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 #2

Open
arition opened this issue Oct 3, 2020 · 0 comments
Open

ONNX support #2

arition opened this issue Oct 3, 2020 · 0 comments
Labels
enhancement New feature or request

Comments

@arition
Copy link
Member

arition commented Oct 3, 2020

The Open Neural Network Exchange (ONNX) is an open standard for representing machine learning models. The biggest advantage of ONNX is that it allows interoperability across different open source AI frameworks, which itself offers more flexibility for AI frameworks adoption.

ONNX provides TensorRT (Windows / LInux, fast Nvidia GPU backend), DirectML (Windows, can be used on all GPUs) and WebGL (all platforms, can be used on all GPUs) backends, which have big advantages compared to pyTorch backend.

Currently, the official node-js backend does not support any GPU functionality. Considering running a python backend to do all of the ML stuffs?

https://www.npmjs.com/package/onnxruntime (node-js CPU only)

https://github.com/microsoft/onnxjs (WebGL, not all ops we need are implemented)

@arition arition added the enhancement New feature or request label Oct 3, 2020
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

1 participant