update codes

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)))

configs/_base_/models/cascade-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_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))
+        ]),
+    # 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),
+                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),
+                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),
+                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)))

configs/_base_/models/fast-rcnn_r50_fpn.py

+# model settings
+model = dict(
+    type='FastRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=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),
+    roi_head=dict(
+        type='StandardRoIHead',
+        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=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        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),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/faster-rcnn_r50-caffe-c4.py

+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='FasterRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        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='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        shared_head=dict(
+            type='ResLayer',
+            depth=50,
+            stage=3,
+            stride=2,
+            dilation=1,
+            style='caffe',
+            norm_cfg=norm_cfg,
+            norm_eval=True,
+            init_cfg=dict(
+                type='Pretrained',
+                checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=1024,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='BBoxHead',
+            with_avg_pool=True,
+            roi_feat_size=7,
+            in_channels=2048,
+            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=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', 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=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=12000,
+            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),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=6000,
+            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)))

configs/_base_/models/faster-rcnn_r50-caffe-dc5.py

+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='FasterRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        strides=(1, 2, 2, 1),
+        dilations=(1, 1, 1, 2),
+        out_indices=(3, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=2048,
+        feat_channels=2048,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        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='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=2048,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=2048,
+            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=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', 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=12000,
+            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),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms=dict(type='nms', iou_threshold=0.7),
+            nms_pre=6000,
+            max_per_img=1000,
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/faster-rcnn_r50_fpn.py

+# model settings
+model = dict(
+    type='FasterRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=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='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        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=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', 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=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            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),
+            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)
+        # soft-nms is also supported for rcnn testing
+        # e.g., nms=dict(type='soft_nms', iou_threshold=0.5, min_score=0.05)
+    ))

configs/_base_/models/mask-rcnn_r50-caffe-c4.py

+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='MaskRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_mask=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        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='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        shared_head=dict(
+            type='ResLayer',
+            depth=50,
+            stage=3,
+            stride=2,
+            dilation=1,
+            style='caffe',
+            norm_cfg=norm_cfg,
+            norm_eval=True),
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=1024,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='BBoxHead',
+            with_avg_pool=True,
+            roi_feat_size=7,
+            in_channels=2048,
+            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=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=None,
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=0,
+            in_channels=2048,
+            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=12000,
+            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=14,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=6000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            max_per_img=1000,
+            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)))

configs/_base_/models/mask-rcnn_r50_fpn.py

+# model settings
+model = dict(
+    type='MaskRCNN',
+    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='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        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=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', 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=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            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=True,
+                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)))

configs/_base_/models/retinanet_r50_fpn.py

+# model settings
+model = dict(
+    type='RetinaNet',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=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,
+        start_level=1,
+        add_extra_convs='on_input',
+        num_outs=5),
+    bbox_head=dict(
+        type='RetinaHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            octave_base_scale=4,
+            scales_per_octave=3,
+            ratios=[0.5, 1.0, 2.0],
+            strides=[8, 16, 32, 64, 128]),
+        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='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='PseudoSampler'),  # Focal loss should use PseudoSampler
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms', iou_threshold=0.5),
+        max_per_img=100))

configs/_base_/models/rpn_r50-caffe-c4.py

+# model settings
+model = dict(
+    type='RPN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    neck=None,
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        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='L1Loss', 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,
+                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=-1,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0)))

configs/_base_/models/rpn_r50_fpn.py

+# model settings
+model = dict(
+    type='RPN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=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='L1Loss', 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,
+                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=-1,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0)))

configs/_base_/models/ssd300.py

+# model settings
+input_size = 300
+model = dict(
+    type='SingleStageDetector',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[1, 1, 1],
+        bgr_to_rgb=True,
+        pad_size_divisor=1),
+    backbone=dict(
+        type='SSDVGG',
+        depth=16,
+        with_last_pool=False,
+        ceil_mode=True,
+        out_indices=(3, 4),
+        out_feature_indices=(22, 34),
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://vgg16_caffe')),
+    neck=dict(
+        type='SSDNeck',
+        in_channels=(512, 1024),
+        out_channels=(512, 1024, 512, 256, 256, 256),
+        level_strides=(2, 2, 1, 1),
+        level_paddings=(1, 1, 0, 0),
+        l2_norm_scale=20),
+    bbox_head=dict(
+        type='SSDHead',
+        in_channels=(512, 1024, 512, 256, 256, 256),
+        num_classes=80,
+        anchor_generator=dict(
+            type='SSDAnchorGenerator',
+            scale_major=False,
+            input_size=input_size,
+            basesize_ratio_range=(0.15, 0.9),
+            strides=[8, 16, 32, 64, 100, 300],
+            ratios=[[2], [2, 3], [2, 3], [2, 3], [2], [2]]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[0.1, 0.1, 0.2, 0.2])),
+    # model training and testing settings
+    train_cfg=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.,
+            ignore_iof_thr=-1,
+            gt_max_assign_all=False),
+        sampler=dict(type='PseudoSampler'),
+        smoothl1_beta=1.,
+        allowed_border=-1,
+        pos_weight=-1,
+        neg_pos_ratio=3,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        nms=dict(type='nms', iou_threshold=0.45),
+        min_bbox_size=0,
+        score_thr=0.02,
+        max_per_img=200))
+cudnn_benchmark = True

configs/_base_/schedules/schedule_1x.py

+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=12,
+        by_epoch=True,
+        milestones=[8, 11],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=16)

configs/_base_/schedules/schedule_20e.py

+# training schedule for 20e
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=20, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=20,
+        by_epoch=True,
+        milestones=[16, 19],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=16)

configs/_base_/schedules/schedule_2x.py

+# training schedule for 2x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=24, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=24,
+        by_epoch=True,
+        milestones=[16, 22],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=16)

dataset-index.yml

+openxlab: true
+voc2007:
+  dataset: OpenDataLab/PASCAL_VOC2007
+  download_root: data
+  data_root: data
+  script: tools/dataset_converters/scripts/preprocess_voc2007.sh
+
+voc2012:
+  dataset: OpenDataLab/PASCAL_VOC2012
+  download_root: data
+  data_root: data
+  script: tools/dataset_converters/scripts/preprocess_voc2012.sh
+
+coco2017:
+  dataset: OpenDataLab/COCO_2017
+  download_root: data
+  data_root: data/coco
+  script: tools/dataset_converters/scripts/preprocess_coco2017.sh