Skip to content
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

Multi-label classification #10

Closed
Baran-phys opened this issue Oct 15, 2020 · 3 comments
Closed

Multi-label classification #10

Baran-phys opened this issue Oct 15, 2020 · 3 comments

Comments

@Baran-phys
Copy link

How can one use this for multi-label classification?

@lucidrains
Copy link
Owner

lucidrains commented Oct 15, 2020

@Hosein47 yea of course! it's just a separate loss function, and independent of the model

for multi-label, you'll go with a binary cross entropy loss instead

@Baran-phys
Copy link
Author

Hmm, tnx. Which transformer method do you deem the best for multi-label classification? I mean Sinkhorn or routing or any other?

@lucidrains
Copy link
Owner

@Hosein47 They will all work for multi-label, since the difference is just in the loss function, not the architecture

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants