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

when there will be next release? #53

Open
Borda opened this issue Aug 4, 2023 · 3 comments
Open

when there will be next release? #53

Borda opened this issue Aug 4, 2023 · 3 comments

Comments

@Borda
Copy link

Borda commented Aug 4, 2023

Hello, we have implemented a metric based on the latest version of this package but PyPPI has the last 0.3.0 and PyPI does not allow any dependency outside their registry so when we refer master no user could use it... Would it be possible to make a release any time soon? Thank you

cc: @SkafteNicki

@toshas
Copy link
Owner

toshas commented Aug 8, 2023

Hi, thanks for your interest in the toolkit.

I'm confused why PPL is inaccessible in 0.3.0; I can see it inside the wheel: https://files.pythonhosted.org/packages/dd/72/687a54bab9a11e351cff3859ece48fb58e13786a493eb13a5da32b42de32/torch_fidelity-0.3.0.tar.gz under torch_fidelity/metric_ppl.py.

I just had a chance to follow the torchmetrics PR comments (Lightning-AI/torchmetrics#1939 (comment)). In any case, the release of 0.4.0 is not blocking your work?

In any case, 0.4.0 will be coming soon-ish, with more metrics, some of which aren't in master yet. Stay tuned!

@Borda
Copy link
Author

Borda commented Aug 8, 2023

In any case, the release of 0.4.0 is not blocking your work?

we have just figured out a way of using the latest release only, but it still would be nice to have a release out after so many years :)
on the PyPI issue https://discuss.python.org/t/packages-installed-from-pypi-cannot-depend-on-packages-which-are-not-also-hosted-on-pypi/3736

@guyleaf
Copy link

guyleaf commented Oct 11, 2024

Hi, will the 0.4.0 be released soon?
I see you adding the DINOv2 extractor.
Compared with the official implementation dgm-eval, I think yours will be more reliable due to having the unit test.

I'd also like to know the error between the official and yours.

Thanks.

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

3 participants