_base_ = [

    '../_base_/models/upernet_cswin.py', '../_base_/datasets/ade20k.py',

    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'

]

model = dict(

    backbone=dict(

        type='CSWin',

        embed_dim=96,

        depth=[2,4,32,2],

        num_heads=[4,8,16,32],

        split_size=[1,2,7,7],

        drop_path_rate=0.6,

        use_chk=False,

    ),

    decode_head=dict(

        in_channels=[96,192,384,768],

        num_classes=150

    ),

    auxiliary_head=dict(

        in_channels=384,

        num_classes=150

    ))

# AdamW optimizer, no weight decay for position embedding & layer norm in backbone

optimizer = dict(_delete_=True, type='AdamW', lr=0.00006, betas=(0.9, 0.999), weight_decay=0.01,

                 paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.),

                                                 'relative_position_bias_table': dict(decay_mult=0.),

                                                 'norm': dict(decay_mult=0.)}))

lr_config = dict(_delete_=True, policy='poly',

                 warmup='linear',

                 warmup_iters=1500,

                 warmup_ratio=1e-6,

                 power=1.0, min_lr=0.0, by_epoch=False)

data=dict(samples_per_gpu=2)