The Khronos Group announces a significant expansion in the ecosystem for the NNEF (Neural Network Exchange Format) open, royalty-free standard that enables hardware manufacturers to reliably exchange trained neural networks between training frameworks and inference engines. New and improved NNEF open source convertors, including for TensorFlow Lite and ONNX, enables NNEF to be used to carry trained frameworks from a wider range of training frameworks. A set of extensions to the NNEF 1.0 specification enables NNEF files to contain richer networks of operations and topologies. Finally, an openly available NNEF Model Zoo enables inferencing engines to test their reliable import of NNEF models. More information on NNEF can be found at the Home Page.
Today The Khronos Group announces a significant expansion in the ecosystem for the NNEF™ (Neural Network Exchange Format) open, royalty-free standard that enables hardware manufacturers to reliably exchange trained neural networks between training frameworks and inference engines. New and improved NNEF open source convertors, including for TensorFlow Lite and ONNX, enables NNEF to be used to carry trained frameworks from a wider range of training frameworks. A set of extensions to the NNEF 1.0 specification enable NNEF files to contain a richer network of operations and topologies. Finally, an openly available NNEF Model Zoo enables inferencing engines to test their reliable import of NNEF models. More information on NNEF can be found at the NNEF Home Page.
All of the presentations and videos from the Khronos OpenVX workshop at the 2019 Embedded Vision Summit are now online. If you were unable to attend this workshop, you may now watch the seven sessions online and follow along with the slide presentations:
Introduction and OpenCL Overview & Update – Neil Trevett, NVIDIA: slides, video
OpenCL & SYCL – Andrew Richards, Codeplay: slides, video
Intel Open Source SYCL Compiler Project – Konstantin S. Bobrovsky, Intel: slides, video
OpenVX Presentations – Frank Brill, Cadence / Niclas Danielsson & Mikael Pendse, Axis : here & here, video
Inference with OpenVX – Mike Schmit, AMD: slides, video
NNEF Presentation – Gergely Debreczeni, AImotive: slides, video
OpenVX Hands-On - Part 1 – Rajy Rawther & Kiriti Nagesh Gowda, AMD: slides, video
Khronos member Au-Zone Technologies has written a guest post on the CNX Embedded Software blog showing how to add Machine Learning (ML) processing to an embedded product with the help from the Khronos Groups Neural Network Exchange Format (NNEF). The post illustrates, with an example implementation, how to detect and classify different pasta types on a moving conveyor belt.
The Khronos Group was in Japan this week for SIGGRAPH Asia 2018. There were five BOF sessions covering Vulkan, OpenXR, WebGL, glTF, NNEF, OpenVX and OpenCL. Most of the presentations from these sessions is now online and we have lots of photos as well. Unfortunately not video this year.
To further its goal of passing trained frameworks to embedded inference engines, the Khronos Group adds to its existing converters with two new bidirectional converters. Now available on the NNEF GitHub, these new tools enable easy conversion of trained models, including quantized models, between TensorFlow or Caffe2 formats and NNEF format.
AImotive, the global provider of full stack, vision-first self-driving technology, today announced the release of aiWare3, the company’s 3rd generation, scalable, low-power, hardware Neural Network (NN) acceleration core. The scalable aiWare3 architecture facilitates low-power continuous operation for autonomous vehicles (AVs) with up to 12 or more high-resolution cameras, LiDARs and/or radar. aiWare3 delivers up to 50 TMAC/s (> 100 TOPS) per chip at more than 2 TMAC/s (4 TOPS) per W1. aiWare3’s IP core is supported by a comprehensive software development kit (SDK) that uses The Khronos Group’s NNEF standard. It will ship to lead customers in Q1 2019.
Neil Trevett, President of the Khronos Group, delivers the presentation “Update on Khronos Standards for Vision and Machine Learning” at the Embedded Vision Alliance’s September 2018 Vision Industry and Technology Forum. Neil Trevett shares updates on recent, current and planned Khronos standardization activities aimed at streamlining the deployment of embedded vision and AI. For the full version of this video, along with hundreds of others on various embedded vision topics, please visit the Embedded Vision website.
Khronos member Peter McGuinness has written an overview about NNEF over on the GFXSpeak blog. The new standard was released in provisional form in December of 2017 and, after a period of consultation with industry, is now ratified in its final form and available for immediate use. As well as the standard itself, Khronos is simultaneously releasing a suite of open source tools to allow developers to immediately begin using the format with the three most popular training frameworks: Tensorflow and Caffe/Caffe2. All of these tools are available on GitHub in the Khronos repo. Learn more about NNEF.
The Khronos Group announces updates to key standards and opens the Khronos Education Forum at SIGGRAPH. With various Khronos events throughout the week, including a day of Birds of a Feather (BOF) sessions and its annual networking reception, Khronos is accelerating open standards ecosystems and continuing its commitment to the SIGGRAPH community of interactive graphics professionals. At SIGGRAPH, Khronos will be talking about the following standards developments and initiatives: NNEF 1.0 Specification Finalized, OpenXR Demonstrates Specification in Hardware Implementation, Ecosystem Grows; New Extensions Released and a Call for Participation - Education Forum Opens for Public Contribution. In addition to standards updates, The Khronos Group is hosting educational sessions and networking events this week, including a full-day of BOF sessions with talks from various members.
The Khronos Group announces the ratification and the public release of the NNEF™ 1.0 (Neural Network Exchange Format) specification. After gathering feedback from the industry review of the provisional specification, Khronos releases NNEF 1.0 as a stable, flexible, and extensible open standard for hardware manufacturers to reliably deploy optimized, accelerated neural network inferencing onto diverse edge devices. Together with this release, an ecosystem of tools is now also available on GitHub, including an NNEF parser and converters from Tensorflow and Caffe. Importers into popular inferencing environments, including Android’s Neural Network API (NNAPI) and Khronos’ OpenVX™, are also being developed.
The Khronos Group standards logos are now available for download on Sketchfab. Sketchfab makes it easy for anyone to publish and find 3D content online. Available logos currently include OpenXR, OpenCL, NNEF, OpenVX, SPIR, Vulkan, WebGL, SYCL and glTF. OpenGL has not been overlooked and will be arriving shortly.
The Khronos Group NNEF Working Group Chair Peter McGuinness discusses fragmentation in the Machine Learning field. Machine learning capabilities are being added to everything from social media platforms, IoT devices and cameras to robots and cars. The pace of innovation is leading to fragmentation, and one potential consequence of that fragmentation is a risk of stalling. A universal transfer standard for neural networks will cut down time wasted on transfer and translation and provide a comprehensive, extensible and well-supported solution that all parts of the ecosystem can depend on. The Neural Network Exchange Format is one of two standards currently being developed to satisfy this need. Learn more about NNEF and how it aims to solve this issue.
The Khronos Group last week announced the launch of a project with Au-zone of Calgary, Canada to produce two conversion tools that will allow developers to import NNEF files into TensorFlow and Caffe2 as well as export NNEF files from those training frameworks. In line with Khronos’ recent policy, the tools will be made available in the second half of 2018 as open source projects on Github where contributions from the open source community will be welcomed. These tools will join the converters for Caffe and Tensorflow (which has two formats to consider) and the NNEF parser that are all already available.