Why does classification ViT have nn.Tanh() in the end? #4580
Unanswered
chris-clem
asked this question in
Q&A
Replies: 1 comment
-
thanks for reporting, I create a ticket to track this issue. #4581 |
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
Uh oh!
There was an error while loading. Please reload this page.
-
Hello together,
I was wondering why does the Vision Transformer (ViT) with
classification=True
havenn.Tanh()
in the end of theclassification_head
(https://github.com/Project-MONAI/MONAI/blob/dev/monai/networks/nets/vit.py#L100)? The other classification models output the raw logits.Best
Christoph
Beta Was this translation helpful? Give feedback.
All reactions