docs

Model Server or Apache MXNet Documentation

Basic Features

• Serving Quick Start - Basic server usage tutorial
• Exporting Quick Start - Tutorial that shows you how to export.
• Installation - Installation procedures and troubleshooting
• Serving Models - Explains how to use mxnet-model-server.
  • REST API - Specification on the API endpoint for MMS
  • Model Zoo - A collection of MMS .model files that you can use with MMS.
• Exporting Models - Explains how to use mxnet-model-export.
  • Export Examples
  • Export an ONNX Model
  • Exported MMS Model File Tour
• Docker - How to use MMS with Docker and cloud services
• Metrics - How to configure logging of metrics

Advanced Features

• Custom Model Service - Describes how to develop custom inference services.
• Client Code Generation - Shows how to use Swagger to create a client API for more than 40 languages. Includes a JavaScript example.
• Unit Tests - Housekeeping unit tests for MMS
• Load Test - Use JMeter to run MMS through the paces and collect load data

Example Projects

• MMS on Fargate, Serverless Inference - The project which illustrates the step-by-step process to launch MMS as a managed inference production service, on ECS Fargate.
• LSTM - An example MMS project for a recurrent neural network (RNN) using long short-term memory (LSTM). The project takes JSON inputs for inference against a model trained with a specific vocabulary.
• Object Detection - An example MMS project that uses a pretrained Single Shot Multi Object Detection (SSD) model that takes image inputs and infers the types and locations of several classes of objects.