update code

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

configs/_base_/datasets/voc0712.py

+# dataset settings
+dataset_type = 'VOCDataset'
+data_root = 'data/VOCdevkit/'
+
+# 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/segmentation/VOCdevkit/'
+
+# 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/segmentation/',
+#         'data/': 's3://openmmlab/datasets/segmentation/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1000, 600), 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=(1000, 600), keep_ratio=True),
+    # avoid bboxes being resized
+    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='RepeatDataset',
+        times=3,
+        dataset=dict(
+            type='ConcatDataset',
+            # VOCDataset will add different `dataset_type` in dataset.metainfo,
+            # which will get error if using ConcatDataset. Adding
+            # `ignore_keys` can avoid this error.
+            ignore_keys=['dataset_type'],
+            datasets=[
+                dict(
+                    type=dataset_type,
+                    data_root=data_root,
+                    ann_file='VOC2007/ImageSets/Main/trainval.txt',
+                    data_prefix=dict(sub_data_root='VOC2007/'),
+                    filter_cfg=dict(
+                        filter_empty_gt=True, min_size=32, bbox_min_size=32),
+                    pipeline=train_pipeline,
+                    backend_args=backend_args),
+                dict(
+                    type=dataset_type,
+                    data_root=data_root,
+                    ann_file='VOC2012/ImageSets/Main/trainval.txt',
+                    data_prefix=dict(sub_data_root='VOC2012/'),
+                    filter_cfg=dict(
+                        filter_empty_gt=True, min_size=32, bbox_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='VOC2007/ImageSets/Main/test.txt',
+        data_prefix=dict(sub_data_root='VOC2007/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+# Pascal VOC2007 uses `11points` as default evaluate mode, while PASCAL
+# VOC2012 defaults to use 'area'.
+val_evaluator = dict(type='VOCMetric', metric='mAP', eval_mode='11points')
+test_evaluator = val_evaluator

configs/_base_/datasets/wider_face.py

+# dataset settings
+dataset_type = 'WIDERFaceDataset'
+data_root = 'data/WIDERFace/'
+# 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/cityscapes/'
+
+# 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
+
+img_scale = (640, 640)  # VGA resolution
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=img_scale, 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=img_scale, 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,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='train.txt',
+        data_prefix=dict(img='WIDER_train'),
+        filter_cfg=dict(filter_empty_gt=True, bbox_min_size=17, 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.txt',
+        data_prefix=dict(img='WIDER_val'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    # TODO: support WiderFace-Evaluation for easy, medium, hard cases
+    type='VOCMetric',
+    metric='mAP',
+    eval_mode='11points')
+test_evaluator = val_evaluator

configs/_base_/datasets/youtube_vis.py

+dataset_type = 'YouTubeVISDataset'
+data_root = 'data/youtube_vis_2019/'
+dataset_version = data_root[-5:-1]  # 2019 or 2021
+
+backend_args = None
+
+# dataset settings
+train_pipeline = [
+    dict(
+        type='UniformRefFrameSample',
+        num_ref_imgs=1,
+        frame_range=100,
+        filter_key_img=True),
+    dict(
+        type='TransformBroadcaster',
+        share_random_params=True,
+        transforms=[
+            dict(type='LoadImageFromFile', backend_args=backend_args),
+            dict(type='LoadTrackAnnotations', with_mask=True),
+            dict(type='Resize', scale=(640, 360), keep_ratio=True),
+            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=(640, 360), keep_ratio=True),
+            dict(type='LoadTrackAnnotations', with_mask=True),
+        ]),
+    dict(type='PackTrackInputs')
+]
+
+# dataloader
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    # sampler=dict(type='TrackImgSampler'),  # image-based sampling
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='TrackAspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        dataset_version=dataset_version,
+        ann_file='annotations/youtube_vis_2019_train.json',
+        data_prefix=dict(img_path='train/JPEGImages'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        dataset_version=dataset_version,
+        ann_file='annotations/youtube_vis_2019_valid.json',
+        data_prefix=dict(img_path='valid/JPEGImages'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader

configs/_base_/default_runtime.py

+default_scope = 'mmdet'
+
+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='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='DetLocalVisualizer', 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_/models/cascade-mask-rcnn_r50_fpn.py

+# model settings
+model = dict(
+    type='CascadeRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_mask=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        type='CascadeRoIHead',
+        num_stages=3,
+        stage_loss_weights=[1, 0.5, 0.25],
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=[
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ],
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=4,
+            in_channels=256,
+            conv_out_channels=256,
+            num_classes=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=[
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.5,
+                    neg_iou_thr=0.5,
+                    min_pos_iou=0.5,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.6,
+                    neg_iou_thr=0.6,
+                    min_pos_iou=0.6,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.7,
+                    neg_iou_thr=0.7,
+                    min_pos_iou=0.7,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False)
+        ]),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))