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

Registering operator for tf.linalg.eig #2326

Open
frytoli opened this issue Apr 19, 2024 · 0 comments
Open

Registering operator for tf.linalg.eig #2326

frytoli opened this issue Apr 19, 2024 · 0 comments
Labels
unsupported ops Issues related to unsupported operators

Comments

@frytoli
Copy link

frytoli commented Apr 19, 2024

Eig

tf.linalg.eig

Describe the operator

Computes the eigen decomposition of a batch of matrices. Very similar to numpy.linalg.eig.

Do you know if this operator be constructed using existing ONNX operators?

I do not believe it can be.

Is this operator used by any model currently? Which one?

N/A

Are you willing to contribute it? (Y/N)

Y

Notes

It looks like MatrixInverse (tf.linalg.inv) has been implemented in Microsoft's extra opset (as discussed in #1617 ). I don't think Eig would be much different of an implementation, but I haven't been able to figure out how MatrixInverse has been mapped (I've seen tf2onnx_custom_ops_tutorial.ipynb and still don't quite get it.). Could you provide any more specific guidance for this op?

@frytoli frytoli added the unsupported ops Issues related to unsupported operators label Apr 19, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
unsupported ops Issues related to unsupported operators
Projects
None yet
Development

No branches or pull requests

1 participant