mxnet-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Mu Li <muli....@gmail.com>
Subject Re: AWS contributing ONNX-MXNet
Date Fri, 17 Nov 2017 00:13:24 GMT
Thanks for letting the mxnet community know it. Given this new converter is
derived from the nnvm-onnx converted developed by Zhi and Tianqi, see this
link
<https://github.com/onnx/onnx-mxnet/blob/master/onnx_mxnet/common.py#L12>
and that link
<https://github.com/onnx/onnx-mxnet/blob/master/onnx_mxnet/import_helper.py#L12>.
Also the nnvm-onnx converter has been annouced on tvmlang.org
<http://tvmlang.org/2017/10/06/nnvm-compiler-announcement.html> , also with
this tutorial
<http://nnvm.tvmlang.org/tutorials/from_onnx.html#sphx-glr-tutorials-from-onnx-py>.
I
think it is worth to *acknowledge* the contributions from our community
members in the announcement to maintain a healthy connection.

On Thu, Nov 16, 2017 at 2:04 PM, Lupesko, Hagay <lupesko@gmail.com> wrote:

> Hey folks,
>
>
>
> Today AWS announced contributing ONNX-MXNet, an open source Python package
> that imports ONNX models into MXNet. @roshrini and I (@lupesko) have worked
> on the code, which is now publicly available [1], and published a blog post
> demonstrating usage of the package [2]. Special thanks to dmlc/nnvm team,
> whose ONNX code was used as a reference for this implementation.
>
>
>
> What is ONNX?
>
> ONNX is an open source format to encode deep learning models. ONNX defines
> a format to store neural network's computational graph, as well as a
> storage format for operators used within a neural network graph. For more
> details, check out onnx.ai [3].
>
>
>
> Why I think ONNX is important for MXNet?
>
> ONNX is an emerging standard, that holds a lot of potential for Deep
> Learning practitioners. With ONNX, people can create and train a network
> with framework A, and deploy it for inference with framework B. The blog
> post we published demonstrates using a Super Res model trained with
> PyTorch, and importing it into MXNet Symbolic API for inference. I strongly
> believe that adopting ONNX early on adds value for deep learning
> practitioners, and thus supporting it adds value for MXNet as well.
>
>
>
> As for next steps, I was thinking that porting the functionality and code
> into MXNet is the logical next step.
>
> Would love to get the community's feedback and contributions!
>
>
>
> [1] https://github.com/onnx/onnx-mxnet
>
> [2] https://aws.amazon.com/blogs/ai/announcing-onnx-support-
> for-apache-mxnet/
>
> [3] https://onnx.ai
>
>

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message