Upload 26 files

configs/_base_/datasets/dior.py

@@ -0,0 +1,79 @@
+# dataset settings
+dataset_type = 'DIORDataset'
+data_root = 'data/DIOR/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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=(800, 800), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(800, 800), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(800, 800), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type='ConcatDataset',
+        ignore_keys=['DATASET_TYPE'],
+        datasets=[
+            dict(
+                type=dataset_type,
+                data_root=data_root,
+                ann_file='ImageSets/Main/train.txt',
+                data_prefix=dict(img_path='JPEGImages-trainval'),
+                filter_cfg=dict(filter_empty_gt=True),
+                pipeline=train_pipeline),
+            dict(
+                type=dataset_type,
+                data_root=data_root,
+                ann_file='ImageSets/Main/val.txt',
+                data_prefix=dict(img_path='JPEGImages-trainval'),
+                filter_cfg=dict(filter_empty_gt=True),
+                pipeline=train_pipeline,
+                backend_args=backend_args)
+        ]))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='ImageSets/Main/test.txt',
+        data_prefix=dict(img_path='JPEGImages-test'),
+        test_mode=True,
+        pipeline=val_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='DOTAMetric', metric='mAP')
+test_evaluator = val_evaluator

configs/_base_/datasets/dota.py

@@ -0,0 +1,85 @@
+# dataset settings
+dataset_type = 'DOTADataset'
+data_root = 'data/split_ss_dota/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        test_mode=True,
+        pipeline=val_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='DOTAMetric', metric='mAP')
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         data_prefix=dict(img_path='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     outfile_prefix='./work_dirs/dota/Task1')

configs/_base_/datasets/dota_coco.py

@@ -0,0 +1,109 @@
+# dataset settings
+dataset_type = 'mmdet.CocoDataset'
+data_root = 'data/split_ms_dota/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='rbox'),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='qbox'),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'instances'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+metainfo = dict(
+    classes=('plane', 'baseball-diamond', 'bridge', 'ground-track-field',
+             'small-vehicle', 'large-vehicle', 'ship', 'tennis-court',
+             'basketball-court', 'storage-tank', 'soccer-ball-field',
+             'roundabout', 'harbor', 'swimming-pool', 'helicopter'))
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='train/train.json',
+        data_prefix=dict(img='train/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='val/val.json',
+        data_prefix=dict(img='val/images/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='RotatedCocoMetric',
+    metric='bbox',
+    classwise=True,
+    backend_args=backend_args)
+
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         ann_file='test/test.json',
+#         data_prefix=dict(img='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     outfile_prefix='./work_dirs/dota/Task1')

configs/_base_/datasets/dota_ms.py

@@ -0,0 +1,90 @@
+# dataset settings
+dataset_type = 'DOTADataset'
+data_root = 'data/split_ms_dota/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        test_mode=True,
+        pipeline=val_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='DOTAMetric', metric='mAP')
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         data_prefix=dict(img_path='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     outfile_prefix='./work_dirs/dota/Task1')

configs/_base_/datasets/dota_qbox.py

@@ -0,0 +1,85 @@
+# dataset settings
+dataset_type = 'DOTADataset'
+data_root = 'data/split_ss_dota/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        test_mode=True,
+        pipeline=val_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='DOTAMetric', metric='mAP', iou_thrs=0.2, predict_box_type='qbox')
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         data_prefix=dict(img_path='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     predict_box_type='qbox',
+#     outfile_prefix='./work_dirs/dota/Task1')

configs/_base_/datasets/dotav15.py

@@ -0,0 +1,85 @@
+# dataset settings
+dataset_type = 'DOTAv15Dataset'
+data_root = 'data/split_ss_dota1_5/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        test_mode=True,
+        pipeline=val_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='DOTAMetric', metric='mAP')
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         data_prefix=dict(img_path='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     outfile_prefix='./work_dirs/dotav15/h2rbox-le90_r50_fpn_adamw-1x_dotav15/Task1')

configs/_base_/datasets/dotav2.py

@@ -0,0 +1,85 @@
+# dataset settings
+dataset_type = 'DOTAv2Dataset'
+data_root = 'data/split_ss_dota2_0/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        test_mode=True,
+        pipeline=val_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='DOTAMetric', metric='mAP')
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         data_prefix=dict(img_path='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     outfile_prefix='./work_dirs/dotav2/h2rbox-le90_r50_fpn_adamw-1x_dotav2/Task1')

configs/_base_/datasets/hrsc.py

@@ -0,0 +1,67 @@
+# dataset settings
+dataset_type = 'HRSCDataset'
+data_root = 'data/hrsc/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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=(800, 512), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(800, 512), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(800, 512), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='ImageSets/trainval.txt',
+        data_prefix=dict(sub_data_root='FullDataSet/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='ImageSets/test.txt',
+        data_prefix=dict(sub_data_root='FullDataSet/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='DOTAMetric', metric='mAP')
+test_evaluator = val_evaluator

configs/_base_/datasets/hrsid.py

@@ -0,0 +1,82 @@
+# dataset settings
+dataset_type = 'mmdet.CocoDataset'
+data_root = 'data/HRSID_JPG/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='rbox'),
+    dict(type='mmdet.Resize', scale=(800, 800), keep_ratio=True),
+    dict(type='mmdet.FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(800, 800), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='qbox'),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'instances'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(800, 800), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+metainfo = dict(classes=('ship', ))
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='annotations/train2017.json',
+        data_prefix=dict(img='JPEGImages/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='annotations/test2017.json',
+        data_prefix=dict(img='JPEGImages/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='RotatedCocoMetric', metric='bbox')
+
+test_evaluator = val_evaluator

configs/_base_/datasets/rsdd.py

@@ -0,0 +1,81 @@
+# dataset settings
+dataset_type = 'mmdet.CocoDataset'
+data_root = 'data/rsdd/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='rbox'),
+    dict(type='mmdet.Resize', scale=(512, 512), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(512, 512), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='qbox'),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'instances'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(512, 512), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+metainfo = dict(classes=('ship', ))
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='ImageSets/train.json',
+        data_prefix=dict(img='JPEGImages/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='ImageSets/test.json',
+        data_prefix=dict(img='JPEGImages/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='RotatedCocoMetric', metric='bbox')
+
+test_evaluator = val_evaluator

configs/_base_/datasets/srsdd.py

@@ -0,0 +1,83 @@
+# dataset settings
+dataset_type = 'mmdet.CocoDataset'
+data_root = 'data/srsdd/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='rbox'),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='qbox'),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'instances'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+metainfo = dict(
+    classes=('Container', 'Dredger', 'LawEnforce', 'Cell-Container', 'ore-oil',
+             'Fishing'))
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='train/train.json',
+        data_prefix=dict(img='train/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='test/test.json',
+        data_prefix=dict(img='test/images/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='RotatedCocoMetric', metric='bbox')
+
+test_evaluator = val_evaluator

configs/_base_/datasets/ssdd.py

@@ -0,0 +1,81 @@
+# dataset settings
+dataset_type = 'mmdet.CocoDataset'
+data_root = 'data/ssdd/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='rbox'),
+    dict(type='mmdet.Resize', scale=(512, 512), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(512, 512), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(
+        type='mmdet.LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(type='ConvertMask2BoxType', box_type='qbox'),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'instances'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(512, 512), keep_ratio=True),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+metainfo = dict(classes=('ship', ))
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='train/train.json',
+        data_prefix=dict(img='train/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        metainfo=metainfo,
+        data_root=data_root,
+        ann_file='test/all/test.json',
+        data_prefix=dict(img='test/all/images/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='RotatedCocoMetric', metric='bbox')
+
+test_evaluator = val_evaluator

configs/_base_/default_runtime.py

@@ -0,0 +1,24 @@
+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),
+    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=vis_backends, name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+
+log_level = 'INFO'
+load_from = None
+resume = False

configs/_base_/schedules/schedule_1x.py

@@ -0,0 +1,27 @@
+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0 / 3,
+        by_epoch=False,
+        begin=0,
+        end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=12,
+        by_epoch=True,
+        milestones=[8, 11],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001),
+    clip_grad=dict(max_norm=35, norm_type=2))

configs/_base_/schedules/schedule_3x.py

@@ -0,0 +1,27 @@
+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=36, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0 / 3,
+        by_epoch=False,
+        begin=0,
+        end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=36,
+        by_epoch=True,
+        milestones=[24, 33],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001),
+    clip_grad=dict(max_norm=35, norm_type=2))

configs/_base_/schedules/schedule_40e.py

@@ -0,0 +1,27 @@
+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=40, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0 / 3,
+        by_epoch=False,
+        begin=0,
+        end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=40,
+        by_epoch=True,
+        milestones=[24, 32, 38],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001),
+    clip_grad=dict(max_norm=35, norm_type=2))

configs/_base_/schedules/schedule_6x.py

@@ -0,0 +1,27 @@
+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=72, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0 / 3,
+        by_epoch=False,
+        begin=0,
+        end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=72,
+        by_epoch=True,
+        milestones=[48, 66],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001),
+    clip_grad=dict(max_norm=35, norm_type=2))

configs/rotated_rtmdet/README.md

@@ -0,0 +1,76 @@
+# RTMDet-R
+
+> [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://arxiv.org/abs/2212.07784)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more efficient model architecture, we explore an architecture that has compatible capacities in the backbone and neck, constructed by a basic building block that consists of large-kernel depth-wise convolutions. We further introduce soft labels when calculating matching costs in the dynamic label assignment to improve accuracy. Together with better training techniques, the resulting object detector, named RTMDet, achieves 52.8% AP on COCO with 300+ FPS on an NVIDIA 3090 GPU, outperforming the current mainstream industrial detectors. RTMDet achieves the best parameter-accuracy trade-off with tiny/small/medium/large/extra-large model sizes for various application scenarios, and obtains new state-of-the-art performance on real-time instance segmentation and rotated object detection. We hope the experimental results can provide new insights into designing versatile real-time object detectors for many object recognition tasks.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/11705038/204995787-ef739910-e196-42c7-a9db-c9c8e28a494d.jpg" height="360"/>
+</div>
+
+## Results and Models
+
+### DOTA-v1.0
+
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/rtmdet-an-empirical-study-of-designing-real/object-detection-in-aerial-images-on-dota-1)](https://paperswithcode.com/sota/object-detection-in-aerial-images-on-dota-1?p=rtmdet-an-empirical-study-of-designing-real)
+
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/rtmdet-an-empirical-study-of-designing-real/one-stage-anchor-free-oriented-object-1)](https://paperswithcode.com/sota/one-stage-anchor-free-oriented-object-1?p=rtmdet-an-empirical-study-of-designing-real)
+
+|  Backbone   | pretrain |  Aug  | mmAP  | mAP50 | mAP75 | Params(M) | FLOPS(G) | TRT-FP16-Latency(ms) |                          Config                          |                                                                                                                                                                       Download                                                                                                                                                                       |
+| :---------: | :------: | :---: | :---: | :---: | :---: | :-------: | :------: | :------------------: | :------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| RTMDet-tiny |    IN    |  RR   | 47.37 | 75.36 | 50.64 |   4.88    |  20.45   |         4.40         |        [config](./rotated_rtmdet_tiny-3x-dota.py)        |                             [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-3x-dota/rotated_rtmdet_tiny-3x-dota-9d821076.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-3x-dota/rotated_rtmdet_tiny-3x-dota_20221201_120814.json)                             |
+| RTMDet-tiny |    IN    | MS+RR | 53.59 | 79.82 | 58.87 |   4.88    |  20.45   |         4.40         |      [config](./rotated_rtmdet_tiny-3x-dota_ms.py)       |                       [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-3x-dota_ms/rotated_rtmdet_tiny-3x-dota_ms-f12286ff.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-3x-dota_ms/rotated_rtmdet_tiny-3x-dota_ms_20221113_201235.log)                        |
+|  RTMDet-s   |    IN    |  RR   | 48.16 | 76.93 | 50.59 |   8.86    |  37.62   |         4.86         |         [config](./rotated_rtmdet_s-3x-dota.py)          |                                   [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_s-3x-dota/rotated_rtmdet_s-3x-dota-11f6ccf5.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_s-3x-dota/rotated_rtmdet_s-3x-dota_20221124_081442.json)                                   |
+|  RTMDet-s   |    IN    | MS+RR | 54.43 | 79.98 | 60.07 |   8.86    |  37.62   |         4.86         |        [config](./rotated_rtmdet_s-3x-dota_ms.py)        |                             [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_s-3x-dota_ms/rotated_rtmdet_s-3x-dota_ms-20ead048.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_s-3x-dota_ms/rotated_rtmdet_s-3x-dota_ms_20221113_201055.json)                             |
+|  RTMDet-m   |    IN    |  RR   | 50.56 | 78.24 | 54.47 |   24.67   |  99.76   |         7.82         |         [config](./rotated_rtmdet_m-3x-dota.py)          |                                   [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_m-3x-dota/rotated_rtmdet_m-3x-dota-beeadda6.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_m-3x-dota/rotated_rtmdet_m-3x-dota_20221122_011234.json)                                   |
+|  RTMDet-m   |    IN    | MS+RR | 55.00 | 80.26 | 61.26 |   24.67   |  99.76   |         7.82         |        [config](./rotated_rtmdet_m-3x-dota_ms.py)        |                             [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_m-3x-dota_ms/rotated_rtmdet_m-3x-dota_ms-c71eb375.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_m-3x-dota_ms/rotated_rtmdet_m-3x-dota_ms_20221122_011234.json)                             |
+|  RTMDet-l   |    IN    |  RR   | 51.01 | 78.85 | 55.21 |   52.27   |  204.21  |        10.82         |         [config](./rotated_rtmdet_l-3x-dota.py)          |                                   [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-3x-dota/rotated_rtmdet_l-3x-dota-23992372.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-3x-dota/rotated_rtmdet_l-3x-dota_20221122_011241.json)                                   |
+|  RTMDet-l   |    IN    | MS+RR | 55.52 | 80.54 | 61.47 |   52.27   |  204.21  |        10.82         |        [config](./rotated_rtmdet_l-3x-dota_ms.py)        |                             [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-3x-dota_ms/rotated_rtmdet_l-3x-dota_ms-2738da34.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-3x-dota_ms/rotated_rtmdet_l-3x-dota_ms_20221122_011241.json)                             |
+|  RTMDet-l   |   COCO   | MS+RR | 56.74 | 81.33 | 63.45 |   52.27   |  204.21  |        10.82         | [config](./rotated_rtmdet_l-coco_pretrain-3x-dota_ms.py) | [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-coco_pretrain-3x-dota_ms/rotated_rtmdet_l-coco_pretrain-3x-dota_ms-06d248a2.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-coco_pretrain-3x-dota_ms/rotated_rtmdet_l-coco_pretrain-3x-dota_ms_20221113_202010.json) |
+
+- By default, DOTA-v1.0 dataset trained with 3x schedule and image size 1024\*1024.
+
+### HRSC
+
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/rtmdet-an-empirical-study-of-designing-real/object-detection-in-aerial-images-on-hrsc2016)](https://paperswithcode.com/sota/object-detection-in-aerial-images-on-hrsc2016?p=rtmdet-an-empirical-study-of-designing-real)
+
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/rtmdet-an-empirical-study-of-designing-real/one-stage-anchor-free-oriented-object-3)](https://paperswithcode.com/sota/one-stage-anchor-free-oriented-object-3?p=rtmdet-an-empirical-study-of-designing-real)
+
+|  Backbone   | pretrain | Aug | mAP 07 | mAP 12 | Params(M) | FLOPS(G) |                   Config                   |                                                                                                                                           Download                                                                                                                                           |
+| :---------: | :------: | :-: | :----: | :----: | :-------: | :------: | :----------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| RTMDet-tiny |    IN    | RR  |  90.6  |  97.1  |   4.88    |  12.54   | [config](./rotated_rtmdet_tiny-9x-hrsc.py) | [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-9x-hrsc/rotated_rtmdet_tiny-9x-hrsc-9f2e3ca6.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-9x-hrsc/rotated_rtmdet_tiny-9x-hrsc_20221125_145920.json) |
+
+- By default, HRSC dataset trained with 9x schedule and image size 800\*800.
+
+### Stronger augmentation
+
+We also provide configs with Mixup, Mosaic and RandomRotate with longer schedule. Training time is less than MS.
+
+DOTA:
+
+| Backbone | pretrain | schedule |       Aug       | mmAP  | mAP50 | mAP75 |                    Config                     |                                                                                                                                                 Download                                                                                                                                                 |
+| :------: | :------: | :------: | :-------------: | :---: | :---: | :---: | :-------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| RTMDet-l |    IN    |   100e   | Mixup+Mosaic+RR | 54.59 | 80.16 | 61.16 | [config](./rotated_rtmdet_l-100e-aug-dota.py) | [model](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-100e-aug-dota/rotated_rtmdet_l-100e-aug-dota-bc59fd88.pth) \| [log](https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-100e-aug-dota/rotated_rtmdet_l-100e-aug-dota_20221124_224135.json) |
+
+**Note**:
+
+1. We follow the latest metrics from the DOTA evaluation server, original voc format mAP is now mAP50.
+2. `IN` means ImageNet pretrain, `COCO` means COCO pretrain.
+3. Different from the report, the inference speed here is measured on an NVIDIA 2080Ti GPU with TensorRT 8.4.3, cuDNN 8.2.0, FP16, batch size=1, and with NMS.
+
+## Citation
+
+```
+@misc{lyu2022rtmdet,
+      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
+      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
+      year={2022},
+      eprint={2212.07784},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

configs/rotated_rtmdet/_base_/default_runtime.py

@@ -0,0 +1,34 @@
+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=12, 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=vis_backends, 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)
+]

configs/rotated_rtmdet/_base_/dota_rr.py

@@ -0,0 +1,101 @@
+# dataset settings
+dataset_type = 'DOTADataset'
+data_root = 'data/split_ss_dota/'
+
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    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', backend_args=backend_args),
+    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=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        test_mode=True,
+        pipeline=val_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='DOTAMetric', metric='mAP')
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=8,
+#     num_workers=8,
+#     persistent_workers=False,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         data_prefix=dict(img_path='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     outfile_prefix='./work_dirs/rtmdet_r/Task1')

configs/rotated_rtmdet/_base_/dota_rr_ms.py

@@ -0,0 +1,100 @@
+# dataset settings
+dataset_type = 'DOTADataset'
+data_root = 'data/split_ms_dota/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    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', backend_args=backend_args),
+    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=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='trainval/annfiles/',
+        data_prefix=dict(img_path='trainval/images/'),
+        test_mode=True,
+        pipeline=val_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='DOTAMetric', metric='mAP')
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=8,
+#     num_workers=8,
+#     persistent_workers=False,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         data_prefix=dict(img_path='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     outfile_prefix='./work_dirs/rtmdet_r/Task1')

configs/rotated_rtmdet/_base_/hrsc_rr.py

@@ -0,0 +1,83 @@
+# dataset settings
+dataset_type = 'HRSCDataset'
+data_root = 'data/hrsc/'
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    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=(800, 800), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(type='RandomRotate', prob=0.5, angle_range=180),
+    dict(type='mmdet.Pad', size=(800, 800), pad_val=dict(img=(114, 114, 114))),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(800, 800), keep_ratio=True),
+    # avoid bboxes being resized
+    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=(800, 800), 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', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(800, 800), keep_ratio=True),
+    dict(type='mmdet.Pad', size=(800, 800), 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=True,
+    dataset=dict(
+        type='RepeatDataset',
+        times=3,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='ImageSets/trainval.txt',
+            data_prefix=dict(sub_data_root='FullDataSet/'),
+            filter_cfg=dict(filter_empty_gt=True),
+            pipeline=train_pipeline,
+            backend_args=backend_args)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='ImageSets/test.txt',
+        data_prefix=dict(sub_data_root='FullDataSet/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = [
+    dict(
+        type='DOTAMetric',
+        eval_mode='11points',
+        prefix='dota_ap07',
+        metric='mAP'),
+    dict(
+        type='DOTAMetric', eval_mode='area', prefix='dota_ap12', metric='mAP'),
+]
+test_evaluator = val_evaluator

configs/rotated_rtmdet/_base_/schedule_3x.py

@@ -0,0 +1,33 @@
+max_epochs = 3 * 12
+base_lr = 0.004 / 16
+interval = 1
+
+train_cfg = dict(
+    type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=interval)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0e-5,
+        by_epoch=False,
+        begin=0,
+        end=1000),
+    dict(
+        type='CosineAnnealingLR',
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.05),
+    paramwise_cfg=dict(
+        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))

configs/rotated_rtmdet/custom.py

@@ -0,0 +1,79 @@
+_base_ = [
+    './_base_/default_runtime.py', './_base_/schedule_3x.py',
+    './_base_/dota_rr_ms.py'
+]
+checkpoint = '/content/drive/MyDrive/RTMDET/epoch_36.pth'  # noqa
+
+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=checkpoint)),
+    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')),
+    bbox_head=dict(
+        type='RotatedRTMDetSepBNHead',
+        num_classes=1,
+        in_channels=256,
+        stacked_convs=2,
+        feat_channels=256,
+        angle_version=angle_version,
+        anchor_generator=dict(
+            type='mmdet.MlvlPointGenerator', offset=0, strides=[8, 16, 32]),
+        bbox_coder=dict(
+            type='DistanceAnglePointCoder', angle_version=angle_version),
+        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')),
+    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),
+)
+
+# batch_size = (2 GPUs) x (4 samples per GPU) = 8
+train_dataloader = dict(batch_size=4, num_workers=4)

configs/rotated_rtmdet/metafile.yml

@@ -0,0 +1,147 @@
+Collections:
+  - Name: rotated_rtmdet
+    Metadata:
+      Training Data:
+        - DOTAv1.0
+        - HRSC
+      Training Techniques:
+        - AdamW
+        - Flat Cosine Annealing
+      Training Resources: 1x RTX3090 GPUs
+      Architecture:
+        - CSPNeXt
+        - CSPNeXtPAFPN
+    README: configs/rotated_rtmdet/README.md
+
+Models:
+  - Name: rotated_rtmdet_tiny-3x-dota
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_tiny-3x-dota.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 75.60
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-3x-dota/rotated_rtmdet_tiny-3x-dota-9d821076.pth
+
+  - Name: rotated_rtmdet_tiny-3x-dota_ms
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_tiny-3x-dota_ms.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 79.82
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-3x-dota_ms/rotated_rtmdet_tiny-3x-dota_ms-f12286ff.pth
+
+  - Name: rotated_rtmdet_s-3x-dota
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_s-3x-dota.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 76.93
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_s-3x-dota/rotated_rtmdet_s-3x-dota-11f6ccf5.pth
+
+  - Name: rotated_rtmdet_s-3x-dota_ms
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_s-3x-dota_ms.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 79.98
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_s-3x-dota_ms/rotated_rtmdet_s-3x-dota_ms-20ead048.pth
+
+  - Name: rotated_rtmdet_m-3x-dota
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_m-3x-dota.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 78.24
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_m-3x-dota/rotated_rtmdet_m-3x-dota-beeadda6.pth
+
+  - Name: rotated_rtmdet_m-3x-dota_ms
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_m-3x-dota_ms.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 80.26
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_m-3x-dota_ms/rotated_rtmdet_m-3x-dota_ms-c71eb375.pth
+
+  - Name: rotated_rtmdet_l-3x-dota
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_l-3x-dota.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 78.85
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-3x-dota/rotated_rtmdet_l-3x-dota-23992372.pth
+
+  - Name: rotated_rtmdet_l-3x-dota_ms
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_l-3x-dota_ms.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 80.54
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-3x-dota_ms/rotated_rtmdet_l-3x-dota_ms-2738da34.pth
+
+  - Name: rotated_rtmdet_l-coco_pretrain-3x-dota_ms
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/rotated_rtmdet_l-coco_pretrain-3x-dota_ms.py
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 81.33
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-coco_pretrain-3x-dota_ms/rotated_rtmdet_l-coco_pretrain-3x-dota_ms-06d248a2.pth
+
+  - Name: rotated_rtmdet_tiny-9x-hrsc
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/
+    Metadata:
+      Training Data: HRSC
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: HRSC
+        Metrics:
+          mAP: 90.6
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_tiny-9x-hrsc/rotated_rtmdet_tiny-9x-hrsc-9f2e3ca6.pth
+
+  - Name: rotated_rtmdet_l-100e-aug-dota
+    In Collection: rotated_rtmdet
+    Config: configs/rotated_rtmdet/
+    Metadata:
+      Training Data: DOTAv1.0
+    Results:
+      - Task: Oriented Object Detection
+        Dataset: DOTAv1.0
+        Metrics:
+          mAP: 80.16
+    Weights: https://download.openmmlab.com/mmrotate/v1.0/rotated_rtmdet/rotated_rtmdet_l-100e-aug-dota/rotated_rtmdet_l-100e-aug-dota-bc59fd88.pth

configs/rotated_rtmdet/rotated_rtmdet_l-3x-dota_ms.py

@@ -0,0 +1,79 @@
+_base_ = [
+    './_base_/default_runtime.py', './_base_/schedule_3x.py',
+    './_base_/dota_rr_ms.py'
+]
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-l_8xb256-rsb-a1-600e_in1k-6a760974.pth'  # noqa
+
+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=checkpoint)),
+    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')),
+    bbox_head=dict(
+        type='RotatedRTMDetSepBNHead',
+        num_classes=15,
+        in_channels=256,
+        stacked_convs=2,
+        feat_channels=256,
+        angle_version=angle_version,
+        anchor_generator=dict(
+            type='mmdet.MlvlPointGenerator', offset=0, strides=[8, 16, 32]),
+        bbox_coder=dict(
+            type='DistanceAnglePointCoder', angle_version=angle_version),
+        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')),
+    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),
+)
+
+# batch_size = (2 GPUs) x (4 samples per GPU) = 8
+train_dataloader = dict(batch_size=4, num_workers=4)