crop_size = (
    256,
    256,
)
model = dict(
    backbone=dict(
        adapter_index=[
            0,
            1,
            2,
            3,
            4,
            5,
            6,
            7,
            8,
            9,
            10,
            11,
            12,
            13,
            14,
            15,
            16,
            17,
            18,
            19,
            20,
            21,
            22,
            23,
        ],
        block_chunks=0,
        depth=24,
        embed_dim=1024,
        ffn_bias=True,
        ffn_layer='mlp',
        has_cat=False,
        img_size=512,
        init_values=1e-05,
        mlp_ratio=4,
        num_heads=16,
        cloud_adapter_config=dict(
            cnn_type='pmaa',
            context_dim=64,
            depth=4,
            emd_dim=1024,
            global_groups=1,
            hidden_channels=64,
            int_type='convnext',
            local_groups=1,
            num_layers=24,
            rank_dim=16,
            return_last_feature=False,
            return_multi_feats=False,
            type='CloudAdapter'),
        patch_size=16,
        proj_bias=True,
        qkv_bias=True,
        type='CloudAdapterDinoVisionTransformer'),
    data_preprocessor=dict(
        bgr_to_rgb=True,
        mean=[
            123.675,
            116.28,
            103.53,
        ],
        pad_val=0,
        seg_pad_val=255,
        size=(
            512,
            512,
        ),
        std=[
            58.395,
            57.12,
            57.375,
        ],
        type='SegDataPreProcessor'),
    decode_head=dict(
        align_corners=False,
        enforce_decoder_input_project=False,
        feat_channels=256,
        in_channels=[
            1024,
            1024,
            1024,
            1024,
        ],
        loss_cls=dict(
            class_weight=[
                1.0,
                1.0,
                1.0,
                1.0,
                0.1,
            ],
            loss_weight=2.0,
            reduction='mean',
            type='mmdet.CrossEntropyLoss',
            use_sigmoid=False),
        loss_dice=dict(
            activate=True,
            eps=1.0,
            loss_weight=5.0,
            naive_dice=True,
            reduction='mean',
            type='mmdet.DiceLoss',
            use_sigmoid=True),
        loss_mask=dict(
            loss_weight=5.0,
            reduction='mean',
            type='mmdet.CrossEntropyLoss',
            use_sigmoid=True),
        num_classes=2,
        num_queries=100,
        num_transformer_feat_level=3,
        out_channels=256,
        pixel_decoder=dict(
            act_cfg=dict(type='ReLU'),
            encoder=dict(
                init_cfg=None,
                layer_cfg=dict(
                    ffn_cfg=dict(
                        act_cfg=dict(inplace=True, type='ReLU'),
                        embed_dims=256,
                        feedforward_channels=1024,
                        ffn_drop=0.0,
                        num_fcs=2),
                    self_attn_cfg=dict(
                        batch_first=True,
                        dropout=0.0,
                        embed_dims=256,
                        im2col_step=64,
                        init_cfg=None,
                        norm_cfg=None,
                        num_heads=8,
                        num_levels=3,
                        num_points=4)),
                num_layers=6),
            init_cfg=None,
            norm_cfg=dict(num_groups=32, type='GN'),
            num_outs=3,
            positional_encoding=dict(normalize=True, num_feats=128),
            type='mmdet.MSDeformAttnPixelDecoder'),
        positional_encoding=dict(normalize=True, num_feats=128),
        strides=[
            4,
            8,
            16,
            32,
        ],
        train_cfg=dict(
            assigner=dict(
                match_costs=[
                    dict(type='mmdet.ClassificationCost', weight=2.0),
                    dict(
                        type='mmdet.CrossEntropyLossCost',
                        use_sigmoid=True,
                        weight=5.0),
                    dict(
                        eps=1.0,
                        pred_act=True,
                        type='mmdet.DiceCost',
                        weight=5.0),
                ],
                type='mmdet.HungarianAssigner'),
            importance_sample_ratio=0.75,
            num_points=12544,
            oversample_ratio=3.0,
            sampler=dict(type='mmdet.MaskPseudoSampler')),
        transformer_decoder=dict(
            init_cfg=None,
            layer_cfg=dict(
                cross_attn_cfg=dict(
                    attn_drop=0.0,
                    batch_first=True,
                    dropout_layer=None,
                    embed_dims=256,
                    num_heads=8,
                    proj_drop=0.0),
                ffn_cfg=dict(
                    act_cfg=dict(inplace=True, type='ReLU'),
                    add_identity=True,
                    dropout_layer=None,
                    embed_dims=256,
                    feedforward_channels=2048,
                    ffn_drop=0.0,
                    num_fcs=2),
                self_attn_cfg=dict(
                    attn_drop=0.0,
                    batch_first=True,
                    dropout_layer=None,
                    embed_dims=256,
                    num_heads=8,
                    proj_drop=0.0)),
            num_layers=9,
            return_intermediate=True),
        type='Mask2FormerHead'),
    test_cfg=dict(mode='whole'),
    train_cfg=dict(),
    type='EncoderDecoder')