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
Hi, thanks for sharing your code. For the function F.kl_div(), the first parameter is input and the second is target. I am confused why the target is not p_mixture on L401-L403?
Thanks.
The text was updated successfully, but these errors were encountered:
Hi @yakexee, I think F.kl_div() defines inputs and targets in the way how NLL loss is used. Since NLL(input, target) = cross_entropy(target, input). I believe F.kl_div(input, target) = KL(target || input). You can check this with an easy example by comparing the results with a KL div function implemented by yourself. Since we are computing KL(p_aug || p_mixture), we called F.kl_div(p_mixture, p_aug). FYI, this loss is adapted from the Augmix's implementation. I hope it helps
Hi, thanks for sharing your code. For the function F.kl_div(), the first parameter is input and the second is target. I am confused why the target is not p_mixture on L401-L403?
Thanks.
The text was updated successfully, but these errors were encountered: