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

501 add vision transformer model #542

Merged
merged 21 commits into from
Sep 18, 2023

Conversation

valhassan
Copy link
Collaborator

Thank you for submitting your PR and helping us with GDL.
Please read the template below, fill it out as appropriate, and make additional changes to your code as needed.
Please feel free to submit your PR even if it doesn't satisfy all of the requirements below.
If you need assistance or review from a maintainer, add the label Status: Help Needed or Status: Review Needed respectively.
After review, a maintainer will add the label Status: Revision Needed if further work is required for the PR to be merged.

Description

This PR adds a vision transformer (Segformer) model architecture. it completes feature #501

Type of change

What types of changes does your code introduce? Put an x in all the boxes that apply:

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Other

How Has This Been Tested?

Unit tests updated

Screenshots (if applicable):

Checklist:

If you're unsure about any of these, don't hesitate to ask. We're here to help!

  • My code follows the code style of this project
  • I have performed a self-review of my own code
  • My PR has a descriptive title
  • My code follows PEP8 (most of it)
  • My code have the proper documentation in the code
  • I have made corresponding changes to the documentation (if applicable)
  • My changes generate no new errors
  • My code is covered by the existing tests (if applicable)
  • My code includes tests that show that my feature works
  • My PR passes Travis CI tests

If your PR does not fulfill all of the requirements in the checklist above, that's OK! If you need help, @-mention a maintainer and/or add the Status: Help Needed label.

@valhassan valhassan linked an issue Sep 15, 2023 that may be closed by this pull request
@@ -95,7 +95,6 @@ def test_stac_input(self):
aoi = AOI(
raster=row['tif'], label=row['gpkg'], split=row['split'],
raster_bands_request=bands)
assert aoi.raster_bands_request == bands
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why remove it ?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good catch, I removed it for testing before pulling recent changes in 'develop'. I would revert back

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we create a new test for a 3 bands model and keep this one a test for a 4 bands model?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, we can, but I think all models in GDL should work with at least 3 bands regardless of configuration. So can we keep the 3 band tests for validating all models in GDL

mpelchat04
mpelchat04 previously approved these changes Sep 18, 2023
CharlesAuthier
CharlesAuthier previously approved these changes Sep 18, 2023
@valhassan valhassan merged commit 8f7df04 into NRCan:develop Sep 18, 2023
1 check passed
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.

Add Vision Transformer Model
3 participants