norm_cfg = dict(type='SyncBN', requires_grad=True)
data_preprocessor = dict(
    type='SegDataPreProcessor',
    mean=[123.675, 116.28, 103.53],
    std=[58.395, 57.12, 57.375],
    bgr_to_rgb=True,
    pad_val=0,
    seg_pad_val=255)
model = dict(
    type='EncoderDecoder',
    data_preprocessor=data_preprocessor,
    pretrained=None,
    backbone=dict(
        type='BEiT',
        img_size=(640, 640),
        patch_size=16,
        in_channels=3,
        embed_dims=768,
        num_layers=12,
        num_heads=12,
        mlp_ratio=4,
        out_indices=(3, 5, 7, 11),
        qv_bias=True,
        attn_drop_rate=0.0,
        drop_path_rate=0.1,
        norm_cfg=dict(type='LN', eps=1e-6),
        act_cfg=dict(type='GELU'),
        norm_eval=False,
        init_values=0.1),
    neck=dict(type='Feature2Pyramid', embed_dim=768, rescales=[4, 2, 1, 0.5]),
    decode_head=dict(
        type='UPerHead',
        in_channels=[768, 768, 768, 768],
        in_index=[0, 1, 2, 3],
        pool_scales=(1, 2, 3, 6),
        channels=768,
        dropout_ratio=0.1,
        num_classes=150,
        norm_cfg=norm_cfg,
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    auxiliary_head=dict(
        type='FCNHead',
        in_channels=768,
        in_index=2,
        channels=256,
        num_convs=1,
        concat_input=False,
        dropout_ratio=0.1,
        num_classes=150,
        norm_cfg=norm_cfg,
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
    # model training and testing settings
    train_cfg=dict(),
    test_cfg=dict(mode='whole'))