# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
    type='EncoderDecoder',
    backbone=dict(
        type='UniFormer',
        embed_dim=[64, 128, 320, 512],
        layers=[3, 4, 8, 3],
        head_dim=64,
        mlp_ratio=4.,
        qkv_bias=True,
        drop_rate=0.,
        attn_drop_rate=0.,
        drop_path_rate=0.1),
    neck=dict(
        type='FPN',
        in_channels=[64, 128, 320, 512],
        out_channels=256,
        num_outs=4),
    decode_head=dict(
        type='FPNHead',
        in_channels=[256, 256, 256, 256],
        in_index=[0, 1, 2, 3],
        feature_strides=[4, 8, 16, 32],
        channels=128,
        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)),
    # model training and testing settings
    train_cfg=dict(),
    test_cfg=dict(mode='whole')
)