Open yangtian6781 opened 1 year ago
i notice that the log of rotated_rtmdet_l-coco_pretrain-3x-dota_ms.py is little different from my log. in same epoch, my loss is little bigger than loss of office log
Hi @mkzhcak, You can try changing the learning rate to half of the original. However, DOTA dataset is much smaller than Coco dataset. However, DOTA dataset is much smaller than COCO, and linear learning rate scaling is only sometimes useful. According to our experience: 1x8b>2x4b>1x4b
thanks for your reply, During the training, I only used the training set for multi-scale training, and then tested on the val set. The map is only 70.7, which may be batch_size is too small. I will use the model of rtmdet_l to add batch to 8, hoping to reproduce the official effect. I have another question, what is an acceptable error between the val set and the test set?
Hi @mkzhcak, You can try changing the learning rate to half of the original. However, DOTA dataset is much smaller than Coco dataset. However, DOTA dataset is much smaller than COCO, and linear learning rate scaling is only sometimes useful. According to our experience: 1x8b>2x4b>1x4b
System environment: sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 2085261137 GPU 0: NVIDIA GeForce RTX 3090 CUDA_HOME: /usr/local/cuda GCC: gcc (Ubuntu 11.3.0-1ubuntu1~22.04) 11.3.0 PyTorch: 1.13.1+cu117 PyTorch compiling details: PyTorch built with:
Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,
TorchVision: 0.14.1+cu117 OpenCV: 4.5.5 MMEngine: 0.6.0
2023/03/02 15:36:53 - mmengine - INFO - Config: default_scope = 'mmrotate' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='mmdet.DetVisualizationHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='RotLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True) log_level = 'INFO' load_from = None resume = False custom_hooks = [ dict(type='mmdet.NumClassCheckHook'), dict( type='EMAHook', ema_type='mmdet.ExpMomentumEMA', momentum=0.0002, update_buffers=True, priority=49) ] max_epochs = 36 base_lr = 0.00025 interval = 12 train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=36, val_interval=12) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='LinearLR', start_factor=1e-05, by_epoch=False, begin=0, end=1000), dict( type='CosineAnnealingLR', eta_min=1.25e-05, begin=18, end=36, T_max=18, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='AdamW', lr=0.00025, weight_decay=0.05), paramwise_cfg=dict( norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True)) dataset_type = 'DOTADataset' data_root = '/home/ljy/mmrotate1/dota_to_val_ms_1024/' file_client_args = dict(backend='disk') train_pipeline = [ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.RandomFlip', prob=0.75, direction=['horizontal', 'vertical', 'diagonal']), dict( type='RandomRotate', prob=0.5, angle_range=180, rect_obj_labels=[9, 11]), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict(type='mmdet.PackDetInputs') ] val_pipeline = [ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict( type='mmdet.PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] test_pipeline = [ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict( type='mmdet.PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] train_dataloader = dict( batch_size=8, num_workers=8, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), batch_sampler=None, pin_memory=False, dataset=dict( type='DOTADataset', data_root='/home/ljy/mmrotate1/dota_to_val_ms_1024/', ann_file='train/annfiles/', data_prefix=dict(img_path='train/images/'), img_shape=(1024, 1024), filter_cfg=dict(filter_empty_gt=True), pipeline=[ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict( type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict( type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.RandomFlip', prob=0.75, direction=['horizontal', 'vertical', 'diagonal']), dict( type='RandomRotate', prob=0.5, angle_range=180, rect_obj_labels=[9, 11]), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict(type='mmdet.PackDetInputs') ])) val_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='DOTADataset', data_root='/home/ljy/mmrotate1/dota_to_val_ms_1024/', ann_file='val/annfiles/', data_prefix=dict(img_path='val/images/'), img_shape=(1024, 1024), test_mode=True, pipeline=[ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict( type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict( type='mmdet.PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='DOTADataset', data_root='/home/ljy/mmrotate1/dota_to_val_ms_1024/', ann_file='val/annfiles/', data_prefix=dict(img_path='val/images/'), img_shape=(1024, 