_base_ = [
    '../_base_/models/setr_mla.py', '../_base_/datasets/cityscapes_768x768.py',
    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
]
crop_size = (768, 768)
data_preprocessor = dict(size=crop_size)
model = dict(
    data_preprocessor=data_preprocessor,
    pretrained=None,
    backbone=dict(
        drop_rate=0,
        init_cfg=dict(
            type='Pretrained', checkpoint='pretrain/vit_large_p16.pth')),
    test_cfg=dict(mode='slide', crop_size=(768, 768), stride=(512, 512)))

optimizer = dict(lr=0.002, weight_decay=0.0)
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=optimizer,
    paramwise_cfg=dict(custom_keys={'head': dict(lr_mult=10.)}))
train_dataloader = dict(batch_size=1)
val_dataloader = dict(batch_size=1)
test_dataloader = val_dataloader