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.

Sign up for GitHub

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

Jump to bottom

Interpolation of positional embeddings when fine-tuning (320x320) when the model is pre-trained on 512x512. #363

Open

AdharshC7777 opened this issue Jul 18, 2024 · 1 comment

AdharshC7777 commented Jul 18, 2024

just as the title says, do we need interpolation of positional embeddings in the scenerio. If yes, why?

sebbelese commented Oct 7, 2024 •

edited

Loading

I would say you need interpolation since your image has not the same resolution as the trained model (higher or lower).

Some details here:
https://discuss.huggingface.co/t/fine-tuning-image-transformer-on-higher-resolution/22623/6

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment