onnx / onnx/models

Add "new" models to ONNX Model Hub tool

Open
#643 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

Add "new" models to ONNX Model Hub tool

What is the problem that this feature solves?

Automatization of downloading recently added models via onnx.hub python tool.

Describe the feature

Currently, the Hub can work only with legacy models according to https://github.com/onnx/models/blob/main/ONNX_HUB_MANIFEST.json. The legacy models are going to be removed, unlike ONNX Hub tool. At least I haven't seen any deprecation note

Relevant Model Zoo feature areas
  • ONNX_HUB_MANIFEST
  • ONNX Model Hub
Notes

As I understand a new manifest can be generated easily https://github.com/onnx/onnx/blob/main/docs/Hub.md#contributing-an-official-model

Contributor guide

No contributing guide indexed for this repository

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 ONNX_HUB_MANIFEST.json with the newer models and read the ONNX Hub contributing guidance in docs/Hub.md. Trace how the onnx.hub Python tool consumes the manifest, then define completion as successfully discovering and downloading recently added models rather than only legacy entries.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, tooling
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.