How to do the inference of the pre-training stage (given some test distorted images, output the DDMs)?

[TK-KXS]

In pre_training/inference_docmae.py, there is an error at...

 34         x = x.permute(0,3,1,2)
 35         ddm = np.empty((256,256,1))
 --> 36         loss, y, mask = self.docmae(x)
 37 
 38         return x, loss, y, mask
 /usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
 1188         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
 1189                 or _global_forward_hooks or _global_forward_pre_hooks):
 ---> 1190             return forward_call(*input, **kwargs)
 1191         # Do not call functions when jit is used
 1192         full_backward_hooks, non_full_backward_hooks = [], []

 TypeError: forward() missing 1 required positional argument: 'ddm'

How to solve this?

[lzk9508]

sorry for long time no response to your issue. please try to run the test.py to get the ddm of an input picture with pre-trained model. inference_docmae.py is dicarded.