onnx: export model constants as outputs, instead of in the initializer list #4073
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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)
Checklist
Other comments