-
Notifications
You must be signed in to change notification settings - Fork 41
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Wrong dimension for L2 normalization? #1
Comments
Good catch, thank you! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
When ReduceDim
mmt/model/model.py
Lines 715 to 725 in 0d848cd
is applied to video expert embeddings it do F.normalize on shape (batch_size, num_tokens, embedding_dim), and reduce by default along dim=1 (num_tokens)
mmt/model/model.py
Lines 431 to 434 in 0d848cd
But here it is applied to shape (batch_size, embedding_dim)
mmt/model/model.py
Lines 423 to 426 in 0d848cd
So normalization along embedding_dim axis.
Is it mistake or not?
The text was updated successfully, but these errors were encountered: