pytorch / pytorch/vision

[RFC] Extend the scope of ImageFolder for segmentation data

Open
#424 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I am starting to work on segmentation problem.

ImageFolder is great but seems to be dedicated for classification.

Would it make sense to modify it such that we can load input/target which can be both list of images as in the case of CamVid dataset?
It is also true that segmentation can also be organized with a list of images and a list of annotations which does not fit the previous requirement.

So I was wondering what the core devs are thinking about it.

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 ImageFolder entry point and its documentation, then compare its classification assumptions with the CamVid input and annotation arrangement described here. The issue does not define an accepted API or implementation scope, so the work is not complete until maintainers agree on how image targets and annotation lists should be represented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
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.