Haffon/ml-suite

Getting Started with Xilinx ML Suite

Xilinx ML Suite v1.3

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

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

See What's New

• Release Notes

Getting Started

1. Clone ML Suite
   git clone https://github.com/Xilinx/ml-suite.git
2. Download Overlays and Pre-Trained Models from ML Suite Lounge
   • Overlays: Download and unzip desired overlays into the ml-suite/overlaybins/ dir, for example: ml-suite/overlaybins/alveo-u200
   • Pre-Trained Models: Download and unzip to the /ml-suite/ dir.
3. Install Anaconda2
   • Note: Ensure that you ran the fix_caffe_opencv_symlink.sh script

References

• ML Suite Overview
• User Guides:
  • Compiler Python API
  • Quantizer Python API
  • xfDNN Python API
• Tutorials and Examples:
  • Jupyter Notebooks
  • Precompiled Examples

Recommended System Requirements

• OS: Ubuntu 16.04.2 LTS, Ubuntu 18.04 LTS, CentOS 7.4
• CPU: 6 Cores (Intel/AMD/Power9)
• Memory: 8 GB

Supported Platforms

Cloud Services

• Amazon AWS EC2 F1
• Nimbix

On Premise Platforms (Visit ML Suite Lounge for Details)

• Alveo U200 Data Center Accelerator Card
• Xilinx Virtex UltraScale+ FPGA VCU1525 Acceleration Development Kit

Release Notes

• Release Notes

Questions and Support

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