Fix tuple error, mentioned in some of the issues #289
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
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
Big LaMa (before and after refinement)
LaMa-Fourier (before and after refinement, of course, parameters tuned to this model could make results even better)
LaMa-Regular (the one on which refinement was failing)
