JavaOne keynote and ONNX

[Paul Sandoz]

Hi,

We demoed the use of the FFM API and code reflection at the Java One keynote, showing a way to translate Java code to ONNX models and execute in the ONNX runtime.

Here’s the link to the start of the keynote:

  https://www.youtube.com/live/mk_2MIWxLI0

Here’s the point in the keynote that starts with FFM API and then proceeds with the ONNX demo:

  https://youtu.be/mk_2MIWxLI0?t=4027

The demo model code is here:

  https://github.com/openjdk/babylon/blob/code-reflection/cr-examples/onnx/src/test/java/oracle/code/onnx/mnist/MNISTModel.java

We are currently working to towards supporting the translation of if/for statements, and will hopefully add some more comprehensive models. We may even explore training if we can perhaps leverage ops in the domain ai.onnx.preview.training and/or other stuff in the ONNX runtime. Implementing reverse mode auto-diff on ONNX models would be a difficult task, but also fascinating one.

Paul.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.openjdk.org/pipermail/babylon-dev/attachments/20250328/6e05d083/attachment.htm>