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

Fix tuple error, mentioned in some of the issues #289

Open
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

ankuPRK
Copy link
Contributor

@ankuPRK ankuPRK commented Jan 8, 2024

Summary

  • We see some GitHub issues when some folks were trying to use the refinement step for non-fourier models. So we add a fix for that.
  • (minor) We also correct a typo in the website link to Geomagical.com

Issues

#274
#167

Problem

In the lama-regular model, the latent feature is a single Tensor, while in lama-fourier and big-lama, the latent feature is a tuple of two tensors. In our refinement code, we assumed the feature to be a tuple.

Solution

This PR adds a function that adapts the feature appropriately. We can't just keep it as-it-is because when Pytorch optimizers (like Adam) don't take a tuple as input.

Visual Results

  • Input Images
    image
    image

  • Big LaMa (before and after refinement)
    image
    image
    image
    image

  • LaMa-Fourier (before and after refinement, of course, parameters tuned to this model could make results even better)
    image
    image
    image
    image

  • LaMa-Regular (the one on which refinement was failing)
    image
    image
    image
    image

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

Successfully merging this pull request may close these issues.

1 participant