pytorch / pytorch/vision

Imagenet Version not documented?

Open
#6,011 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

📚 The doc issue

Hello torchvision team,

First, thanks for the epic work you are all putting into this tool! I would like to know the exact version of imagenet used at pertaining different models in torchvision, for research purposes regarding model inversion. All of them use the 2012 Imagenet Dataset version or maybe some newer version?

Thank you,
Tudor

Suggest a potential alternative/fix

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

Review the torchvision model documentation and existing references to ImageNet-trained models. Determine the ImageNet dataset version used for each applicable model, then document those versions clearly so researchers can identify the training data.

Written by the indexing model from the issue text.

Assessment

Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.