README.md

Xilinx ML Suite v1.4

The Xilinx Machine Learning (ML) Suite provides users with the tools to develop and deploy Machine Learning applications for Real-time Inference. It provides support for many common machine learning frameworks such as Caffe, Tensorflow, and MXNet.

The ML Suite is composed of three basic parts:

1. ML Framework and Open Source Support - Support for high level ML Frameworks and other open source projects.
2. xfDNN Middleware - Software Library and Tools to Interface with ML Frameworks and optimize networks for Real-time Inference.
3. xDNN IP - High Performance CNN processing engine.

Learn More: ML Suite Overview
Watch: Webinar on Xilinx FPGA Accelerated Inference
Forum: ML Suite Forum

See What's New

• Release Notes
• Integration of Deephi DECENT Quantizer for Caffe
• xfDNN Runtime API upgraded to support multi-output networks
• XDNNv3 fully integrated for all platforms & models
• Ease of use enhancements
  • Docker Images
  • Run on FPGA using Caffe's custom Python layer
  • HDF5 format used for network weights

Getting Started

• Install XRT (Only necessary for On-Premise deployment)
• Start Docker Container
• Jupyter Notebook Tutorials
  • Caffe Image Classification
  • Caffe Object Detection w/ YOLOv2
• Command Line Examples
  • Caffe ImageNet Benchmark Models
  • Caffe VOC SSD Example
  • Deployment Mode Examples
• In-Browser GoogLeNet Demo
• REST Server Example
• Container Pipeline Example

References

• ML Suite Overview
• Performance Whitepaper
• Accuracy Benchmarks

System Requirements

Questions and Support

• FAQ
• ML Suite Forum
• AWS F1 Application Execution on Xilinx Virtex UltraScale Devices