2023-02-12 02:04:57,937 - mmrotate - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.8.5 (default, Sep 4 2020, 07:30:14) [GCC 7.3.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: GeForce RTX 3090 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.0, V11.0.221 GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 PyTorch: 1.7.1+cu110 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 v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.0 - 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 - CuDNN 8.0.5 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -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, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=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: 0.8.2+cu110 OpenCV: 4.6.0 MMCV: 1.7.0 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 11.0 MMRotate: 0.3.3+3737ed0 ------------------------------------------------------------ 2023-02-12 02:04:58,291 - mmrotate - INFO - Distributed training: True 2023-02-12 02:04:58,746 - mmrotate - INFO - Config: dataset_type = 'DOTADataset' data_root = '/opt/data/private/LYX/data/split_ms_dota/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict(type='RResize', img_scale=(1024, 1024)), dict( type='RRandomFlip', flip_ratio=[0.25, 0.25, 0.25], direction=['horizontal', 'vertical', 'diagonal'], version='le90'), dict( type='PolyRandomRotate', rotate_ratio=0.5, angles_range=180, auto_bound=False, rect_classes=[9, 11], version='le90'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1024, 1024), flip=False, transforms=[ dict(type='RResize'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=1, workers_per_gpu=2, train=dict( type='DOTADataset', ann_file= '/opt/data/private/LYX/data/split_ms_dota/trainval_2/annfiles/', img_prefix= '/opt/data/private/LYX/data/split_ms_dota/trainval_2/images/', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict(type='RResize', img_scale=(1024, 1024)), dict( type='RRandomFlip', flip_ratio=[0.25, 0.25, 0.25], direction=['horizontal', 'vertical', 'diagonal'], version='le90'), dict( type='PolyRandomRotate', rotate_ratio=0.5, angles_range=180, auto_bound=False, rect_classes=[9, 11], version='le90'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ], version='le90'), val=dict( type='DOTADataset', ann_file='/opt/data/private/LYX/data/split_ms_dota/val/annfiles/', img_prefix='/opt/data/private/LYX/data/split_ms_dota/val/images/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1024, 1024), flip=False, transforms=[ dict(type='RResize'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img']) ]) ], version='le90'), test=dict( type='DOTADataset', ann_file='/opt/data/private/LYX/data/split_ms_dota/test/images/', img_prefix='/opt/data/private/LYX/data/split_ms_dota/test/images/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1024, 1024), flip=False, transforms=[ dict(type='RResize'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img']) ]) ], version='le90')) evaluation = dict(interval=3, metric='mAP') optimizer = dict( type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2)) lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=0.3333333333333333, step=[8, 11]) runner = dict(type='EpochBasedRunner', max_epochs=12) checkpoint_config = dict(interval=1) log_config = dict(interval=500, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] opencv_num_threads = 0 mp_start_method = 'fork' angle_version = 'le90' gpu_number = 8 model = dict( type='OrientedRCNN', backbone=dict( type='LSKNet', embed_dims=[64, 128, 320, 512], drop_rate=0.1, drop_path_rate=0.1, depths=[2, 2, 4, 2], init_cfg=dict( type='Pretrained', checkpoint='/opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar' ), norm_cfg=dict(type='SyncBN', requires_grad=True)), neck=dict( type='FPN', in_channels=[64, 128, 320, 512], out_channels=256, num_outs=5), rpn_head=dict( type='OrientedRPNHead', in_channels=256, feat_channels=256, version='le90', anchor_generator=dict( type='AnchorGenerator', scales=[8], ratios=[0.5, 1.0, 2.0], strides=[4, 8, 16, 32, 64]), bbox_coder=dict( type='MidpointOffsetCoder', angle_range='le90', target_means=[0.0, 0.0, 0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0, 0.5, 0.5]), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict( type='SmoothL1Loss', beta=0.1111111111111111, loss_weight=1.0)), roi_head=dict( type='OrientedStandardRoIHead', bbox_roi_extractor=dict( type='RotatedSingleRoIExtractor', roi_layer=dict( type='RoIAlignRotated', out_size=7, sample_num=2, clockwise=True), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=dict( type='RotatedShared2FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=15, bbox_coder=dict( type='DeltaXYWHAOBBoxCoder', angle_range='le90', norm_factor=None, edge_swap=True, proj_xy=True, target_means=(0.0, 0.0, 0.0, 0.0, 0.0), target_stds=(0.1, 0.1, 0.2, 0.2, 0.1)), reg_class_agnostic=True, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='SmoothL1Loss', beta=1.0, 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, gpu_assign_thr=800, 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=0, pos_weight=-1, debug=False), rpn_proposal=dict( nms_pre=2000, max_per_img=2000, nms=dict(type='nms', iou_threshold=0.8), 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=False, iou_calculator=dict(type='RBboxOverlaps2D'), gpu_assign_thr=800, ignore_iof_thr=-1), sampler=dict( type='RRandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=-1, debug=False)), test_cfg=dict( rpn=dict( nms_pre=2000, max_per_img=2000, nms=dict(type='nms', iou_threshold=0.8), min_bbox_size=0), rcnn=dict( nms_pre=2000, min_bbox_size=0, score_thr=0.05, nms=dict(iou_thr=0.1), max_per_img=2000))) custom_hooks = [ dict(type='ExpMomentumEMAHook', total_iter=102492, priority=49) ] work_dir = './work_dirs/lskb1_dota_ema_finetune' auto_resume = False gpu_ids = range(0, 8) 2023-02-12 02:04:58,746 - mmrotate - INFO - Set random seed to 0, deterministic: False 2023-02-12 02:04:59,037 - mmrotate - INFO - initialize LSKNet with init_cfg {'type': 'Pretrained', 'checkpoint': '/opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar'} 2023-02-12 02:04:59,952 - mmrotate - INFO - initialize FPN with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} 2023-02-12 02:05:00,002 - mmrotate - INFO - initialize OrientedRPNHead with init_cfg {'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01} 2023-02-12 02:05:00,012 - mmrotate - INFO - initialize RotatedShared2FCBBoxHead with init_cfg [{'type': 'Normal', 'std': 0.01, 'override': {'name': 'fc_cls'}}, {'type': 'Normal', 'std': 0.001, 'override': {'name': 'fc_reg'}}, {'type': 'Xavier', 'layer': 'Linear', 'override': [{'name': 'shared_fcs'}, {'name': 'cls_fcs'}, {'name': 'reg_fcs'}]}] Name of parameter - Initialization information backbone.patch_embed1.proj.weight - torch.Size([64, 3, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed1.proj.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed1.norm.weight - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed1.norm.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.layer_scale_1 - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.layer_scale_2 - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.norm1.weight - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.norm1.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.norm2.weight - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.norm2.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.proj_1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.proj_1.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv0.weight - torch.Size([64, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv0.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([64, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv1.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv1.bias - torch.Size([32]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv2.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv2.bias - torch.Size([32]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv.weight - torch.Size([64, 32, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.spatial_gating_unit.conv.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.proj_2.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.attn.proj_2.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.mlp.fc1.weight - torch.Size([512, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.mlp.fc1.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.mlp.dwconv.dwconv.weight - torch.Size([512, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.mlp.dwconv.dwconv.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.mlp.fc2.weight - torch.Size([64, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.0.mlp.fc2.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.layer_scale_1 - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.layer_scale_2 - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.norm1.weight - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.norm1.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.norm2.weight - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.norm2.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.proj_1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.proj_1.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv0.weight - torch.Size([64, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv0.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([64, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv1.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv1.bias - torch.Size([32]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv2.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv2.bias - torch.Size([32]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv.weight - torch.Size([64, 32, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.spatial_gating_unit.conv.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.proj_2.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.attn.proj_2.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.mlp.fc1.weight - torch.Size([512, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.mlp.fc1.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.mlp.dwconv.dwconv.weight - torch.Size([512, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.mlp.dwconv.dwconv.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.mlp.fc2.weight - torch.Size([64, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block1.1.mlp.fc2.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.norm1.weight - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.norm1.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed2.proj.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed2.proj.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed2.norm.weight - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed2.norm.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.layer_scale_1 - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.layer_scale_2 - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.norm1.weight - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.norm1.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.norm2.weight - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.norm2.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.proj_1.weight - torch.Size([128, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.proj_1.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv0.weight - torch.Size([128, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv0.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([128, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv1.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv1.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv2.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv2.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv.weight - torch.Size([128, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.spatial_gating_unit.conv.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.proj_2.weight - torch.Size([128, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.attn.proj_2.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.mlp.fc1.weight - torch.Size([1024, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.mlp.fc1.bias - torch.Size([1024]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.mlp.dwconv.dwconv.weight - torch.Size([1024, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.mlp.dwconv.dwconv.bias - torch.Size([1024]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.mlp.fc2.weight - torch.Size([128, 1024, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.0.mlp.fc2.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.layer_scale_1 - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.layer_scale_2 - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.norm1.weight - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.norm1.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.norm2.weight - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.norm2.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.proj_1.weight - torch.Size([128, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.proj_1.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv0.weight - torch.Size([128, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv0.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([128, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv1.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv1.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv2.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv2.bias - torch.Size([64]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv.weight - torch.Size([128, 64, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.spatial_gating_unit.conv.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.proj_2.weight - torch.Size([128, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.attn.proj_2.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.mlp.fc1.weight - torch.Size([1024, 128, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.mlp.fc1.bias - torch.Size([1024]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.mlp.dwconv.dwconv.weight - torch.Size([1024, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.mlp.dwconv.dwconv.bias - torch.Size([1024]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.mlp.fc2.weight - torch.Size([128, 1024, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block2.1.mlp.fc2.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.norm2.weight - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.norm2.bias - torch.Size([128]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed3.proj.weight - torch.Size([320, 128, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed3.proj.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed3.norm.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed3.norm.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.layer_scale_1 - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.layer_scale_2 - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.norm1.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.norm1.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.norm2.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.norm2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.proj_1.weight - torch.Size([320, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.proj_1.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv0.weight - torch.Size([320, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv0.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([320, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv1.weight - torch.Size([160, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv1.bias - torch.Size([160]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv2.weight - torch.Size([160, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv2.bias - torch.Size([160]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv.weight - torch.Size([320, 160, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.spatial_gating_unit.conv.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.proj_2.weight - torch.Size([320, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.attn.proj_2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.mlp.fc1.weight - torch.Size([1280, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.mlp.fc1.bias - torch.Size([1280]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.mlp.dwconv.dwconv.weight - torch.Size([1280, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.mlp.dwconv.dwconv.bias - torch.Size([1280]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.mlp.fc2.weight - torch.Size([320, 1280, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.0.mlp.fc2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.layer_scale_1 - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.layer_scale_2 - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.norm1.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.norm1.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.norm2.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.norm2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.proj_1.weight - torch.Size([320, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.proj_1.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv0.weight - torch.Size([320, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv0.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([320, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv1.weight - torch.Size([160, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv1.bias - torch.Size([160]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv2.weight - torch.Size([160, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv2.bias - torch.Size([160]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv.weight - torch.Size([320, 160, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.spatial_gating_unit.conv.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.proj_2.weight - torch.Size([320, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.attn.proj_2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.mlp.fc1.weight - torch.Size([1280, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.mlp.fc1.bias - torch.Size([1280]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.mlp.dwconv.dwconv.weight - torch.Size([1280, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.mlp.dwconv.dwconv.bias - torch.Size([1280]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.mlp.fc2.weight - torch.Size([320, 1280, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.1.mlp.fc2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.layer_scale_1 - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.layer_scale_2 - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.norm1.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.norm1.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.norm2.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.norm2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.proj_1.weight - torch.Size([320, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.proj_1.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv0.weight - torch.Size([320, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv0.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([320, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv1.weight - torch.Size([160, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv1.bias - torch.Size([160]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv2.weight - torch.Size([160, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv2.bias - torch.Size([160]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv.weight - torch.Size([320, 160, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.spatial_gating_unit.conv.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.proj_2.weight - torch.Size([320, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.attn.proj_2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.mlp.fc1.weight - torch.Size([1280, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.mlp.fc1.bias - torch.Size([1280]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.mlp.dwconv.dwconv.weight - torch.Size([1280, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.mlp.dwconv.dwconv.bias - torch.Size([1280]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.mlp.fc2.weight - torch.Size([320, 1280, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.2.mlp.fc2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.layer_scale_1 - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.layer_scale_2 - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.norm1.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.norm1.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.norm2.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.norm2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.proj_1.weight - torch.Size([320, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.proj_1.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv0.weight - torch.Size([320, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv0.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([320, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv1.weight - torch.Size([160, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv1.bias - torch.Size([160]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv2.weight - torch.Size([160, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv2.bias - torch.Size([160]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv.weight - torch.Size([320, 160, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.spatial_gating_unit.conv.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.proj_2.weight - torch.Size([320, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.attn.proj_2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.mlp.fc1.weight - torch.Size([1280, 320, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.mlp.fc1.bias - torch.Size([1280]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.mlp.dwconv.dwconv.weight - torch.Size([1280, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.mlp.dwconv.dwconv.bias - torch.Size([1280]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.mlp.fc2.weight - torch.Size([320, 1280, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block3.3.mlp.fc2.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.norm3.weight - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.norm3.bias - torch.Size([320]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed4.proj.weight - torch.Size([512, 320, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed4.proj.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed4.norm.weight - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.patch_embed4.norm.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.layer_scale_1 - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.layer_scale_2 - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.norm1.weight - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.norm1.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.norm2.weight - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.norm2.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.proj_1.weight - torch.Size([512, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.proj_1.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv0.weight - torch.Size([512, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv0.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([512, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv1.bias - torch.Size([256]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv2.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv2.bias - torch.Size([256]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.spatial_gating_unit.conv.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.proj_2.weight - torch.Size([512, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.attn.proj_2.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.mlp.fc1.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.mlp.fc1.bias - torch.Size([2048]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.mlp.dwconv.dwconv.weight - torch.Size([2048, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.mlp.dwconv.dwconv.bias - torch.Size([2048]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.mlp.fc2.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.0.mlp.fc2.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.layer_scale_1 - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.layer_scale_2 - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.norm1.weight - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.norm1.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.norm2.weight - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.norm2.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.proj_1.weight - torch.Size([512, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.proj_1.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv0.weight - torch.Size([512, 1, 5, 5]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv0.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv_spatial.weight - torch.Size([512, 1, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv_spatial.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv1.bias - torch.Size([256]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv2.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv2.bias - torch.Size([256]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv_squeeze.weight - torch.Size([2, 2, 7, 7]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv_squeeze.bias - torch.Size([2]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.spatial_gating_unit.conv.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.proj_2.weight - torch.Size([512, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.attn.proj_2.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.mlp.fc1.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.mlp.fc1.bias - torch.Size([2048]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.mlp.dwconv.dwconv.weight - torch.Size([2048, 1, 3, 3]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.mlp.dwconv.dwconv.bias - torch.Size([2048]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.mlp.fc2.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.block4.1.mlp.fc2.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.norm4.weight - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar backbone.norm4.bias - torch.Size([512]): PretrainedInit: load from /opt/data/private/LYX/data/pretrained/lsk9_b1.pth.tar neck.lateral_convs.0.conv.weight - torch.Size([256, 64, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OrientedRCNN neck.lateral_convs.1.conv.weight - torch.Size([256, 128, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OrientedRCNN neck.lateral_convs.2.conv.weight - torch.Size([256, 320, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OrientedRCNN neck.lateral_convs.3.conv.weight - torch.Size([256, 512, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OrientedRCNN neck.fpn_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OrientedRCNN neck.fpn_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OrientedRCNN neck.fpn_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OrientedRCNN neck.fpn_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OrientedRCNN rpn_head.rpn_conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_conv.bias - torch.Size([256]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_cls.weight - torch.Size([3, 256, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_cls.bias - torch.Size([3]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_reg.weight - torch.Size([18, 256, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_reg.bias - torch.Size([18]): NormalInit: mean=0, std=0.01, bias=0 roi_head.bbox_head.fc_cls.weight - torch.Size([16, 1024]): XavierInit: gain=1, distribution=normal, bias=0 roi_head.bbox_head.fc_cls.bias - torch.Size([16]): NormalInit: mean=0, std=0.01, bias=0 roi_head.bbox_head.fc_reg.weight - torch.Size([5, 1024]): XavierInit: gain=1, distribution=normal, bias=0 roi_head.bbox_head.fc_reg.bias - torch.Size([5]): NormalInit: mean=0, std=0.001, bias=0 roi_head.bbox_head.shared_fcs.0.weight - torch.Size([1024, 12544]): XavierInit: gain=1, distribution=normal, bias=0 roi_head.bbox_head.shared_fcs.0.bias - torch.Size([1024]): XavierInit: gain=1, distribution=normal, bias=0 roi_head.bbox_head.shared_fcs.1.weight - torch.Size([1024, 1024]): XavierInit: gain=1, distribution=normal, bias=0 roi_head.bbox_head.shared_fcs.1.bias - torch.Size([1024]): XavierInit: gain=1, distribution=normal, bias=0 2023-02-12 02:09:23,571 - mmrotate - INFO - Start running, host: root@interactive71916, work_dir: /opt/data/private/LYX/selective-large-kernel/work_dirs/lskb1_dota_ema_finetune 2023-02-12 02:09:23,571 - mmrotate - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) StepLrUpdaterHook (49 ) ExpMomentumEMAHook (NORMAL ) CheckpointHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_epoch: (VERY_HIGH ) StepLrUpdaterHook (49 ) ExpMomentumEMAHook (NORMAL ) DistSamplerSeedHook (LOW ) IterTimerHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_iter: (VERY_HIGH ) StepLrUpdaterHook (LOW ) IterTimerHook (LOW ) DistEvalHook -------------------- after_train_iter: (ABOVE_NORMAL) OptimizerHook (49 ) ExpMomentumEMAHook (NORMAL ) CheckpointHook (LOW ) IterTimerHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- after_train_epoch: (49 ) ExpMomentumEMAHook (NORMAL ) CheckpointHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_val_epoch: (NORMAL ) DistSamplerSeedHook (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook -------------------- before_val_iter: (LOW ) IterTimerHook -------------------- after_val_iter: (LOW ) IterTimerHook -------------------- after_val_epoch: (VERY_LOW ) TextLoggerHook -------------------- after_run: (VERY_LOW ) TextLoggerHook -------------------- 2023-02-12 02:09:23,572 - mmrotate - INFO - workflow: [('train', 1)], max: 12 epochs 2023-02-12 02:09:23,636 - mmrotate - INFO - Checkpoints will be saved to /opt/data/private/LYX/selective-large-kernel/work_dirs/lskb1_dota_ema_finetune by HardDiskBackend. 2023-02-12 02:12:06,625 - mmrotate - INFO - Epoch [1][500/8541] lr: 9.987e-05, eta: 9:13:52, time: 0.326, data_time: 0.011, memory: 7627, loss_rpn_cls: 0.1940, loss_rpn_bbox: 0.1758, loss_cls: 0.2490, acc: 93.6185, loss_bbox: 0.2490, loss: 0.8678, grad_norm: 4.4288 2023-02-12 02:14:58,503 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 02:14:58,504 - mmrotate - INFO - Epoch [1][1000/8541] lr: 1.000e-04, eta: 9:26:18, time: 0.344, data_time: 0.004, memory: 9460, loss_rpn_cls: 0.0675, loss_rpn_bbox: 0.1180, loss_cls: 0.2387, acc: 92.0222, loss_bbox: 0.2684, loss: 0.6925, grad_norm: 3.1049 2023-02-12 02:17:22,854 - mmrotate - INFO - Epoch [1][1500/8541] lr: 1.000e-04, eta: 8:57:39, time: 0.289, data_time: 0.004, memory: 9460, loss_rpn_cls: 0.0507, loss_rpn_bbox: 0.0922, loss_cls: 0.2158, acc: 92.3147, loss_bbox: 0.2199, loss: 0.5785, grad_norm: 2.7828 2023-02-12 02:19:45,330 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 02:19:45,330 - mmrotate - INFO - Epoch [1][2000/8541] lr: 1.000e-04, eta: 8:40:34, time: 0.285, data_time: 0.004, memory: 9460, loss_rpn_cls: 0.0422, loss_rpn_bbox: 0.0857, loss_cls: 0.2031, acc: 92.5107, loss_bbox: 0.2030, loss: 0.5341, grad_norm: 2.6322 2023-02-12 02:22:09,691 - mmrotate - INFO - Epoch [1][2500/8541] lr: 1.000e-04, eta: 8:30:36, time: 0.289, data_time: 0.004, memory: 9505, loss_rpn_cls: 0.0395, loss_rpn_bbox: 0.0819, loss_cls: 0.1893, acc: 92.8833, loss_bbox: 0.1880, loss: 0.4986, grad_norm: 2.5261 2023-02-12 02:24:31,886 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 02:24:31,886 - mmrotate - INFO - Epoch [1][3000/8541] lr: 1.000e-04, eta: 8:21:58, time: 0.284, data_time: 0.004, memory: 9505, loss_rpn_cls: 0.0358, loss_rpn_bbox: 0.0754, loss_cls: 0.1841, acc: 93.0799, loss_bbox: 0.1821, loss: 0.4774, grad_norm: 2.4130 2023-02-12 02:26:57,372 - mmrotate - INFO - Epoch [1][3500/8541] lr: 1.000e-04, eta: 8:16:41, time: 0.291, data_time: 0.004, memory: 9505, loss_rpn_cls: 0.0329, loss_rpn_bbox: 0.0737, loss_cls: 0.1774, acc: 93.2833, loss_bbox: 0.1725, loss: 0.4565, grad_norm: 2.3142 2023-02-12 02:29:19,598 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 02:29:19,598 - mmrotate - INFO - Epoch [1][4000/8541] lr: 1.000e-04, eta: 8:10:46, time: 0.284, data_time: 0.004, memory: 9505, loss_rpn_cls: 0.0325, loss_rpn_bbox: 0.0745, loss_cls: 0.1742, acc: 93.3444, loss_bbox: 0.1696, loss: 0.4507, grad_norm: 2.3705 2023-02-12 02:31:43,452 - mmrotate - INFO - Epoch [1][4500/8541] lr: 1.000e-04, eta: 8:06:14, time: 0.288, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0317, loss_rpn_bbox: 0.0698, loss_cls: 0.1662, acc: 93.6567, loss_bbox: 0.1631, loss: 0.4308, grad_norm: 2.2247 2023-02-12 02:34:34,367 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 02:34:34,367 - mmrotate - INFO - Epoch [1][5000/8541] lr: 1.000e-04, eta: 8:10:55, time: 0.342, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0287, loss_rpn_bbox: 0.0673, loss_cls: 0.1643, acc: 93.6826, loss_bbox: 0.1607, loss: 0.4210, grad_norm: 2.1784 2023-02-12 02:36:59,391 - mmrotate - INFO - Epoch [1][5500/8541] lr: 1.000e-04, eta: 8:06:37, time: 0.290, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0613, loss_cls: 0.1577, acc: 93.9180, loss_bbox: 0.1509, loss: 0.3966, grad_norm: 2.1120 2023-02-12 02:39:22,687 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 02:39:22,688 - mmrotate - INFO - Epoch [1][6000/8541] lr: 1.000e-04, eta: 8:02:10, time: 0.287, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0265, loss_rpn_bbox: 0.0665, loss_cls: 0.1564, acc: 93.9220, loss_bbox: 0.1567, loss: 0.4061, grad_norm: 2.1096 2023-02-12 02:42:37,629 - mmrotate - INFO - Epoch [1][6500/8541] lr: 1.000e-04, eta: 8:10:46, time: 0.390, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0676, loss_cls: 0.1600, acc: 93.7530, loss_bbox: 0.1564, loss: 0.4095, grad_norm: 2.1011 2023-02-12 02:45:47,220 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 02:45:47,220 - mmrotate - INFO - Epoch [1][7000/8541] lr: 1.000e-04, eta: 8:16:26, time: 0.379, data_time: 0.005, memory: 9637, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0626, loss_cls: 0.1520, acc: 94.1367, loss_bbox: 0.1480, loss: 0.3865, grad_norm: 2.0639 2023-02-12 02:48:28,438 - mmrotate - INFO - Epoch [1][7500/8541] lr: 1.000e-04, eta: 8:14:56, time: 0.322, data_time: 0.005, memory: 9637, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0619, loss_cls: 0.1484, acc: 94.1984, loss_bbox: 0.1458, loss: 0.3791, grad_norm: 1.9879 2023-02-12 02:50:54,488 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 02:50:54,489 - mmrotate - INFO - Epoch [1][8000/8541] lr: 1.000e-04, eta: 8:10:19, time: 0.292, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0586, loss_cls: 0.1447, acc: 94.3059, loss_bbox: 0.1429, loss: 0.3701, grad_norm: 1.9295 2023-02-12 02:53:20,528 - mmrotate - INFO - Epoch [1][8500/8541] lr: 1.000e-04, eta: 8:05:57, time: 0.292, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0619, loss_cls: 0.1450, acc: 94.2745, loss_bbox: 0.1432, loss: 0.3719, grad_norm: 2.0025 2023-02-12 02:53:32,569 - mmrotate - INFO - Saving checkpoint at 1 epochs 2023-02-12 02:56:02,814 - mmrotate - INFO - Epoch [2][500/8541] lr: 1.000e-04, eta: 7:59:43, time: 0.296, data_time: 0.010, memory: 9637, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0609, loss_cls: 0.1464, acc: 94.2410, loss_bbox: 0.1402, loss: 0.3699, grad_norm: 1.9597 2023-02-12 02:58:42,212 - mmrotate - INFO - Epoch [2][1000/8541] lr: 1.000e-04, eta: 7:58:01, time: 0.319, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0596, loss_cls: 0.1452, acc: 94.2687, loss_bbox: 0.1397, loss: 0.3655, grad_norm: 1.9179 2023-02-12 03:01:07,636 - mmrotate - INFO - Epoch [2][1500/8541] lr: 1.000e-04, eta: 7:54:05, time: 0.291, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0574, loss_cls: 0.1422, acc: 94.3681, loss_bbox: 0.1365, loss: 0.3563, grad_norm: 1.8672 2023-02-12 03:03:32,196 - mmrotate - INFO - Epoch [2][2000/8541] lr: 1.000e-04, eta: 7:50:11, time: 0.289, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0597, loss_cls: 0.1400, acc: 94.4050, loss_bbox: 0.1372, loss: 0.3567, grad_norm: 1.8814 2023-02-12 03:05:56,712 - mmrotate - INFO - Epoch [2][2500/8541] lr: 1.000e-04, eta: 7:46:23, time: 0.289, data_time: 0.004, memory: 9637, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0546, loss_cls: 0.1409, acc: 94.4127, loss_bbox: 0.1360, loss: 0.3507, grad_norm: 1.8164 2023-02-12 03:08:53,229 - mmrotate - INFO - Epoch [2][3000/8541] lr: 1.000e-04, eta: 7:46:56, time: 0.353, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0550, loss_cls: 0.1325, acc: 94.6945, loss_bbox: 0.1303, loss: 0.3371, grad_norm: 1.8113 2023-02-12 03:12:36,154 - mmrotate - INFO - Epoch [2][3500/8541] lr: 1.000e-04, eta: 7:52:59, time: 0.446, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0555, loss_cls: 0.1373, acc: 94.5463, loss_bbox: 0.1329, loss: 0.3450, grad_norm: 1.8098 2023-02-12 03:14:59,648 - mmrotate - INFO - Epoch [2][4000/8541] lr: 1.000e-04, eta: 7:48:46, time: 0.287, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0521, loss_cls: 0.1340, acc: 94.6632, loss_bbox: 0.1298, loss: 0.3335, grad_norm: 1.7690 2023-02-12 03:17:24,934 - mmrotate - INFO - Epoch [2][4500/8541] lr: 1.000e-04, eta: 7:44:54, time: 0.291, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0564, loss_cls: 0.1380, acc: 94.4908, loss_bbox: 0.1347, loss: 0.3479, grad_norm: 1.8195 2023-02-12 03:20:23,436 - mmrotate - INFO - Epoch [2][5000/8541] lr: 1.000e-04, eta: 7:44:47, time: 0.357, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0519, loss_cls: 0.1316, acc: 94.7497, loss_bbox: 0.1312, loss: 0.3318, grad_norm: 1.7616 2023-02-12 03:22:44,767 - mmrotate - INFO - Epoch [2][5500/8541] lr: 1.000e-04, eta: 7:40:33, time: 0.283, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0493, loss_cls: 0.1304, acc: 94.7974, loss_bbox: 0.1274, loss: 0.3234, grad_norm: 1.7499 2023-02-12 03:25:22,306 - mmrotate - INFO - Epoch [2][6000/8541] lr: 1.000e-04, eta: 7:38:05, time: 0.315, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0554, loss_cls: 0.1313, acc: 94.7388, loss_bbox: 0.1303, loss: 0.3347, grad_norm: 1.7447 2023-02-12 03:28:28,238 - mmrotate - INFO - Epoch [2][6500/8541] lr: 1.000e-04, eta: 7:38:21, time: 0.372, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0519, loss_cls: 0.1298, acc: 94.7942, loss_bbox: 0.1273, loss: 0.3258, grad_norm: 1.7330 2023-02-12 03:30:52,396 - mmrotate - INFO - Epoch [2][7000/8541] lr: 1.000e-04, eta: 7:34:30, time: 0.288, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0493, loss_cls: 0.1280, acc: 94.8428, loss_bbox: 0.1245, loss: 0.3186, grad_norm: 1.6614 2023-02-12 03:33:14,867 - mmrotate - INFO - Epoch [2][7500/8541] lr: 1.000e-04, eta: 7:30:36, time: 0.285, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0520, loss_cls: 0.1260, acc: 94.9456, loss_bbox: 0.1252, loss: 0.3191, grad_norm: 1.7068 2023-02-12 03:35:40,251 - mmrotate - INFO - Epoch [2][8000/8541] lr: 1.000e-04, eta: 7:27:03, time: 0.291, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0520, loss_cls: 0.1292, acc: 94.8071, loss_bbox: 0.1273, loss: 0.3251, grad_norm: 1.6928 2023-02-12 03:38:04,064 - mmrotate - INFO - Epoch [2][8500/8541] lr: 1.000e-04, eta: 7:23:25, time: 0.288, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0524, loss_cls: 0.1307, acc: 94.7872, loss_bbox: 0.1262, loss: 0.3257, grad_norm: 1.7407 2023-02-12 03:38:15,808 - mmrotate - INFO - Saving checkpoint at 2 epochs 2023-02-12 03:40:46,221 - mmrotate - INFO - Epoch [3][500/8541] lr: 1.000e-04, eta: 7:18:56, time: 0.295, data_time: 0.011, memory: 9910, loss_rpn_cls: 0.0153, loss_rpn_bbox: 0.0478, loss_cls: 0.1242, acc: 94.9262, loss_bbox: 0.1240, loss: 0.3113, grad_norm: 1.6251 2023-02-12 03:43:07,982 - mmrotate - INFO - Epoch [3][1000/8541] lr: 1.000e-04, eta: 7:15:18, time: 0.283, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0148, loss_rpn_bbox: 0.0489, loss_cls: 0.1241, acc: 95.0094, loss_bbox: 0.1239, loss: 0.3117, grad_norm: 1.6606 2023-02-12 03:45:32,697 - mmrotate - INFO - Epoch [3][1500/8541] lr: 1.000e-04, eta: 7:11:59, time: 0.289, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0150, loss_rpn_bbox: 0.0505, loss_cls: 0.1254, acc: 94.9674, loss_bbox: 0.1217, loss: 0.3126, grad_norm: 1.6659 2023-02-12 03:47:58,151 - mmrotate - INFO - Epoch [3][2000/8541] lr: 1.000e-04, eta: 7:08:45, time: 0.291, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0153, loss_rpn_bbox: 0.0496, loss_cls: 0.1226, acc: 95.0450, loss_bbox: 0.1217, loss: 0.3093, grad_norm: 1.7041 2023-02-12 03:50:22,434 - mmrotate - INFO - Epoch [3][2500/8541] lr: 1.000e-04, eta: 7:05:28, time: 0.289, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0143, loss_rpn_bbox: 0.0531, loss_cls: 0.1251, acc: 94.9220, loss_bbox: 0.1207, loss: 0.3133, grad_norm: 1.7090 2023-02-12 03:53:02,934 - mmrotate - INFO - Epoch [3][3000/8541] lr: 1.000e-04, eta: 7:03:21, time: 0.321, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0151, loss_rpn_bbox: 0.0475, loss_cls: 0.1233, acc: 95.0279, loss_bbox: 0.1214, loss: 0.3074, grad_norm: 1.6535 2023-02-12 03:55:26,252 - mmrotate - INFO - Epoch [3][3500/8541] lr: 1.000e-04, eta: 7:00:04, time: 0.287, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0151, loss_rpn_bbox: 0.0491, loss_cls: 0.1232, acc: 95.0242, loss_bbox: 0.1176, loss: 0.3050, grad_norm: 1.6682 2023-02-12 03:57:48,227 - mmrotate - INFO - Epoch [3][4000/8541] lr: 1.000e-04, eta: 6:56:45, time: 0.284, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0142, loss_rpn_bbox: 0.0453, loss_cls: 0.1195, acc: 95.1236, loss_bbox: 0.1175, loss: 0.2965, grad_norm: 1.6106 2023-02-12 04:00:59,899 - mmrotate - INFO - Epoch [3][4500/8541] lr: 1.000e-04, eta: 6:56:34, time: 0.383, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0139, loss_rpn_bbox: 0.0487, loss_cls: 0.1235, acc: 95.0354, loss_bbox: 0.1178, loss: 0.3039, grad_norm: 1.6470 2023-02-12 04:03:22,474 - mmrotate - INFO - Epoch [3][5000/8541] lr: 1.000e-04, eta: 6:53:16, time: 0.285, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0133, loss_rpn_bbox: 0.0478, loss_cls: 0.1201, acc: 95.1276, loss_bbox: 0.1203, loss: 0.3015, grad_norm: 1.6355 2023-02-12 04:05:46,418 - mmrotate - INFO - Epoch [3][5500/8541] lr: 1.000e-04, eta: 6:50:06, time: 0.288, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0135, loss_rpn_bbox: 0.0434, loss_cls: 0.1196, acc: 95.1644, loss_bbox: 0.1147, loss: 0.2911, grad_norm: 1.6119 2023-02-12 04:08:10,549 - mmrotate - INFO - Epoch [3][6000/8541] lr: 1.000e-04, eta: 6:46:58, time: 0.288, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0145, loss_rpn_bbox: 0.0487, loss_cls: 0.1217, acc: 95.0655, loss_bbox: 0.1210, loss: 0.3059, grad_norm: 1.6411 2023-02-12 04:11:07,033 - mmrotate - INFO - Epoch [3][6500/8541] lr: 1.000e-04, eta: 6:45:40, time: 0.353, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0139, loss_rpn_bbox: 0.0482, loss_cls: 0.1206, acc: 95.0951, loss_bbox: 0.1193, loss: 0.3020, grad_norm: 1.6288 2023-02-12 04:13:29,503 - mmrotate - INFO - Epoch [3][7000/8541] lr: 1.000e-04, eta: 6:42:28, time: 0.285, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0140, loss_rpn_bbox: 0.0473, loss_cls: 0.1201, acc: 95.1370, loss_bbox: 0.1164, loss: 0.2978, grad_norm: 1.5836 2023-02-12 04:16:59,669 - mmrotate - INFO - Epoch [3][7500/8541] lr: 1.000e-04, eta: 6:42:52, time: 0.420, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0137, loss_rpn_bbox: 0.0448, loss_cls: 0.1159, acc: 95.2884, loss_bbox: 0.1137, loss: 0.2881, grad_norm: 1.5646 2023-02-12 04:19:22,824 - mmrotate - INFO - Epoch [3][8000/8541] lr: 1.000e-04, eta: 6:39:40, time: 0.286, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0138, loss_rpn_bbox: 0.0469, loss_cls: 0.1181, acc: 95.2005, loss_bbox: 0.1171, loss: 0.2959, grad_norm: 1.6450 2023-02-12 04:22:34,066 - mmrotate - INFO - Epoch [3][8500/8541] lr: 1.000e-04, eta: 6:38:54, time: 0.382, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0135, loss_rpn_bbox: 0.0477, loss_cls: 0.1191, acc: 95.1364, loss_bbox: 0.1172, loss: 0.2975, grad_norm: 1.6151 2023-02-12 04:22:45,593 - mmrotate - INFO - Saving checkpoint at 3 epochs 2023-02-12 04:25:26,070 - mmrotate - INFO - +--------------------+-------+--------+--------+-------+ | class | gts | dets | recall | ap | +--------------------+-------+--------+--------+-------+ | plane | 23860 | 31686 | 0.958 | 0.903 | | baseball-diamond | 1727 | 3953 | 0.931 | 0.871 | | bridge | 4142 | 16379 | 0.787 | 0.626 | | ground-track-field | 1134 | 5150 | 0.972 | 0.842 | | small-vehicle | 33183 | 76107 | 0.882 | 0.710 | | large-vehicle | 29737 | 75368 | 0.948 | 0.855 | | ship | 80574 | 106005 | 0.923 | 0.891 | | tennis-court | 4389 | 6866 | 0.975 | 0.906 | | basketball-court | 1097 | 2632 | 0.980 | 0.870 | | storage-tank | 28751 | 31936 | 0.737 | 0.709 | | soccer-ball-field | 1242 | 4964 | 0.916 | 0.800 | | roundabout | 1536 | 5888 | 0.890 | 0.789 | | harbor | 15489 | 32718 | 0.884 | 0.769 | | swimming-pool | 3456 | 6779 | 0.849 | 0.698 | | helicopter | 765 | 2963 | 0.903 | 0.795 | +--------------------+-------+--------+--------+-------+ | mAP | | | | 0.802 | +--------------------+-------+--------+--------+-------+ 2023-02-12 04:25:26,182 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 04:25:26,182 - mmrotate - INFO - Epoch(val) [3][2034] mAP: 0.8022 2023-02-12 04:27:53,270 - mmrotate - INFO - Epoch [4][500/8541] lr: 1.000e-04, eta: 6:35:03, time: 0.294, data_time: 0.011, memory: 9910, loss_rpn_cls: 0.0130, loss_rpn_bbox: 0.0461, loss_cls: 0.1159, acc: 95.2776, loss_bbox: 0.1163, loss: 0.2913, grad_norm: 1.5730 2023-02-12 04:30:18,709 - mmrotate - INFO - Epoch [4][1000/8541] lr: 1.000e-04, eta: 6:32:00, time: 0.291, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0117, loss_rpn_bbox: 0.0470, loss_cls: 0.1130, acc: 95.3780, loss_bbox: 0.1119, loss: 0.2837, grad_norm: 1.5940 2023-02-12 04:33:21,329 - mmrotate - INFO - Epoch [4][1500/8541] lr: 1.000e-04, eta: 6:30:42, time: 0.365, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0119, loss_rpn_bbox: 0.0452, loss_cls: 0.1146, acc: 95.3118, loss_bbox: 0.1165, loss: 0.2883, grad_norm: 1.5685 2023-02-12 04:35:45,701 - mmrotate - INFO - Epoch [4][2000/8541] lr: 1.000e-04, eta: 6:27:36, time: 0.289, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0124, loss_rpn_bbox: 0.0465, loss_cls: 0.1136, acc: 95.3258, loss_bbox: 0.1157, loss: 0.2882, grad_norm: 1.5650 2023-02-12 04:38:36,326 - mmrotate - INFO - Epoch [4][2500/8541] lr: 1.000e-04, eta: 6:25:41, time: 0.341, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0125, loss_rpn_bbox: 0.0449, loss_cls: 0.1133, acc: 95.3853, loss_bbox: 0.1147, loss: 0.2853, grad_norm: 1.5821 2023-02-12 04:41:54,212 - mmrotate - INFO - Epoch [4][3000/8541] lr: 1.000e-04, eta: 6:24:55, time: 0.396, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0122, loss_rpn_bbox: 0.0487, loss_cls: 0.1110, acc: 95.4530, loss_bbox: 0.1122, loss: 0.2842, grad_norm: 1.6263 2023-02-12 04:44:32,447 - mmrotate - INFO - Epoch [4][3500/8541] lr: 1.000e-04, eta: 6:22:23, time: 0.317, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0126, loss_rpn_bbox: 0.0440, loss_cls: 0.1122, acc: 95.3960, loss_bbox: 0.1121, loss: 0.2809, grad_norm: 1.5512 2023-02-12 04:46:55,272 - mmrotate - INFO - Epoch [4][4000/8541] lr: 1.000e-04, eta: 6:19:14, time: 0.286, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0123, loss_rpn_bbox: 0.0429, loss_cls: 0.1100, acc: 95.4958, loss_bbox: 0.1092, loss: 0.2744, grad_norm: 1.5397 2023-02-12 04:49:19,250 - mmrotate - INFO - Epoch [4][4500/8541] lr: 1.000e-04, eta: 6:16:08, time: 0.288, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0126, loss_rpn_bbox: 0.0427, loss_cls: 0.1128, acc: 95.4159, loss_bbox: 0.1114, loss: 0.2795, grad_norm: 1.5797 2023-02-12 04:52:06,714 - mmrotate - INFO - Epoch [4][5000/8541] lr: 1.000e-04, eta: 6:13:59, time: 0.335, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0125, loss_rpn_bbox: 0.0452, loss_cls: 0.1120, acc: 95.4236, loss_bbox: 0.1112, loss: 0.2809, grad_norm: 1.5777 2023-02-12 04:54:30,491 - mmrotate - INFO - Epoch [4][5500/8541] lr: 1.000e-04, eta: 6:10:55, time: 0.288, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0122, loss_rpn_bbox: 0.0437, loss_cls: 0.1137, acc: 95.3720, loss_bbox: 0.1130, loss: 0.2827, grad_norm: 1.6002 2023-02-12 04:56:53,032 - mmrotate - INFO - Epoch [4][6000/8541] lr: 1.000e-04, eta: 6:07:49, time: 0.285, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0114, loss_rpn_bbox: 0.0454, loss_cls: 0.1110, acc: 95.4815, loss_bbox: 0.1102, loss: 0.2780, grad_norm: 1.5719 2023-02-12 04:59:18,481 - mmrotate - INFO - Epoch [4][6500/8541] lr: 1.000e-04, eta: 6:04:51, time: 0.291, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0116, loss_rpn_bbox: 0.0405, loss_cls: 0.1101, acc: 95.4745, loss_bbox: 0.1097, loss: 0.2718, grad_norm: 1.5188 2023-02-12 05:02:13,170 - mmrotate - INFO - Epoch [4][7000/8541] lr: 1.000e-04, eta: 6:02:56, time: 0.349, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0123, loss_rpn_bbox: 0.0454, loss_cls: 0.1113, acc: 95.4750, loss_bbox: 0.1115, loss: 0.2804, grad_norm: 1.5514 2023-02-12 05:04:38,545 - mmrotate - INFO - Epoch [4][7500/8541] lr: 1.000e-04, eta: 5:59:59, time: 0.291, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0119, loss_rpn_bbox: 0.0442, loss_cls: 0.1097, acc: 95.5487, loss_bbox: 0.1088, loss: 0.2747, grad_norm: 1.5976 2023-02-12 05:07:00,979 - mmrotate - INFO - Epoch [4][8000/8541] lr: 1.000e-04, eta: 5:56:56, time: 0.285, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0111, loss_rpn_bbox: 0.0424, loss_cls: 0.1078, acc: 95.5859, loss_bbox: 0.1086, loss: 0.2699, grad_norm: 1.5410 2023-02-12 05:09:23,643 - mmrotate - INFO - Epoch [4][8500/8541] lr: 1.000e-04, eta: 5:53:55, time: 0.285, data_time: 0.004, memory: 9910, loss_rpn_cls: 0.0118, loss_rpn_bbox: 0.0438, loss_cls: 0.1085, acc: 95.5712, loss_bbox: 0.1081, loss: 0.2722, grad_norm: 1.5472 2023-02-12 05:09:35,548 - mmrotate - INFO - Saving checkpoint at 4 epochs 2023-02-12 05:12:07,782 - mmrotate - INFO - Epoch [5][500/8541] lr: 1.000e-04, eta: 5:50:31, time: 0.300, data_time: 0.010, memory: 10130, loss_rpn_cls: 0.0111, loss_rpn_bbox: 0.0461, loss_cls: 0.1063, acc: 95.6355, loss_bbox: 0.1068, loss: 0.2703, grad_norm: 1.5597 2023-02-12 05:14:32,305 - mmrotate - INFO - Epoch [5][1000/8541] lr: 1.000e-04, eta: 5:47:36, time: 0.289, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0106, loss_rpn_bbox: 0.0416, loss_cls: 0.1056, acc: 95.6426, loss_bbox: 0.1074, loss: 0.2652, grad_norm: 1.5069 2023-02-12 05:17:21,685 - mmrotate - INFO - Epoch [5][1500/8541] lr: 1.000e-04, eta: 5:45:29, time: 0.339, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0114, loss_rpn_bbox: 0.0440, loss_cls: 0.1055, acc: 95.6770, loss_bbox: 0.1089, loss: 0.2698, grad_norm: 1.5273 2023-02-12 05:19:49,012 - mmrotate - INFO - Epoch [5][2000/8541] lr: 1.000e-04, eta: 5:42:39, time: 0.295, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0098, loss_rpn_bbox: 0.0429, loss_cls: 0.1066, acc: 95.6011, loss_bbox: 0.1109, loss: 0.2703, grad_norm: 1.5044 2023-02-12 05:22:14,252 - mmrotate - INFO - Epoch [5][2500/8541] lr: 1.000e-04, eta: 5:39:47, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0105, loss_rpn_bbox: 0.0429, loss_cls: 0.1061, acc: 95.6418, loss_bbox: 0.1080, loss: 0.2675, grad_norm: 1.5228 2023-02-12 05:24:37,223 - mmrotate - INFO - Epoch [5][3000/8541] lr: 1.000e-04, eta: 5:36:51, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0108, loss_rpn_bbox: 0.0451, loss_cls: 0.1089, acc: 95.5156, loss_bbox: 0.1112, loss: 0.2760, grad_norm: 1.5984 2023-02-12 05:27:02,710 - mmrotate - INFO - Epoch [5][3500/8541] lr: 1.000e-04, eta: 5:34:00, time: 0.291, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0106, loss_rpn_bbox: 0.0429, loss_cls: 0.1068, acc: 95.6141, loss_bbox: 0.1066, loss: 0.2668, grad_norm: 1.5079 2023-02-12 05:29:24,884 - mmrotate - INFO - Epoch [5][4000/8541] lr: 1.000e-04, eta: 5:31:05, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0102, loss_rpn_bbox: 0.0394, loss_cls: 0.1025, acc: 95.7883, loss_bbox: 0.1030, loss: 0.2552, grad_norm: 1.4542 2023-02-12 05:32:06,850 - mmrotate - INFO - Epoch [5][4500/8541] lr: 1.000e-04, eta: 5:28:43, time: 0.324, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0106, loss_rpn_bbox: 0.0424, loss_cls: 0.1049, acc: 95.7232, loss_bbox: 0.1059, loss: 0.2638, grad_norm: 1.5408 2023-02-12 05:34:53,458 - mmrotate - INFO - Epoch [5][5000/8541] lr: 1.000e-04, eta: 5:26:28, time: 0.333, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0102, loss_rpn_bbox: 0.0424, loss_cls: 0.1029, acc: 95.7707, loss_bbox: 0.1058, loss: 0.2612, grad_norm: 1.5022 2023-02-12 05:37:37,088 - mmrotate - INFO - Epoch [5][5500/8541] lr: 1.000e-04, eta: 5:24:08, time: 0.327, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0108, loss_rpn_bbox: 0.0423, loss_cls: 0.1072, acc: 95.5828, loss_bbox: 0.1076, loss: 0.2679, grad_norm: 1.4866 2023-02-12 05:40:01,026 - mmrotate - INFO - Epoch [5][6000/8541] lr: 1.000e-04, eta: 5:21:16, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0104, loss_rpn_bbox: 0.0420, loss_cls: 0.1046, acc: 95.7044, loss_bbox: 0.1083, loss: 0.2653, grad_norm: 1.5378 2023-02-12 05:42:25,917 - mmrotate - INFO - Epoch [5][6500/8541] lr: 1.000e-04, eta: 5:18:27, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0101, loss_rpn_bbox: 0.0451, loss_cls: 0.1052, acc: 95.6983, loss_bbox: 0.1066, loss: 0.2671, grad_norm: 1.5701 2023-02-12 05:44:48,959 - mmrotate - INFO - Epoch [5][7000/8541] lr: 1.000e-04, eta: 5:15:35, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0105, loss_rpn_bbox: 0.0454, loss_cls: 0.1033, acc: 95.7421, loss_bbox: 0.1062, loss: 0.2654, grad_norm: 1.5188 2023-02-12 05:47:39,544 - mmrotate - INFO - Epoch [5][7500/8541] lr: 1.000e-04, eta: 5:13:24, time: 0.341, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0102, loss_rpn_bbox: 0.0397, loss_cls: 0.1024, acc: 95.8029, loss_bbox: 0.1043, loss: 0.2567, grad_norm: 1.5395 2023-02-12 05:50:03,203 - mmrotate - INFO - Epoch [5][8000/8541] lr: 1.000e-04, eta: 5:10:34, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0102, loss_rpn_bbox: 0.0430, loss_cls: 0.0999, acc: 95.8726, loss_bbox: 0.1041, loss: 0.2572, grad_norm: 1.4822 2023-02-12 05:53:07,360 - mmrotate - INFO - Epoch [5][8500/8541] lr: 1.000e-04, eta: 5:08:41, time: 0.368, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0094, loss_rpn_bbox: 0.0407, loss_cls: 0.0997, acc: 95.8953, loss_bbox: 0.1006, loss: 0.2504, grad_norm: 1.4921 2023-02-12 05:53:19,270 - mmrotate - INFO - Saving checkpoint at 5 epochs 2023-02-12 05:56:20,680 - mmrotate - INFO - Epoch [6][500/8541] lr: 1.000e-04, eta: 5:06:10, time: 0.358, data_time: 0.010, memory: 10130, loss_rpn_cls: 0.0098, loss_rpn_bbox: 0.0428, loss_cls: 0.0982, acc: 95.9649, loss_bbox: 0.1016, loss: 0.2524, grad_norm: 1.5078 2023-02-12 05:58:43,431 - mmrotate - INFO - Epoch [6][1000/8541] lr: 1.000e-04, eta: 5:03:18, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0099, loss_rpn_bbox: 0.0426, loss_cls: 0.1002, acc: 95.8582, loss_bbox: 0.1041, loss: 0.2567, grad_norm: 1.4733 2023-02-12 06:01:04,922 - mmrotate - INFO - Epoch [6][1500/8541] lr: 1.000e-04, eta: 5:00:26, time: 0.283, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0094, loss_rpn_bbox: 0.0426, loss_cls: 0.1013, acc: 95.8012, loss_bbox: 0.1034, loss: 0.2567, grad_norm: 1.4857 2023-02-12 06:03:29,361 - mmrotate - INFO - Epoch [6][2000/8541] lr: 1.000e-04, eta: 4:57:38, time: 0.289, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0095, loss_rpn_bbox: 0.0424, loss_cls: 0.0999, acc: 95.8803, loss_bbox: 0.1017, loss: 0.2535, grad_norm: 1.4990 2023-02-12 06:05:50,540 - mmrotate - INFO - Epoch [6][2500/8541] lr: 1.000e-04, eta: 4:54:47, time: 0.282, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0091, loss_rpn_bbox: 0.0422, loss_cls: 0.1005, acc: 95.8433, loss_bbox: 0.1038, loss: 0.2557, grad_norm: 1.5176 2023-02-12 06:08:25,443 - mmrotate - INFO - Epoch [6][3000/8541] lr: 1.000e-04, eta: 4:52:13, time: 0.310, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0092, loss_rpn_bbox: 