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

Why are we padding the corner images if they don't contribute to training? #203

Open
KristinaUlicna opened this issue Sep 4, 2023 · 0 comments
Assignees
Labels
help wanted Extra attention is needed question Further information is requested

Comments

@KristinaUlicna
Copy link
Collaborator

KristinaUlicna commented Sep 4, 2023

This line in the FeatureExtractor relabels the corner / boundary patches to Annotation.UNKNOWN:

node_attrs[GraphAttrs.NODE_GROUND_TRUTH] = Annotation.UNKNOWN

I'm not sure if this makes sense, as the UNKNOWN ground truth labels don't contribute to the training.
This will likely interfere with #200 when merged into main. Any ideas @chris-soelistyo ?

Kind of linked to #134

@KristinaUlicna KristinaUlicna added help wanted Extra attention is needed question Further information is requested labels Sep 4, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
help wanted Extra attention is needed question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants