-
-
Notifications
You must be signed in to change notification settings - Fork 130
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-Target Classification #430
Comments
@YonyBresler This has been something the community has requested for in the past as well and would be an awesome addition. I can assure you that your contribution would be most welcomed. I can work with you for the PR. |
Thanks for your feedback @manujosephv , I finished a first pass at this, and have a PR in #441 , happy to hear your (or any other community member) feedback |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is your feature request related to a problem? Please describe.
Currently, regression allows for multi-target training, while classification only supports a single target.
Describe the solution you'd like
Add support for multi-target classification, including data handling, output layer size shaping, and appropriate loss.
Describe alternatives you've considered
You currently need to train multiple models, which is both slower and may not get the same performance as learning a common embedding
Additional context
I'm prepared to contribute this feature myself, but wanted to check:
The text was updated successfully, but these errors were encountered: