pytorch / pytorch/vision

Deterministic order of classes and images for the Omniglot dataset

Open
#8,677 1 comment 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

By sorting the output of the list_files() and list_dir() helper functions, the order of samples in the Omniglot dataset can be made deterministic across OSes.

Motivation, pitch

Right now, it is quite difficult to obtain reproducible accuracies across machine with the same few-shot learning setup when the Omniglot dataset is used.

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

Locate the Omniglot dataset implementation and search for the list_files() and list_dir() helpers. Check how their outputs determine class and image ordering, then verify that sorting them makes sample order reproducible across operating systems. Done means deterministic ordering is covered by the relevant dataset tests, if present.

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.