Length: 1/2 day (4 Hours)
Course Description
This course introduces the Xtensa Neural Network Compiler (XNNC) v2.
The purpose of the Xtensa® Neural Network Compiler (XNNC) is to convert a floating-point Convolutional Neural Network (CNN) into an optimized, fixed-point solution for Cadence Tensilica® processors. The course aims to guide the user to the effective use of configuring and running supported neural network models through the different stages and modes of the XNNC workflow. This includes how to configure inputs and outputs for a network and the usage of the Custom Operator Application Interface (API).
The course describes the added support for Graph Lowering (Glow) Compiler techniques, Tensorflow convertors, Open Neural Network eXchange (ONNX), and Caffe2. The course also explains the use of new Quantization schemes and Xtensa Exchange Formats for generated DSP codes.
Learning Objectives
After completing this course, you will be able to:
- Configure and run the supported neural network models through different stages and modes of the XNNC workflow.
- Understand the use of new Quantization schemes and Xtensa Exchange Formats for generated DSP codes.
Software Used in This Course
Software Release(s)
Xtensa Software Tools release RI-2020.4, Xtensa Xplorer 8.0.13
Modules in this Course
- About This Course
- XNNC Inputs
- XNNC Outputs
- Customer Operations
Audience
- Software Engineers and Architects
- Neural Network Architects
- Machine Learning Researchers
Prerequisites
You must have experience with or knowledge of the following:
- Machine Learning, Computer Vision and Imaging Concepts
- Neural Network Frameworks (specifically Caffe2, OnnX and Tensorflow)
- Some familiarity with DSP Processors and Embedded Programming
You must have completed one of the following courses:OR- Tensilica Xtensa NX Processor Fundamentals
Related Courses
