The 2020 Embedded Vision Summit will be a fully online experience made up of five sessions taking place Tuesdays and Thursdays from September 15 through September 25 from 9:00 am to 2:00 pm PT. In addition to presentations, the virtual Embedded Vision Summit will include exhibit booths, networking opportunities, trainings and workshops.
The landscape of processors and tools for accelerating inferencing and vision applications continues to evolve rapidly. Khronos standards, such as OpenCL, OpenVX, SYCL and NNEF, play an increasingly central role in connecting application developers to the latest silicon—productively, efficiently and portably. In this talk, Neil will provide an overview and the latest updates on Khronos standards relevant for machine learning and computer vision, and will preview how they are likely to evolve in the future.
Democratizing Computer Vision and Machine Learning with Open, Royalty-Free Standards: OpenVX
In this talk, we will present the latest features in OpenVX 1.3 and how these features are being leveraged by OpenVX adopters. We will clear up some misconceptions about OpenVX adoption and usability. In addition, we will analyze implementations and learn about the performance, portability and memory footprint advantages of OpenVX via open-sourced samples.
Deploying AI Software to Embedded Devices Using Open Standards
Speaker: Andrew Richards, Founder and CEO, Codeplay Track:FUNDAMENTALS Date and Time: September 22nd at 1:30pm PT Website:Click to View
AI software developers need to deploy diverse classes of algorithms in embedded devices, including deep learning, machine vision and sensor fusion. Adapting these algorithms to run efficiently on embedded devices typically involves using accelerator processors, such as GPUs or neural network accelerators. Quickly deploying high-performance AI algorithms to different processors requires open standards. There are a variety of open standards available to help: SYCL, OpenCL, SPIR-V, OpenMP, OpenVX and ONNX. This talk will present proven workflows that combine these standards to enable AI software developed on a PC to run efficiently on a variety of embedded devices using accelerated programming models.