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
Thanks for your code and I lean a lot from it. However, when I read your code, I do get a question:
In the paper, you stated "we visualize the gradients of the loss with respect to individual features
(pixels)" . But the gradient of a pixel should have 3 dimensions (since it is RGB), so how you visualize it? (get the average or max or ...?)
The text was updated successfully, but these errors were encountered:
Thanks for your code and I lean a lot from it. However, when I read your code, I do get a question:
In the paper, you stated "we visualize the gradients of the loss with respect to individual features
(pixels)" . But the gradient of a pixel should have 3 dimensions (since it is RGB), so how you visualize it? (get the average or max or ...?)
The text was updated successfully, but these errors were encountered: