You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Gradient penalty claculation should change when D has an auxiliary classifier or the gradient penalty should only be calculated over the real/fake output? Is there any intuition behind of whatever is the best solution?
Thanks!
The text was updated successfully, but these errors were encountered:
dougsouza
changed the title
Gradient Penalty with Auxiary classifier
Gradient Penalty with Auxiliary classifier
Feb 14, 2019
@Johnson-yue, yes. I tried gradient penalty only in the real/fake output of the network. But I didn't pursue much, I went back to spectral normalization.
Gradient penalty claculation should change when D has an auxiliary classifier or the gradient penalty should only be calculated over the real/fake output? Is there any intuition behind of whatever is the best solution?
Thanks!
The text was updated successfully, but these errors were encountered: