search

corenel / pytorch-adda

A PyTorch implementation for Adversarial Discriminative Domain Adaptation
MIT License
474 stars 139 forks source link

Criterion problem #11

Open chihhuiho opened 6 years ago

chihhuiho commented 6 years ago

Thanks for sharing the code. I have a question about the line 25 in adapt.py (criterion = nn.CrossEntropyLoss() ). Since nn.LogSoftmax() is added in discriminator.py (line 21). Is it correct to use CrossEntropyLoss as criterion ? Or maybe I miss something? Thanks in advance.

jinfengr commented 6 years ago

The same question here, I also tried NLLLoss()

TuGang-Git commented 2 years ago

The same question here, I also tried NLLLoss()

How was the result?