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.

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

Pad image with another mode than "constant" #22

Open
thibo73800 opened this issue Sep 7, 2021 · 0 comments · Fixed by #276 or #289
Open

Pad image with another mode than "constant" #22

thibo73800 opened this issue Sep 7, 2021 · 0 comments · Fixed by #276 or #289
Assignees
@tflahaul
Labels
aloscene aloscene discussion good first issue Good for newcomers quick-fix

Comments

@thibo73800
Copy link
Contributor

For the moment, we pad the image with a constant value.

Under the hood, SpatialAugmentedTensor._pad() calls torchvision.transforms.functional.pad, which accept a keyword "padding_mode". We could accept this keyword too and pass it.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@tflahaul tflahaul

Labels
aloscene aloscene discussion good first issue Good for newcomers quick-fix
Projects
None yet
Milestone
No milestone
2 participants
@thibo73800 @tflahaul