pytorch / pytorch/vision

`split` argument of `ImageNet()` should also accept `"test"` in addition to `"train"` and `"val"`.

Open
#8,770 1 comment 1 reaction 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

image-net.org says that the dataset of it also has 100,000 test images in addition to 1,281,167 training images and 50,000 validation images, then it's available in Kaggle as shown below:

The most highly-used subset of ImageNet is the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012-2017 image classification and localization dataset. This dataset spans 1000 object classes and contains 1,281,167 training images, 50,000 validation images and 100,000 test images. This subset is available on Kaggle.

Then, it actually has 100,000 test images in addition to 1,281,167 training images and 50,000 validation images as shown below:

Screenshot 2024-12-01 103021

Motivation, pitch

So, split argument of ImageNet() should also accept "test" in addition to "train" and "val".

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 locating the ImageNet() dataset entry point and the existing validation for the train and val split values. Check the related dataset tests, then update coverage so split="test" is accepted and the completed behavior is verified for the 100,000-image test split.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.