search

DeLightCMU / CASD

85 stars 21 forks source link

why self.ca_iw always be False in the code? #13

Open UcanSee opened 3 years ago

UcanSee commented 3 years ago

https://github.com/DeLightCMU/CASD/blob/d95a16ad1dc64fdbcd5333405b5825aaaaea156b/lib/nets/network.py#L218

Here self.ca_iw set to be False, and I can not see any codes setting it to be True, does it mean the consistence loss is always zero during training? Am I got something wrong or the code is not complete?

Justinhzy commented 3 years ago

Hi, In line216, you can find that self.ca_iw is false at the first several epochs, then it is set to true. I will complete the paralleled code soon.