Hidden linear layer between the convolutions and the classifier #453
Unanswered
raquelhortab
asked this question in
Q&A
Replies: 1 comment
-
(and, does anyone know if the library can do that or should I write it myself?) |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
If I've got a hidden linear layer between the convolutions and the classifier, wouldn't I get more interesting CAMs if the gradients from said layer were used as well?
Beta Was this translation helpful? Give feedback.
All reactions