add reppoints head, reppoints detector and the config files.

configs/reppoints/bbox_r50_grid_center_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='minmax',
+        use_grid_points=True))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/bbox_r50_grid_center_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/bbox_r50_grid_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='minmax',
+        use_grid_points=True))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/bbox_r50_grid_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_minmax_r50_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='minmax'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_minmax_r50_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r101_dcn_fpn_2x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet101',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        dcn=dict(
+            modulated=False, deformable_groups=1, fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r101_dcn_fpn_2x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r101_dcn_fpn_2x_mt.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet101',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        dcn=dict(
+            modulated=False, deformable_groups=1, fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 960)],
+        keep_ratio=True,
+        multiscale_mode='range'),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r101_dcn_fpn_2x_mt'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r101_fpn_2x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet101',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r101_fpn_2x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r101_fpn_2x_mt.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet101',
+    backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 960)],
+        keep_ratio=True,
+        multiscale_mode='range'),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r101_fpn_2x_mt'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r50_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r50_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r50_fpn_2x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r50_fpn_2x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_r50_fpn_2x_mt.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 960)],
+        keep_ratio=True,
+        multiscale_mode='range'),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_r50_fpn_2x_mt'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_x101_dcn_fpn_2x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='open-mmlab://resnext101_32x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        dcn=dict(
+            modulated=False,
+            groups=32,
+            deformable_groups=1,
+            fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_x101_dcn_fpn_2x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_moment_x101_dcn_fpn_2x_mt.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='open-mmlab://resnext101_32x4d',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=32,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        dcn=dict(
+            modulated=False,
+            groups=32,
+            deformable_groups=1,
+            fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='moment'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='Resize',
+        img_scale=[(1333, 480), (1333, 960)],
+        keep_ratio=True,
+        multiscale_mode='range'),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[16, 22])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 24
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_moment_x101_dcn_fpn_2x_mt'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

configs/reppoints/reppoints_partial_minmax_r50_fpn_1x.py

+# model settings
+norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+
+model = dict(
+    type='RepPointsDetector',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        norm_cfg=norm_cfg),
+    bbox_head=dict(
+        type='RepPointsHead',
+        num_classes=81,
+        in_channels=256,
+        feat_channels=256,
+        point_feat_channels=256,
+        stacked_convs=3,
+        num_points=9,
+        gradient_mul=0.1,
+        point_strides=[8, 16, 32, 64, 128],
+        point_base_scale=4,
+        norm_cfg=norm_cfg,
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
+        loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
+        transform_method='partial_minmax'))
+# training and testing settings
+train_cfg = dict(
+    init=dict(
+        assigner=dict(type='PointAssigner', scale=4, pos_num=1),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    refine=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        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_thr=0.5),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/reppoints_partial_minmax_r50_fpn_1x'
+load_from = None
+resume_from = None
+auto_resume = True
+workflow = [('train', 1)]

mmdet/models/anchor_heads/__init__.py

@@ -3,11 +3,13 @@ from .fcos_head import FCOSHead
 from .ga_retina_head import GARetinaHead
 from .ga_rpn_head import GARPNHead
 from .guided_anchor_head import FeatureAdaption, GuidedAnchorHead
+from .reppoints_head import RepPointsHead
 from .retina_head import RetinaHead
 from .rpn_head import RPNHead
 from .ssd_head import SSDHead
 
 __all__ = [
     'AnchorHead', 'GuidedAnchorHead', 'FeatureAdaption', 'RPNHead',
-    'GARPNHead', 'RetinaHead', 'GARetinaHead', 'SSDHead', 'FCOSHead'
+    'GARPNHead', 'RetinaHead', 'GARetinaHead', 'SSDHead', 'FCOSHead',
+    'RepPointsHead'
 ]

mmdet/models/detectors/__init__.py

@@ -8,6 +8,7 @@ from .grid_rcnn import GridRCNN
 from .htc import HybridTaskCascade
 from .mask_rcnn import MaskRCNN
 from .mask_scoring_rcnn import MaskScoringRCNN
+from .reppoints_detector import RepPointsDetector
 from .retinanet import RetinaNet
 from .rpn import RPN
 from .single_stage import SingleStageDetector
@@ -16,5 +17,6 @@ from .two_stage import TwoStageDetector
 __all__ = [
     'BaseDetector', 'SingleStageDetector', 'TwoStageDetector', 'RPN',
     'FastRCNN', 'FasterRCNN', 'MaskRCNN', 'CascadeRCNN', 'HybridTaskCascade',
-    'DoubleHeadRCNN', 'RetinaNet', 'FCOS', 'GridRCNN', 'MaskScoringRCNN'
+    'DoubleHeadRCNN', 'RetinaNet', 'FCOS', 'GridRCNN', 'MaskScoringRCNN',
+    'RepPointsDetector'
 ]

mmdet/models/detectors/reppoints_detector.py

+import torch
+
+from mmdet.core import bbox2result, bbox_mapping_back, multiclass_nms
+from ..registry import DETECTORS
+from .single_stage import SingleStageDetector
+
+
+@DETECTORS.register_module
+class RepPointsDetector(SingleStageDetector):
+    """RepPoints: Point Set Representation for Object Detection.
+
+        This detector is the implementation of:
+        - RepPoints detector (https://arxiv.org/pdf/1904.11490)
+    """
+
+    def __init__(self,
+                 backbone,
+                 neck,
+                 bbox_head,
+                 train_cfg=None,
+                 test_cfg=None,
+                 pretrained=None):
+        super(RepPointsDetector,
+              self).__init__(backbone, neck, bbox_head, train_cfg, test_cfg,
+                             pretrained)
+
+    def merge_aug_results(self, aug_bboxes, aug_scores, img_metas):
+        """Merge augmented detection bboxes and scores.
+
+        Args:
+            aug_bboxes (list[Tensor]): shape (n, 4*#class)
+            aug_scores (list[Tensor] or None): shape (n, #class)
+            img_shapes (list[Tensor]): shape (3, ).
+
+        Returns:
+            tuple: (bboxes, scores)
+        """
+        recovered_bboxes = []
+        for bboxes, img_info in zip(aug_bboxes, img_metas):
+            img_shape = img_info[0]['img_shape']
+            scale_factor = img_info[0]['scale_factor']
+            flip = img_info[0]['flip']
+            bboxes = bbox_mapping_back(bboxes, img_shape, scale_factor, flip)
+            recovered_bboxes.append(bboxes)
+        bboxes = torch.cat(recovered_bboxes, dim=0)
+        if aug_scores is None:
+            return bboxes
+        else:
+            scores = torch.cat(aug_scores, dim=0)
+            return bboxes, scores
+
+    def aug_test(self, imgs, img_metas, rescale=False):
+        # recompute feats to save memory
+        feats = self.extract_feats(imgs)
+
+        aug_bboxes = []
+        aug_scores = []
+        for x, img_meta in zip(feats, img_metas):
+            # only one image in the batch
+            outs = self.bbox_head(x)
+            bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
+            det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
+            aug_bboxes.append(det_bboxes)
+            aug_scores.append(det_scores)
+
+        # after merging, bboxes will be rescaled to the original image size
+        merged_bboxes, merged_scores = self.merge_aug_results(
+            aug_bboxes, aug_scores, img_metas)
+        det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
+                                                self.test_cfg.score_thr,
+                                                self.test_cfg.nms,
+                                                self.test_cfg.max_per_img)
+
+        if rescale:
+            _det_bboxes = det_bboxes
+        else:
+            _det_bboxes = det_bboxes.clone()
+            _det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
+        bbox_results = bbox2result(_det_bboxes, det_labels,
+                                   self.bbox_head.num_classes)
+        return bbox_results