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

Continuation of Issue#352 #355

Closed
nabenabe0928 opened this issue Dec 6, 2021 · 1 comment
Closed

Continuation of Issue#352 #355

nabenabe0928 opened this issue Dec 6, 2021 · 1 comment

Comments

@nabenabe0928
Copy link
Contributor

nabenabe0928 commented Dec 6, 2021

The issue is the division between multiclass and continuous.
The quick solution is to filter continuous by checking whether labels cover the integer of [0, C).
However, it causes the following issues:

  1. numerical class labels of random integers are not allowed
  2. 1-indexed class labels are not allowed
  3. rank regression will be mis-recognized as multiclass

To address those issues, we need to enhance input_validator or preprocessing BEFORE instantiating dataset class.
At least, we know that the given task is either classification or regression, so we should use this knowledge.

@ravinkohli
Copy link
Contributor

It has been resolved with #386

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