Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can onnxmltool add support for shape override in onnxmltools.convert_tensorflow? #495

Closed
ancienticybeing opened this issue Sep 9, 2021 · 6 comments · Fixed by #497
Closed

Comments

@ancienticybeing
Copy link

ancienticybeing commented Sep 9, 2021

Some Tensorflow models require specifying shape overrides in input names in order to be converted, would like to have onnxmltools support that.

@ancienticybeing ancienticybeing changed the title Can onnxmltool add support for shape override in tfonnx.process_tf_graph? Can onnxmltool add support for shape override in onnxmltools.convert_tensorflow? Sep 9, 2021
@ancienticybeing
Copy link
Author

Can you publish a release ?

@xadupre
Copy link
Collaborator

xadupre commented Sep 15, 2021

I'll do that this week or the next one. I'd like to merge #496 first.

@ancienticybeing
Copy link
Author

I'll do that this week or the next one. I'd like to merge #496 first.

Just checking again to see any possibility to publish a new release this week? Thanks!

@xadupre
Copy link
Collaborator

xadupre commented Oct 4, 2021

Sorry for being late. onnxruntime 1.9.0 was released last week so I wanted to make sure onnxmltools support opset 15 before doing another release. It should be done by tomorrow.

@ancienticybeing
Copy link
Author

Just checking again to see if we can have the new release out this week? thanks!

@xadupre
Copy link
Collaborator

xadupre commented Oct 22, 2021

I'm really sorry for the delay. I just released 1.10.0 on pypi.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants