Proposal of MxNet-to-ONNX exporter

[Marek Kolodziej <mk...@gmail.com>]

def mxnet.contrib.onnx._export.export_model( sym, params, input_shape,
output):
    """
    Exports a given MXNet symbol object file or path to saved file to ONNX
model file.
    Input Parameters -
    ----------
    sym -
        A str object (path to json file) or mxnet symbol object or
checkpointed mxnet symbol object
    params -
        A str object (path to params file) or dict object containing the
model params
    input_shape -
        list of tuple object , specifies the shape of each input to the
model
    output -
        path to the output file, including the filename.  Default: current
path , filename: model.onnx

    Return Type –
    ----------
    onnx_model_path -
    str object , path to saved .onnx file.
    """
    ...
    return onnx_model_path

Re: Proposal of MxNet-to-ONNX exporter

[Hagay Lupesko <lu...@gmail.com>]

Marek,

Can you add more details on your proposal?
(Implementation details, operator coverage, test coverage planned)

I am aware of similar work done by other contributors (Roshani, Rajan and
Anirudh) - how is this going to align? Should you guys work together?

Hagay

On Mon, May 21, 2018, 11:17 Marek Kolodziej <mk...@gmail.com> wrote:

> def mxnet.contrib.onnx._export.export_model( sym, params, input_shape,
> output):
>     """
>     Exports a given MXNet symbol object file or path to saved file to ONNX
> model file.
>     Input Parameters -
>     ----------
>     sym -
>         A str object (path to json file) or mxnet symbol object or
> checkpointed mxnet symbol object
>     params -
>         A str object (path to params file) or dict object containing the
> model params
>     input_shape -
>         list of tuple object , specifies the shape of each input to the
> model
>     output -
>         path to the output file, including the filename.  Default: current
> path , filename: model.onnx
>
>     Return Type –
>     ----------
>     onnx_model_path -
>     str object , path to saved .onnx file.
>     """
>     ...
>     return onnx_model_path
>