Introduction¶

Kenning provides an API for deploying deep learning applications on edge devices using various model training and compilation frameworks.

This documentation consists of the following chapters:

• The Kenning section provides a project description, installation steps and a quick start guide,

• The Deep Learning deployment stack section describes a typical model deployment flow on edge devices,

• The Defining optimization pipelines in Kenning section describes a way to create advanced optimization scenarios with JSON config,

• The Using Kenning via command line arguments section describes executable scripts available in |projecturl|,

• The Kenning measurements section describes data gathered during the compilation and evaluation process,

• The ONNX support in deep learning frameworks section covers ONNX model format support in deep learning frameworks,

• The Sample autogenerated report section provides a sample report generated using Kenning,

• The Creating applications with Kenning section describes KenningFlow and its usage,

• The Developing Kenning blocks section describes a way to develop new Kenning components,

• The Kenning API section provides an in-depth description of the Kenning API.