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

Added binary cat vs dog classification target type to Oxford pet dataset #8388

Merged
merged 5 commits into from
Apr 29, 2024

Conversation

matlabninja
Copy link
Contributor

@matlabninja matlabninja commented Apr 19, 2024

Added "binary-category" as a target type to the Oxford pet dataset. Uses the second numeric input in the annotation to get the species and outputs 0 for cat and 1 for dog. Discussed in #8364 . Notebook showing this in action can be found here

Copy link

pytorch-bot bot commented Apr 19, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/vision/8388

Note: Links to docs will display an error until the docs builds have been completed.

❌ 17 New Failures, 20 Unrelated Failures

As of commit 10c2015 with merge base ff31b6e (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

Copy link
Member

@NicolasHug NicolasHug left a comment

Choose a reason for hiding this comment

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

Thanks for the PR @matlabninja , this LGTM. There seem to be one minor lint issue (see below). I wasn't able to push the changes directly as the PR was created from your main branch on your fork.

lint issue should be fixed. Tests are passing locally, let's wait for the CI and I'll merge the PR

torchvision/datasets/oxford_iiit_pet.py Outdated Show resolved Hide resolved
@NicolasHug NicolasHug marked this pull request as ready for review April 29, 2024 13:03
@NicolasHug NicolasHug merged commit 06ad737 into pytorch:main Apr 29, 2024
7 of 18 checks passed
@matlabninja
Copy link
Contributor Author

Thanks for closing @NicolasHug!

facebook-github-bot pushed a commit that referenced this pull request May 8, 2024
… pet dataset (#8388)

Reviewed By: vmoens

Differential Revision: D57099465

fbshipit-source-id: 4bd587ee4ac6fea210ea412a1a6c7c1b81e6ea36

Co-authored-by: Nicolas Hug <nh.nicolas.hug@gmail.com>
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants