test single报错

[thorory]

使用DAT_light_x2.pth 和 DAT_2_x2.pth模型

Traceback (most recent call last):
File "basicsr/test.py", line 44, in
test_pipeline(root_path)
File "basicsr/test.py", line 34, in test_pipeline
model = build_model(opt)
File "/root/dataDisk/DAT-main/basicsr/models/init.py", line 27, in build_model
model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/root/dataDisk/DAT-main/basicsr/models/sr_model.py", line 30, in init
self.load_network(self.net_g, load_path, self.opt['path'].get('strict_load_g', True), param_key)
File "/root/dataDisk/DAT-main/basicsr/models/base_model.py", line 303, in load_network
net.load_state_dict(load_net, strict=strict)
File "/root/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1223, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DAT:

size mismatch for conv_first.weight: copying a param with shape torch.Size([60, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([180, 3, 3, 3]).
size mismatch for conv_first.bias: copying a param with shape torch.Size([60]) from checkpoint, the shape in current model is torch.Size([180]).
size mismatch for before_RG.1.weight: copying a param with shape torch.Size([60]) from checkpoint, the shape in current model is torch.Size([180]).
size mismatch for before_RG.1.bias: copying a param with shape torch.Size([60]) from checkpoint, the shape in current model is torch.Size([180]).
size mismatch for layers.0.blocks.0.norm1.weight: copying a param with shape torch.Size([60]) from checkpoint, the shape in current model is torch.Size([180]).
size mismatch for layers.0.blocks.0.norm1.bias: copying a param with shape torch.Size([60]) from checkpoint, the shape in current model is torch.Size([180]).
size mismatch for layers.0.blocks.0.attn.qkv.weight: copying a param with shape torch.Size([180, 60]) from checkpoint, the shape in current model is torch.Size([540, 180]).
size mismatch for layers.0.blocks.0.attn.qkv.bias: copying a param with shape torch.Size([180]) from checkpoint, the shape in current model is torch.Size([540]).
size mismatch for layers.0.blocks.0.attn.proj.weight: copying a param with shape torch.Size([60, 60]) from checkpoint, the shape in current model is torch.Size([180, 180]).

[HuaqingHe]

I have the same issue while using DAT_S_x4.pth .
Change the # network structures network_g in test single.yml can solve it.