0.0416, loss_cls: 0.0994, acc: 95.9126, loss_bbox: 0.1025, loss: 0.2527, grad_norm: 1.5344 2023-02-12 06:10:47,982 - mmrotate - INFO - Epoch [6][3500/8541] lr: 1.000e-04, eta: 4:49:24, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0101, loss_rpn_bbox: 0.0402, loss_cls: 0.1015, acc: 95.8079, loss_bbox: 0.1037, loss: 0.2556, grad_norm: 1.5231 2023-02-12 06:13:11,947 - mmrotate - INFO - Epoch [6][4000/8541] lr: 1.000e-04, eta: 4:46:38, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0102, loss_rpn_bbox: 0.0419, loss_cls: 0.1012, acc: 95.8232, loss_bbox: 0.1027, loss: 0.2560, grad_norm: 1.5061 2023-02-12 06:15:35,642 - mmrotate - INFO - Epoch [6][4500/8541] lr: 1.000e-04, eta: 4:43:51, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0103, loss_rpn_bbox: 0.0411, loss_cls: 0.0987, acc: 95.9444, loss_bbox: 0.1020, loss: 0.2521, grad_norm: 1.4782 2023-02-12 06:18:00,589 - mmrotate - INFO - Epoch [6][5000/8541] lr: 1.000e-04, eta: 4:41:07, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0097, loss_rpn_bbox: 0.0425, loss_cls: 0.0987, acc: 95.8982, loss_bbox: 0.1032, loss: 0.2542, grad_norm: 1.4935 2023-02-12 06:20:23,728 - mmrotate - INFO - Epoch [6][5500/8541] lr: 1.000e-04, eta: 4:38:21, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0096, loss_rpn_bbox: 0.0420, loss_cls: 0.1007, acc: 95.8407, loss_bbox: 0.1025, loss: 0.2549, grad_norm: 1.4959 2023-02-12 06:23:10,794 - mmrotate - INFO - Epoch [6][6000/8541] lr: 1.000e-04, eta: 4:36:02, time: 0.334, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0100, loss_rpn_bbox: 0.0429, loss_cls: 0.1022, acc: 95.7721, loss_bbox: 0.1043, loss: 0.2593, grad_norm: 1.5287 2023-02-12 06:26:30,101 - mmrotate - INFO - Epoch [6][6500/8541] lr: 1.000e-04, eta: 4:34:17, time: 0.399, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0097, loss_rpn_bbox: 0.0417, loss_cls: 0.0985, acc: 95.9618, loss_bbox: 0.0986, loss: 0.2486, grad_norm: 1.4939 2023-02-12 06:28:53,124 - mmrotate - INFO - Epoch [6][7000/8541] lr: 1.000e-04, eta: 4:31:30, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0087, loss_rpn_bbox: 0.0379, loss_cls: 0.0971, acc: 95.9975, loss_bbox: 0.1013, loss: 0.2450, grad_norm: 1.4763 2023-02-12 06:31:17,629 - mmrotate - INFO - Epoch [6][7500/8541] lr: 1.000e-04, eta: 4:28:46, time: 0.289, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0090, loss_rpn_bbox: 0.0408, loss_cls: 0.0958, acc: 96.0593, loss_bbox: 0.0993, loss: 0.2448, grad_norm: 1.4470 2023-02-12 06:34:00,174 - mmrotate - INFO - Epoch [6][8000/8541] lr: 1.000e-04, eta: 4:26:20, time: 0.325, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0088, loss_rpn_bbox: 0.0407, loss_cls: 0.0967, acc: 96.0479, loss_bbox: 0.1016, loss: 0.2479, grad_norm: 1.4766 2023-02-12 06:36:26,050 - mmrotate - INFO - Epoch [6][8500/8541] lr: 1.000e-04, eta: 4:23:37, time: 0.292, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0092, loss_rpn_bbox: 0.0445, loss_cls: 0.0996, acc: 95.9076, loss_bbox: 0.1041, loss: 0.2573, grad_norm: 1.5296 2023-02-12 06:36:38,104 - mmrotate - INFO - Saving checkpoint at 6 epochs 2023-02-12 06:39:13,737 - mmrotate - INFO - +--------------------+-------+-------+--------+-------+ | class | gts | dets | recall | ap | +--------------------+-------+-------+--------+-------+ | plane | 23860 | 33516 | 0.960 | 0.905 | | baseball-diamond | 1727 | 2629 | 0.956 | 0.894 | | bridge | 4142 | 9816 | 0.809 | 0.705 | | ground-track-field | 1134 | 2944 | 0.978 | 0.881 | | small-vehicle | 33183 | 66057 | 0.902 | 0.807 | | large-vehicle | 29737 | 49512 | 0.962 | 0.883 | | ship | 80574 | 91514 | 0.923 | 0.897 | | tennis-court | 4389 | 6432 | 0.982 | 0.908 | | basketball-court | 1097 | 1567 | 0.984 | 0.888 | | storage-tank | 28751 | 29605 | 0.733 | 0.715 | | soccer-ball-field | 1242 | 3823 | 0.927 | 0.856 | | roundabout | 1536 | 3116 | 0.925 | 0.891 | | harbor | 15489 | 22483 | 0.907 | 0.862 | | swimming-pool | 3456 | 9092 | 0.875 | 0.734 | | helicopter | 765 | 1477 | 0.902 | 0.850 | +--------------------+-------+-------+--------+-------+ | mAP | | | | 0.845 | +--------------------+-------+-------+--------+-------+ 2023-02-12 06:39:13,845 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 06:39:13,846 - mmrotate - INFO - Epoch(val) [6][2034] mAP: 0.8452 2023-02-12 06:41:40,645 - mmrotate - INFO - Epoch [7][500/8541] lr: 1.000e-04, eta: 4:20:31, time: 0.293, data_time: 0.011, memory: 10130, loss_rpn_cls: 0.0088, loss_rpn_bbox: 0.0406, loss_cls: 0.0942, acc: 96.1211, loss_bbox: 0.0979, loss: 0.2415, grad_norm: 1.4824 2023-02-12 06:44:38,752 - mmrotate - INFO - Epoch [7][1000/8541] lr: 1.000e-04, eta: 4:18:20, time: 0.356, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0091, loss_rpn_bbox: 0.0428, loss_cls: 0.0954, acc: 96.0647, loss_bbox: 0.1013, loss: 0.2486, grad_norm: 1.5092 2023-02-12 06:47:03,747 - mmrotate - INFO - Epoch [7][1500/8541] lr: 1.000e-04, eta: 4:15:37, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0088, loss_rpn_bbox: 0.0392, loss_cls: 0.0969, acc: 96.0057, loss_bbox: 0.1032, loss: 0.2482, grad_norm: 1.4743 2023-02-12 06:49:26,970 - mmrotate - INFO - Epoch [7][2000/8541] lr: 1.000e-04, eta: 4:12:53, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0086, loss_rpn_bbox: 0.0386, loss_cls: 0.0957, acc: 96.0571, loss_bbox: 0.0987, loss: 0.2417, grad_norm: 1.4536 2023-02-12 06:51:50,399 - mmrotate - INFO - Epoch [7][2500/8541] lr: 1.000e-04, eta: 4:10:09, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0087, loss_rpn_bbox: 0.0388, loss_cls: 0.0932, acc: 96.1268, loss_bbox: 0.0988, loss: 0.2394, grad_norm: 1.4668 2023-02-12 06:54:14,791 - mmrotate - INFO - Epoch [7][3000/8541] lr: 1.000e-04, eta: 4:07:26, time: 0.289, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0085, loss_rpn_bbox: 0.0419, loss_cls: 0.0962, acc: 96.0456, loss_bbox: 0.1003, loss: 0.2469, grad_norm: 1.4977 2023-02-12 06:56:51,965 - mmrotate - INFO - Epoch [7][3500/8541] lr: 1.000e-04, eta: 4:04:55, time: 0.314, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0092, loss_rpn_bbox: 0.0407, loss_cls: 0.0976, acc: 95.9821, loss_bbox: 0.1006, loss: 0.2481, grad_norm: 1.5074 2023-02-12 06:59:13,414 - mmrotate - INFO - Epoch [7][4000/8541] lr: 1.000e-04, eta: 4:02:11, time: 0.283, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0093, loss_rpn_bbox: 0.0421, loss_cls: 0.0941, acc: 96.1006, loss_bbox: 0.0991, loss: 0.2445, grad_norm: 1.5069 2023-02-12 07:01:38,774 - mmrotate - INFO - Epoch [7][4500/8541] lr: 1.000e-04, eta: 3:59:30, time: 0.291, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0089, loss_rpn_bbox: 0.0401, loss_cls: 0.0980, acc: 95.9637, loss_bbox: 0.1009, loss: 0.2479, grad_norm: 1.4762 2023-02-12 07:04:02,291 - mmrotate - INFO - Epoch [7][5000/8541] lr: 1.000e-04, eta: 3:56:48, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0086, loss_rpn_bbox: 0.0445, loss_cls: 0.0966, acc: 96.0107, loss_bbox: 0.1014, loss: 0.2510, grad_norm: 1.5236 2023-02-12 07:06:25,994 - mmrotate - INFO - Epoch [7][5500/8541] lr: 1.000e-04, eta: 3:54:06, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0086, loss_rpn_bbox: 0.0394, loss_cls: 0.0932, acc: 96.1489, loss_bbox: 0.0984, loss: 0.2397, grad_norm: 1.4277 2023-02-12 07:08:49,980 - mmrotate - INFO - Epoch [7][6000/8541] lr: 1.000e-04, eta: 3:51:25, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0085, loss_rpn_bbox: 0.0390, loss_cls: 0.0941, acc: 96.0863, loss_bbox: 0.0983, loss: 0.2399, grad_norm: 1.4687 2023-02-12 07:11:58,428 - mmrotate - INFO - Epoch [7][6500/8541] lr: 1.000e-04, eta: 3:49:19, time: 0.377, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0089, loss_rpn_bbox: 0.0397, loss_cls: 0.0959, acc: 96.0163, loss_bbox: 0.0992, loss: 0.2436, grad_norm: 1.4894 2023-02-12 07:14:21,737 - mmrotate - INFO - Epoch [7][7000/8541] lr: 1.000e-04, eta: 3:46:37, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0090, loss_rpn_bbox: 0.0424, loss_cls: 0.0981, acc: 95.9375, loss_bbox: 0.1014, loss: 0.2509, grad_norm: 1.4815 2023-02-12 07:16:44,024 - mmrotate - INFO - Epoch [7][7500/8541] lr: 1.000e-04, eta: 3:43:55, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0089, loss_rpn_bbox: 0.0399, loss_cls: 0.0953, acc: 96.0625, loss_bbox: 0.0991, loss: 0.2433, grad_norm: 1.4609 2023-02-12 07:19:48,706 - mmrotate - INFO - Epoch [7][8000/8541] lr: 1.000e-04, eta: 3:41:44, time: 0.369, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0082, loss_rpn_bbox: 0.0379, loss_cls: 0.0937, acc: 96.1363, loss_bbox: 0.0985, loss: 0.2383, grad_norm: 1.4031 2023-02-12 07:22:12,761 - mmrotate - INFO - Epoch [7][8500/8541] lr: 1.000e-04, eta: 3:39:03, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0080, loss_rpn_bbox: 0.0403, loss_cls: 0.0935, acc: 96.1287, loss_bbox: 0.0978, loss: 0.2396, grad_norm: 1.4790 2023-02-12 07:22:25,045 - mmrotate - INFO - Saving checkpoint at 7 epochs 2023-02-12 07:24:55,020 - mmrotate - INFO - Epoch [8][500/8541] lr: 1.000e-04, eta: 3:36:04, time: 0.295, data_time: 0.011, memory: 10130, loss_rpn_cls: 0.0082, loss_rpn_bbox: 0.0365, loss_cls: 0.0895, acc: 96.3042, loss_bbox: 0.0949, loss: 0.2290, grad_norm: 1.4363 2023-02-12 07:27:52,993 - mmrotate - INFO - Epoch [8][1000/8541] lr: 1.000e-04, eta: 3:33:47, time: 0.356, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0081, loss_rpn_bbox: 0.0410, loss_cls: 0.0916, acc: 96.2484, loss_bbox: 0.0966, loss: 0.2373, grad_norm: 1.4771 2023-02-12 07:30:15,896 - mmrotate - INFO - Epoch [8][1500/8541] lr: 1.000e-04, eta: 3:31:06, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0084, loss_rpn_bbox: 0.0395, loss_cls: 0.0924, acc: 96.1661, loss_bbox: 0.0984, loss: 0.2386, grad_norm: 1.4659 2023-02-12 07:32:38,130 - mmrotate - INFO - Epoch [8][2000/8541] lr: 1.000e-04, eta: 3:28:25, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0074, loss_rpn_bbox: 0.0382, loss_cls: 0.0939, acc: 96.1031, loss_bbox: 0.0988, loss: 0.2383, grad_norm: 1.4569 2023-02-12 07:36:09,796 - mmrotate - INFO - Epoch [8][2500/8541] lr: 1.000e-04, eta: 3:26:29, time: 0.423, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0085, loss_rpn_bbox: 0.0394, loss_cls: 0.0915, acc: 96.2090, loss_bbox: 0.0968, loss: 0.2362, grad_norm: 1.4925 2023-02-12 07:38:32,687 - mmrotate - INFO - Epoch [8][3000/8541] lr: 1.000e-04, eta: 3:23:48, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0084, loss_rpn_bbox: 0.0392, loss_cls: 0.0924, acc: 96.1890, loss_bbox: 0.0966, loss: 0.2365, grad_norm: 1.4572 2023-02-12 07:40:58,566 - mmrotate - INFO - Epoch [8][3500/8541] lr: 1.000e-04, eta: 3:21:09, time: 0.292, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0072, loss_rpn_bbox: 0.0385, loss_cls: 0.0897, acc: 96.2620, loss_bbox: 0.0968, loss: 0.2323, grad_norm: 1.4284 2023-02-12 07:43:21,973 - mmrotate - INFO - Epoch [8][4000/8541] lr: 1.000e-04, eta: 3:18:28, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0086, loss_rpn_bbox: 0.0399, loss_cls: 0.0921, acc: 96.1897, loss_bbox: 0.0978, loss: 0.2384, grad_norm: 1.4541 2023-02-12 07:45:43,879 - mmrotate - INFO - Epoch [8][4500/8541] lr: 1.000e-04, eta: 3:15:47, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0083, loss_rpn_bbox: 0.0396, loss_cls: 0.0963, acc: 96.0435, loss_bbox: 0.0986, loss: 0.2428, grad_norm: 1.5117 2023-02-12 07:48:07,059 - mmrotate - INFO - Epoch [8][5000/8541] lr: 1.000e-04, eta: 3:13:07, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0083, loss_rpn_bbox: 0.0376, loss_cls: 0.0905, acc: 96.2560, loss_bbox: 0.0946, loss: 0.2310, grad_norm: 1.5005 2023-02-12 07:50:30,889 - mmrotate - INFO - Epoch [8][5500/8541] lr: 1.000e-04, eta: 3:10:28, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0082, loss_rpn_bbox: 0.0383, loss_cls: 0.0914, acc: 96.2149, loss_bbox: 0.0959, loss: 0.2340, grad_norm: 1.4594 2023-02-12 07:53:11,661 - mmrotate - INFO - Epoch [8][6000/8541] lr: 1.000e-04, eta: 3:07:59, time: 0.321, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0087, loss_rpn_bbox: 0.0408, loss_cls: 0.0924, acc: 96.2075, loss_bbox: 0.0976, loss: 0.2394, grad_norm: 1.4764 2023-02-12 07:55:33,744 - mmrotate - INFO - Epoch [8][6500/8541] lr: 1.000e-04, eta: 3:05:19, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0080, loss_rpn_bbox: 0.0405, loss_cls: 0.0949, acc: 96.0665, loss_bbox: 0.0981, loss: 0.2416, grad_norm: 1.4793 2023-02-12 07:57:57,985 - mmrotate - INFO - Epoch [8][7000/8541] lr: 1.000e-04, eta: 3:02:40, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0078, loss_rpn_bbox: 0.0376, loss_cls: 0.0910, acc: 96.2268, loss_bbox: 0.0969, loss: 0.2333, grad_norm: 1.4377 2023-02-12 08:00:21,360 - mmrotate - INFO - Epoch [8][7500/8541] lr: 1.000e-04, eta: 3:00:01, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0086, loss_rpn_bbox: 0.0405, loss_cls: 0.0943, acc: 96.1169, loss_bbox: 0.0973, loss: 0.2407, grad_norm: 1.5380 2023-02-12 08:02:44,914 - mmrotate - INFO - Epoch [8][8000/8541] lr: 1.000e-04, eta: 2:57:23, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0083, loss_rpn_bbox: 0.0377, loss_cls: 0.0921, acc: 96.2142, loss_bbox: 0.0948, loss: 0.2329, grad_norm: 1.4791 2023-02-12 08:05:38,465 - mmrotate - INFO - Epoch [8][8500/8541] lr: 1.000e-04, eta: 2:55:00, time: 0.347, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0096, loss_rpn_bbox: 0.0408, loss_cls: 0.0952, acc: 96.0699, loss_bbox: 0.0984, loss: 0.2441, grad_norm: 1.5513 2023-02-12 08:05:50,128 - mmrotate - INFO - Saving checkpoint at 8 epochs 2023-02-12 08:08:20,897 - mmrotate - INFO - Epoch [9][500/8541] lr: 1.000e-05, eta: 2:52:05, time: 0.296, data_time: 0.011, memory: 10130, loss_rpn_cls: 0.0070, loss_rpn_bbox: 0.0368, loss_cls: 0.0838, acc: 96.4996, loss_bbox: 0.0901, loss: 0.2178, grad_norm: 1.2736 2023-02-12 08:11:36,238 - mmrotate - INFO - Epoch [9][1000/8541] lr: 1.000e-05, eta: 2:49:51, time: 0.391, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0070, loss_rpn_bbox: 0.0355, loss_cls: 0.0840, acc: 96.4989, loss_bbox: 0.0909, loss: 0.2173, grad_norm: 1.2489 2023-02-12 08:14:01,401 - mmrotate - INFO - Epoch [9][1500/8541] lr: 1.000e-05, eta: 2:47:14, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0065, loss_rpn_bbox: 0.0354, loss_cls: 0.0820, acc: 96.5945, loss_bbox: 0.0885, loss: 0.2123, grad_norm: 1.2638 2023-02-12 08:17:00,843 - mmrotate - INFO - Epoch [9][2000/8541] lr: 1.000e-05, eta: 2:44:52, time: 0.359, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0065, loss_rpn_bbox: 0.0364, loss_cls: 0.0807, acc: 96.6375, loss_bbox: 0.0871, loss: 0.2108, grad_norm: 1.2634 2023-02-12 08:19:25,726 - mmrotate - INFO - Epoch [9][2500/8541] lr: 1.000e-05, eta: 2:42:14, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0063, loss_rpn_bbox: 0.0350, loss_cls: 0.0796, acc: 96.6820, loss_bbox: 0.0876, loss: 0.2085, grad_norm: 1.2491 2023-02-12 08:21:51,135 - mmrotate - INFO - Epoch [9][3000/8541] lr: 1.000e-05, eta: 2:39:37, time: 0.291, data_time: 0.005, memory: 10130, loss_rpn_cls: 0.0057, loss_rpn_bbox: 0.0307, loss_cls: 0.0787, acc: 96.7315, loss_bbox: 0.0851, loss: 0.2002, grad_norm: 1.2245 2023-02-12 08:24:16,533 - mmrotate - INFO - Epoch [9][3500/8541] lr: 1.000e-05, eta: 2:37:00, time: 0.291, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0059, loss_rpn_bbox: 0.0318, loss_cls: 0.0775, acc: 96.7577, loss_bbox: 0.0860, loss: 0.2012, grad_norm: 1.2332 2023-02-12 08:26:41,786 - mmrotate - INFO - Epoch [9][4000/8541] lr: 1.000e-05, eta: 2:34:23, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0058, loss_rpn_bbox: 0.0329, loss_cls: 0.0790, acc: 96.6867, loss_bbox: 0.0871, loss: 0.2048, grad_norm: 1.2546 2023-02-12 08:29:08,564 - mmrotate - INFO - Epoch [9][4500/8541] lr: 1.000e-05, eta: 2:31:46, time: 0.294, data_time: 0.005, memory: 10130, loss_rpn_cls: 0.0058, loss_rpn_bbox: 0.0324, loss_cls: 0.0772, acc: 96.7743, loss_bbox: 0.0844, loss: 0.1998, grad_norm: 1.2365 2023-02-12 08:31:47,135 - mmrotate - INFO - Epoch [9][5000/8541] lr: 1.000e-05, eta: 2:29:15, time: 0.317, data_time: 0.005, memory: 10130, loss_rpn_cls: 0.0059, loss_rpn_bbox: 0.0309, loss_cls: 0.0775, acc: 96.7552, loss_bbox: 0.0848, loss: 0.1991, grad_norm: 1.2215 2023-02-12 08:34:38,023 - mmrotate - INFO - Epoch [9][5500/8541] lr: 1.000e-05, eta: 2:26:48, time: 0.342, data_time: 0.005, memory: 10130, loss_rpn_cls: 0.0055, loss_rpn_bbox: 0.0325, loss_cls: 0.0749, acc: 96.8776, loss_bbox: 0.0855, loss: 0.1984, grad_norm: 1.2292 2023-02-12 08:37:02,648 - mmrotate - INFO - Epoch [9][6000/8541] lr: 1.000e-05, eta: 2:24:11, time: 0.289, data_time: 0.005, memory: 10130, loss_rpn_cls: 0.0059, loss_rpn_bbox: 0.0307, loss_cls: 0.0770, acc: 96.8091, loss_bbox: 0.0849, loss: 0.1985, grad_norm: 1.2672 2023-02-12 08:39:48,266 - mmrotate - INFO - Epoch [9][6500/8541] lr: 1.000e-05, eta: 2:21:42, time: 0.331, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0056, loss_rpn_bbox: 0.0342, loss_cls: 0.0773, acc: 96.7719, loss_bbox: 0.0855, loss: 0.2026, grad_norm: 1.2627 2023-02-12 08:42:10,667 - mmrotate - INFO - Epoch [9][7000/8541] lr: 1.000e-05, eta: 2:19:04, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0054, loss_rpn_bbox: 0.0323, loss_cls: 0.0757, acc: 96.8372, loss_bbox: 0.0845, loss: 0.1979, grad_norm: 1.2367 2023-02-12 08:44:34,298 - mmrotate - INFO - Epoch [9][7500/8541] lr: 1.000e-05, eta: 2:16:27, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0057, loss_rpn_bbox: 0.0336, loss_cls: 0.0748, acc: 96.8781, loss_bbox: 0.0829, loss: 0.1969, grad_norm: 1.2395 2023-02-12 08:47:02,353 - mmrotate - INFO - Epoch [9][8000/8541] lr: 1.000e-05, eta: 2:13:52, time: 0.296, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0059, loss_rpn_bbox: 0.0318, loss_cls: 0.0763, acc: 96.8203, loss_bbox: 0.0837, loss: 0.1977, grad_norm: 1.2610 2023-02-12 08:49:26,617 - mmrotate - INFO - Epoch [9][8500/8541] lr: 1.000e-05, eta: 2:11:15, time: 0.289, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0057, loss_rpn_bbox: 0.0314, loss_cls: 0.0749, acc: 96.8678, loss_bbox: 0.0837, loss: 0.1957, grad_norm: 1.2556 2023-02-12 08:49:38,725 - mmrotate - INFO - Saving checkpoint at 9 epochs 2023-02-12 08:52:17,009 - mmrotate - INFO - +--------------------+-------+-------+--------+-------+ | class | gts | dets | recall | ap | +--------------------+-------+-------+--------+-------+ | plane | 23860 | 27070 | 0.959 | 0.907 | | baseball-diamond | 1727 | 2658 | 0.970 | 0.903 | | bridge | 4142 | 8312 | 0.857 | 0.773 | | ground-track-field | 1134 | 2821 | 0.993 | 0.898 | | small-vehicle | 33183 | 50130 | 0.901 | 0.842 | | large-vehicle | 29737 | 44477 | 0.969 | 0.896 | | ship | 80574 | 89612 | 0.927 | 0.901 | | tennis-court | 4389 | 5442 | 0.991 | 0.909 | | basketball-court | 1097 | 1996 | 0.996 | 0.904 | | storage-tank | 28751 | 26301 | 0.712 | 0.714 | | soccer-ball-field | 1242 | 2445 | 0.935 | 0.881 | | roundabout | 1536 | 2726 | 0.942 | 0.903 | | harbor | 15489 | 21679 | 0.926 | 0.881 | | swimming-pool | 3456 | 5932 | 0.890 | 0.758 | | helicopter | 765 | 1280 | 0.928 | 0.896 | +--------------------+-------+-------+--------+-------+ | mAP | | | | 0.864 | +--------------------+-------+-------+--------+-------+ 2023-02-12 08:52:17,120 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 08:52:17,120 - mmrotate - INFO - Epoch(val) [9][2034] mAP: 0.8643 2023-02-12 08:55:35,450 - mmrotate - INFO - Epoch [10][500/8541] lr: 1.000e-05, eta: 2:08:39, time: 0.396, data_time: 0.011, memory: 10130, loss_rpn_cls: 0.0051, loss_rpn_bbox: 0.0323, loss_cls: 0.0750, acc: 96.8580, loss_bbox: 0.0827, loss: 0.1951, grad_norm: 1.2110 2023-02-12 08:58:13,119 - mmrotate - INFO - Epoch [10][1000/8541] lr: 1.000e-05, eta: 2:06:07, time: 0.315, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0051, loss_rpn_bbox: 0.0305, loss_cls: 0.0737, acc: 96.9257, loss_bbox: 0.0832, loss: 0.1924, grad_norm: 1.2047 2023-02-12 09:00:35,792 - mmrotate - INFO - Epoch [10][1500/8541] lr: 1.000e-05, eta: 2:03:30, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0056, loss_rpn_bbox: 0.0316, loss_cls: 0.0754, acc: 96.8500, loss_bbox: 0.0841, loss: 0.1967, grad_norm: 1.2559 2023-02-12 09:02:58,600 - mmrotate - INFO - Epoch [10][2000/8541] lr: 1.000e-05, eta: 2:00:53, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0054, loss_rpn_bbox: 0.0310, loss_cls: 0.0747, acc: 96.8681, loss_bbox: 0.0830, loss: 0.1942, grad_norm: 1.2369 2023-02-12 09:05:20,527 - mmrotate - INFO - Epoch [10][2500/8541] lr: 1.000e-05, eta: 1:58:16, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0053, loss_rpn_bbox: 0.0313, loss_cls: 0.0749, acc: 96.8709, loss_bbox: 0.0834, loss: 0.1949, grad_norm: 1.2386 2023-02-12 09:07:44,537 - mmrotate - INFO - Epoch [10][3000/8541] lr: 1.000e-05, eta: 1:55:40, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0053, loss_rpn_bbox: 0.0325, loss_cls: 0.0744, acc: 96.8973, loss_bbox: 0.0826, loss: 0.1949, grad_norm: 1.2480 2023-02-12 09:10:07,460 - mmrotate - INFO - Epoch [10][3500/8541] lr: 1.000e-05, eta: 1:53:04, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0054, loss_rpn_bbox: 0.0322, loss_cls: 0.0728, acc: 96.9714, loss_bbox: 0.0831, loss: 0.1935, grad_norm: 1.2281 2023-02-12 09:12:31,182 - mmrotate - INFO - Epoch [10][4000/8541] lr: 1.000e-05, eta: 1:50:28, time: 0.287, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0325, loss_cls: 0.0732, acc: 96.9384, loss_bbox: 0.0843, loss: 0.1951, grad_norm: 1.2383 2023-02-12 09:15:43,253 - mmrotate - INFO - Epoch [10][4500/8541] lr: 1.000e-05, eta: 1:48:05, time: 0.384, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0057, loss_rpn_bbox: 0.0317, loss_cls: 0.0724, acc: 96.9921, loss_bbox: 0.0831, loss: 0.1928, grad_norm: 1.2530 2023-02-12 09:18:07,255 - mmrotate - INFO - Epoch [10][5000/8541] lr: 1.000e-05, eta: 1:45:29, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0051, loss_rpn_bbox: 0.0318, loss_cls: 0.0738, acc: 96.9208, loss_bbox: 0.0827, loss: 0.1934, grad_norm: 1.2684 2023-02-12 09:20:31,556 - mmrotate - INFO - Epoch [10][5500/8541] lr: 1.000e-05, eta: 1:42:53, time: 0.289, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0054, loss_rpn_bbox: 0.0341, loss_cls: 0.0743, acc: 96.8854, loss_bbox: 0.0845, loss: 0.1984, grad_norm: 1.2672 2023-02-12 09:23:20,548 - mmrotate - INFO - Epoch [10][6000/8541] lr: 1.000e-05, eta: 1:40:23, time: 0.338, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0319, loss_cls: 0.0711, acc: 97.0395, loss_bbox: 0.0813, loss: 0.1892, grad_norm: 1.2452 2023-02-12 09:25:43,071 - mmrotate - INFO - Epoch [10][6500/8541] lr: 1.000e-05, eta: 1:37:47, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0325, loss_cls: 0.0722, acc: 96.9863, loss_bbox: 0.0823, loss: 0.1920, grad_norm: 1.2254 2023-02-12 09:28:05,871 - mmrotate - INFO - Epoch [10][7000/8541] lr: 1.000e-05, eta: 1:35:12, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0053, loss_rpn_bbox: 0.0323, loss_cls: 0.0708, acc: 97.0445, loss_bbox: 0.0814, loss: 0.1899, grad_norm: 1.2427 2023-02-12 09:30:28,821 - mmrotate - INFO - Epoch [10][7500/8541] lr: 1.000e-05, eta: 1:32:36, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0054, loss_rpn_bbox: 0.0322, loss_cls: 0.0725, acc: 96.9797, loss_bbox: 0.0819, loss: 0.1920, grad_norm: 1.2383 2023-02-12 09:32:51,021 - mmrotate - INFO - Epoch [10][8000/8541] lr: 1.000e-05, eta: 1:30:00, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0316, loss_cls: 0.0729, acc: 96.9611, loss_bbox: 0.0816, loss: 0.1912, grad_norm: 1.2332 2023-02-12 09:35:15,132 - mmrotate - INFO - Epoch [10][8500/8541] lr: 1.000e-05, eta: 1:27:25, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0049, loss_rpn_bbox: 0.0316, loss_cls: 0.0713, acc: 97.0423, loss_bbox: 0.0808, loss: 0.1885, grad_norm: 1.2361 2023-02-12 09:35:27,410 - mmrotate - INFO - Saving checkpoint at 10 epochs 2023-02-12 09:38:12,444 - mmrotate - INFO - Epoch [11][500/8541] lr: 1.000e-05, eta: 1:24:39, time: 0.325, data_time: 0.011, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0314, loss_cls: 0.0718, acc: 96.9982, loss_bbox: 0.0805, loss: 0.1887, grad_norm: 1.2461 2023-02-12 09:40:38,114 - mmrotate - INFO - Epoch [11][1000/8541] lr: 1.000e-05, eta: 1:22:04, time: 0.291, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0054, loss_rpn_bbox: 0.0313, loss_cls: 0.0730, acc: 96.9442, loss_bbox: 0.0821, loss: 0.1918, grad_norm: 1.2459 2023-02-12 09:42:59,911 - mmrotate - INFO - Epoch [11][1500/8541] lr: 1.000e-05, eta: 1:19:29, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0314, loss_cls: 0.0711, acc: 97.0392, loss_bbox: 0.0797, loss: 0.1871, grad_norm: 1.2591 2023-02-12 09:45:22,518 - mmrotate - INFO - Epoch [11][2000/8541] lr: 1.000e-05, eta: 1:16:54, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0051, loss_rpn_bbox: 0.0310, loss_cls: 0.0710, acc: 97.0269, loss_bbox: 0.0815, loss: 0.1887, grad_norm: 1.2438 2023-02-12 09:48:10,391 - mmrotate - INFO - Epoch [11][2500/8541] lr: 1.000e-05, eta: 1:14:24, time: 0.336, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0046, loss_rpn_bbox: 0.0316, loss_cls: 0.0720, acc: 96.9829, loss_bbox: 0.0828, loss: 0.1910, grad_norm: 1.2513 2023-02-12 09:50:36,477 - mmrotate - INFO - Epoch [11][3000/8541] lr: 1.000e-05, eta: 1:11:50, time: 0.292, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0052, loss_rpn_bbox: 0.0321, loss_cls: 0.0730, acc: 96.9418, loss_bbox: 0.0827, loss: 0.1930, grad_norm: 1.2739 2023-02-12 09:52:59,189 - mmrotate - INFO - Epoch [11][3500/8541] lr: 1.000e-05, eta: 1:09:15, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0053, loss_rpn_bbox: 0.0321, loss_cls: 0.0699, acc: 97.0727, loss_bbox: 0.0813, loss: 0.1886, grad_norm: 1.2461 2023-02-12 09:55:21,394 - mmrotate - INFO - Epoch [11][4000/8541] lr: 1.000e-05, eta: 1:06:41, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0049, loss_rpn_bbox: 0.0301, loss_cls: 0.0715, acc: 97.0265, loss_bbox: 0.0810, loss: 0.1875, grad_norm: 1.2562 2023-02-12 09:57:43,098 - mmrotate - INFO - Epoch [11][4500/8541] lr: 1.000e-05, eta: 1:04:06, time: 0.283, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0047, loss_rpn_bbox: 0.0316, loss_cls: 0.0706, acc: 97.0514, loss_bbox: 0.0799, loss: 0.1869, grad_norm: 1.2514 2023-02-12 10:00:06,215 - mmrotate - INFO - Epoch [11][5000/8541] lr: 1.000e-05, eta: 1:01:32, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0055, loss_rpn_bbox: 0.0306, loss_cls: 0.0708, acc: 97.0456, loss_bbox: 0.0806, loss: 0.1876, grad_norm: 1.2690 2023-02-12 10:02:29,325 - mmrotate - INFO - Epoch [11][5500/8541] lr: 1.000e-05, eta: 0:58:58, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0049, loss_rpn_bbox: 0.0311, loss_cls: 0.0699, acc: 97.0734, loss_bbox: 0.0804, loss: 0.1862, grad_norm: 1.2383 2023-02-12 10:04:51,798 - mmrotate - INFO - Epoch [11][6000/8541] lr: 1.000e-05, eta: 0:56:24, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0312, loss_cls: 0.0718, acc: 96.9854, loss_bbox: 0.0820, loss: 0.1901, grad_norm: 1.2698 2023-02-12 10:07:12,248 - mmrotate - INFO - Epoch [11][6500/8541] lr: 1.000e-05, eta: 0:53:50, time: 0.281, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0048, loss_rpn_bbox: 0.0304, loss_cls: 0.0705, acc: 97.0475, loss_bbox: 0.0802, loss: 0.1859, grad_norm: 1.2491 2023-02-12 10:09:36,009 - mmrotate - INFO - Epoch [11][7000/8541] lr: 1.000e-05, eta: 0:51:16, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0052, loss_rpn_bbox: 0.0316, loss_cls: 0.0701, acc: 97.0815, loss_bbox: 0.0814, loss: 0.1883, grad_norm: 1.2540 2023-02-12 10:12:00,250 - mmrotate - INFO - Epoch [11][7500/8541] lr: 1.000e-05, eta: 0:48:43, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0046, loss_rpn_bbox: 0.0306, loss_cls: 0.0695, acc: 97.1024, loss_bbox: 0.0807, loss: 0.1854, grad_norm: 1.2123 2023-02-12 10:15:08,250 - mmrotate - INFO - Epoch [11][8000/8541] lr: 1.000e-05, eta: 0:46:14, time: 0.376, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0051, loss_rpn_bbox: 0.0320, loss_cls: 0.0701, acc: 97.0699, loss_bbox: 0.0797, loss: 0.1869, grad_norm: 1.2601 2023-02-12 10:18:13,840 - mmrotate - INFO - Epoch [11][8500/8541] lr: 1.000e-05, eta: 0:43:44, time: 0.371, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0305, loss_cls: 0.0708, acc: 97.0347, loss_bbox: 0.0804, loss: 0.1867, grad_norm: 1.2681 2023-02-12 10:18:25,729 - mmrotate - INFO - Saving checkpoint at 11 epochs 2023-02-12 10:20:54,971 - mmrotate - INFO - Epoch [12][500/8541] lr: 1.000e-06, eta: 0:40:57, time: 0.293, data_time: 0.011, memory: 10130, loss_rpn_cls: 0.0049, loss_rpn_bbox: 0.0300, loss_cls: 0.0679, acc: 97.1600, loss_bbox: 0.0797, loss: 0.1826, grad_norm: 1.2410 2023-02-12 10:23:17,404 - mmrotate - INFO - Epoch [12][1000/8541] lr: 1.000e-06, eta: 0:38:23, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0053, loss_rpn_bbox: 0.0300, loss_cls: 0.0718, acc: 96.9974, loss_bbox: 0.0817, loss: 0.1888, grad_norm: 1.2500 2023-02-12 10:25:39,465 - mmrotate - INFO - Epoch [12][1500/8541] lr: 1.000e-06, eta: 0:35:50, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0049, loss_rpn_bbox: 0.0310, loss_cls: 0.0699, acc: 97.0828, loss_bbox: 0.0788, loss: 0.1847, grad_norm: 1.2574 2023-02-12 10:28:01,997 - mmrotate - INFO - Epoch [12][2000/8541] lr: 1.000e-06, eta: 0:33:16, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0048, loss_rpn_bbox: 0.0297, loss_cls: 0.0690, acc: 97.1284, loss_bbox: 0.0796, loss: 0.1831, grad_norm: 1.2336 2023-02-12 10:30:26,149 - mmrotate - INFO - Epoch [12][2500/8541] lr: 1.000e-06, eta: 0:30:43, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0301, loss_cls: 0.0705, acc: 97.0683, loss_bbox: 0.0798, loss: 0.1853, grad_norm: 1.2418 2023-02-12 10:32:48,337 - mmrotate - INFO - Epoch [12][3000/8541] lr: 1.000e-06, eta: 0:28:10, time: 0.284, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0051, loss_rpn_bbox: 0.0298, loss_cls: 0.0691, acc: 97.0961, loss_bbox: 0.0786, loss: 0.1826, grad_norm: 1.2009 2023-02-12 10:35:28,126 - mmrotate - INFO - Epoch [12][3500/8541] lr: 1.000e-06, eta: 0:25:38, time: 0.320, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0050, loss_rpn_bbox: 0.0319, loss_cls: 0.0703, acc: 97.0687, loss_bbox: 0.0816, loss: 0.1888, grad_norm: 1.2243 2023-02-12 10:37:53,022 - mmrotate - INFO - Epoch [12][4000/8541] lr: 1.000e-06, eta: 0:23:05, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0048, loss_rpn_bbox: 0.0306, loss_cls: 0.0682, acc: 97.1773, loss_bbox: 0.0789, loss: 0.1825, grad_norm: 1.2074 2023-02-12 10:40:15,567 - mmrotate - INFO - Epoch [12][4500/8541] lr: 1.000e-06, eta: 0:20:32, time: 0.285, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0042, loss_rpn_bbox: 0.0298, loss_cls: 0.0678, acc: 97.1695, loss_bbox: 0.0777, loss: 0.1795, grad_norm: 1.2103 2023-02-12 10:42:38,655 - mmrotate - INFO - Epoch [12][5000/8541] lr: 1.000e-06, eta: 0:17:59, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0046, loss_rpn_bbox: 0.0313, loss_cls: 0.0687, acc: 97.1511, loss_bbox: 0.0792, loss: 0.1838, grad_norm: 1.2422 2023-02-12 10:45:04,066 - mmrotate - INFO - Epoch [12][5500/8541] lr: 1.000e-06, eta: 0:15:26, time: 0.291, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0045, loss_rpn_bbox: 0.0301, loss_cls: 0.0681, acc: 97.1623, loss_bbox: 0.0777, loss: 0.1803, grad_norm: 1.2009 2023-02-12 10:48:14,308 - mmrotate - INFO - Epoch [12][6000/8541] lr: 1.000e-06, eta: 0:12:55, time: 0.380, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0047, loss_rpn_bbox: 0.0304, loss_cls: 0.0700, acc: 97.0671, loss_bbox: 0.0797, loss: 0.1849, grad_norm: 1.2459 2023-02-12 10:50:38,392 - mmrotate - INFO - Epoch [12][6500/8541] lr: 1.000e-06, eta: 0:10:22, time: 0.288, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0046, loss_rpn_bbox: 0.0307, loss_cls: 0.0683, acc: 97.1546, loss_bbox: 0.0793, loss: 0.1828, grad_norm: 1.2276 2023-02-12 10:53:32,690 - mmrotate - INFO - Epoch [12][7000/8541] lr: 1.000e-06, eta: 0:07:50, time: 0.349, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0049, loss_rpn_bbox: 0.0327, loss_cls: 0.0696, acc: 97.0910, loss_bbox: 0.0805, loss: 0.1876, grad_norm: 1.2586 2023-02-12 10:55:57,818 - mmrotate - INFO - Epoch [12][7500/8541] lr: 1.000e-06, eta: 0:05:17, time: 0.290, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0047, loss_rpn_bbox: 0.0287, loss_cls: 0.0681, acc: 97.1527, loss_bbox: 0.0791, loss: 0.1806, grad_norm: 1.2266 2023-02-12 10:58:20,984 - mmrotate - INFO - Epoch [12][8000/8541] lr: 1.000e-06, eta: 0:02:45, time: 0.286, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0047, loss_rpn_bbox: 0.0307, loss_cls: 0.0695, acc: 97.1011, loss_bbox: 0.0811, loss: 0.1860, grad_norm: 1.2599 2023-02-12 11:01:37,525 - mmrotate - INFO - Epoch [12][8500/8541] lr: 1.000e-06, eta: 0:00:12, time: 0.393, data_time: 0.004, memory: 10130, loss_rpn_cls: 0.0049, loss_rpn_bbox: 0.0316, loss_cls: 0.0721, acc: 96.9961, loss_bbox: 0.0822, loss: 0.1908, grad_norm: 1.2890 2023-02-12 11:01:49,220 - mmrotate - INFO - Saving checkpoint at 12 epochs 2023-02-12 11:04:27,450 - mmrotate - INFO - +--------------------+-------+-------+--------+-------+ | class | gts | dets | recall | ap | +--------------------+-------+-------+--------+-------+ | plane | 23860 | 25701 | 0.958 | 0.907 | | baseball-diamond | 1727 | 2303 | 0.975 | 0.905 | | bridge | 4142 | 7437 | 0.869 | 0.784 | | ground-track-field | 1134 | 2292 | 0.994 | 0.901 | | small-vehicle | 33183 | 46127 | 0.902 | 0.856 | | large-vehicle | 29737 | 44095 | 0.973 | 0.899 | | ship | 80574 | 87361 | 0.922 | 0.901 | | tennis-court | 4389 | 5176 | 0.994 | 0.909 | | basketball-court | 1097 | 1688 | 0.996 | 0.908 | | storage-tank | 28751 | 24622 | 0.703 | 0.713 | | soccer-ball-field | 1242 | 2179 | 0.936 | 0.890 | | roundabout | 1536 | 2341 | 0.941 | 0.904 | | harbor | 15489 | 20946 | 0.937 | 0.887 | | swimming-pool | 3456 | 5159 | 0.886 | 0.772 | | helicopter | 765 | 1009 | 0.941 | 0.901 | +--------------------+-------+-------+--------+-------+ | mAP | | | | 0.869 | +--------------------+-------+-------+--------+-------+ 2023-02-12 11:04:27,570 - mmrotate - INFO - Exp name: lskb1_dota_ema_finetune.py 2023-02-12 11:04:27,571 - mmrotate - INFO - Epoch(val) [12][2034] mAP: 0.8691