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

[QST] running sklearn model using cuml? #4869

Closed
saurabhr opened this issue Aug 20, 2022 · 1 comment
Closed

[QST] running sklearn model using cuml? #4869

saurabhr opened this issue Aug 20, 2022 · 1 comment
Labels
? - Needs Triage Need team to review and classify cuml-cpu question Further information is requested

Comments

@saurabhr
Copy link

saurabhr commented Aug 20, 2022

Hi,

I have multiple sklearn trained models saved using joblib and their sizes are 5gb on average. I want to test samples using these models. Can I load these saved models using cuml?

@saurabhr saurabhr added ? - Needs Triage Need team to review and classify question Further information is requested labels Aug 20, 2022
@viclafargue
Copy link
Contributor

viclafargue commented Aug 22, 2022

Hello, it is unfortunately not currently possible to do so. However, we are working on offering some CPU/GPU interoperability features in the near future. In the meantime, depending on the models you would like to run, there could be a way to turn the said model into a cuML one manually. To do so, you can refer to this issue that was about turning a cuML model into an sklearn one : #3626. For some of the models the conversion can be done in reverse in a similar fashion.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
? - Needs Triage Need team to review and classify cuml-cpu question Further information is requested
Projects
None yet
Development

No branches or pull requests

4 participants