update codes

configs/_base_/datasets/coco_instance.py

+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'datasets/coco_mini/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        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='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# 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,
+#         ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoMetric',
+#     metric=['bbox', 'segm'],
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_instance/test')

configs/_base_/datasets/coco_instance_semantic.py

+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(
+        type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(
+        type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/', seg='stuffthingmaps/train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        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='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/coco_panoptic.py

+# dataset settings
+dataset_type = 'CocoPanopticDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadPanopticAnnotations', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='LoadPanopticAnnotations', backend_args=backend_args),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/panoptic_train2017.json',
+        data_prefix=dict(
+            img='train2017/', seg='annotations/panoptic_train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        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='annotations/panoptic_val2017.json',
+        data_prefix=dict(img='val2017/', seg='annotations/panoptic_val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoPanopticMetric',
+    ann_file=data_root + 'annotations/panoptic_val2017.json',
+    seg_prefix=data_root + 'annotations/panoptic_val2017/',
+    backend_args=backend_args)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=1,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file='annotations/panoptic_image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoPanopticMetric',
+#     format_only=True,
+#     ann_file=data_root + 'annotations/panoptic_image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_panoptic/test')

configs/_base_/datasets/coco_semantic.py

+# dataset settings
+dataset_type = 'CocoSegDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(
+        type='LoadAnnotations',
+        with_bbox=False,
+        with_label=False,
+        with_seg=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(
+        type='LoadAnnotations',
+        with_bbox=False,
+        with_label=False,
+        with_seg=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor'))
+]
+
+# For stuffthingmaps_semseg, please refer to
+# `docs/en/user_guides/dataset_prepare.md`
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='train2017/',
+            seg_map_path='stuffthingmaps_semseg/train2017/'),
+        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,
+        data_prefix=dict(
+            img_path='val2017/',
+            seg_map_path='stuffthingmaps_semseg/val2017/'),
+        pipeline=test_pipeline))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='SemSegMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/deepfashion.py

+# dataset settings
+dataset_type = 'DeepFashionDataset'
+data_root = 'data/DeepFashion/In-shop/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', scale=(750, 1101), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(750, 1101), keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=2,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='Anno/segmentation/DeepFashion_segmentation_train.json',
+            data_prefix=dict(img='Img/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            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='Anno/segmentation/DeepFashion_segmentation_query.json',
+        data_prefix=dict(img='Img/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+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,
+        ann_file='Anno/segmentation/DeepFashion_segmentation_gallery.json',
+        data_prefix=dict(img='Img/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root +
+    'Anno/segmentation/DeepFashion_segmentation_query.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root +
+    'Anno/segmentation/DeepFashion_segmentation_gallery.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)

configs/_base_/datasets/dsdl.py

+dataset_type = 'DSDLDetDataset'
+data_root = 'path to dataset folder'
+train_ann = 'path to train yaml file'
+val_ann = 'path to val yaml file'
+
+backend_args = None
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': "s3://open_data/",
+#         'data/': "s3://open_data/"
+#     }))
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'instances'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=train_ann,
+        filter_cfg=dict(filter_empty_gt=True, min_size=32, bbox_min_size=32),
+        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=val_ann,
+        test_mode=True,
+        pipeline=test_pipeline))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='CocoMetric', metric='bbox')
+# val_evaluator = dict(type='VOCMetric', metric='mAP', eval_mode='11points')
+test_evaluator = val_evaluator

configs/_base_/datasets/isaid_instance.py

+# dataset settings
+dataset_type = 'iSAIDDataset'
+data_root = 'data/iSAID/'
+backend_args = None
+
+# Please see  `projects/iSAID/README.md` for data preparation
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', scale=(800, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(800, 800), keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='train/instancesonly_filtered_train.json',
+        data_prefix=dict(img='train/images/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        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='val/instancesonly_filtered_val.json',
+        data_prefix=dict(img='val/images/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'val/instancesonly_filtered_val.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/lvis_v0.5_instance.py

+# dataset settings
+dataset_type = 'LVISV05Dataset'
+data_root = 'data/lvis_v0.5/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/lvis_v0.5/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='RandomChoiceResize',
+        scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                (1333, 768), (1333, 800)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='ClassBalancedDataset',
+        oversample_thr=1e-3,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/lvis_v0.5_train.json',
+            data_prefix=dict(img='train2017/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            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='annotations/lvis_v0.5_val.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='LVISMetric',
+    ann_file=data_root + 'annotations/lvis_v0.5_val.json',
+    metric=['bbox', 'segm'],
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/lvis_v1_instance.py

+# dataset settings
+_base_ = 'lvis_v0.5_instance.py'
+dataset_type = 'LVISV1Dataset'
+data_root = 'data/lvis_v1/'
+
+train_dataloader = dict(
+    dataset=dict(
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/lvis_v1_train.json',
+            data_prefix=dict(img=''))))
+val_dataloader = dict(
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/lvis_v1_val.json',
+        data_prefix=dict(img='')))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(ann_file=data_root + 'annotations/lvis_v1_val.json')
+test_evaluator = val_evaluator

configs/_base_/datasets/mot_challenge.py

+# dataset settings
+dataset_type = 'MOTChallengeDataset'
+data_root = 'data/MOT17/'
+img_scale = (1088, 1088)
+
+backend_args = None
+# data pipeline
+train_pipeline = [
+    dict(
+        type='UniformRefFrameSample',
+        num_ref_imgs=1,
+        frame_range=10,
+        filter_key_img=True),
+    dict(
+        type='TransformBroadcaster',
+        share_random_params=True,
+        transforms=[
+            dict(type='LoadImageFromFile', backend_args=backend_args),
+            dict(type='LoadTrackAnnotations'),
+            dict(
+                type='RandomResize',
+                scale=img_scale,
+                ratio_range=(0.8, 1.2),
+                keep_ratio=True,
+                clip_object_border=False),
+            dict(type='PhotoMetricDistortion')
+        ]),
+    dict(
+        type='TransformBroadcaster',
+        # different cropped positions for different frames
+        share_random_params=False,
+        transforms=[
+            dict(
+                type='RandomCrop', crop_size=img_scale, bbox_clip_border=False)
+        ]),
+    dict(
+        type='TransformBroadcaster',
+        share_random_params=True,
+        transforms=[
+            dict(type='RandomFlip', prob=0.5),
+        ]),
+    dict(type='PackTrackInputs')
+]
+
+test_pipeline = [
+    dict(
+        type='TransformBroadcaster',
+        transforms=[
+            dict(type='LoadImageFromFile', backend_args=backend_args),
+            dict(type='Resize', scale=img_scale, keep_ratio=True),
+            dict(type='LoadTrackAnnotations')
+        ]),
+    dict(type='PackTrackInputs')
+]
+
+# dataloader
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='TrackImgSampler'),  # image-based sampling
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        visibility_thr=-1,
+        ann_file='annotations/half-train_cocoformat.json',
+        data_prefix=dict(img_path='train'),
+        metainfo=dict(classes=('pedestrian', )),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    # Now we support two ways to test, image_based and video_based
+    # if you want to use video_based sampling, you can use as follows
+    # sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
+    sampler=dict(type='TrackImgSampler'),  # image-based sampling
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/half-val_cocoformat.json',
+        data_prefix=dict(img_path='train'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+# evaluator
+val_evaluator = dict(
+    type='MOTChallengeMetric', metric=['HOTA', 'CLEAR', 'Identity'])
+test_evaluator = val_evaluator

configs/_base_/datasets/mot_challenge_det.py

+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/MOT17/'
+
+backend_args = None
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args, to_float32=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomResize',
+        scale=(1088, 1088),
+        ratio_range=(0.8, 1.2),
+        keep_ratio=True,
+        clip_object_border=False),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='RandomCrop', crop_size=(1088, 1088), bbox_clip_border=False),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1088, 1088), keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/half-train_cocoformat.json',
+        data_prefix=dict(img='train/'),
+        metainfo=dict(classes=('pedestrian', )),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        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='annotations/half-val_cocoformat.json',
+        data_prefix=dict(img='train/'),
+        metainfo=dict(classes=('pedestrian', )),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/half-val_cocoformat.json',
+    metric='bbox',
+    format_only=False)
+test_evaluator = val_evaluator

configs/_base_/datasets/mot_challenge_reid.py

+# dataset settings
+dataset_type = 'ReIDDataset'
+data_root = 'data/MOT17/'
+
+backend_args = None
+# data pipeline
+train_pipeline = [
+    dict(
+        type='TransformBroadcaster',
+        share_random_params=False,
+        transforms=[
+            dict(
+                type='LoadImageFromFile',
+                backend_args=backend_args,
+                to_float32=True),
+            dict(
+                type='Resize',
+                scale=(128, 256),
+                keep_ratio=False,
+                clip_object_border=False),
+            dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+        ]),
+    dict(type='PackReIDInputs', meta_keys=('flip', 'flip_direction'))
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args, to_float32=True),
+    dict(type='Resize', scale=(128, 256), keep_ratio=False),
+    dict(type='PackReIDInputs')
+]
+
+# dataloader
+train_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        triplet_sampler=dict(num_ids=8, ins_per_id=4),
+        data_prefix=dict(img_path='reid/imgs'),
+        ann_file='reid/meta/train_80.txt',
+        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,
+        triplet_sampler=None,
+        data_prefix=dict(img_path='reid/imgs'),
+        ann_file='reid/meta/val_20.txt',
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+# evaluator
+val_evaluator = dict(type='ReIDMetrics', metric=['mAP', 'CMC'])
+test_evaluator = val_evaluator

configs/_base_/datasets/objects365v1_detection.py

+# dataset settings
+dataset_type = 'Objects365V1Dataset'
+data_root = 'data/Objects365/Obj365_v1/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        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='annotations/objects365_val.json',
+        data_prefix=dict(img='val/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/objects365_val.json',
+    metric='bbox',
+    sort_categories=True,
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/objects365v2_detection.py

+# dataset settings
+dataset_type = 'Objects365V2Dataset'
+data_root = 'data/Objects365/Obj365_v2/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/zhiyuan_objv2_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        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='annotations/zhiyuan_objv2_val.json',
+        data_prefix=dict(img='val/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/zhiyuan_objv2_val.json',
+    metric='bbox',
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/openimages_detection.py

+# dataset settings
+dataset_type = 'OpenImagesDataset'
+data_root = 'data/OpenImages/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1024, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1024, 800), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='LoadAnnotations', with_bbox=True),
+    # TODO: find a better way to collect image_level_labels
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'instances', 'image_level_labels'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=0,  # workers_per_gpu > 0 may occur out of memory
+    persistent_workers=False,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/oidv6-train-annotations-bbox.csv',
+        data_prefix=dict(img='OpenImages/train/'),
+        label_file='annotations/class-descriptions-boxable.csv',
+        hierarchy_file='annotations/bbox_labels_600_hierarchy.json',
+        meta_file='annotations/train-image-metas.pkl',
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=0,
+    persistent_workers=False,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/validation-annotations-bbox.csv',
+        data_prefix=dict(img='OpenImages/validation/'),
+        label_file='annotations/class-descriptions-boxable.csv',
+        hierarchy_file='annotations/bbox_labels_600_hierarchy.json',
+        meta_file='annotations/validation-image-metas.pkl',
+        image_level_ann_file='annotations/validation-'
+        'annotations-human-imagelabels-boxable.csv',
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='OpenImagesMetric',
+    iou_thrs=0.5,
+    ioa_thrs=0.5,
+    use_group_of=True,
+    get_supercategory=True)
+test_evaluator = val_evaluator

configs/_base_/datasets/refcoco+.py

+# dataset settings
+dataset_type = 'RefCocoDataset'
+data_root = 'data/coco/'
+
+backend_args = None
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(
+        type='LoadAnnotations',
+        with_mask=True,
+        with_bbox=False,
+        with_seg=False,
+        with_label=False),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'gt_masks', 'text'))
+]
+
+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,
+        data_prefix=dict(img_path='train2014/'),
+        ann_file='refcoco+/instances.json',
+        split_file='refcoco+/refs(unc).p',
+        split='val',
+        text_mode='select_first',
+        pipeline=test_pipeline))
+
+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='train2014/'),
+        ann_file='refcoco+/instances.json',
+        split_file='refcoco+/refs(unc).p',
+        split='testA',  # or 'testB'
+        text_mode='select_first',
+        pipeline=test_pipeline))
+
+val_evaluator = dict(type='RefSegMetric', metric=['cIoU', 'mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/refcoco.py

+# dataset settings
+dataset_type = 'RefCocoDataset'
+data_root = 'data/coco/'
+
+backend_args = None
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(
+        type='LoadAnnotations',
+        with_mask=True,
+        with_bbox=False,
+        with_seg=False,
+        with_label=False),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'gt_masks', 'text'))
+]
+
+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,
+        data_prefix=dict(img_path='train2014/'),
+        ann_file='refcoco/instances.json',
+        split_file='refcoco/refs(unc).p',
+        split='val',
+        text_mode='select_first',
+        pipeline=test_pipeline))
+
+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='train2014/'),
+        ann_file='refcoco/instances.json',
+        split_file='refcoco/refs(unc).p',
+        split='testA',  # or 'testB'
+        text_mode='select_first',
+        pipeline=test_pipeline))
+
+val_evaluator = dict(type='RefSegMetric', metric=['cIoU', 'mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/refcocog.py

+# dataset settings
+dataset_type = 'RefCocoDataset'
+data_root = 'data/coco/'
+
+backend_args = None
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(
+        type='LoadAnnotations',
+        with_mask=True,
+        with_bbox=False,
+        with_seg=False,
+        with_label=False),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'gt_masks', 'text'))
+]
+
+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,
+        data_prefix=dict(img_path='train2014/'),
+        ann_file='refcocog/instances.json',
+        split_file='refcocog/refs(umd).p',
+        split='val',
+        text_mode='select_first',
+        pipeline=test_pipeline))
+
+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='train2014/'),
+        ann_file='refcocog/instances.json',
+        split_file='refcocog/refs(umd).p',
+        split='test',
+        text_mode='select_first',
+        pipeline=test_pipeline))
+
+val_evaluator = dict(type='RefSegMetric', metric=['cIoU', 'mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/semi_coco_detection.py

+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+color_space = [
+    [dict(type='ColorTransform')],
+    [dict(type='AutoContrast')],
+    [dict(type='Equalize')],
+    [dict(type='Sharpness')],
+    [dict(type='Posterize')],
+    [dict(type='Solarize')],
+    [dict(type='Color')],
+    [dict(type='Contrast')],
+    [dict(type='Brightness')],
+]
+
+geometric = [
+    [dict(type='Rotate')],
+    [dict(type='ShearX')],
+    [dict(type='ShearY')],
+    [dict(type='TranslateX')],
+    [dict(type='TranslateY')],
+]
+
+scale = [(1333, 400), (1333, 1200)]
+
+branch_field = ['sup', 'unsup_teacher', 'unsup_student']
+# pipeline used to augment labeled data,
+# which will be sent to student model for supervised training.
+sup_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='RandomResize', scale=scale, keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='RandAugment', aug_space=color_space, aug_num=1),
+    dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
+    dict(
+        type='MultiBranch',
+        branch_field=branch_field,
+        sup=dict(type='PackDetInputs'))
+]
+
+# pipeline used to augment unlabeled data weakly,
+# which will be sent to teacher model for predicting pseudo instances.
+weak_pipeline = [
+    dict(type='RandomResize', scale=scale, keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'flip', 'flip_direction',
+                   'homography_matrix')),
+]
+
+# pipeline used to augment unlabeled data strongly,
+# which will be sent to student model for unsupervised training.
+strong_pipeline = [
+    dict(type='RandomResize', scale=scale, keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(
+        type='RandomOrder',
+        transforms=[
+            dict(type='RandAugment', aug_space=color_space, aug_num=1),
+            dict(type='RandAugment', aug_space=geometric, aug_num=1),
+        ]),
+    dict(type='RandomErasing', n_patches=(1, 5), ratio=(0, 0.2)),
+    dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'flip', 'flip_direction',
+                   'homography_matrix')),
+]
+
+# pipeline used to augment unlabeled data into different views
+unsup_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadEmptyAnnotations'),
+    dict(
+        type='MultiBranch',
+        branch_field=branch_field,
+        unsup_teacher=weak_pipeline,
+        unsup_student=strong_pipeline,
+    )
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+batch_size = 5
+num_workers = 5
+# There are two common semi-supervised learning settings on the coco dataset：
+# (1) Divide the train2017 into labeled and unlabeled datasets
+# by a fixed percentage, such as 1%, 2%, 5% and 10%.
+# The format of labeled_ann_file and unlabeled_ann_file are
+# instances_train2017.{fold}@{percent}.json, and
+# instances_train2017.{fold}@{percent}-unlabeled.json
+# `fold` is used for cross-validation, and `percent` represents
+# the proportion of labeled data in the train2017.
+# (2) Choose the train2017 as the labeled dataset
+# and unlabeled2017 as the unlabeled dataset.
+# The labeled_ann_file and unlabeled_ann_file are
+# instances_train2017.json and image_info_unlabeled2017.json
+# We use this configuration by default.
+labeled_dataset = dict(
+    type=dataset_type,
+    data_root=data_root,
+    ann_file='annotations/instances_train2017.json',
+    data_prefix=dict(img='train2017/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=sup_pipeline,
+    backend_args=backend_args)
+
+unlabeled_dataset = dict(
+    type=dataset_type,
+    data_root=data_root,
+    ann_file='annotations/instances_unlabeled2017.json',
+    data_prefix=dict(img='unlabeled2017/'),
+    filter_cfg=dict(filter_empty_gt=False),
+    pipeline=unsup_pipeline,
+    backend_args=backend_args)
+
+train_dataloader = dict(
+    batch_size=batch_size,
+    num_workers=num_workers,
+    persistent_workers=True,
+    sampler=dict(
+        type='GroupMultiSourceSampler',
+        batch_size=batch_size,
+        source_ratio=[1, 4]),
+    dataset=dict(
+        type='ConcatDataset', datasets=[labeled_dataset, unlabeled_dataset]))
+
+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='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric='bbox',
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/v3det.py

+# dataset settings
+dataset_type = 'V3DetDataset'
+data_root = 'data/V3Det/'
+
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomChoiceResize',
+        scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                (1333, 768), (1333, 800)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='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=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='ClassBalancedDataset',
+        oversample_thr=1e-3,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/v3det_2023_v1_train.json',
+            data_prefix=dict(img=''),
+            filter_cfg=dict(filter_empty_gt=True, min_size=4),
+            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='annotations/v3det_2023_v1_val.json',
+        data_prefix=dict(img=''),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/v3det_2023_v1_val.json',
+    metric='bbox',
+    format_only=False,
+    backend_args=backend_args,
+    use_mp_eval=True,
+    proposal_nums=[300])
+test_evaluator = val_evaluator