Jump to content

Onnx

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by Tom.Reding (talk | contribs) at 02:07, 12 October 2018 (WP:GenFixes on, 3+ incoming mainspace links, removed orphan tag). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Open Neural Network Exchange (ONNX) is a format for deep learning models that allows interoperability between different open source AI frameworks. ONNX is being co-developed by Microsoft, Amazon and Facebook as an open-source project.[1][2][3] In its initial release the project will support Caffe2, PyTorch, MXNet and Microsoft CNTK Deep learning framework.

References

  1. ^ onnx: Open Neural Network Exchange, onnx, 2017-09-11, retrieved 2017-09-11
  2. ^ "Microsoft, Facebook Partner on AI Framework Interoperability". {{cite news}}: Cite has empty unknown parameter: |dead-url= (help)
  3. ^ "Model Server for Apache MXNet introduces ONNX support and Amazon CloudWatch integration". Retrieved 8 February 2018.