configs/detection/vitdet/vitdet_faster_rcnn.py [8:78]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    pretrained=pretrained,
    backbone=dict(
        type='ViTDet',
        img_size=1024,
        patch_size=16,
        embed_dim=768,
        depth=12,
        num_heads=12,
        drop_path_rate=0.1,
        window_size=14,
        mlp_ratio=4,
        qkv_bias=True,
        window_block_indexes=[
            # 2, 5, 8 11 for global attention
            0,
            1,
            3,
            4,
            6,
            7,
            9,
            10,
        ],
        residual_block_indexes=[],
        use_rel_pos=True),
    neck=dict(
        type='SFP',
        in_channels=768,
        out_channels=256,
        scale_factors=(4.0, 2.0, 1.0, 0.5),
        norm_cfg=norm_cfg,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        num_convs=2,
        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='Shared4Conv1FCBBoxHead',
            conv_out_channels=256,
            norm_cfg=norm_cfg,
            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),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



configs/detection/vitdet/vitdet_mask_rcnn.py [8:78]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    pretrained=pretrained,
    backbone=dict(
        type='ViTDet',
        img_size=1024,
        patch_size=16,
        embed_dim=768,
        depth=12,
        num_heads=12,
        drop_path_rate=0.1,
        window_size=14,
        mlp_ratio=4,
        qkv_bias=True,
        window_block_indexes=[
            # 2, 5, 8 11 for global attention
            0,
            1,
            3,
            4,
            6,
            7,
            9,
            10,
        ],
        residual_block_indexes=[],
        use_rel_pos=True),
    neck=dict(
        type='SFP',
        in_channels=768,
        out_channels=256,
        scale_factors=(4.0, 2.0, 1.0, 0.5),
        norm_cfg=norm_cfg,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        num_convs=2,
        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='Shared4Conv1FCBBoxHead',
            conv_out_channels=256,
            norm_cfg=norm_cfg,
            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),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -