请问怎么将model zoo内模型导出为onnx/导出为onnx报错怎么解决。

[timeuser4]

当我使用以下代码导出时报错：
`import torchreid
from torch.autograd import Variable
import torch
import onnx

input_name = ['input']
output_name = ['output']
model = torch.load('osnet_x1_0_msmt17_256x128_amsgrad_ep150_stp60_lr0.0015_b64_fb10_softmax_labelsmooth_flip.pth')
model.eval()
input = Variable(torch.randn(1, 3, 256, 128))
torch.onnx.export(model, input, 'osnet_ain_x1_0.onnx', input_names=input_name,output_names=output_name, verbose=True, export_params=True)

错误信息为：C:\Users\28455\AppData\Roaming\Python\Python310\site-packages\torchreid\reid\metrics\rank.py:11: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.
warnings.warn(
Traceback (most recent call last):
File "C:\Users\28455\gitclone\yolov5\pth2onnx.py", line 12, in
model.eval()
AttributeError: 'collections.OrderedDict' object has no attribute 'eval'`
请问这是为什么

[timeuser4]

如有回答，不胜感激