biaozhou

No。I don't solve it。

I think you can find another version of the paper. Maybe it receives good results.

I also meet > when i run 'main.py', i got following error. > > `Traceback (most recent call last): > > File "Domain_Adaption/pytorch-adda/main.py", line 41, in > src_encoder, src_classifier, src_data_loader)...

> Seems like same as #20 but with more details. Also, i'm facing the same error. you can use this solution。https://stackoverflow.com/questions/56033173/kmnist-runtimeerror-output-with-shape-1-28-28-doesnt-match-the-broadcast

you can see this。https://blog.csdn.net/weixin_43159148/article/details/88778371。but I also meet other problem

why the loss don't include critic loss?The paper final loss =classifier loss + wasserstain loss +gradient penalty loss.