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

Huggingface's Tranformers implementation? #16

Closed
thedarkzeno opened this issue Oct 27, 2022 · 3 comments
Closed

Huggingface's Tranformers implementation? #16

thedarkzeno opened this issue Oct 27, 2022 · 3 comments

Comments

@thedarkzeno
Copy link

Is there an implementation that uses the clip model from the transformers lib? If not how hard would it be to implement?

@timojl
Copy link
Owner

timojl commented Oct 27, 2022

I'm not aware of any such implementation. What would be the advantage? I prefer using the CLIP code to Huggingface Transformers since the latter comes with several dependencies. However, implementing it should be straightforward by replacing the CLIP initialization here: https://github.com/timojl/clipseg/blob/master/models/clipseg.py#L86

@timojl timojl closed this as completed Oct 27, 2022
@NielsRogge
Copy link

Hi,

See #18

@thedarkzeno
Copy link
Author

thedarkzeno commented Nov 7, 2022

Hi,

See #18

@NielsRogge
Great, I had implemented a version that supported de HFs models, but it's good to see an official implementation.
Will there be a training script with the transformers framework?

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