Hands-on OpenVX Inference Tutorial

In this tutorial, we will learn how to run inference efficiently using OpenVX and OpenVX Extensions. OpenVX is an open, royalty-free standard for cross platform acceleration of computer vision applications. It is designed by the Khronos Group to facilitate portable, optimized and power-efficient processing of methods for vision algorithms.

The tutorial will go over each step required to convert a pre-trained neural net model into an OpenVX Graph and run this graph efficiently on any target hardware.

In this tutorial, we will also learn about AMD MIVisionX which delivers open source implementation of OpenVX and OpenVX Extensions along with Neural Net Model Compiler & Optimizer.

MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX delivers highly optimized open source implementation of the Khronos OpenVX™ and OpenVX™ Extensions along with Convolution Neural Net Model Compiler & Optimizer supporting ONNX, and Khronos NNEF™ exchange formats. The toolkit allows for rapid prototyping and deployment of optimized workloads on a wide range of computer hardware, including small embedded x86 CPUs, APUs, discrete GPUs, and heterogeneous servers.

The tutorial will give the attendees hands-on experience with neural nets and help them create an inference engine.

Agenda

When: Friday 14th June 2019

Where: AMD 2485 Augustine Dr, Santa Clara, CA 95054

Start Time: 2:30 PM

• 2:30 pm - Register and network
• 3:00 pm - Tutorial starts
  • Machine Learning & Industry Trends: Ajit Mathews - Corporate Vice President, AMD
  • OpenVX & Machine learning with MIVisionX: Mike Schmit - Director of Software Engineering, AMD
  • OpenVX Hands-on Inference: Kiriti & Rajy, AMD
• 5:30 PM - Wrap up and adjourn

*** Bring PHOTO ID (passport, driver license, etc.) ***

Tutorial Requirements:

Install the appropriate terminal program on your laptop:

• Windows laptop - install MobaXterm - https://mobaxterm.mobatek.net/
• Linux Laptop - install SSH - sudo apt install openssh-server
• Mac - install Xquartz - https://www.xquartz.org/

Tickets

• Only limited seats are available for the tutorial. Book your tickets now at Eventbrite
• Limited free tickets are available for students. Please email yang.lei@ieee.org with your .edu email account to reserve your free ticket.

Event sponsored and organized by:

IEEE Signal Processing Society (SPS)

Co-sponsors:

• Computational Intelligence Society (CIS)

• Circuits and Systems Society (CASS)
• Computer Society (CS)
• ValleyML.ai