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

[ONNX] Support opset 17 operators #81075

Open
8 tasks
justinchuby opened this issue Jul 8, 2022 · 5 comments
Open
8 tasks

[ONNX] Support opset 17 operators #81075

justinchuby opened this issue Jul 8, 2022 · 5 comments
Assignees
Labels
good first issue module: onnx onnx-triaged OSS contribution wanted triaged

Comments

@justinchuby
Copy link
Collaborator

@justinchuby justinchuby commented Jul 8, 2022

Tracking issue on the onnx opset 17 support.

  • Add version 17 as a known version
  • stft
  • istft
  • bartlett_window
  • blackman_window
  • hamming_window
  • hann_window
  • kaiser_window

Closes #80834

@cpuhrsch cpuhrsch added module: onnx triaged labels Jul 8, 2022
@AllenTiTaiWang AllenTiTaiWang added the onnx-triaged label Jul 11, 2022
@justinchuby justinchuby self-assigned this Jul 14, 2022
@iver56
Copy link

@iver56 iver56 commented Jul 22, 2022

Justin, you listed istft here, but I can't find istft in ONNX's list of operators. Is the idea to implement istft in terms of the available onnx operators?

Edit: This PR also lists ISTFT in its description, but there's no mention of ISTFT in the code changes. Now I'm confused. Does ONNX opset 17 support ISTFT or not?

@justinchuby
Copy link
Collaborator Author

@justinchuby justinchuby commented Jul 22, 2022

Hi @iver56, I can confirm that ISTFT is not in opset 17. However onnx is open to including it as a new op (please feel free to open an issue in the onnx/onnx repo if not already existed). We plan to support exporting istft from pytorch in spite of the missing ISTFI op.

@stonelazy
Copy link

@stonelazy stonelazy commented Jul 26, 2022

If I may add, even though ISTFT is not available, both forward and inverse operations for DFT are supported by ONNX. Reference This should help users implement ISTFT on their own.
Would it be possible to include support for FFT as well ?

@justinchuby
Copy link
Collaborator Author

@justinchuby justinchuby commented Jul 26, 2022

@stonelazy i think so. Do you have a list of related torch functions you think could be fitting?

@justinchuby justinchuby added good first issue OSS contribution wanted labels Jul 26, 2022
@stonelazy
Copy link

@stonelazy stonelazy commented Jul 27, 2022

@stonelazy i think so. Do you have a list of related torch functions you think could be fitting?

I hope am not wrong, below are the torch's equivalent in ONNX.
Torch's FFT's equivalent is ONNX's DFT
Torch's IFFT is same ONNX's DFT but with inverse option selected.
Torch's Melscale equivalent is ONNX's Melweight.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
good first issue module: onnx onnx-triaged OSS contribution wanted triaged
Projects
None yet
Development

No branches or pull requests

5 participants