Presentations and other assets from this event are presented here. For information on upcoming events, click here.
Don’t miss this year’s OpenVX Workshop at Embedded Vision Summit. Khronos will present a day-long hands-on workshop all about OpenVX cross-platform neural network acceleration API for embedded vision applications. We’ve developed a new curriculum so even if you attended in past years, this is a do-not-miss, jam-packed tutorial with new information on computer vision algorithms for feature tracking and neural networks mapped to the graph API. We’ll be doing a hands-on practice session that gives participants a chance to solve real computer vision problems using OpenVX with the folks who created the API. We’ll also be talking about the OpenVX roadmap and what’s to come.
Date: Thursday, May 24, 2018 from 8:00am - 5:30pm
This workshop covers Khronos standards related to neural networks and computer vision. The primary focus of this workshop is about the new standard NNEF (Neural Network Exchange Format) based neural network inference workflows. A set of examples for neural networks and computer vision mapped to OpenVX graph API are discussed. Also covered is the deployment model that pre-compiles a graph to create optimized binaries for deployment use cases, such as, inference neural networks. The course includes demo session that shows the participants how to solve real computer vision and neural networks problems using Khronos standards.
Engineers, researchers, and software developers who develop vision and neural network applications and want to benefit from transparent HW acceleration. Also, managers that want to get a general understanding of the structure and uses of Khronos standards.
Fee: $50
Agenda
You will find a collection of the presentations for this workshop here. You may download a .zip file here.
| Time-slot | Topic | Speaker |
|---|---|---|
| 08:55-09:00 | Kick-Off | Radhakrishna Giduthuri (AMD) |
| 09:00-09:15 | Khronos Ecosystem for Embedded Vision | Frank Brill (Cadence) |
| 09:15-09:45 | Overview of NNEF | Peter McGuinness (Independent) |
| 09:45-10:30 | Overview of OpenVX | Niclas Danielsson (Axis Communications) |
| 10:30-11:00 | Morning Break | |
| 11:00-12:00 | Neural Network Inference with NNEF and OpenVX with an example | Radhakrishna Giduthuri (AMD) |
| 12:00-12:15 | OpenVX Safety-critical APIs | Frank Brill (Cadence) |
| 12:15-12:30 | OpenVX Extensions | Radhakrishna Giduthuri (AMD) |
| 12:30-13:30 | Lunch Break | |
| 13:30-15:00 | Vendor presentations and demos | AIMotive, AMD, Au-Zone, Axis Communications, Cadence, PeakHills Group, Verisilicon |
| 15:00-15:30 | Afternoon Break | |
| 15:30-16:15 | Modern C++ for accelerators: a SYCL deep dive | Andrew Richards (Codeplay) |
| 16:15-17:00 | TensorFlow acceleration for neural network inference using SYCL ecosystem | Andrew Richards (Codeplay) |
| 17:00-17:30 | OpenVX/NNEF Roadmap and General Q&A | Frank Brill (Cadence) |
Developing Computer Vision Algorithms for Networked Cameras
Speaker: Dukhwan Kim, Software Architect, Intel
Date & Time: Tuesday, May 22, 2:50 PM - 3:20 PM
Location: Mission City Ballroom B2-B5
Video analytics is one of the key elements in network cameras. Computer vision capabilities such as pedestrian detection, face detection and recognition and object detection and tracking are necessary for effective video analysis. With recent advances in deep learning technology, many developers are now utilizing deep learning to implement these capabilities. However, developing a deep learning algorithm requires more than just training models using Caffe or TensorFlow. It should start from an understanding of use cases, which affect the nature of required training dataset, and should be tightly bound with the hardware platform to get the best performance. In this presentation, we will explain how we have developed and optimized production-quality video analytics algorithms for computer vision applications.
Programming Techniques for Implementing Inference Software Efficiently
Speaker: Andrew Richards, (Khronos SYCL chair | CEO & Founder, Codeplay)
Date & Time: Tuesday, May 22, 4:10 PM - 4:40 PM
Location: Mission City Ballroom B2-B5
This talk will explore the approaches to implement deep neural networks in software, from how to map software to the highly-parallel processors needed for AI, to major AI frameworks. This will cover the LLVM compiler chain and the OpenCL, HSA and SYCL programming standards (including how they compare with CUDA), as well as TensorFlow and Caffe.
The OpenVX Computer Vision and Neural Network Inference Library Standard for Portable, Efficient Code
Speaker: Radhakrishna Giduthuri, Software Architect, Advanced Micro Devices
Date & Time: Tuesday, May 22, 4:50 PM - 5:20 PM
Location: Mission City Ballroom B2-B5
OpenVX is an industry-standard computer vision and neural network inference API designed for efficient implementation on a variety of embedded platforms. The API incorporates the concept of a dataflow graph, which enables implementers to apply a range of optimizations appropriate to their architectures, such as image tiling and kernel fusion. Application developers can use this API to create high-performance computer vision and AI applications quickly, without having to perform complex device-specific optimizations for data management and kernel execution, since these optimizations are handled by the OpenVX implementation provided by the processor vendor. This talk will describe the current status of OpenVX, with particular focus on neural network inference capabilities and the most recent enhancements. The talk will conclude with summary of the currently available implementations and an overview of the roadmap for the OpenVX API and its implementations.
APIs for Accelerating Vision and Inferencing: Options and Trade-offs
Speaker: Neil Trevett, President of The Khronos Group, Vice President at NVIDIA
Date & Time: Tuesday, May 22, 5:30 PM - 6:00 PM
Location: Mission City Ballroom B2-B5
The landscape of SDKs, APIs and file formats for accelerating inferencing and vision applications continues to rapidly evolve. Low-level compute APIs, such as OpenCL, Vulkan and CUDA are being used to accelerate inferencing engines such as OpenVX, CoreML, NNAPI and TensorRT. Inferencing engines are being fed via neural network file formats such as NNEF and ONNX. Some of these APIs, like OpenCV, are vision-specific, while others, like OpenCL, are general-purpose. Some engines, like CoreML and TensorRT, are supplier-specific, while others, such as OpenVX, are open standards that any supplier can adopt. Which ones should you use for your project?
In this presentation, Neil Trevett, President of the Khronos Group standards organization, presents the current landscape of APIs, file formats and SDKs for inferencing and vision acceleration, explaining where each one fits in the development flow. Neil also highlights where these APIs overlap and where they complement each other, and previews some of the latest developments in these APIs.
Conference Code of Conduct: The Khronos Group is dedicated to providing a harassment-free conference experience for everyone. Visit our Code of Conduct page to learn more.
Khronos videos, presentations, and upcoming events. Skip to the Footer
