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

BatchToSpaceND: support 3d inputs #572

Closed
vadimkantorov opened this issue Jun 5, 2019 · 2 comments
Closed

BatchToSpaceND: support 3d inputs #572

vadimkantorov opened this issue Jun 5, 2019 · 2 comments
Labels
enhancement New feature or request

Comments

@vadimkantorov
Copy link

vadimkantorov commented Jun 5, 2019

I'm trying to convert the OpenSeq2Seq's wav2letter model checkpoints from TensorFlow to ONNX.

It contains BatchToSpaceND ops. Inputs are however a 3d tensor. Currently tfonnx supports NHWC.

Proposal: if the input is 3d, insert automatically an Unsqueeze op or a rewriter in order to reshape to NH1C and then back to NHC.

@lucienwang1009 lucienwang1009 added the enhancement New feature or request label Jun 6, 2019
@vadimkantorov
Copy link
Author

vadimkantorov commented Jun 8, 2019

BatchToSpaceND is used by TensorFlow to implement dilated convolutions (and this is the case for wav2letter model). So theoretically tfonnx could fold them.

@vadimkantorov
Copy link
Author

fixed in #598 ?

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

No branches or pull requests

2 participants