memory: 9772 loss: 0.4471 loss_rpn_cls: 0.0105 loss_rpn_bbox: 0.0111 loss_cls: 0.0873 acc: 96.6797 loss_bbox: 0.1352 loss_mask: 0.2030 2022/11/01 15:58:49 - mmengine - INFO - Epoch(train) [152][30/125] lr: 2.0000e-04 eta: 0:09:12 time: 0.4994 data_time: 0.1286 memory: 10789 loss: 0.4647 loss_rpn_cls: 0.0110 loss_rpn_bbox: 0.0120 loss_cls: 0.0990 acc: 95.3369 loss_bbox: 0.1517 loss_mask: 0.1910 2022/11/01 15:58:51 - mmengine - INFO - Epoch(train) [152][35/125] lr: 2.0000e-04 eta: 0:09:12 time: 0.5113 data_time: 0.1217 memory: 10996 loss: 0.4444 loss_rpn_cls: 0.0103 loss_rpn_bbox: 0.0112 loss_cls: 0.0942 acc: 96.2646 loss_bbox: 0.1491 loss_mask: 0.1796 2022/11/01 15:58:53 - mmengine - INFO - Epoch(train) [152][40/125] lr: 2.0000e-04 eta: 0:09:07 time: 0.4454 data_time: 0.0841 memory: 10571 loss: 0.4350 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0102 loss_cls: 0.0876 acc: 94.8975 loss_bbox: 0.1433 loss_mask: 0.1855 2022/11/01 15:58:55 - mmengine - INFO - Epoch(train) [152][45/125] lr: 2.0000e-04 eta: 0:09:07 time: 0.4100 data_time: 0.0862 memory: 9844 loss: 0.4060 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0091 loss_cls: 0.0794 acc: 98.1201 loss_bbox: 0.1206 loss_mask: 0.1908 2022/11/01 15:58:57 - mmengine - INFO - Epoch(train) [152][50/125] lr: 2.0000e-04 eta: 0:09:01 time: 0.3549 data_time: 0.0542 memory: 10158 loss: 0.3892 loss_rpn_cls: 0.0047 loss_rpn_bbox: 0.0105 loss_cls: 0.0716 acc: 98.0957 loss_bbox: 0.1110 loss_mask: 0.1915 2022/11/01 15:58:58 - mmengine - INFO - Epoch(train) [152][55/125] lr: 2.0000e-04 eta: 0:09:01 time: 0.3499 data_time: 0.0488 memory: 9560 loss: 0.3969 loss_rpn_cls: 0.0058 loss_rpn_bbox: 0.0105 loss_cls: 0.0737 acc: 97.5098 loss_bbox: 0.1103 loss_mask: 0.1966 2022/11/01 15:59:01 - mmengine - INFO - Epoch(train) [152][60/125] lr: 2.0000e-04 eta: 0:08:55 time: 0.3942 data_time: 0.0636 memory: 10774 loss: 0.4299 loss_rpn_cls: 0.0085 loss_rpn_bbox: 0.0105 loss_cls: 0.0866 acc: 98.6328 loss_bbox: 0.1246 loss_mask: 0.1998 2022/11/01 15:59:03 - mmengine - INFO - Epoch(train) [152][65/125] lr: 2.0000e-04 eta: 0:08:55 time: 0.4093 data_time: 0.0567 memory: 9602 loss: 0.4636 loss_rpn_cls: 0.0108 loss_rpn_bbox: 0.0119 loss_cls: 0.0964 acc: 97.4854 loss_bbox: 0.1395 loss_mask: 0.2050 2022/11/01 15:59:04 - mmengine - INFO - Epoch(train) [152][70/125] lr: 2.0000e-04 eta: 0:08:49 time: 0.3903 data_time: 0.0619 memory: 9658 loss: 0.4344 loss_rpn_cls: 0.0109 loss_rpn_bbox: 0.0112 loss_cls: 0.0857 acc: 98.6084 loss_bbox: 0.1232 loss_mask: 0.2034 2022/11/01 15:59:06 - mmengine - INFO - Epoch(train) [152][75/125] lr: 2.0000e-04 eta: 0:08:49 time: 0.3675 data_time: 0.0568 memory: 9621 loss: 0.4196 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0102 loss_cls: 0.0789 acc: 95.9473 loss_bbox: 0.1231 loss_mask: 0.1985 2022/11/01 15:59:08 - mmengine - INFO - Epoch(train) [152][80/125] lr: 2.0000e-04 eta: 0:08:43 time: 0.3941 data_time: 0.0689 memory: 10418 loss: 0.4186 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0096 loss_cls: 0.0833 acc: 96.9482 loss_bbox: 0.1250 loss_mask: 0.1939 2022/11/01 15:59:10 - mmengine - INFO - Epoch(train) [152][85/125] lr: 2.0000e-04 eta: 0:08:43 time: 0.3979 data_time: 0.0690 memory: 9572 loss: 0.4290 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0109 loss_cls: 0.0808 acc: 98.5840 loss_bbox: 0.1172 loss_mask: 0.2122 2022/11/01 15:59:12 - mmengine - INFO - Epoch(train) [152][90/125] lr: 2.0000e-04 eta: 0:08:37 time: 0.3797 data_time: 0.0699 memory: 9260 loss: 0.4373 loss_rpn_cls: 0.0095 loss_rpn_bbox: 0.0095 loss_cls: 0.0797 acc: 96.8994 loss_bbox: 0.1175 loss_mask: 0.2212 2022/11/01 15:59:15 - mmengine - INFO - Epoch(train) [152][95/125] lr: 2.0000e-04 eta: 0:08:37 time: 0.4490 data_time: 0.0932 memory: 10599 loss: 0.4563 loss_rpn_cls: 0.0108 loss_rpn_bbox: 0.0100 loss_cls: 0.0932 acc: 96.7773 loss_bbox: 0.1357 loss_mask: 0.2066 2022/11/01 15:59:17 - mmengine - INFO - Epoch(train) [152][100/125] lr: 2.0000e-04 eta: 0:08:32 time: 0.4623 data_time: 0.0942 memory: 9400 loss: 0.4471 loss_rpn_cls: 0.0090 loss_rpn_bbox: 0.0108 loss_cls: 0.0920 acc: 97.9248 loss_bbox: 0.1350 loss_mask: 0.2002 2022/11/01 15:59:19 - mmengine - INFO - Epoch(train) [152][105/125] lr: 2.0000e-04 eta: 0:08:32 time: 0.3952 data_time: 0.0783 memory: 9182 loss: 0.3908 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0078 loss_cls: 0.0718 acc: 97.2900 loss_bbox: 0.1056 loss_mask: 0.1994 2022/11/01 15:59:21 - mmengine - INFO - Epoch(train) [152][110/125] lr: 2.0000e-04 eta: 0:08:26 time: 0.3809 data_time: 0.0724 memory: 9455 loss: 0.4126 loss_rpn_cls: 0.0100 loss_rpn_bbox: 0.0091 loss_cls: 0.0764 acc: 95.4590 loss_bbox: 0.1104 loss_mask: 0.2067 2022/11/01 15:59:23 - mmengine - INFO - Epoch(train) [152][115/125] lr: 2.0000e-04 eta: 0:08:26 time: 0.4016 data_time: 0.0905 memory: 9556 loss: 0.4525 loss_rpn_cls: 0.0121 loss_rpn_bbox: 0.0115 loss_cls: 0.0918 acc: 96.0938 loss_bbox: 0.1375 loss_mask: 0.1996 2022/11/01 15:59:25 - mmengine - INFO - Epoch(train) [152][120/125] lr: 2.0000e-04 eta: 0:08:21 time: 0.4271 data_time: 0.0849 memory: 10734 loss: 0.4536 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0122 loss_cls: 0.0958 acc: 96.1670 loss_bbox: 0.1509 loss_mask: 0.1853 2022/11/01 15:59:27 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 15:59:27 - mmengine - INFO - Epoch(train) [152][125/125] lr: 2.0000e-04 eta: 0:08:21 time: 0.4001 data_time: 0.0492 memory: 9505 loss: 0.4383 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0106 loss_cls: 0.0858 acc: 96.8506 loss_bbox: 0.1361 loss_mask: 0.1984 2022/11/01 15:59:30 - mmengine - INFO - Epoch(train) [153][5/125] lr: 2.0000e-04 eta: 0:08:21 time: 0.5329 data_time: 0.2135 memory: 9805 loss: 0.4228 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0090 loss_cls: 0.0761 acc: 97.4609 loss_bbox: 0.1234 loss_mask: 0.2072 2022/11/01 15:59:32 - mmengine - INFO - Epoch(train) [153][10/125] lr: 2.0000e-04 eta: 0:08:12 time: 0.5611 data_time: 0.2273 memory: 10516 loss: 0.4418 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0122 loss_cls: 0.0799 acc: 98.4131 loss_bbox: 0.1330 loss_mask: 0.2079 2022/11/01 15:59:34 - mmengine - INFO - Epoch(train) [153][15/125] lr: 2.0000e-04 eta: 0:08:12 time: 0.3969 data_time: 0.0597 memory: 9037 loss: 0.3947 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0096 loss_cls: 0.0675 acc: 98.2666 loss_bbox: 0.1031 loss_mask: 0.2076 2022/11/01 15:59:37 - mmengine - INFO - Epoch(train) [153][20/125] lr: 2.0000e-04 eta: 0:08:07 time: 0.4765 data_time: 0.1378 memory: 9854 loss: 0.3781 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0090 loss_cls: 0.0731 acc: 96.6309 loss_bbox: 0.1021 loss_mask: 0.1871 2022/11/01 15:59:39 - mmengine - INFO - Epoch(train) [153][25/125] lr: 2.0000e-04 eta: 0:08:07 time: 0.5009 data_time: 0.1218 memory: 9629 loss: 0.4371 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0128 loss_cls: 0.0905 acc: 95.7031 loss_bbox: 0.1344 loss_mask: 0.1901 2022/11/01 15:59:41 - mmengine - INFO - Epoch(train) [153][30/125] lr: 2.0000e-04 eta: 0:08:02 time: 0.4401 data_time: 0.0550 memory: 9844 loss: 0.4685 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0147 loss_cls: 0.0952 acc: 97.8760 loss_bbox: 0.1421 loss_mask: 0.2072 2022/11/01 15:59:44 - mmengine - INFO - Epoch(train) [153][35/125] lr: 2.0000e-04 eta: 0:08:02 time: 0.4458 data_time: 0.0728 memory: 10368 loss: 0.4427 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0146 loss_cls: 0.0848 acc: 98.1201 loss_bbox: 0.1329 loss_mask: 0.2034 2022/11/01 15:59:46 - mmengine - INFO - Epoch(train) [153][40/125] lr: 2.0000e-04 eta: 0:07:56 time: 0.4409 data_time: 0.0789 memory: 9874 loss: 0.4153 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0105 loss_cls: 0.0761 acc: 96.8750 loss_bbox: 0.1193 loss_mask: 0.2013 2022/11/01 15:59:48 - mmengine - INFO - Epoch(train) [153][45/125] lr: 2.0000e-04 eta: 0:07:56 time: 0.4220 data_time: 0.0686 memory: 10198 loss: 0.4241 loss_rpn_cls: 0.0090 loss_rpn_bbox: 0.0085 loss_cls: 0.0837 acc: 97.3389 loss_bbox: 0.1246 loss_mask: 0.1983 2022/11/01 15:59:50 - mmengine - INFO - Epoch(train) [153][50/125] lr: 2.0000e-04 eta: 0:07:51 time: 0.4152 data_time: 0.0479 memory: 10903 loss: 0.3985 loss_rpn_cls: 0.0065 loss_rpn_bbox: 0.0082 loss_cls: 0.0797 acc: 97.9980 loss_bbox: 0.1222 loss_mask: 0.1819 2022/11/01 15:59:52 - mmengine - INFO - Epoch(train) [153][55/125] lr: 2.0000e-04 eta: 0:07:51 time: 0.4292 data_time: 0.0697 memory: 9804 loss: 0.4070 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0082 loss_cls: 0.0793 acc: 96.2402 loss_bbox: 0.1239 loss_mask: 0.1884 2022/11/01 15:59:55 - mmengine - INFO - Epoch(train) [153][60/125] lr: 2.0000e-04 eta: 0:07:46 time: 0.4682 data_time: 0.0811 memory: 10105 loss: 0.4324 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0097 loss_cls: 0.0824 acc: 95.8740 loss_bbox: 0.1342 loss_mask: 0.1988 2022/11/01 15:59:57 - mmengine - INFO - Epoch(train) [153][65/125] lr: 2.0000e-04 eta: 0:07:46 time: 0.4534 data_time: 0.0632 memory: 9553 loss: 0.4493 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0125 loss_cls: 0.0871 acc: 99.2676 loss_bbox: 0.1310 loss_mask: 0.2118 2022/11/01 15:59:59 - mmengine - INFO - Epoch(train) [153][70/125] lr: 2.0000e-04 eta: 0:07:40 time: 0.4108 data_time: 0.0635 memory: 9456 loss: 0.4487 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0115 loss_cls: 0.0877 acc: 96.4844 loss_bbox: 0.1292 loss_mask: 0.2136 2022/11/01 16:00:01 - mmengine - INFO - Epoch(train) [153][75/125] lr: 2.0000e-04 eta: 0:07:40 time: 0.3980 data_time: 0.0579 memory: 9358 loss: 0.4003 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0092 loss_cls: 0.0762 acc: 98.1934 loss_bbox: 0.1182 loss_mask: 0.1906 2022/11/01 16:00:04 - mmengine - INFO - Epoch(train) [153][80/125] lr: 2.0000e-04 eta: 0:07:35 time: 0.4932 data_time: 0.1583 memory: 9531 loss: 0.4356 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0105 loss_cls: 0.0869 acc: 96.3379 loss_bbox: 0.1246 loss_mask: 0.2048 2022/11/01 16:00:05 - mmengine - INFO - Epoch(train) [153][85/125] lr: 2.0000e-04 eta: 0:07:35 time: 0.4737 data_time: 0.1460 memory: 9681 loss: 0.4566 loss_rpn_cls: 0.0087 loss_rpn_bbox: 0.0104 loss_cls: 0.0903 acc: 96.7529 loss_bbox: 0.1318 loss_mask: 0.2153 2022/11/01 16:00:08 - mmengine - INFO - Epoch(train) [153][90/125] lr: 2.0000e-04 eta: 0:07:30 time: 0.3760 data_time: 0.0385 memory: 9919 loss: 0.4373 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0106 loss_cls: 0.0869 acc: 96.6553 loss_bbox: 0.1304 loss_mask: 0.2021 2022/11/01 16:00:10 - mmengine - INFO - Epoch(train) [153][95/125] lr: 2.0000e-04 eta: 0:07:30 time: 0.4418 data_time: 0.1012 memory: 9547 loss: 0.4354 loss_rpn_cls: 0.0094 loss_rpn_bbox: 0.0114 loss_cls: 0.0917 acc: 97.9980 loss_bbox: 0.1279 loss_mask: 0.1950 2022/11/01 16:00:12 - mmengine - INFO - Epoch(train) [153][100/125] lr: 2.0000e-04 eta: 0:07:24 time: 0.4212 data_time: 0.0896 memory: 9664 loss: 0.4303 loss_rpn_cls: 0.0087 loss_rpn_bbox: 0.0102 loss_cls: 0.0896 acc: 95.8496 loss_bbox: 0.1261 loss_mask: 0.1956 2022/11/01 16:00:14 - mmengine - INFO - Epoch(train) [153][105/125] lr: 2.0000e-04 eta: 0:07:24 time: 0.3789 data_time: 0.0363 memory: 9618 loss: 0.4269 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0087 loss_cls: 0.0866 acc: 95.5566 loss_bbox: 0.1323 loss_mask: 0.1920 2022/11/01 16:00:16 - mmengine - INFO - Epoch(train) [153][110/125] lr: 2.0000e-04 eta: 0:07:19 time: 0.3976 data_time: 0.0442 memory: 9612 loss: 0.4099 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0081 loss_cls: 0.0809 acc: 97.5830 loss_bbox: 0.1238 loss_mask: 0.1897 2022/11/01 16:00:18 - mmengine - INFO - Epoch(train) [153][115/125] lr: 2.0000e-04 eta: 0:07:19 time: 0.4403 data_time: 0.0557 memory: 9479 loss: 0.4065 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0087 loss_cls: 0.0789 acc: 96.7285 loss_bbox: 0.1214 loss_mask: 0.1902 2022/11/01 16:00:20 - mmengine - INFO - Epoch(train) [153][120/125] lr: 2.0000e-04 eta: 0:07:14 time: 0.4538 data_time: 0.0514 memory: 9821 loss: 0.4416 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0097 loss_cls: 0.0883 acc: 96.7041 loss_bbox: 0.1388 loss_mask: 0.1968 2022/11/01 16:00:22 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 16:00:22 - mmengine - INFO - Epoch(train) [153][125/125] lr: 2.0000e-04 eta: 0:07:14 time: 0.3994 data_time: 0.0278 memory: 9645 loss: 0.4322 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0107 loss_cls: 0.0855 acc: 95.7031 loss_bbox: 0.1311 loss_mask: 0.1970 2022/11/01 16:00:25 - mmengine - INFO - Epoch(train) [154][5/125] lr: 2.0000e-04 eta: 0:07:14 time: 0.5140 data_time: 0.1629 memory: 9482 loss: 0.4150 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0125 loss_cls: 0.0801 acc: 94.6777 loss_bbox: 0.1200 loss_mask: 0.1942 2022/11/01 16:00:28 - mmengine - INFO - Epoch(train) [154][10/125] lr: 2.0000e-04 eta: 0:07:05 time: 0.5493 data_time: 0.1858 memory: 9472 loss: 0.4452 loss_rpn_cls: 0.0090 loss_rpn_bbox: 0.0115 loss_cls: 0.0923 acc: 96.3867 loss_bbox: 0.1320 loss_mask: 0.2005 2022/11/01 16:00:31 - mmengine - INFO - Epoch(train) [154][15/125] lr: 2.0000e-04 eta: 0:07:05 time: 0.5183 data_time: 0.1710 memory: 9785 loss: 0.4313 loss_rpn_cls: 0.0105 loss_rpn_bbox: 0.0092 loss_cls: 0.0890 acc: 96.2891 loss_bbox: 0.1238 loss_mask: 0.1987 2022/11/01 16:00:33 - mmengine - INFO - Epoch(train) [154][20/125] lr: 2.0000e-04 eta: 0:07:00 time: 0.4987 data_time: 0.1799 memory: 9509 loss: 0.4241 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0098 loss_cls: 0.0831 acc: 95.9961 loss_bbox: 0.1247 loss_mask: 0.1972 2022/11/01 16:00:36 - mmengine - INFO - Epoch(train) [154][25/125] lr: 2.0000e-04 eta: 0:07:00 time: 0.5149 data_time: 0.1783 memory: 9798 loss: 0.3954 loss_rpn_cls: 0.0057 loss_rpn_bbox: 0.0099 loss_cls: 0.0748 acc: 98.6328 loss_bbox: 0.1163 loss_mask: 0.1888 2022/11/01 16:00:38 - mmengine - INFO - Epoch(train) [154][30/125] lr: 2.0000e-04 eta: 0:06:56 time: 0.5927 data_time: 0.2349 memory: 9346 loss: 0.4142 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0112 loss_cls: 0.0791 acc: 97.0215 loss_bbox: 0.1194 loss_mask: 0.1964 2022/11/01 16:00:41 - mmengine - INFO - Epoch(train) [154][35/125] lr: 2.0000e-04 eta: 0:06:56 time: 0.4820 data_time: 0.1379 memory: 9496 loss: 0.4302 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0114 loss_cls: 0.0822 acc: 97.0947 loss_bbox: 0.1253 loss_mask: 0.2029 2022/11/01 16:00:42 - mmengine - INFO - Epoch(train) [154][40/125] lr: 2.0000e-04 eta: 0:06:51 time: 0.3986 data_time: 0.0569 memory: 10064 loss: 0.4155 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0096 loss_cls: 0.0782 acc: 96.2891 loss_bbox: 0.1253 loss_mask: 0.1960 2022/11/01 16:00:44 - mmengine - INFO - Epoch(train) [154][45/125] lr: 2.0000e-04 eta: 0:06:51 time: 0.3713 data_time: 0.0370 memory: 9488 loss: 0.4286 loss_rpn_cls: 0.0063 loss_rpn_bbox: 0.0121 loss_cls: 0.0851 acc: 97.7539 loss_bbox: 0.1336 loss_mask: 0.1915 2022/11/01 16:00:46 - mmengine - INFO - Epoch(train) [154][50/125] lr: 2.0000e-04 eta: 0:06:45 time: 0.3580 data_time: 0.0415 memory: 9609 loss: 0.4193 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0122 loss_cls: 0.0847 acc: 96.9727 loss_bbox: 0.1245 loss_mask: 0.1915 2022/11/01 16:00:48 - mmengine - INFO - Epoch(train) [154][55/125] lr: 2.0000e-04 eta: 0:06:45 time: 0.3593 data_time: 0.0514 memory: 9364 loss: 0.4201 loss_rpn_cls: 0.0090 loss_rpn_bbox: 0.0097 loss_cls: 0.0787 acc: 96.8506 loss_bbox: 0.1164 loss_mask: 0.2064 2022/11/01 16:00:50 - mmengine - INFO - Epoch(train) [154][60/125] lr: 2.0000e-04 eta: 0:06:40 time: 0.3811 data_time: 0.0764 memory: 9335 loss: 0.4336 loss_rpn_cls: 0.0085 loss_rpn_bbox: 0.0085 loss_cls: 0.0821 acc: 95.7275 loss_bbox: 0.1216 loss_mask: 0.2129 2022/11/01 16:00:52 - mmengine - INFO - Epoch(train) [154][65/125] lr: 2.0000e-04 eta: 0:06:40 time: 0.4346 data_time: 0.0947 memory: 11131 loss: 0.4420 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0097 loss_cls: 0.0921 acc: 97.7295 loss_bbox: 0.1363 loss_mask: 0.1964 2022/11/01 16:00:54 - mmengine - INFO - Epoch(train) [154][70/125] lr: 2.0000e-04 eta: 0:06:34 time: 0.4202 data_time: 0.0786 memory: 9625 loss: 0.4308 loss_rpn_cls: 0.0103 loss_rpn_bbox: 0.0116 loss_cls: 0.0861 acc: 98.0713 loss_bbox: 0.1268 loss_mask: 0.1960 2022/11/01 16:00:56 - mmengine - INFO - Epoch(train) [154][75/125] lr: 2.0000e-04 eta: 0:06:34 time: 0.4124 data_time: 0.0587 memory: 10673 loss: 0.3985 loss_rpn_cls: 0.0087 loss_rpn_bbox: 0.0096 loss_cls: 0.0702 acc: 97.3633 loss_bbox: 0.1120 loss_mask: 0.1981 2022/11/01 16:00:59 - mmengine - INFO - Epoch(train) [154][80/125] lr: 2.0000e-04 eta: 0:06:29 time: 0.4475 data_time: 0.0625 memory: 11223 loss: 0.3915 loss_rpn_cls: 0.0049 loss_rpn_bbox: 0.0085 loss_cls: 0.0688 acc: 96.8262 loss_bbox: 0.1205 loss_mask: 0.1887 2022/11/01 16:01:00 - mmengine - INFO - Epoch(train) [154][85/125] lr: 2.0000e-04 eta: 0:06:29 time: 0.4151 data_time: 0.0646 memory: 9329 loss: 0.4308 loss_rpn_cls: 0.0096 loss_rpn_bbox: 0.0095 loss_cls: 0.0860 acc: 96.3623 loss_bbox: 0.1211 loss_mask: 0.2046 2022/11/01 16:01:02 - mmengine - INFO - Epoch(train) [154][90/125] lr: 2.0000e-04 eta: 0:06:24 time: 0.3792 data_time: 0.0550 memory: 9608 loss: 0.4403 loss_rpn_cls: 0.0108 loss_rpn_bbox: 0.0132 loss_cls: 0.0864 acc: 97.1680 loss_bbox: 0.1177 loss_mask: 0.2122 2022/11/01 16:01:04 - mmengine - INFO - Epoch(train) [154][95/125] lr: 2.0000e-04 eta: 0:06:24 time: 0.4024 data_time: 0.0635 memory: 10437 loss: 0.4097 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0121 loss_cls: 0.0773 acc: 95.9961 loss_bbox: 0.1219 loss_mask: 0.1920 2022/11/01 16:01:06 - mmengine - INFO - Epoch(train) [154][100/125] lr: 2.0000e-04 eta: 0:06:19 time: 0.4116 data_time: 0.0717 memory: 9835 loss: 0.4439 loss_rpn_cls: 0.0085 loss_rpn_bbox: 0.0096 loss_cls: 0.0884 acc: 97.4609 loss_bbox: 0.1398 loss_mask: 0.1976 2022/11/01 16:01:09 - mmengine - INFO - Epoch(train) [154][105/125] lr: 2.0000e-04 eta: 0:06:19 time: 0.4128 data_time: 0.0800 memory: 9619 loss: 0.4481 loss_rpn_cls: 0.0087 loss_rpn_bbox: 0.0093 loss_cls: 0.0905 acc: 97.4609 loss_bbox: 0.1366 loss_mask: 0.2030 2022/11/01 16:01:10 - mmengine - INFO - Epoch(train) [154][110/125] lr: 2.0000e-04 eta: 0:06:13 time: 0.3998 data_time: 0.0667 memory: 9654 loss: 0.4012 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0098 loss_cls: 0.0760 acc: 97.8271 loss_bbox: 0.1160 loss_mask: 0.1918 2022/11/01 16:01:12 - mmengine - INFO - Epoch(train) [154][115/125] lr: 2.0000e-04 eta: 0:06:13 time: 0.3648 data_time: 0.0432 memory: 9661 loss: 0.3974 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0087 loss_cls: 0.0738 acc: 98.0957 loss_bbox: 0.1124 loss_mask: 0.1956 2022/11/01 16:01:15 - mmengine - INFO - Epoch(train) [154][120/125] lr: 2.0000e-04 eta: 0:06:08 time: 0.4131 data_time: 0.0597 memory: 10258 loss: 0.4251 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0085 loss_cls: 0.0811 acc: 98.2178 loss_bbox: 0.1233 loss_mask: 0.2042 2022/11/01 16:01:17 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 16:01:17 - mmengine - INFO - Epoch(train) [154][125/125] lr: 2.0000e-04 eta: 0:06:08 time: 0.4376 data_time: 0.0571 memory: 10835 loss: 0.4372 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0113 loss_cls: 0.0817 acc: 96.6797 loss_bbox: 0.1310 loss_mask: 0.2039 2022/11/01 16:01:20 - mmengine - INFO - Epoch(train) [155][5/125] lr: 2.0000e-04 eta: 0:06:08 time: 0.5260 data_time: 0.1683 memory: 10214 loss: 0.4242 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0110 loss_cls: 0.0787 acc: 97.5098 loss_bbox: 0.1225 loss_mask: 0.2027 2022/11/01 16:01:22 - mmengine - INFO - Epoch(train) [155][10/125] lr: 2.0000e-04 eta: 0:06:00 time: 0.5244 data_time: 0.1826 memory: 10043 loss: 0.4200 loss_rpn_cls: 0.0098 loss_rpn_bbox: 0.0110 loss_cls: 0.0774 acc: 96.1914 loss_bbox: 0.1211 loss_mask: 0.2006 2022/11/01 16:01:24 - mmengine - INFO - Epoch(train) [155][15/125] lr: 2.0000e-04 eta: 0:06:00 time: 0.4237 data_time: 0.0653 memory: 10969 loss: 0.4375 loss_rpn_cls: 0.0094 loss_rpn_bbox: 0.0098 loss_cls: 0.0863 acc: 97.6807 loss_bbox: 0.1362 loss_mask: 0.1958 2022/11/01 16:01:26 - mmengine - INFO - Epoch(train) [155][20/125] lr: 2.0000e-04 eta: 0:05:55 time: 0.4319 data_time: 0.0565 memory: 10927 loss: 0.4681 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0114 loss_cls: 0.0996 acc: 97.7539 loss_bbox: 0.1497 loss_mask: 0.1981 2022/11/01 16:01:28 - mmengine - INFO - Epoch(train) [155][25/125] lr: 2.0000e-04 eta: 0:05:55 time: 0.3831 data_time: 0.0403 memory: 9342 loss: 0.4417 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0117 loss_cls: 0.0910 acc: 97.7783 loss_bbox: 0.1330 loss_mask: 0.1986 2022/11/01 16:01:30 - mmengine - INFO - Epoch(train) [155][30/125] lr: 2.0000e-04 eta: 0:05:49 time: 0.3520 data_time: 0.0412 memory: 9495 loss: 0.4401 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0100 loss_cls: 0.0865 acc: 96.1182 loss_bbox: 0.1280 loss_mask: 0.2088 2022/11/01 16:01:33 - mmengine - INFO - Epoch(train) [155][35/125] lr: 2.0000e-04 eta: 0:05:49 time: 0.5405 data_time: 0.2194 memory: 9788 loss: 0.4683 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0112 loss_cls: 0.0940 acc: 95.6787 loss_bbox: 0.1394 loss_mask: 0.2159 2022/11/01 16:01:35 - mmengine - INFO - Epoch(train) [155][40/125] lr: 2.0000e-04 eta: 0:05:45 time: 0.5212 data_time: 0.1974 memory: 9250 loss: 0.4383 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0091 loss_cls: 0.0857 acc: 96.8506 loss_bbox: 0.1270 loss_mask: 0.2096 2022/11/01 16:01:37 - mmengine - INFO - Epoch(train) [155][45/125] lr: 2.0000e-04 eta: 0:05:45 time: 0.3637 data_time: 0.0391 memory: 9719 loss: 0.4285 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0085 loss_cls: 0.0809 acc: 95.9961 loss_bbox: 0.1272 loss_mask: 0.2060 2022/11/01 16:01:39 - mmengine - INFO - Epoch(train) [155][50/125] lr: 2.0000e-04 eta: 0:05:39 time: 0.3812 data_time: 0.0582 memory: 9739 loss: 0.4559 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0126 loss_cls: 0.0880 acc: 95.1660 loss_bbox: 0.1422 loss_mask: 0.2048 2022/11/01 16:01:41 - mmengine - INFO - Epoch(train) [155][55/125] lr: 2.0000e-04 eta: 0:05:39 time: 0.3786 data_time: 0.0653 memory: 9907 loss: 0.4774 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0133 loss_cls: 0.0957 acc: 95.2148 loss_bbox: 0.1486 loss_mask: 0.2103 2022/11/01 16:01:43 - mmengine - INFO - Epoch(train) [155][60/125] lr: 2.0000e-04 eta: 0:05:34 time: 0.3919 data_time: 0.0747 memory: 9619 loss: 0.4899 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0109 loss_cls: 0.0986 acc: 96.1426 loss_bbox: 0.1498 loss_mask: 0.2218 2022/11/01 16:01:45 - mmengine - INFO - Epoch(train) [155][65/125] lr: 2.0000e-04 eta: 0:05:34 time: 0.3808 data_time: 0.0674 memory: 9407 loss: 0.4562 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0106 loss_cls: 0.0902 acc: 98.2422 loss_bbox: 0.1338 loss_mask: 0.2133 2022/11/01 16:01:46 - mmengine - INFO - Epoch(train) [155][70/125] lr: 2.0000e-04 eta: 0:05:29 time: 0.3642 data_time: 0.0486 memory: 9349 loss: 0.4025 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0094 loss_cls: 0.0740 acc: 97.9736 loss_bbox: 0.1137 loss_mask: 0.1989 2022/11/01 16:01:48 - mmengine - INFO - Epoch(train) [155][75/125] lr: 2.0000e-04 eta: 0:05:29 time: 0.3775 data_time: 0.0478 memory: 10445 loss: 0.4089 loss_rpn_cls: 0.0063 loss_rpn_bbox: 0.0077 loss_cls: 0.0748 acc: 98.5596 loss_bbox: 0.1169 loss_mask: 0.2032 2022/11/01 16:01:50 - mmengine - INFO - Epoch(train) [155][80/125] lr: 2.0000e-04 eta: 0:05:24 time: 0.3976 data_time: 0.0712 memory: 9433 loss: 0.4195 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0107 loss_cls: 0.0814 acc: 96.9482 loss_bbox: 0.1207 loss_mask: 0.1994 2022/11/01 16:01:52 - mmengine - INFO - Epoch(train) [155][85/125] lr: 2.0000e-04 eta: 0:05:24 time: 0.4004 data_time: 0.0674 memory: 9283 loss: 0.4013 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0102 loss_cls: 0.0777 acc: 95.5078 loss_bbox: 0.1147 loss_mask: 0.1914 2022/11/01 16:01:54 - mmengine - INFO - Epoch(train) [155][90/125] lr: 2.0000e-04 eta: 0:05:19 time: 0.4106 data_time: 0.0614 memory: 9955 loss: 0.4254 loss_rpn_cls: 0.0066 loss_rpn_bbox: 0.0098 loss_cls: 0.0818 acc: 95.2393 loss_bbox: 0.1245 loss_mask: 0.2027 2022/11/01 16:01:56 - mmengine - INFO - Epoch(train) [155][95/125] lr: 2.0000e-04 eta: 0:05:19 time: 0.4010 data_time: 0.0696 memory: 9171 loss: 0.4239 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0101 loss_cls: 0.0805 acc: 96.5576 loss_bbox: 0.1182 loss_mask: 0.2092 2022/11/01 16:01:58 - mmengine - INFO - Epoch(train) [155][100/125] lr: 2.0000e-04 eta: 0:05:13 time: 0.4032 data_time: 0.0930 memory: 9365 loss: 0.3884 loss_rpn_cls: 0.0049 loss_rpn_bbox: 0.0068 loss_cls: 0.0742 acc: 97.3633 loss_bbox: 0.1031 loss_mask: 0.1994 2022/11/01 16:02:00 - mmengine - INFO - Epoch(train) [155][105/125] lr: 2.0000e-04 eta: 0:05:13 time: 0.4051 data_time: 0.0856 memory: 9616 loss: 0.4154 loss_rpn_cls: 0.0066 loss_rpn_bbox: 0.0076 loss_cls: 0.0854 acc: 97.2900 loss_bbox: 0.1190 loss_mask: 0.1968 2022/11/01 16:02:02 - mmengine - INFO - Epoch(train) [155][110/125] lr: 2.0000e-04 eta: 0:05:08 time: 0.3671 data_time: 0.0468 memory: 9498 loss: 0.4510 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0082 loss_cls: 0.0928 acc: 97.3389 loss_bbox: 0.1368 loss_mask: 0.2047 2022/11/01 16:02:05 - mmengine - INFO - Epoch(train) [155][115/125] lr: 2.0000e-04 eta: 0:05:08 time: 0.4613 data_time: 0.1494 memory: 9655 loss: 0.4255 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0085 loss_cls: 0.0778 acc: 98.8281 loss_bbox: 0.1257 loss_mask: 0.2066 2022/11/01 16:02:07 - mmengine - INFO - Epoch(train) [155][120/125] lr: 2.0000e-04 eta: 0:05:03 time: 0.4956 data_time: 0.1688 memory: 9739 loss: 0.4144 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0100 loss_cls: 0.0771 acc: 96.5576 loss_bbox: 0.1163 loss_mask: 0.2041 2022/11/01 16:02:09 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 16:02:09 - mmengine - INFO - Epoch(train) [155][125/125] lr: 2.0000e-04 eta: 0:05:03 time: 0.4339 data_time: 0.0756 memory: 9791 loss: 0.4380 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0104 loss_cls: 0.0899 acc: 96.6553 loss_bbox: 0.1252 loss_mask: 0.2036 2022/11/01 16:02:15 - mmengine - INFO - Epoch(train) [156][5/125] lr: 2.0000e-04 eta: 0:05:03 time: 0.7501 data_time: 0.3788 memory: 9609 loss: 0.4416 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0125 loss_cls: 0.0881 acc: 96.9482 loss_bbox: 0.1321 loss_mask: 0.1997 2022/11/01 16:02:16 - mmengine - INFO - Epoch(train) [156][10/125] lr: 2.0000e-04 eta: 0:04:56 time: 0.7099 data_time: 0.3670 memory: 9838 loss: 0.4383 loss_rpn_cls: 0.0098 loss_rpn_bbox: 0.0141 loss_cls: 0.0873 acc: 94.8242 loss_bbox: 0.1286 loss_mask: 0.1985 2022/11/01 16:02:18 - mmengine - INFO - Epoch(train) [156][15/125] lr: 2.0000e-04 eta: 0:04:56 time: 0.3746 data_time: 0.0443 memory: 9449 loss: 0.4161 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0108 loss_cls: 0.0822 acc: 95.9473 loss_bbox: 0.1184 loss_mask: 0.1958 2022/11/01 16:02:20 - mmengine - INFO - Epoch(train) [156][20/125] lr: 2.0000e-04 eta: 0:04:51 time: 0.3887 data_time: 0.0548 memory: 9430 loss: 0.3922 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0081 loss_cls: 0.0755 acc: 96.0938 loss_bbox: 0.1087 loss_mask: 0.1922 2022/11/01 16:02:22 - mmengine - INFO - Epoch(train) [156][25/125] lr: 2.0000e-04 eta: 0:04:51 time: 0.4064 data_time: 0.0726 memory: 9775 loss: 0.4185 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0080 loss_cls: 0.0822 acc: 95.4590 loss_bbox: 0.1281 loss_mask: 0.1934 2022/11/01 16:02:24 - mmengine - INFO - Epoch(train) [156][30/125] lr: 2.0000e-04 eta: 0:04:46 time: 0.3852 data_time: 0.0561 memory: 9387 loss: 0.4325 loss_rpn_cls: 0.0062 loss_rpn_bbox: 0.0080 loss_cls: 0.0836 acc: 96.9971 loss_bbox: 0.1341 loss_mask: 0.2006 2022/11/01 16:02:26 - mmengine - INFO - Epoch(train) [156][35/125] lr: 2.0000e-04 eta: 0:04:46 time: 0.3948 data_time: 0.0593 memory: 9312 loss: 0.4107 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0082 loss_cls: 0.0816 acc: 96.5576 loss_bbox: 0.1118 loss_mask: 0.2015 2022/11/01 16:02:28 - mmengine - INFO - Epoch(train) [156][40/125] lr: 2.0000e-04 eta: 0:04:41 time: 0.4259 data_time: 0.0820 memory: 9272 loss: 0.4169 loss_rpn_cls: 0.0084 loss_rpn_bbox: 0.0092 loss_cls: 0.0789 acc: 96.8506 loss_bbox: 0.1099 loss_mask: 0.2106 2022/11/01 16:02:31 - mmengine - INFO - Epoch(train) [156][45/125] lr: 2.0000e-04 eta: 0:04:41 time: 0.4228 data_time: 0.0740 memory: 9429 loss: 0.4267 loss_rpn_cls: 0.0078 loss_rpn_bbox: 0.0092 loss_cls: 0.0762 acc: 97.6074 loss_bbox: 0.1209 loss_mask: 0.2126 2022/11/01 16:02:33 - mmengine - INFO - Epoch(train) [156][50/125] lr: 2.0000e-04 eta: 0:04:36 time: 0.4630 data_time: 0.1037 memory: 9097 loss: 0.4076 loss_rpn_cls: 0.0063 loss_rpn_bbox: 0.0077 loss_cls: 0.0739 acc: 97.9248 loss_bbox: 0.1127 loss_mask: 0.2070 2022/11/01 16:02:35 - mmengine - INFO - Epoch(train) [156][55/125] lr: 2.0000e-04 eta: 0:04:36 time: 0.4861 data_time: 0.1111 memory: 10765 loss: 0.4167 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0093 loss_cls: 0.0752 acc: 98.1445 loss_bbox: 0.1141 loss_mask: 0.2121 2022/11/01 16:02:38 - mmengine - INFO - Epoch(train) [156][60/125] lr: 2.0000e-04 eta: 0:04:31 time: 0.4491 data_time: 0.0856 memory: 9482 loss: 0.4580 loss_rpn_cls: 0.0078 loss_rpn_bbox: 0.0117 loss_cls: 0.0853 acc: 97.8271 loss_bbox: 0.1320 loss_mask: 0.2213 2022/11/01 16:02:40 - mmengine - INFO - Epoch(train) [156][65/125] lr: 2.0000e-04 eta: 0:04:31 time: 0.4643 data_time: 0.0963 memory: 9567 loss: 0.4797 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0121 loss_cls: 0.0942 acc: 96.0205 loss_bbox: 0.1373 loss_mask: 0.2280 2022/11/01 16:02:42 - mmengine - INFO - Epoch(train) [156][70/125] lr: 2.0000e-04 eta: 0:04:26 time: 0.4230 data_time: 0.0624 memory: 9433 loss: 0.4432 loss_rpn_cls: 0.0075 loss_rpn_bbox: 0.0116 loss_cls: 0.0887 acc: 96.4600 loss_bbox: 0.1280 loss_mask: 0.2073 2022/11/01 16:02:44 - mmengine - INFO - Epoch(train) [156][75/125] lr: 2.0000e-04 eta: 0:04:26 time: 0.4045 data_time: 0.0522 memory: 10863 loss: 0.4352 loss_rpn_cls: 0.0078 loss_rpn_bbox: 0.0108 loss_cls: 0.0856 acc: 98.3154 loss_bbox: 0.1279 loss_mask: 0.2030 2022/11/01 16:02:46 - mmengine - INFO - Epoch(train) [156][80/125] lr: 2.0000e-04 eta: 0:04:21 time: 0.4576 data_time: 0.0816 memory: 9838 loss: 0.4641 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0118 loss_cls: 0.0903 acc: 98.0957 loss_bbox: 0.1385 loss_mask: 0.2165 2022/11/01 16:02:49 - mmengine - INFO - Epoch(train) [156][85/125] lr: 2.0000e-04 eta: 0:04:21 time: 0.5023 data_time: 0.1015 memory: 11024 loss: 0.4552 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0136 loss_cls: 0.0918 acc: 96.7773 loss_bbox: 0.1408 loss_mask: 0.2009 2022/11/01 16:02:51 - mmengine - INFO - Epoch(train) [156][90/125] lr: 2.0000e-04 eta: 0:04:17 time: 0.4940 data_time: 0.0918 memory: 9880 loss: 0.4317 loss_rpn_cls: 0.0108 loss_rpn_bbox: 0.0119 loss_cls: 0.0890 acc: 95.2881 loss_bbox: 0.1380 loss_mask: 0.1819 2022/11/01 16:02:53 - mmengine - INFO - Epoch(train) [156][95/125] lr: 2.0000e-04 eta: 0:04:17 time: 0.4236 data_time: 0.0736 memory: 9701 loss: 0.4162 loss_rpn_cls: 0.0099 loss_rpn_bbox: 0.0110 loss_cls: 0.0797 acc: 96.3379 loss_bbox: 0.1263 loss_mask: 0.1893 2022/11/01 16:02:56 - mmengine - INFO - Epoch(train) [156][100/125] lr: 2.0000e-04 eta: 0:04:12 time: 0.4311 data_time: 0.0743 memory: 11093 loss: 0.4322 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0130 loss_cls: 0.0852 acc: 97.4121 loss_bbox: 0.1376 loss_mask: 0.1895 2022/11/01 16:02:58 - mmengine - INFO - Epoch(train) [156][105/125] lr: 2.0000e-04 eta: 0:04:12 time: 0.4194 data_time: 0.0612 memory: 9439 loss: 0.4055 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0129 loss_cls: 0.0817 acc: 97.1924 loss_bbox: 0.1295 loss_mask: 0.1741 2022/11/01 16:03:00 - mmengine - INFO - Epoch(train) [156][110/125] lr: 2.0000e-04 eta: 0:04:07 time: 0.4078 data_time: 0.0740 memory: 9749 loss: 0.4112 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0112 loss_cls: 0.0802 acc: 96.7041 loss_bbox: 0.1213 loss_mask: 0.1912 2022/11/01 16:03:02 - mmengine - INFO - Epoch(train) [156][115/125] lr: 2.0000e-04 eta: 0:04:07 time: 0.3971 data_time: 0.0714 memory: 9407 loss: 0.4440 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0098 loss_cls: 0.0862 acc: 96.1670 loss_bbox: 0.1349 loss_mask: 0.2049 2022/11/01 16:03:04 - mmengine - INFO - Epoch(train) [156][120/125] lr: 2.0000e-04 eta: 0:04:02 time: 0.3888 data_time: 0.0654 memory: 9564 loss: 0.4289 loss_rpn_cls: 0.0096 loss_rpn_bbox: 0.0096 loss_cls: 0.0830 acc: 96.6553 loss_bbox: 0.1323 loss_mask: 0.1944 2022/11/01 16:03:05 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 16:03:05 - mmengine - INFO - Epoch(train) [156][125/125] lr: 2.0000e-04 eta: 0:04:02 time: 0.3810 data_time: 0.0489 memory: 9592 loss: 0.4253 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0085 loss_cls: 0.0796 acc: 97.3145 loss_bbox: 0.1267 loss_mask: 0.2034 2022/11/01 16:03:09 - mmengine - INFO - Epoch(train) [157][5/125] lr: 2.0000e-04 eta: 0:04:02 time: 0.5169 data_time: 0.1727 memory: 9472 loss: 0.4182 loss_rpn_cls: 0.0058 loss_rpn_bbox: 0.0082 loss_cls: 0.0730 acc: 97.7295 loss_bbox: 0.1220 loss_mask: 0.2092 2022/11/01 16:03:11 - mmengine - INFO - Epoch(train) [157][10/125] lr: 2.0000e-04 eta: 0:03:54 time: 0.5298 data_time: 0.1725 memory: 9618 loss: 0.4381 loss_rpn_cls: 0.0085 loss_rpn_bbox: 0.0098 loss_cls: 0.0809 acc: 96.3623 loss_bbox: 0.1302 loss_mask: 0.2087 2022/11/01 16:03:14 - mmengine - INFO - Epoch(train) [157][15/125] lr: 2.0000e-04 eta: 0:03:54 time: 0.5147 data_time: 0.1439 memory: 9390 loss: 0.4325 loss_rpn_cls: 0.0098 loss_rpn_bbox: 0.0114 loss_cls: 0.0792 acc: 97.6318 loss_bbox: 0.1226 loss_mask: 0.2095 2022/11/01 16:03:16 - mmengine - INFO - Epoch(train) [157][20/125] lr: 2.0000e-04 eta: 0:03:49 time: 0.5309 data_time: 0.1680 memory: 9759 loss: 0.4359 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0200 loss_cls: 0.0785 acc: 95.3125 loss_bbox: 0.1264 loss_mask: 0.2027 2022/11/01 16:03:18 - mmengine - INFO - Epoch(train) [157][25/125] lr: 2.0000e-04 eta: 0:03:49 time: 0.3988 data_time: 0.0517 memory: 10108 loss: 0.4631 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0201 loss_cls: 0.0912 acc: 96.5576 loss_bbox: 0.1510 loss_mask: 0.1933 2022/11/01 16:03:20 - mmengine - INFO - Epoch(train) [157][30/125] lr: 2.0000e-04 eta: 0:03:44 time: 0.3809 data_time: 0.0441 memory: 9342 loss: 0.4447 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0092 loss_cls: 0.0902 acc: 97.3389 loss_bbox: 0.1320 loss_mask: 0.2066 2022/11/01 16:03:22 - mmengine - INFO - Epoch(train) [157][35/125] lr: 2.0000e-04 eta: 0:03:44 time: 0.3932 data_time: 0.0638 memory: 9733 loss: 0.4426 loss_rpn_cls: 0.0063 loss_rpn_bbox: 0.0087 loss_cls: 0.0867 acc: 97.0947 loss_bbox: 0.1217 loss_mask: 0.2192 2022/11/01 16:03:24 - mmengine - INFO - Epoch(train) [157][40/125] lr: 2.0000e-04 eta: 0:03:39 time: 0.3869 data_time: 0.0667 memory: 9403 loss: 0.4568 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0089 loss_cls: 0.0868 acc: 95.5566 loss_bbox: 0.1309 loss_mask: 0.2233 2022/11/01 16:03:26 - mmengine - INFO - Epoch(train) [157][45/125] lr: 2.0000e-04 eta: 0:03:39 time: 0.3839 data_time: 0.0635 memory: 9560 loss: 0.4525 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0108 loss_cls: 0.0855 acc: 97.2168 loss_bbox: 0.1286 loss_mask: 0.2190 2022/11/01 16:03:28 - mmengine - INFO - Epoch(train) [157][50/125] lr: 2.0000e-04 eta: 0:03:34 time: 0.3918 data_time: 0.0566 memory: 9188 loss: 0.3926 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0111 loss_cls: 0.0732 acc: 97.2168 loss_bbox: 0.1092 loss_mask: 0.1912 2022/11/01 16:03:30 - mmengine - INFO - Epoch(train) [157][55/125] lr: 2.0000e-04 eta: 0:03:34 time: 0.4586 data_time: 0.1237 memory: 10318 loss: 0.4113 loss_rpn_cls: 0.0098 loss_rpn_bbox: 0.0108 loss_cls: 0.0822 acc: 96.5820 loss_bbox: 0.1176 loss_mask: 0.1910 2022/11/01 16:03:33 - mmengine - INFO - Epoch(train) [157][60/125] lr: 2.0000e-04 eta: 0:03:30 time: 0.5287 data_time: 0.1845 memory: 9446 loss: 0.4178 loss_rpn_cls: 0.0102 loss_rpn_bbox: 0.0110 loss_cls: 0.0815 acc: 97.7051 loss_bbox: 0.1244 loss_mask: 0.1907 2022/11/01 16:03:35 - mmengine - INFO - Epoch(train) [157][65/125] lr: 2.0000e-04 eta: 0:03:30 time: 0.4587 data_time: 0.1257 memory: 9559 loss: 0.4009 loss_rpn_cls: 0.0078 loss_rpn_bbox: 0.0083 loss_cls: 0.0719 acc: 98.1445 loss_bbox: 0.1171 loss_mask: 0.1958 2022/11/01 16:03:37 - mmengine - INFO - Epoch(train) [157][70/125] lr: 2.0000e-04 eta: 0:03:25 time: 0.3834 data_time: 0.0673 memory: 9694 loss: 0.4336 loss_rpn_cls: 0.0071 loss_rpn_bbox: 0.0078 loss_cls: 0.0827 acc: 96.9727 loss_bbox: 0.1349 loss_mask: 0.2011 2022/11/01 16:03:39 - mmengine - INFO - Epoch(train) [157][75/125] lr: 2.0000e-04 eta: 0:03:25 time: 0.3643 data_time: 0.0458 memory: 9691 loss: 0.4075 loss_rpn_cls: 0.0048 loss_rpn_bbox: 0.0074 loss_cls: 0.0756 acc: 97.1436 loss_bbox: 0.1316 loss_mask: 0.1880 2022/11/01 16:03:40 - mmengine - INFO - Epoch(train) [157][80/125] lr: 2.0000e-04 eta: 0:03:20 time: 0.3715 data_time: 0.0538 memory: 9893 loss: 0.4340 loss_rpn_cls: 0.0078 loss_rpn_bbox: 0.0105 loss_cls: 0.0812 acc: 96.5820 loss_bbox: 0.1374 loss_mask: 0.1970 2022/11/01 16:03:42 - mmengine - INFO - Epoch(train) [157][85/125] lr: 2.0000e-04 eta: 0:03:20 time: 0.3719 data_time: 0.0493 memory: 9345 loss: 0.4238 loss_rpn_cls: 0.0122 loss_rpn_bbox: 0.0106 loss_cls: 0.0838 acc: 98.3154 loss_bbox: 0.1248 loss_mask: 0.1924 2022/11/01 16:03:44 - mmengine - INFO - Epoch(train) [157][90/125] lr: 2.0000e-04 eta: 0:03:15 time: 0.3724 data_time: 0.0525 memory: 9560 loss: 0.4089 loss_rpn_cls: 0.0114 loss_rpn_bbox: 0.0086 loss_cls: 0.0804 acc: 97.0947 loss_bbox: 0.1126 loss_mask: 0.1959 2022/11/01 16:03:46 - mmengine - INFO - Epoch(train) [157][95/125] lr: 2.0000e-04 eta: 0:03:15 time: 0.4042 data_time: 0.0627 memory: 10867 loss: 0.4689 loss_rpn_cls: 0.0088 loss_rpn_bbox: 0.0117 loss_cls: 0.0933 acc: 94.3115 loss_bbox: 0.1458 loss_mask: 0.2092 2022/11/01 16:03:48 - mmengine - INFO - Epoch(train) [157][100/125] lr: 2.0000e-04 eta: 0:03:10 time: 0.4047 data_time: 0.0597 memory: 9442 loss: 0.4480 loss_rpn_cls: 0.0076 loss_rpn_bbox: 0.0115 loss_cls: 0.0884 acc: 95.6299 loss_bbox: 0.1440 loss_mask: 0.1965 2022/11/01 16:03:50 - mmengine - INFO - Epoch(train) [157][105/125] lr: 2.0000e-04 eta: 0:03:10 time: 0.3692 data_time: 0.0538 memory: 9413 loss: 0.3983 loss_rpn_cls: 0.0068 loss_rpn_bbox: 0.0081 loss_cls: 0.0767 acc: 96.9482 loss_bbox: 0.1158 loss_mask: 0.1909 2022/11/01 16:03:53 - mmengine - INFO - Epoch(train) [157][110/125] lr: 2.0000e-04 eta: 0:03:05 time: 0.4527 data_time: 0.1252 memory: 9136 loss: 0.4056 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0079 loss_cls: 0.0788 acc: 95.4834 loss_bbox: 0.1074 loss_mask: 0.2046 2022/11/01 16:03:55 - mmengine - INFO - Epoch(train) [157][115/125] lr: 2.0000e-04 eta: 0:03:05 time: 0.4912 data_time: 0.1630 memory: 9590 loss: 0.4442 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0085 loss_cls: 0.0880 acc: 96.8750 loss_bbox: 0.1169 loss_mask: 0.2226 2022/11/01 16:03:57 - mmengine - INFO - Epoch(train) [157][120/125] lr: 2.0000e-04 eta: 0:03:00 time: 0.3827 data_time: 0.0644 memory: 9479 loss: 0.4334 loss_rpn_cls: 0.0075 loss_rpn_bbox: 0.0101 loss_cls: 0.0850 acc: 97.4609 loss_bbox: 0.1231 loss_mask: 0.2077 2022/11/01 16:03:58 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 16:03:58 - mmengine - INFO - Epoch(train) [157][125/125] lr: 2.0000e-04 eta: 0:03:00 time: 0.3267 data_time: 0.0131 memory: 9648 loss: 0.3880 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0093 loss_cls: 0.0736 acc: 97.9004 loss_bbox: 0.1169 loss_mask: 0.1810 2022/11/01 16:04:02 - mmengine - INFO - Epoch(train) [158][5/125] lr: 2.0000e-04 eta: 0:03:00 time: 0.5396 data_time: 0.2369 memory: 9187 loss: 0.3803 loss_rpn_cls: 0.0063 loss_rpn_bbox: 0.0073 loss_cls: 0.0694 acc: 96.6309 loss_bbox: 0.1087 loss_mask: 0.1885 2022/11/01 16:04:04 - mmengine - INFO - Epoch(train) [158][10/125] lr: 2.0000e-04 eta: 0:02:53 time: 0.5378 data_time: 0.2346 memory: 9769 loss: 0.3892 loss_rpn_cls: 0.0050 loss_rpn_bbox: 0.0083 loss_cls: 0.0706 acc: 96.6797 loss_bbox: 0.1146 loss_mask: 0.1907 2022/11/01 16:04:05 - mmengine - INFO - Epoch(train) [158][15/125] lr: 2.0000e-04 eta: 0:02:53 time: 0.3269 data_time: 0.0176 memory: 9413 loss: 0.4083 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0098 loss_cls: 0.0752 acc: 96.5088 loss_bbox: 0.1240 loss_mask: 0.1904 2022/11/01 16:04:07 - mmengine - INFO - Epoch(train) [158][20/125] lr: 2.0000e-04 eta: 0:02:48 time: 0.3544 data_time: 0.0402 memory: 9596 loss: 0.4170 loss_rpn_cls: 0.0106 loss_rpn_bbox: 0.0097 loss_cls: 0.0792 acc: 95.6543 loss_bbox: 0.1244 loss_mask: 0.1931 2022/11/01 16:04:09 - mmengine - INFO - Epoch(train) [158][25/125] lr: 2.0000e-04 eta: 0:02:48 time: 0.3769 data_time: 0.0630 memory: 9740 loss: 0.4048 loss_rpn_cls: 0.0079 loss_rpn_bbox: 0.0091 loss_cls: 0.0775 acc: 97.0459 loss_bbox: 0.1196 loss_mask: 0.1907 2022/11/01 16:04:11 - mmengine - INFO - Epoch(train) [158][30/125] lr: 2.0000e-04 eta: 0:02:43 time: 0.3982 data_time: 0.0871 memory: 9508 loss: 0.4034 loss_rpn_cls: 0.0065 loss_rpn_bbox: 0.0105 loss_cls: 0.0738 acc: 97.5586 loss_bbox: 0.1185 loss_mask: 0.1940 2022/11/01 16:04:13 - mmengine - INFO - Epoch(train) [158][35/125] lr: 2.0000e-04 eta: 0:02:43 time: 0.3711 data_time: 0.0603 memory: 9312 loss: 0.3889 loss_rpn_cls: 0.0059 loss_rpn_bbox: 0.0098 loss_cls: 0.0683 acc: 97.4609 loss_bbox: 0.1143 loss_mask: 0.1906 2022/11/01 16:04:15 - mmengine - INFO - Epoch(train) [158][40/125] lr: 2.0000e-04 eta: 0:02:38 time: 0.3429 data_time: 0.0336 memory: 9158 loss: 0.3768 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0077 loss_cls: 0.0689 acc: 95.2637 loss_bbox: 0.1017 loss_mask: 0.1912 2022/11/01 16:04:17 - mmengine - INFO - Epoch(train) [158][45/125] lr: 2.0000e-04 eta: 0:02:38 time: 0.3939 data_time: 0.0584 memory: 10816 loss: 0.4101 loss_rpn_cls: 0.0112 loss_rpn_bbox: 0.0105 loss_cls: 0.0786 acc: 95.0928 loss_bbox: 0.1150 loss_mask: 0.1947 2022/11/01 16:04:18 - mmengine - INFO - Epoch(train) [158][50/125] lr: 2.0000e-04 eta: 0:02:33 time: 0.3917 data_time: 0.0533 memory: 9426 loss: 0.4270 loss_rpn_cls: 0.0112 loss_rpn_bbox: 0.0105 loss_cls: 0.0781 acc: 97.0459 loss_bbox: 0.1211 loss_mask: 0.2061 2022/11/01 16:04:20 - mmengine - INFO - Epoch(train) [158][55/125] lr: 2.0000e-04 eta: 0:02:33 time: 0.3581 data_time: 0.0436 memory: 9567 loss: 0.4265 loss_rpn_cls: 0.0091 loss_rpn_bbox: 0.0088 loss_cls: 0.0781 acc: 97.9004 loss_bbox: 0.1194 loss_mask: 0.2110 2022/11/01 16:04:22 - mmengine - INFO - Epoch(train) [158][60/125] lr: 2.0000e-04 eta: 0:02:28 time: 0.3728 data_time: 0.0575 memory: 9514 loss: 0.4248 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0097 loss_cls: 0.0848 acc: 96.9971 loss_bbox: 0.1235 loss_mask: 0.1983 2022/11/01 16:04:25 - mmengine - INFO - Epoch(train) [158][65/125] lr: 2.0000e-04 eta: 0:02:28 time: 0.5106 data_time: 0.1778 memory: 10525 loss: 0.4173 loss_rpn_cls: 0.0074 loss_rpn_bbox: 0.0097 loss_cls: 0.0840 acc: 97.2412 loss_bbox: 0.1234 loss_mask: 0.1930 2022/11/01 16:04:27 - mmengine - INFO - Epoch(train) [158][70/125] lr: 2.0000e-04 eta: 0:02:24 time: 0.5011 data_time: 0.1475 memory: 9707 loss: 0.4249 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0095 loss_cls: 0.0833 acc: 96.7041 loss_bbox: 0.1279 loss_mask: 0.1970 2022/11/01 16:04:30 - mmengine - INFO - Epoch(train) [158][75/125] lr: 2.0000e-04 eta: 0:02:24 time: 0.4385 data_time: 0.0420 memory: 9752 loss: 0.4304 loss_rpn_cls: 0.0063 loss_rpn_bbox: 0.0098 loss_cls: 0.0831 acc: 97.7051 loss_bbox: 0.1359 loss_mask: 0.1953 2022/11/01 16:04:32 - mmengine - INFO - Epoch(train) [158][80/125] lr: 2.0000e-04 eta: 0:02:19 time: 0.4469 data_time: 0.0618 memory: 9501 loss: 0.4375 loss_rpn_cls: 0.0095 loss_rpn_bbox: 0.0118 loss_cls: 0.0816 acc: 97.8271 loss_bbox: 0.1314 loss_mask: 0.2033 2022/11/01 16:04:34 - mmengine - INFO - Epoch(train) [158][85/125] lr: 2.0000e-04 eta: 0:02:19 time: 0.3906 data_time: 0.0609 memory: 9658 loss: 0.4236 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0114 loss_cls: 0.0804 acc: 97.2412 loss_bbox: 0.1215 loss_mask: 0.2006 2022/11/01 16:04:35 - mmengine - INFO - Epoch(train) [158][90/125] lr: 2.0000e-04 eta: 0:02:14 time: 0.3862 data_time: 0.0570 memory: 9701 loss: 0.4146 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0102 loss_cls: 0.0815 acc: 97.4121 loss_bbox: 0.1302 loss_mask: 0.1855 2022/11/01 16:04:37 - mmengine - INFO - Epoch(train) [158][95/125] lr: 2.0000e-04 eta: 0:02:14 time: 0.3735 data_time: 0.0383 memory: 9414 loss: 0.4198 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0102 loss_cls: 0.0813 acc: 96.5332 loss_bbox: 0.1313 loss_mask: 0.1901 2022/11/01 16:04:39 - mmengine - INFO - Epoch(train) [158][100/125] lr: 2.0000e-04 eta: 0:02:09 time: 0.3686 data_time: 0.0447 memory: 9710 loss: 0.4673 loss_rpn_cls: 0.0089 loss_rpn_bbox: 0.0103 loss_cls: 0.0964 acc: 98.0225 loss_bbox: 0.1425 loss_mask: 0.2091 2022/11/01 16:04:41 - mmengine - INFO - Epoch(train) [158][105/125] lr: 2.0000e-04 eta: 0:02:09 time: 0.4092 data_time: 0.0780 memory: 10561 loss: 0.4667 loss_rpn_cls: 0.0092 loss_rpn_bbox: 0.0092 loss_cls: 0.0987 acc: 97.0215 loss_bbox: 0.1418 loss_mask: 0.2078 2022/11/01 16:04:43 - mmengine - INFO - Epoch(train) [158][110/125] lr: 2.0000e-04 eta: 0:02:04 time: 0.4105 data_time: 0.0733 memory: 9723 loss: 0.4574 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0106 loss_cls: 0.0917 acc: 96.1914 loss_bbox: 0.1358 loss_mask: 0.2096 2022/11/01 16:04:45 - mmengine - INFO - Epoch(train) [158][115/125] lr: 2.0000e-04 eta: 0:02:04 time: 0.3694 data_time: 0.0437 memory: 9798 loss: 0.4837 loss_rpn_cls: 0.0119 loss_rpn_bbox: 0.0147 loss_cls: 0.0992 acc: 94.6533 loss_bbox: 0.1430 loss_mask: 0.2149 2022/11/01 16:04:48 - mmengine - INFO - Epoch(train) [158][120/125] lr: 2.0000e-04 eta: 0:02:00 time: 0.4484 data_time: 0.0944 memory: 10931 loss: 0.4574 loss_rpn_cls: 0.0100 loss_rpn_bbox: 0.0122 loss_cls: 0.0964 acc: 94.6289 loss_bbox: 0.1405 loss_mask: 0.1982 2022/11/01 16:04:50 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 16:04:50 - mmengine - INFO - Epoch(train) [158][125/125] lr: 2.0000e-04 eta: 0:02:00 time: 0.4388 data_time: 0.0799 memory: 9769 loss: 0.4454 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0113 loss_cls: 0.0916 acc: 96.1670 loss_bbox: 0.1447 loss_mask: 0.1897 2022/11/01 16:04:53 - mmengine - INFO - Epoch(train) [159][5/125] lr: 2.0000e-04 eta: 0:02:00 time: 0.5373 data_time: 0.1830 memory: 10812 loss: 0.4318 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0123 loss_cls: 0.0828 acc: 97.0215 loss_bbox: 0.1396 loss_mask: 0.1909 2022/11/01 16:04:55 - mmengine - INFO - Epoch(train) [159][10/125] lr: 2.0000e-04 eta: 0:01:52 time: 0.5693 data_time: 0.2071 memory: 9776 loss: 0.4328 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0106 loss_cls: 0.0839 acc: 96.4844 loss_bbox: 0.1317 loss_mask: 0.2000 2022/11/01 16:04:58 - mmengine - INFO - Epoch(train) [159][15/125] lr: 2.0000e-04 eta: 0:01:52 time: 0.4889 data_time: 0.1135 memory: 10530 loss: 0.4613 loss_rpn_cls: 0.0070 loss_rpn_bbox: 0.0112 loss_cls: 0.0942 acc: 95.5078 loss_bbox: 0.1433 loss_mask: 0.2057 2022/11/01 16:05:00 - mmengine - INFO - Epoch(train) [159][20/125] lr: 2.0000e-04 eta: 0:01:48 time: 0.4942 data_time: 0.1118 memory: 9619 loss: 0.4495 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0102 loss_cls: 0.0888 acc: 96.7041 loss_bbox: 0.1357 loss_mask: 0.2080 2022/11/01 16:05:02 - mmengine - INFO - Epoch(train) [159][25/125] lr: 2.0000e-04 eta: 0:01:48 time: 0.4131 data_time: 0.0634 memory: 9628 loss: 0.4379 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0096 loss_cls: 0.0838 acc: 96.4355 loss_bbox: 0.1305 loss_mask: 0.2058 2022/11/01 16:05:04 - mmengine - INFO - Epoch(train) [159][30/125] lr: 2.0000e-04 eta: 0:01:43 time: 0.3810 data_time: 0.0555 memory: 9660 loss: 0.4461 loss_rpn_cls: 0.0100 loss_rpn_bbox: 0.0125 loss_cls: 0.0855 acc: 96.6553 loss_bbox: 0.1286 loss_mask: 0.2095 2022/11/01 16:05:07 - mmengine - INFO - Epoch(train) [159][35/125] lr: 2.0000e-04 eta: 0:01:43 time: 0.4602 data_time: 0.1196 memory: 9455 loss: 0.4301 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0116 loss_cls: 0.0837 acc: 97.0459 loss_bbox: 0.1139 loss_mask: 0.2113 2022/11/01 16:05:09 - mmengine - INFO - Epoch(train) [159][40/125] lr: 2.0000e-04 eta: 0:01:38 time: 0.5122 data_time: 0.1375 memory: 9313 loss: 0.4197 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0087 loss_cls: 0.0846 acc: 97.2900 loss_bbox: 0.1208 loss_mask: 0.1978 2022/11/01 16:05:11 - mmengine - INFO - Epoch(train) [159][45/125] lr: 2.0000e-04 eta: 0:01:38 time: 0.4546 data_time: 0.0608 memory: 9655 loss: 0.3979 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0084 loss_cls: 0.0771 acc: 96.8750 loss_bbox: 0.1205 loss_mask: 0.1852 2022/11/01 16:05:14 - mmengine - INFO - Epoch(train) [159][50/125] lr: 2.0000e-04 eta: 0:01:34 time: 0.4613 data_time: 0.0718 memory: 9416 loss: 0.4074 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0098 loss_cls: 0.0775 acc: 96.4844 loss_bbox: 0.1241 loss_mask: 0.1883 2022/11/01 16:05:16 - mmengine - INFO - Epoch(train) [159][55/125] lr: 2.0000e-04 eta: 0:01:34 time: 0.4411 data_time: 0.0754 memory: 9834 loss: 0.4627 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0116 loss_cls: 0.0946 acc: 93.7744 loss_bbox: 0.1454 loss_mask: 0.2030 2022/11/01 16:05:18 - mmengine - INFO - Epoch(train) [159][60/125] lr: 2.0000e-04 eta: 0:01:29 time: 0.4673 data_time: 0.1107 memory: 9877 loss: 0.4542 loss_rpn_cls: 0.0072 loss_rpn_bbox: 0.0115 loss_cls: 0.0936 acc: 97.9004 loss_bbox: 0.1481 loss_mask: 0.1939 2022/11/01 16:05:20 - mmengine - INFO - Epoch(train) [159][65/125] lr: 2.0000e-04 eta: 0:01:29 time: 0.4664 data_time: 0.1031 memory: 9704 loss: 0.4047 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0119 loss_cls: 0.0782 acc: 96.3623 loss_bbox: 0.1230 loss_mask: 0.1852 2022/11/01 16:05:22 - mmengine - INFO - Epoch(train) [159][70/125] lr: 2.0000e-04 eta: 0:01:24 time: 0.3935 data_time: 0.0501 memory: 9730 loss: 0.4102 loss_rpn_cls: 0.0061 loss_rpn_bbox: 0.0124 loss_cls: 0.0804 acc: 97.3389 loss_bbox: 0.1221 loss_mask: 0.1892 2022/11/01 16:05:24 - mmengine - INFO - Epoch(train) [159][75/125] lr: 2.0000e-04 eta: 0:01:24 time: 0.4021 data_time: 0.0681 memory: 9714 loss: 0.4361 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0105 loss_cls: 0.0859 acc: 95.8496 loss_bbox: 0.1332 loss_mask: 0.1996 2022/11/01 16:05:26 - mmengine - INFO - Epoch(train) [159][80/125] lr: 2.0000e-04 eta: 0:01:19 time: 0.3910 data_time: 0.0521 memory: 9534 loss: 0.3932 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0079 loss_cls: 0.0727 acc: 96.8994 loss_bbox: 0.1067 loss_mask: 0.1985 2022/11/01 16:05:28 - mmengine - INFO - Epoch(train) [159][85/125] lr: 2.0000e-04 eta: 0:01:19 time: 0.4009 data_time: 0.0712 memory: 9719 loss: 0.3968 loss_rpn_cls: 0.0081 loss_rpn_bbox: 0.0075 loss_cls: 0.0781 acc: 94.2139 loss_bbox: 0.1075 loss_mask: 0.1956 2022/11/01 16:05:31 - mmengine - INFO - Epoch(train) [159][90/125] lr: 2.0000e-04 eta: 0:01:15 time: 0.4285 data_time: 0.0886 memory: 9619 loss: 0.4387 loss_rpn_cls: 0.0069 loss_rpn_bbox: 0.0079 loss_cls: 0.0877 acc: 97.5830 loss_bbox: 0.1314 loss_mask: 0.2048 2022/11/01 16:05:33 - mmengine - INFO - Epoch(train) [159][95/125] lr: 2.0000e-04 eta: 0:01:15 time: 0.4180 data_time: 0.0651 memory: 9283 loss: 0.3939 loss_rpn_cls: 0.0053 loss_rpn_bbox: 0.0078 loss_cls: 0.0723 acc: 98.2178 loss_bbox: 0.1171 loss_mask: 0.1915 2022/11/01 16:05:35 - mmengine - INFO - Epoch(train) [159][100/125] lr: 2.0000e-04 eta: 0:01:10 time: 0.4238 data_time: 0.0793 memory: 9616 loss: 0.3850 loss_rpn_cls: 0.0058 loss_rpn_bbox: 0.0112 loss_cls: 0.0697 acc: 97.3633 loss_bbox: 0.1107 loss_mask: 0.1878 2022/11/01 16:05:37 - mmengine - INFO - Epoch(train) [159][105/125] lr: 2.0000e-04 eta: 0:01:10 time: 0.4545 data_time: 0.1114 memory: 10138 loss: 0.4672 loss_rpn_cls: 0.0124 loss_rpn_bbox: 0.0169 loss_cls: 0.0900 acc: 96.9238 loss_bbox: 0.1384 loss_mask: 0.2095 2022/11/01 16:05:39 - mmengine - INFO - Epoch(train) [159][110/125] lr: 2.0000e-04 eta: 0:01:05 time: 0.4630 data_time: 0.1260 memory: 9348 loss: 0.4673 loss_rpn_cls: 0.0124 loss_rpn_bbox: 0.0139 loss_cls: 0.0894 acc: 96.8262 loss_bbox: 0.1329 loss_mask: 0.2187 2022/11/01 16:05:41 - mmengine - INFO - Epoch(train) [159][115/125] lr: 2.0000e-04 eta: 0:01:05 time: 0.4072 data_time: 0.0776 memory: 10067 loss: 0.4380 loss_rpn_cls: 0.0087 loss_rpn_bbox: 0.0092 loss_cls: 0.0858 acc: 97.0459 loss_bbox: 0.1282 loss_mask: 0.2060 2022/11/01 16:05:43 - mmengine - INFO - Epoch(train) [159][120/125] lr: 2.0000e-04 eta: 0:01:00 time: 0.3834 data_time: 0.0285 memory: 9592 loss: 0.4383 loss_rpn_cls: 0.0107 loss_rpn_bbox: 0.0104 loss_cls: 0.0910 acc: 97.4609 loss_bbox: 0.1370 loss_mask: 0.1891 2022/11/01 16:05:45 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 16:05:45 - mmengine - INFO - Epoch(train) [159][125/125] lr: 2.0000e-04 eta: 0:01:00 time: 0.3604 data_time: 0.0195 memory: 9894 loss: 0.4114 loss_rpn_cls: 0.0101 loss_rpn_bbox: 0.0111 loss_cls: 0.0806 acc: 97.3145 loss_bbox: 0.1184 loss_mask: 0.1912 2022/11/01 16:05:49 - mmengine - INFO - Epoch(train) [160][5/125] lr: 2.0000e-04 eta: 0:01:00 time: 0.5227 data_time: 0.1909 memory: 9512 loss: 0.3986 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0105 loss_cls: 0.0762 acc: 96.8262 loss_bbox: 0.1118 loss_mask: 0.1924 2022/11/01 16:05:52 - mmengine - INFO - Epoch(train) [160][10/125] lr: 2.0000e-04 eta: 0:00:53 time: 0.6666 data_time: 0.2625 memory: 11382 loss: 0.4247 loss_rpn_cls: 0.0100 loss_rpn_bbox: 0.0111 loss_cls: 0.0851 acc: 96.2402 loss_bbox: 0.1273 loss_mask: 0.1912 2022/11/01 16:05:54 - mmengine - INFO - Epoch(train) [160][15/125] lr: 2.0000e-04 eta: 0:00:53 time: 0.5072 data_time: 0.0949 memory: 9129 loss: 0.4167 loss_rpn_cls: 0.0137 loss_rpn_bbox: 0.0114 loss_cls: 0.0792 acc: 98.2666 loss_bbox: 0.1188 loss_mask: 0.1936 2022/11/01 16:05:55 - mmengine - INFO - Epoch(train) [160][20/125] lr: 2.0000e-04 eta: 0:00:49 time: 0.3838 data_time: 0.0399 memory: 9429 loss: 0.3997 loss_rpn_cls: 0.0093 loss_rpn_bbox: 0.0098 loss_cls: 0.0732 acc: 96.5820 loss_bbox: 0.1081 loss_mask: 0.1994 2022/11/01 16:05:58 - mmengine - INFO - Epoch(train) [160][25/125] lr: 2.0000e-04 eta: 0:00:49 time: 0.4769 data_time: 0.1326 memory: 11330 loss: 0.4651 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0092 loss_cls: 0.0965 acc: 93.4082 loss_bbox: 0.1408 loss_mask: 0.2113 2022/11/01 16:06:00 - mmengine - INFO - Epoch(train) [160][30/125] lr: 2.0000e-04 eta: 0:00:44 time: 0.4835 data_time: 0.1408 memory: 9244 loss: 0.4231 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0083 loss_cls: 0.0869 acc: 96.7041 loss_bbox: 0.1215 loss_mask: 0.1987 2022/11/01 16:06:02 - mmengine - INFO - Epoch(train) [160][35/125] lr: 2.0000e-04 eta: 0:00:44 time: 0.3814 data_time: 0.0568 memory: 9224 loss: 0.3579 loss_rpn_cls: 0.0060 loss_rpn_bbox: 0.0069 loss_cls: 0.0657 acc: 97.7295 loss_bbox: 0.0906 loss_mask: 0.1886 2022/11/01 16:06:04 - mmengine - INFO - Epoch(train) [160][40/125] lr: 2.0000e-04 eta: 0:00:39 time: 0.3859 data_time: 0.0631 memory: 9316 loss: 0.3920 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0078 loss_cls: 0.0724 acc: 96.5576 loss_bbox: 0.1110 loss_mask: 0.1945 2022/11/01 16:06:06 - mmengine - INFO - Epoch(train) [160][45/125] lr: 2.0000e-04 eta: 0:00:39 time: 0.4047 data_time: 0.0590 memory: 10696 loss: 0.4206 loss_rpn_cls: 0.0062 loss_rpn_bbox: 0.0106 loss_cls: 0.0824 acc: 96.4355 loss_bbox: 0.1327 loss_mask: 0.1887 2022/11/01 16:06:08 - mmengine - INFO - Epoch(train) [160][50/125] lr: 2.0000e-04 eta: 0:00:35 time: 0.4081 data_time: 0.0624 memory: 9387 loss: 0.4101 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0108 loss_cls: 0.0833 acc: 97.9248 loss_bbox: 0.1264 loss_mask: 0.1828 2022/11/01 16:06:10 - mmengine - INFO - Epoch(train) [160][55/125] lr: 2.0000e-04 eta: 0:00:35 time: 0.3727 data_time: 0.0647 memory: 9830 loss: 0.3993 loss_rpn_cls: 0.0064 loss_rpn_bbox: 0.0116 loss_cls: 0.0757 acc: 96.9482 loss_bbox: 0.1176 loss_mask: 0.1879 2022/11/01 16:06:12 - mmengine - INFO - Epoch(train) [160][60/125] lr: 2.0000e-04 eta: 0:00:30 time: 0.3755 data_time: 0.0512 memory: 9566 loss: 0.4298 loss_rpn_cls: 0.0080 loss_rpn_bbox: 0.0116 loss_cls: 0.0790 acc: 95.4102 loss_bbox: 0.1252 loss_mask: 0.2060 2022/11/01 16:06:14 - mmengine - INFO - Epoch(train) [160][65/125] lr: 2.0000e-04 eta: 0:00:30 time: 0.4318 data_time: 0.0678 memory: 10631 loss: 0.4497 loss_rpn_cls: 0.0083 loss_rpn_bbox: 0.0123 loss_cls: 0.0861 acc: 96.5576 loss_bbox: 0.1329 loss_mask: 0.2101 2022/11/01 16:06:16 - mmengine - INFO - Epoch(train) [160][70/125] lr: 2.0000e-04 eta: 0:00:25 time: 0.4538 data_time: 0.0765 memory: 10798 loss: 0.4661 loss_rpn_cls: 0.0086 loss_rpn_bbox: 0.0135 loss_cls: 0.0929 acc: 97.7783 loss_bbox: 0.1466 loss_mask: 0.2043 2022/11/01 16:06:19 - mmengine - INFO - Epoch(train) [160][75/125] lr: 2.0000e-04 eta: 0:00:25 time: 0.4242 data_time: 0.0833 memory: 9309 loss: 0.4267 loss_rpn_cls: 0.0085 loss_rpn_bbox: 0.0089 loss_cls: 0.0797 acc: 97.9492 loss_bbox: 0.1228 loss_mask: 0.2068 2022/11/01 16:06:20 - mmengine - INFO - Epoch(train) [160][80/125] lr: 2.0000e-04 eta: 0:00:21 time: 0.4026 data_time: 0.0895 memory: 9808 loss: 0.3938 loss_rpn_cls: 0.0053 loss_rpn_bbox: 0.0084 loss_cls: 0.0691 acc: 97.3633 loss_bbox: 0.1148 loss_mask: 0.1963 2022/11/01 16:06:22 - mmengine - INFO - Epoch(train) [160][85/125] lr: 2.0000e-04 eta: 0:00:21 time: 0.3805 data_time: 0.0668 memory: 9332 loss: 0.4171 loss_rpn_cls: 0.0053 loss_rpn_bbox: 0.0124 loss_cls: 0.0744 acc: 97.1680 loss_bbox: 0.1281 loss_mask: 0.1970 2022/11/01 16:06:24 - mmengine - INFO - Epoch(train) [160][90/125] lr: 2.0000e-04 eta: 0:00:16 time: 0.3950 data_time: 0.0730 memory: 9388 loss: 0.3897 loss_rpn_cls: 0.0053 loss_rpn_bbox: 0.0109 loss_cls: 0.0652 acc: 98.0713 loss_bbox: 0.1102 loss_mask: 0.1981 2022/11/01 16:06:27 - mmengine - INFO - Epoch(train) [160][95/125] lr: 2.0000e-04 eta: 0:00:16 time: 0.4611 data_time: 0.1176 memory: 9430 loss: 0.3833 loss_rpn_cls: 0.0067 loss_rpn_bbox: 0.0079 loss_cls: 0.0683 acc: 95.9473 loss_bbox: 0.1053 loss_mask: 0.1952 2022/11/01 16:06:29 - mmengine - INFO - Epoch(train) [160][100/125] lr: 2.0000e-04 eta: 0:00:11 time: 0.4304 data_time: 0.0897 memory: 9759 loss: 0.4062 loss_rpn_cls: 0.0082 loss_rpn_bbox: 0.0104 loss_cls: 0.0782 acc: 97.5586 loss_bbox: 0.1060 loss_mask: 0.2034 2022/11/01 16:06:31 - mmengine - INFO - Epoch(train) [160][105/125] lr: 2.0000e-04 eta: 0:00:11 time: 0.3820 data_time: 0.0534 memory: 9404 loss: 0.4301 loss_rpn_cls: 0.0111 loss_rpn_bbox: 0.0118 loss_cls: 0.0838 acc: 95.1904 loss_bbox: 0.1127 loss_mask: 0.2106 2022/11/01 16:06:33 - mmengine - INFO - Epoch(train) [160][110/125] lr: 2.0000e-04 eta: 0:00:06 time: 0.4161 data_time: 0.0548 memory: 9638 loss: 0.4379 loss_rpn_cls: 0.0097 loss_rpn_bbox: 0.0091 loss_cls: 0.0864 acc: 96.0205 loss_bbox: 0.1218 loss_mask: 0.2109 2022/11/01 16:06:35 - mmengine - INFO - Epoch(train) [160][115/125] lr: 2.0000e-04 eta: 0:00:06 time: 0.4136 data_time: 0.0551 memory: 9768 loss: 0.4220 loss_rpn_cls: 0.0073 loss_rpn_bbox: 0.0094 loss_cls: 0.0879 acc: 96.1914 loss_bbox: 0.1249 loss_mask: 0.1925 2022/11/01 16:06:38 - mmengine - INFO - Epoch(train) [160][120/125] lr: 2.0000e-04 eta: 0:00:02 time: 0.4997 data_time: 0.1736 memory: 9661 loss: 0.4399 loss_rpn_cls: 0.0096 loss_rpn_bbox: 0.0103 loss_cls: 0.0940 acc: 97.0703 loss_bbox: 0.1330 loss_mask: 0.1930 2022/11/01 16:06:40 - mmengine - INFO - Exp name: mask-rcnn_resnet50-oclip_fpn_160e_ctw1500_20221101_154448 2022/11/01 16:06:40 - mmengine - INFO - Epoch(train) [160][125/125] lr: 2.0000e-04 eta: 0:00:02 time: 0.4643 data_time: 0.1551 memory: 9496 loss: 0.4347 loss_rpn_cls: 0.0077 loss_rpn_bbox: 0.0085 loss_cls: 0.0838 acc: 96.9727 loss_bbox: 0.1242 loss_mask: 0.2104 2022/11/01 16:06:40 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/11/01 16:08:08 - mmengine - INFO - Epoch(val) [160][5/500] eta: 0:00:02 time: 8.3079 data_time: 5.5434 memory: 34867 2022/11/01 16:08:22 - mmengine - INFO - Epoch(val) [160][10/500] eta: 1:19:03 time: 9.6808 data_time: 5.5439 memory: 34874 2022/11/01 16:08:43 - mmengine - INFO - Epoch(val) [160][15/500] eta: 1:19:03 time: 3.4777 data_time: 0.0030 memory: 34801 2022/11/01 16:08:57 - mmengine - INFO - Epoch(val) [160][20/500] eta: 0:27:46 time: 3.4717 data_time: 0.0060 memory: 34789 2022/11/01 16:09:04 - mmengine - INFO - Epoch(val) [160][25/500] eta: 0:27:46 time: 2.0862 data_time: 0.0064 memory: 34776 2022/11/01 16:09:10 - mmengine - INFO - Epoch(val) [160][30/500] eta: 0:10:40 time: 1.3636 data_time: 0.0028 memory: 34769 2022/11/01 16:09:11 - mmengine - INFO - Epoch(val) [160][35/500] eta: 0:10:40 time: 0.7210 data_time: 0.0021 memory: 1440 2022/11/01 16:09:17 - mmengine - INFO - Epoch(val) [160][40/500] eta: 0:05:18 time: 0.6916 data_time: 0.0020 memory: 34801 2022/11/01 16:09:18 - mmengine - INFO - Epoch(val) [160][45/500] eta: 0:05:18 time: 0.6911 data_time: 0.0026 memory: 1529 2022/11/01 16:09:38 - mmengine - INFO - Epoch(val) [160][50/500] eta: 0:15:35 time: 2.0793 data_time: 0.0041 memory: 34814 2022/11/01 16:09:52 - mmengine - INFO - Epoch(val) [160][55/500] eta: 0:15:35 time: 3.4444 data_time: 0.0039 memory: 34808 2022/11/01 16:09:53 - mmengine - INFO - Epoch(val) [160][60/500] eta: 0:10:37 time: 1.4492 data_time: 0.0027 memory: 1327 2022/11/01 16:09:59 - mmengine - INFO - Epoch(val) [160][65/500] eta: 0:10:37 time: 0.7072 data_time: 0.0028 memory: 34703 2022/11/01 16:10:00 - mmengine - INFO - Epoch(val) [160][70/500] eta: 0:05:02 time: 0.7027 data_time: 0.0030 memory: 1529 2022/11/01 16:10:13 - mmengine - INFO - Epoch(val) [160][75/500] eta: 0:05:02 time: 1.3535 data_time: 0.0028 memory: 34821 2022/11/01 16:10:13 - mmengine - INFO - Epoch(val) [160][80/500] eta: 0:09:29 time: 1.3566 data_time: 0.0032 memory: 1327 2022/11/01 16:10:34 - mmengine - INFO - Epoch(val) [160][85/500] eta: 0:09:29 time: 2.0721 data_time: 0.0032 memory: 34764 2022/11/01 16:10:41 - mmengine - INFO - Epoch(val) [160][90/500] eta: 0:18:52 time: 2.7625 data_time: 0.0026 memory: 34847 2022/11/01 16:11:01 - mmengine - INFO - Epoch(val) [160][95/500] eta: 0:18:52 time: 2.7773 data_time: 0.0024 memory: 34749 2022/11/01 16:11:02 - mmengine - INFO - Epoch(val) [160][100/500] eta: 0:13:51 time: 2.0798 data_time: 0.0021 memory: 1512 2022/11/01 16:11:02 - mmengine - INFO - Epoch(val) [160][105/500] eta: 0:13:51 time: 0.0698 data_time: 0.0020 memory: 1327 2022/11/01 16:11:15 - mmengine - INFO - Epoch(val) [160][110/500] eta: 0:08:57 time: 1.3786 data_time: 0.0023 memory: 34840 2022/11/01 16:11:16 - mmengine - INFO - Epoch(val) [160][115/500] eta: 0:08:57 time: 1.3767 data_time: 0.0027 memory: 1327 2022/11/01 16:11:16 - mmengine - INFO - Epoch(val) [160][120/500] eta: 0:00:30 time: 0.0811 data_time: 0.0024 memory: 1327 2022/11/01 16:11:17 - mmengine - INFO - Epoch(val) [160][125/500] eta: 0:00:30 time: 0.0966 data_time: 0.0019 memory: 1529 2022/11/01 16:11:17 - mmengine - INFO - Epoch(val) [160][130/500] eta: 0:00:30 time: 0.0815 data_time: 0.0021 memory: 1327 2022/11/01 16:11:17 - mmengine - INFO - Epoch(val) [160][135/500] eta: 0:00:30 time: 0.0683 data_time: 0.0021 memory: 1394 2022/11/01 16:11:18 - mmengine - INFO - Epoch(val) [160][140/500] eta: 0:00:26 time: 0.0733 data_time: 0.0021 memory: 1327 2022/11/01 16:11:31 - mmengine - INFO - Epoch(val) [160][145/500] eta: 0:00:26 time: 1.3569 data_time: 0.0024 memory: 34867 2022/11/01 16:11:31 - mmengine - INFO - Epoch(val) [160][150/500] eta: 0:07:54 time: 1.3566 data_time: 0.0025 memory: 1327 2022/11/01 16:11:38 - mmengine - INFO - Epoch(val) [160][155/500] eta: 0:07:54 time: 0.7025 data_time: 0.0026 memory: 34808 2022/11/01 16:11:38 - mmengine - INFO - Epoch(val) [160][160/500] eta: 0:03:59 time: 0.7040 data_time: 0.0028 memory: 1529 2022/11/01 16:11:39 - mmengine - INFO - Epoch(val) [160][165/500] eta: 0:03:59 time: 0.0767 data_time: 0.0029 memory: 1361 2022/11/01 16:11:52 - mmengine - INFO - Epoch(val) [160][170/500] eta: 0:07:30 time: 1.3663 data_time: 0.0029 memory: 34853 2022/11/01 16:11:52 - mmengine - INFO - Epoch(val) [160][175/500] eta: 0:07:30 time: 1.3690 data_time: 0.0101 memory: 1529 2022/11/01 16:11:53 - mmengine - INFO - Epoch(val) [160][180/500] eta: 0:00:25 time: 0.0788 data_time: 0.0098 memory: 1529 2022/11/01 16:11:53 - mmengine - INFO - Epoch(val) [160][185/500] eta: 0:00:25 time: 0.0691 data_time: 0.0020 memory: 1327 2022/11/01 16:11:53 - mmengine - INFO - Epoch(val) [160][190/500] eta: 0:00:20 time: 0.0648 data_time: 0.0019 memory: 1377 2022/11/01 16:11:54 - mmengine - INFO - Epoch(val) [160][195/500] eta: 0:00:20 time: 0.0635 data_time: 0.0019 memory: 1361 2022/11/01 16:12:00 - mmengine - INFO - Epoch(val) [160][200/500] eta: 0:03:21 time: 0.6708 data_time: 0.0022 memory: 34756 2022/11/01 16:12:07 - mmengine - INFO - Epoch(val) [160][205/500] eta: 0:03:21 time: 1.3308 data_time: 0.0023 memory: 34678 2022/11/01 16:12:07 - mmengine - INFO - Epoch(val) [160][210/500] eta: 0:03:30 time: 0.7270 data_time: 0.0020 memory: 1529 2022/11/01 16:12:08 - mmengine - INFO - Epoch(val) [160][215/500] eta: 0:03:30 time: 0.0684 data_time: 0.0020 memory: 1327 2022/11/01 16:12:14 - mmengine - INFO - Epoch(val) [160][220/500] eta: 0:03:06 time: 0.6650 data_time: 0.0021 memory: 34710 2022/11/01 16:12:14 - mmengine - INFO - Epoch(val) [160][225/500] eta: 0:03:06 time: 0.6686 data_time: 0.0022 memory: 1529 2022/11/01 16:12:21 - mmengine - INFO - Epoch(val) [160][230/500] eta: 0:03:14 time: 0.7195 data_time: 0.0022 memory: 34776 2022/11/01 16:12:22 - mmengine - INFO - Epoch(val) [160][235/500] eta: 0:03:14 time: 0.7206 data_time: 0.0023 memory: 1529 2022/11/01 16:12:22 - mmengine - INFO - Epoch(val) [160][240/500] eta: 0:00:19 time: 0.0759 data_time: 0.0024 memory: 1529 2022/11/01 16:12:22 - mmengine - INFO - Epoch(val) [160][245/500] eta: 0:00:19 time: 0.0728 data_time: 0.0023 memory: 1529 2022/11/01 16:12:23 - mmengine - INFO - Epoch(val) [160][250/500] eta: 0:00:17 time: 0.0711 data_time: 0.0023 memory: 1327 2022/11/01 16:12:37 - mmengine - INFO - Epoch(val) [160][255/500] eta: 0:00:17 time: 1.4100 data_time: 0.0023 memory: 34789 2022/11/01 16:12:37 - mmengine - INFO - Epoch(val) [160][260/500] eta: 0:05:37 time: 1.4052 data_time: 0.0022 memory: 1327 2022/11/01 16:12:51 - mmengine - INFO - Epoch(val) [160][265/500] eta: 0:05:37 time: 1.4681 data_time: 0.0022 memory: 34840 2022/11/01 16:12:52 - mmengine - INFO - Epoch(val) [160][270/500] eta: 0:05:38 time: 1.4734 data_time: 0.0022 memory: 1445 2022/11/01 16:12:52 - mmengine - INFO - Epoch(val) [160][275/500] eta: 0:05:38 time: 0.0848 data_time: 0.0080 memory: 1512 2022/11/01 16:12:59 - mmengine - INFO - Epoch(val) [160][280/500] eta: 0:02:34 time: 0.7032 data_time: 0.0081 memory: 34860 2022/11/01 16:12:59 - mmengine - INFO - Epoch(val) [160][285/500] eta: 0:02:34 time: 0.7016 data_time: 0.0035 memory: 1327 2022/11/01 16:13:06 - mmengine - INFO - Epoch(val) [160][290/500] eta: 0:02:27 time: 0.7029 data_time: 0.0036 memory: 34834 2022/11/01 16:13:06 - mmengine - INFO - Epoch(val) [160][295/500] eta: 0:02:27 time: 0.6916 data_time: 0.0026 memory: 1377 2022/11/01 16:13:06 - mmengine - INFO - Epoch(val) [160][300/500] eta: 0:00:13 time: 0.0700 data_time: 0.0025 memory: 1327 2022/11/01 16:13:07 - mmengine - INFO - Epoch(val) [160][305/500] eta: 0:00:13 time: 0.0658 data_time: 0.0028 memory: 1310 2022/11/01 16:13:07 - mmengine - INFO - Epoch(val) [160][310/500] eta: 0:00:11 time: 0.0613 data_time: 0.0026 memory: 1361 2022/11/01 16:13:07 - mmengine - INFO - Epoch(val) [160][315/500] eta: 0:00:11 time: 0.0706 data_time: 0.0021 memory: 1478 2022/11/01 16:13:08 - mmengine - INFO - Epoch(val) [160][320/500] eta: 0:00:14 time: 0.0795 data_time: 0.0022 memory: 1478 2022/11/01 16:13:08 - mmengine - INFO - Epoch(val) [160][325/500] eta: 0:00:14 time: 0.0759 data_time: 0.0023 memory: 1529 2022/11/01 16:13:08 - mmengine - INFO - Epoch(val) [160][330/500] eta: 0:00:12 time: 0.0728 data_time: 0.0023 memory: 1327 2022/11/01 16:13:09 - mmengine - INFO - Epoch(val) [160][335/500] eta: 0:00:12 time: 0.0725 data_time: 0.0022 memory: 1445 2022/11/01 16:13:09 - mmengine - INFO - Epoch(val) [160][340/500] eta: 0:00:11 time: 0.0707 data_time: 0.0021 memory: 1512 2022/11/01 16:13:10 - mmengine - INFO - Epoch(val) [160][345/500] eta: 0:00:11 time: 0.0692 data_time: 0.0028 memory: 1445 2022/11/01 16:13:16 - mmengine - INFO - Epoch(val) [160][350/500] eta: 0:01:41 time: 0.6771 data_time: 0.0030 memory: 34782 2022/11/01 16:13:23 - mmengine - INFO - Epoch(val) [160][355/500] eta: 0:01:41 time: 1.3674 data_time: 0.0031 memory: 34756 2022/11/01 16:13:24 - mmengine - INFO - Epoch(val) [160][360/500] eta: 0:01:46 time: 0.7580 data_time: 0.0034 memory: 1344 2022/11/01 16:13:30 - mmengine - INFO - Epoch(val) [160][365/500] eta: 0:01:46 time: 0.6708 data_time: 0.0029 memory: 34671 2022/11/01 16:13:37 - mmengine - INFO - Epoch(val) [160][370/500] eta: 0:02:55 time: 1.3482 data_time: 0.0026 memory: 34821 2022/11/01 16:13:37 - mmengine - INFO - Epoch(val) [160][375/500] eta: 0:02:55 time: 0.7449 data_time: 0.0029 memory: 1327 2022/11/01 16:13:38 - mmengine - INFO - Epoch(val) [160][380/500] eta: 0:00:08 time: 0.0737 data_time: 0.0028 memory: 1512 2022/11/01 16:13:38 - mmengine - INFO - Epoch(val) [160][385/500] eta: 0:00:08 time: 0.0736 data_time: 0.0022 memory: 1495 2022/11/01 16:13:38 - mmengine - INFO - Epoch(val) [160][390/500] eta: 0:00:07 time: 0.0720 data_time: 0.0023 memory: 1529 2022/11/01 16:13:39 - mmengine - INFO - Epoch(val) [160][395/500] eta: 0:00:07 time: 0.0985 data_time: 0.0024 memory: 1327 2022/11/01 16:13:39 - mmengine - INFO - Epoch(val) [160][400/500] eta: 0:00:09 time: 0.0988 data_time: 0.0023 memory: 1512 2022/11/01 16:13:40 - mmengine - INFO - Epoch(val) [160][405/500] eta: 0:00:09 time: 0.0692 data_time: 0.0021 memory: 1495 2022/11/01 16:13:40 - mmengine - INFO - Epoch(val) [160][410/500] eta: 0:00:05 time: 0.0645 data_time: 0.0021 memory: 1394 2022/11/01 16:13:41 - mmengine - INFO - Epoch(val) [160][415/500] eta: 0:00:05 time: 0.0756 data_time: 0.0021 memory: 1327 2022/11/01 16:13:41 - mmengine - INFO - Epoch(val) [160][420/500] eta: 0:00:07 time: 0.0913 data_time: 0.0023 memory: 1495 2022/11/01 16:13:41 - mmengine - INFO - Epoch(val) [160][425/500] eta: 0:00:07 time: 0.0892 data_time: 0.0025 memory: 1327 2022/11/01 16:13:42 - mmengine - INFO - Epoch(val) [160][430/500] eta: 0:00:04 time: 0.0712 data_time: 0.0024 memory: 1529 2022/11/01 16:13:42 - mmengine - INFO - Epoch(val) [160][435/500] eta: 0:00:04 time: 0.0744 data_time: 0.0022 memory: 1327 2022/11/01 16:13:43 - mmengine - INFO - Epoch(val) [160][440/500] eta: 0:00:04 time: 0.0788 data_time: 0.0024 memory: 1411 2022/11/01 16:13:43 - mmengine - INFO - Epoch(val) [160][445/500] eta: 0:00:04 time: 0.0696 data_time: 0.0024 memory: 1478 2022/11/01 16:13:43 - mmengine - INFO - Epoch(val) [160][450/500] eta: 0:00:03 time: 0.0653 data_time: 0.0021 memory: 1327 2022/11/01 16:13:44 - mmengine - INFO - Epoch(val) [160][455/500] eta: 0:00:03 time: 0.0676 data_time: 0.0021 memory: 1529 2022/11/01 16:13:44 - mmengine - INFO - Epoch(val) [160][460/500] eta: 0:00:02 time: 0.0690 data_time: 0.0020 memory: 1361 2022/11/01 16:13:44 - mmengine - INFO - Epoch(val) [160][465/500] eta: 0:00:02 time: 0.0643 data_time: 0.0020 memory: 1462 2022/11/01 16:13:44 - mmengine - INFO - Epoch(val) [160][470/500] eta: 0:00:01 time: 0.0620 data_time: 0.0021 memory: 1360 2022/11/01 16:13:45 - mmengine - INFO - Epoch(val) [160][475/500] eta: 0:00:01 time: 0.0687 data_time: 0.0026 memory: 1529 2022/11/01 16:13:51 - mmengine - INFO - Epoch(val) [160][480/500] eta: 0:00:13 time: 0.6845 data_time: 0.0028 memory: 34860 2022/11/01 16:13:52 - mmengine - INFO - Epoch(val) [160][485/500] eta: 0:00:13 time: 0.6780 data_time: 0.0024 memory: 1327 2022/11/01 16:13:52 - mmengine - INFO - Epoch(val) [160][490/500] eta: 0:00:00 time: 0.0700 data_time: 0.0106 memory: 1462 2022/11/01 16:13:52 - mmengine - INFO - Epoch(val) [160][495/500] eta: 0:00:00 time: 0.0732 data_time: 0.0105 memory: 1529 2022/11/01 16:13:53 - mmengine - INFO - Epoch(val) [160][500/500] eta: 0:00:00 time: 0.0653 data_time: 0.0019 memory: 1327 2022/11/01 16:13:53 - mmengine - INFO - Evaluating hmean-iou... 2022/11/01 16:13:53 - mmengine - INFO - prediction score threshold: 0.30, recall: 0.8849, precision: 0.4773, hmean: 0.6201 2022/11/01 16:13:53 - mmengine - INFO - prediction score threshold: 0.40, recall: 0.8735, precision: 0.5224, hmean: 0.6538 2022/11/01 16:13:53 - mmengine - INFO - prediction score threshold: 0.50, recall: 0.8650, precision: 0.5684, hmean: 0.6860 2022/11/01 16:13:53 - mmengine - INFO - prediction score threshold: 0.60, recall: 0.8527, precision: 0.6135, hmean: 0.7136 2022/11/01 16:13:53 - mmengine - INFO - prediction score threshold: 0.70, recall: 0.8387, precision: 0.6486, hmean: 0.7315 2022/11/01 16:13:53 - mmengine - INFO - prediction score threshold: 0.80, recall: 0.8153, precision: 0.6880, hmean: 0.7462 2022/11/01 16:13:53 - mmengine - INFO - prediction score threshold: 0.90, recall: 0.7593, precision: 0.7530, hmean: 0.7562 2022/11/01 16:13:53 - mmengine - INFO - Epoch(val) [160][500/500] icdar/precision: 0.7530 icdar/recall: 0.7593 icdar/hmean: 0.7562