pytorch / pytorch/vision

[RFC] Add `expand` option to `affine` transformation

Open
#5,665 0 comments 4 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

module: transforms needs discussion prototype
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

We would like to ask for some feedback about adding expand argument to affine image/mask transformations.

Currently, rotate op has extend argument which does the following:

Do you think that it would be helpful to have expand option with affine image/mask transformations ?

Originally posted by @vfdev-5 in https://github.com/pytorch/vision/pull/5638#discussion_r833095644

cc @vfdev-5 @datumbox @bjuncek

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 with the linked torchvision rotate operation and the existing affine image and mask transformations. Determine how an expand option should behave and whether it should match rotate's current behavior. Done requires an agreed API and implementation scope, along with corresponding tests for expanded affine outputs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.