Let's enable ND support for images/masks
Open
Nobody has claimed this yet.
module: transforms
prototype
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
Originally posted by @vfdev-5 in https://github.com/pytorch/vision/pull/5613#discussion_r828077791
cc @vfdev-5 @datumbox @bjuncek
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the original discussion in pull request 5613, which is the only implementation context named in the issue. Identify the image and mask handling involved and define done as consistent support for N-dimensional inputs, with coverage for the affected cases; no specific files or tests are named.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100