Skip to content

Conversation

@chriselion
Copy link
Contributor

@chriselion chriselion commented Jun 4, 2020

Proposed change(s)

Recent versions of barracuda don't properly read the constants from the onnx file, so the onnx files unusable for inference.

This changes the onnx export to put them in the "outputs" for the model, so we can be sure they're preserved in export and read in barracuda.

I'm working on yamato tests in parallel for this, but wanted to get the fix in now.

Useful links (Github issues, JIRA tickets, ML-Agents forum threads etc.)

Types of change(s)

  • Bug fix
  • New feature
  • Code refactor
  • Breaking change
  • Documentation update
  • Other (please describe)

Checklist

  • Added tests that prove my fix is effective or that my feature works
  • Updated the changelog (if applicable)
  • Updated the documentation (if applicable)
  • Updated the migration guide (if applicable)

Other comments

@chriselion chriselion requested a review from ervteng June 4, 2020 22:48
@chriselion chriselion changed the title export model constants as outputs, instead of in the initializer list onnx: export model constants as outputs, instead of in the initializer list Jun 4, 2020
Copy link
Contributor

@ervteng ervteng left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

:shipit:

@chriselion chriselion merged commit b9aa094 into master Jun 4, 2020
@delete-merged-branch delete-merged-branch bot deleted the onnx-constants-as-output branch June 4, 2020 23:34
@github-actions github-actions bot locked as resolved and limited conversation to collaborators Jun 5, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants