search

hanzhaoml / MDAN

Demo code for the MDAN paper.
117 stars 19 forks source link

Parenthesis for max should include min term #1

Closed redone17 closed 5 years ago

redone17 commented 5 years ago

https://github.com/KeiraZhao/MDAN/blob/4eaec5b0d49a3af446b3b52850f646dfed507a14/main_amazon.py#L143

Would it rather be:

loss = torch.max(losses + mu * torch.min(domain_losses))

to correspond with Eq(5) of https://papers.nips.cc/paper/8075-adversarial-multiple-source-domain-adaptation.pdf?