Skip to content

Update docs to mention rotated boxes and keypoints #9113

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

NicolasHug
Copy link
Member

No description provided.

Copy link

pytorch-bot bot commented Jun 23, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/vision/9113

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

❌ 1 New Failure, 1 Unrelated Failure

As of commit 4715de9 with merge base 342eb92 (image):

NEW FAILURE - The following job has failed:

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

@AntoineSimoulin AntoineSimoulin left a comment

Choose a reason for hiding this comment

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

Looking good. I just left some clarifying comments and questions!

video classification, etc. See
- They can transform images **but also** bounding boxes, masks, videos and
keypoints. This provides support for tasks beyond image classification:
detection, segmentation, video classification, etc. See
Copy link
Member

Choose a reason for hiding this comment

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

Maybe add "pose estimation"?

# boxes, segmentation / detection masks, or videos.
# The Torchvision transforms in the ``torchvision.transforms.v2`` namespace
# support tasks beyond image classification: they can also transform rotated or
# aligned bounding boxes, segmentation / detection masks, videos, and keypoints.
Copy link
Member

Choose a reason for hiding this comment

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

Maybe "axis-aligned"?


- Images as pure tensors, :class:`~torchvision.tv_tensors.Image` or PIL image
- Videos as :class:`~torchvision.tv_tensors.Video`
- Aligned and rotated bounding boxes as :class:`~torchvision.tv_tensors.BoundingBoxes`
Copy link
Member

Choose a reason for hiding this comment

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

Maybe "Axis-aligned" to be a bit more specific?

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