[Announce] Next generation of ONNX Model Zoo

Feature Request

What is the problem that this feature solves?

• All of existing ONNX Model Zoo models use opset_version<13, which is a quite old version (opset 12 released on May 8, 2020 in ONNX 1.7.0).
• Existing models are hard to reproduce with outdated script ​
• Same model usually has few versions​
• No sufficient state-of-art models in the past 2 years

Describe the feature

• Introduce new upload way with required reproduction files: https://github.com/onnx/models/pull/613
• Move existing models (< opset_version 13) to models/legacy: https://github.com/onnx/models/issues/616
• Add a few existing models from torch_hub or torchvision with opset_version 18 16: https://github.com/onnx/models/pull/614
• Add more state-of-the-art models with opset_version 18 16: https://github.com/onnx/models/pull/615
• Utilize benchmark tool (MLAgility) to verify uploaded models
• Keep single version of model and going forward ONNX Model Zoo will regularly bump opset_version
• New models directory hierarchy:
  • models/python: user-contribution-based models. There will be models along with reproduction script to ensure the models are reproducible.
  • models/mlagility: only contains models and test_data_set; reproduction script can be found at https://github.com/groq/mlagility/tree/main/models.
  • models/legacy: old models with opset_version < 13
• ONNX Hub will support download models from the three source above
• Web interface to view ONNX Model Zoo models
• Eventually we will remove models under legacy

Relevant Model Zoo feature areas

Which area in the Model Zoo infrastructure does this impact?
Feature Area (e.g. CI, file organization, model storage, other):
Model storage/CI

Notes

Currently this feature is working in progress and we are developing in the "new-models" branch first. Ultimately we will move this branch into the main branch.

If anyone has any question/concern, feel free to raise in this thread. Thank you for the contribution.

cc @abock @ramkrishna2910

Start by reading the new-models branch and the linked work in PRs 613–615 and issue 616. Review the proposed models/python, models/mlagility, and models/legacy hierarchy, then inspect how ONNX Hub and MLAgility are expected to use them. Done would require the broader migration, reproduction workflow, benchmarking, and upload organization described here.