thuml/CDAN

Learning rate setting

zyc573823770 opened this issue · 1 comments

zyc573823770 commented

classifier's learning rate set to 10 times than feature extractor according to paper, but It is setting the same in code, is that on purpose after many experiments or just an error?

zyc573823770 commented 
optimizer = optim.SGD(model.parameters(), lr=args.lr, weight_decay=0.0005, momentum=0.9)
optimizer_ad = optim.SGD(ad_net.parameters(), lr=args.lr, weight_decay=0.0005, momentum=0.9)