pytorch / pytorch/vision

Move image loading logic to _load_image in VOC datasets (similar to COCO)

Open
#4,975 3 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

🚀 The feature

This would allow simple stubbing out image loading if needed for fast dataset transformed metadata access (when image reading is not needed) by dataset._load_image = lambda _: None and also make API more consistent across datasets.

It's also impossible to monkey-patch __getitem__ at instance level: https://stackoverflow.com/questions/57413453/is-it-possible-to-override-getitem-at-instance-level-in-python :(

Motivation, pitch

N/A

Alternatives

No response

Additional context

No response

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 comparing image-loading behavior in the VOC dataset classes with the existing COCO _load_image API, then inspect how getitem currently reads images. Done means VOC datasets expose a callable _load_image that can be replaced with a stub while preserving normal dataset behavior and API consistency.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.