Logits or softmax probabilities about confusion HOT 3 CLOSED

Hi Yan,

For both models of confusion, the preferred usage is softmax probabilities (obtained after feeding the logits through a softmax). You can, alternatively, try the logits for pairwise confusion, but the loss weight will have to be scaled to a very small value to prevent oscillations, and hence we recommend operating on the softmax probabilities themselves.

Abhi

from confusion.

Thank you!

from confusion.

@abhimanyudubey

In the Entropy confusion (https://github.com/abhimanyudubey/confusion/blob/master/confusion_pytorch/__init__.py#L15), it seems that you missed a negative sign according to the paper. isn't this a loss function?

from confusion.