pytorch / pytorch/vision

[docs] torchvision.ops.roi_pool doesn't mention dtype of boxes tensor

Open
#4,816 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

🐛 Describe the bug

Is it integer, some specific integer type or float32? Again, this is related to bbox formats / coordinate frames

Same problem for roi_align

Versions

N/A

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the documentation entry points for torchvision.ops.roi_pool and roi_align. Document the expected dtype of their boxes tensors, including any relevant coordinate-format details, and confirm that both operator descriptions answer the issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, documentation
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.