1024), test_mode=True, pipeline=[ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict( type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict( type='mmdet.PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) val_evaluator = dict(type='DOTAMetric', metric='mAP') test_evaluator = dict(type='DOTAMetric', metric='mAP') checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth' angle_version = 'le90' model = dict( type='mmdet.RTMDet', data_preprocessor=dict( type='mmdet.DetDataPreprocessor', mean=[103.53, 116.28, 123.675], std=[57.375, 57.12, 58.395], bgr_to_rgb=False, boxtype2tensor=False, batch_augments=None), backbone=dict( type='mmdet.CSPNeXt', arch='P5', expand_ratio=0.5, deepen_factor=0.33, widen_factor=0.5, channel_attention=True, norm_cfg=dict(type='SyncBN'), act_cfg=dict(type='SiLU'), init_cfg=dict( type='Pretrained', prefix='backbone.', checkpoint= 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth' )), neck=dict( type='mmdet.CSPNeXtPAFPN', in_channels=[128, 256, 512], out_channels=128, num_csp_blocks=1, expand_ratio=0.5, norm_cfg=dict(type='SyncBN'), act_cfg=dict(type='SiLU')), bbox_head=dict( type='RotatedRTMDetSepBNHead', num_classes=15, in_channels=128, stacked_convs=2, feat_channels=128, angle_version='le90', anchor_generator=dict( type='mmdet.MlvlPointGenerator', offset=0, strides=[8, 16, 32]), bbox_coder=dict(type='DistanceAnglePointCoder', angle_version='le90'), loss_cls=dict( type='mmdet.QualityFocalLoss', use_sigmoid=True, beta=2.0, loss_weight=1.0), loss_bbox=dict(type='RotatedIoULoss', mode='linear', loss_weight=2.0), with_objectness=False, exp_on_reg=False, share_conv=True, pred_kernel_size=1, use_hbbox_loss=False, scale_angle=False, loss_angle=None, norm_cfg=dict(type='SyncBN'), act_cfg=dict(type='SiLU')), train_cfg=dict( assigner=dict( type='mmdet.DynamicSoftLabelAssigner', iou_calculator=dict(type='RBboxOverlaps2D'), topk=13), allowed_border=-1, pos_weight=-1, debug=False), test_cfg=dict( nms_pre=2000, min_bbox_size=0, score_thr=0.05, nms=dict(type='nms_rotated', iou_threshold=0.1), max_per_img=2000)) launcher = 'none' work_dir = '/home/ljy/mmrotate1/work_dirs/rtmdet_dota_s'
@zytx121
Hi @mkzhcak, the results of val
and test
can vary greatly. It is recommended to use tainval
set for training and test
set for testing.
Branch
1.x branch https://mmrotate.readthedocs.io/en/1.x/
📚 The doc issue
i notice two lines code in python file:
batch_size = (2 GPUs) x (4 samples per GPU) = 8
train_dataloader = dict(batch_size=4, num_workers=4)
我用一张3090进行训练,有如下问题: 1.上面的代码是否意味着我用的是batchsize=4,那行注释是什么意思?是都意味着我用两张显卡训练的时候batchsize自动设置成8 2.如果我用的是batchsize=4,为了复现出论文的结果,是否应该按照‘batch/2的时候,学习率也要同时除以2’的原则把学习率除以二
下面是我的详细配置:
System environment: sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 1783001956 GPU 0: NVIDIA GeForce RTX 3090 CUDA_HOME: /usr/local/cuda GCC: gcc (Ubuntu 11.3.0-1ubuntu1~22.04) 11.3.0 PyTorch: 1.13.1+cu117 PyTorch compiling details: PyTorch built with:
Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,
TorchVision: 0.14.1+cu117 OpenCV: 4.5.5 MMEngine: 0.6.0
Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: none Distributed training: False GPU number: 1
2023/02/28 09:44:26 - mmengine - INFO - Config: default_scope = 'mmrotate' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='mmdet.DetVisualizationHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='RotLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True) log_level = 'INFO' load_from = None resume = False custom_hooks = [ dict(type='mmdet.NumClassCheckHook'), dict( type='EMAHook', ema_type='mmdet.ExpMomentumEMA', momentum=0.0002, update_buffers=True, priority=49) ] max_epochs = 36 base_lr = 0.00025 interval = 12 train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=36, val_interval=12) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='LinearLR', start_factor=1e-05, by_epoch=False, begin=0, end=1000), dict( type='CosineAnnealingLR', eta_min=1.25e-05, begin=18, end=36, T_max=18, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='AdamW', lr=0.00025, weight_decay=0.05), paramwise_cfg=dict( norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True)) dataset_type = 'DOTADataset' data_root = '/home/ljy/mmrotate1/dota_to_val_ms_1024/' file_client_args = dict(backend='disk') train_pipeline = [ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.RandomFlip', prob=0.75, direction=['horizontal', 'vertical', 'diagonal']), dict( type='RandomRotate', prob=0.5, angle_range=180, rect_obj_labels=[9, 11]), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict(type='mmdet.PackDetInputs') ] val_pipeline = [ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict( type='mmdet.PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] test_pipeline = [ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict( type='mmdet.PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] train_dataloader = dict( batch_size=4, num_workers=4, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), batch_sampler=None, pin_memory=False, dataset=dict( type='DOTADataset', data_root='/home/ljy/mmrotate1/dota_to_val_ms_1024/', ann_file='train/annfiles/', data_prefix=dict(img_path='train/images/'), img_shape=(1024, 1024), filter_cfg=dict(filter_empty_gt=True), pipeline=[ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict( type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict( type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.RandomFlip', prob=0.75, direction=['horizontal', 'vertical', 'diagonal']), dict( type='RandomRotate', prob=0.5, angle_range=180, rect_obj_labels=[9, 11]), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict(type='mmdet.PackDetInputs') ])) val_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='DOTADataset', data_root='/home/ljy/mmrotate1/dota_to_val_ms_1024/', ann_file='val/annfiles/', data_prefix=dict(img_path='val/images/'), img_shape=(1024, 1024), test_mode=True, pipeline=[ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict( type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict( type='mmdet.PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='DOTADataset', data_root='/home/ljy/mmrotate1/dota_to_val_ms_1024/', ann_file='val/annfiles/', data_prefix=dict(img_path='val/images/'), img_shape=(1024, 1024), test_mode=True, pipeline=[ dict( type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), dict( type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), dict( type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), dict( type='mmdet.Pad', size=(1024, 1024), pad_val=dict(img=(114, 114, 114))), dict( type='mmdet.PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) val_evaluator = dict(type='DOTAMetric', metric='mAP') test_evaluator = dict(type='DOTAMetric', metric='mAP') checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-l_8xb256-rsb-a1-600e_in1k-6a760974.pth' angle_version = 'le90' model = dict( type='mmdet.RTMDet', data_preprocessor=dict( type='mmdet.DetDataPreprocessor', mean=[103.53, 116.28, 123.675], std=[57.375, 57.12, 58.395], bgr_to_rgb=False, boxtype2tensor=False, batch_augments=None), backbone=dict( type='mmdet.CSPNeXt', arch='P5', expand_ratio=0.5, deepen_factor=1, widen_factor=1, channel_attention=True, norm_cfg=dict(type='SyncBN'), act_cfg=dict(type='SiLU'), init_cfg=dict( type='Pretrained', prefix='backbone.', checkpoint= 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth' )), neck=dict( type='mmdet.CSPNeXtPAFPN', in_channels=[256, 512, 1024], out_channels=256, num_csp_blocks=3, expand_ratio=0.5, norm_cfg=dict(type='SyncBN'), act_cfg=dict(type='SiLU'), init_cfg=dict( type='Pretrained', prefix='neck.', checkpoint= 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth' )), bbox_head=dict( type='RotatedRTMDetSepBNHead', num_classes=15, in_channels=256, stacked_convs=2, feat_channels=256, angle_version='le90', anchor_generator=dict( type='mmdet.MlvlPointGenerator', offset=0, strides=[8, 16, 32]), bbox_coder=dict(type='DistanceAnglePointCoder', angle_version='le90'), loss_cls=dict( type='mmdet.QualityFocalLoss', use_sigmoid=True, beta=2.0, loss_weight=1.0), loss_bbox=dict(type='RotatedIoULoss', mode='linear', loss_weight=2.0), with_objectness=False, exp_on_reg=True, share_conv=True, pred_kernel_size=1, use_hbbox_loss=False, scale_angle=False, loss_angle=None, norm_cfg=dict(type='SyncBN'), act_cfg=dict(type='SiLU'), init_cfg=dict( type='Pretrained', prefix='bbox_head.', checkpoint= 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth' )), train_cfg=dict( assigner=dict( type='mmdet.DynamicSoftLabelAssigner', iou_calculator=dict(type='RBboxOverlaps2D'), topk=13), allowed_border=-1, pos_weight=-1, debug=False), test_cfg=dict( nms_pre=2000, min_bbox_size=0, score_thr=0.05, nms=dict(type='nms_rotated', iou_threshold=0.1), max_per_img=2000)) coco_ckpt = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth' launcher = 'none' work_dir = '/home/ljy/mmrotate1/work_dirs/rtmdet_dota'
Suggest a potential alternative/fix
No response