model-archiver 1.0b20181019

Model Archiver is used for creating archives of trained neural net models that can be consumed by MXNet-Model-Server inference

Model Archiver is a tool used for creating archives of trained neural net models that can be consumed by MXNet-Model-Server inference.

Use the Model Archiver CLI to start create a .mar file.

Model Archiver is part of MMS. However,you ca install Model Archiver stand alone.

Detailed documentation and examples are provided in the README.

Prerequisites

ONNX support is optional in model-archiver tool. It’s not installed by default with model-archiver.

If you wish to package a ONNX model, you will need to first install a protobuf compiler, onnx and mxnet manually.

Instructions for installing Model Archiver with ONNX.

Installation

pip install model-archiver

Development

We welcome new contributors of all experience levels. For information on how to install MMS for development, refer to the MMS docs.

Important links

• Official source code repo

• Download releases

• Issue tracker

Source code

You can check the latest source code as follows:

git clone https://github.com/awslabs/mxnet-model-server.git

Testing

After installation, try out the MMS Quickstart for Create a model archive and Serving a Model.

Help and Support

• Documentation

• Forum

Citation

If you use MMS in a publication or project, please cite MMS: https://github.com/awslabs/mxnet-model-server