Neural network standard initiatives launched by industry group
The Khronos Group, an open consortium of leading hardware and softwarecompanies, has announced the creation of two standardization initiatives to address the growing industry interest in the deployment and acceleration of neural network technology.
First, Khronos created a working group to create an application program interface (API) independent standard file format for exchanging deep learning data between training systems and inference engines. The aim of the Khronos Neural Network Exchange Format (NNEF) is to simplify the process of using a tool to create a network, and run that network on other toolkits or inference engines. This, according to Khronos, can reduce deployment friction and encourage a richer mix of cross-platform deep learning tools, engines, and applications. Work for generating requirements and detailed design proposals for the NNEF is underway, and companies are welcome to contact Khronos for input.
"AdasWorks initiated the creation of the NNEF working group as we saw the growing need for platform-independent neural network-based software solutions in the autonomous driving space," said Laszlo Kishonti, founder and CEO of AdasWorks. "We cooperate closely with chip companies to help them build low-power, high-performance neural network hardware and believe firmly that an industry standard, which works across multiple platforms, will be beneficial for the whole market. We are happy to see numerous companies joining the initiative."
Secondly, the OpenVX group—an open, royalty-free standard for cross platform acceleration of computer vision applications—has released an extension to enable convolutional neural network (CNN) topologies to be represented as OpenVX graphs and mixed with traditional vision functions. The OpenVX Neural Network extension defines a multi-dimensional tensor object data structure which can be used to connect neural network layers, represented as OpenVX nodes, to create flexible CNN topologies. OpenVX neural network layer types, according to Khronos, include convolution, pooling, fully connected, normalization, soft-max and activation – with nine different activation functions. The extension enables neural network inferencing to be mixed with traditional vision processing operations in the same OpenVX graph.
"Intel supports and welcomes the adoption of OpenVX and the OpenVX Neural Network Extension as an important element in proliferating computer vision deep learning usage models," said Ron Friedman, Intel Corporate vice president and general manager of IP Blocks and Technologies. "Khronos OpenVX Neural Network Extension brings algorithms tuned for deep learning to the embedded computer vision and machine intelligence hardware devices."
Learn more about both initiatives in the Khronos press release.
Share your vision-related news by contacting James Carroll, Senior Web Editor, Vision Systems Design
To receive news like this in your inbox, click here.
Join our LinkedIn group | Like us on Facebook | Follow us on Twitter
Learn more: search the Vision Systems Design Buyer's Guide for companies, new products, press releases, and videos
James Carroll
Former VSD Editor James Carroll joined the team 2013. Carroll covered machine vision and imaging from numerous angles, including application stories, industry news, market updates, and new products. In addition to writing and editing articles, Carroll managed the Innovators Awards program and webcasts.