pytorch / pytorch/vision

COCO dataset to also return image_id

Open
#3,608 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

So that copies like https://github.com/facebookresearch/detr/blob/master/datasets/coco.py are not needed

In general, I found it useful to return original datum ids, in case the user wants to load some extra information (regardless of COCO). Part of the problem is the Tuple return type which means any changes are not BC.

Maybe return_dict constructor arg could be introduced which would be more extensible, just like DETR did

cc @pmeier

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 the proposed API with the linked DETR implementation in datasets/coco.py, then locate the corresponding COCO dataset entry point in this repository. Determine whether image_id should be returned directly or through a return_dict option, and define how existing tuple-returning callers remain compatible; done means the chosen API is documented and covered by tests.

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
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.