NNEF tagged news

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 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.

OpenVX & Neural Networks Workshop at Embedded Vision Summit - final curriculum now onlineThe curriculum for the 2018 OpenVX Workshop at the Embedded Vision Summit in May has been finalized. The Khronos Group will be presenting a day-long hands-on workshop all about OpenVX cross-platform neural network acceleration API for embedded vision applications. Khronos has developed a new curriculum making this a do-not-miss tutorial with new information on computer vision algorithms for feature tracking and neural networks mapped to the graph API. The tutorials will be presented by speakers from Khronos member companies AMD, Axis Communications, Cadence and Codeplay. There will be hands-on practice sessions with the folks who created the OpenVX API to give participants a chance to solve real computer vision problems. Discussions will also include the OpenVX roadmap and what’s to come. Registration is now open but space is limited, so be sure not to wait too long.

OpenVX Workshop at Embedded Vision Summit - Neural Networks and Embedded VisionDon’t miss this year’s OpenVX Workshop at Embedded Vision Summit on May 24th, 2018. 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.

2018 Embedded Vision Summit - May 22-24 - Registration now openDon’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. Registration is now open. Early bird pricing ends April 10th.

Registration now open for the Khronos Standards for Neural Networks and Embedded Vision workshop at the Embedded Vision Summit in Santa Clara. Early bird pricing is now $99. This seminar is intended for 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.

Buy your tickets today

Khronos Group announces two NNEF Request for Quotes (RFQ)The Khronos Group has posted two new RFQs, both for NNEF:

  • Caffe2 to NNEF Converter: The project will deliver Caffe2 to NNEF converter that receives a set of Caffe2 protobuf files and generates semantically and functionally equivalent NNEF container.
  • TensorFlow to NNEF Converter: The project will deliver a converter between Tensorflow and NNEF that receives a TensorFlow protobuf file and generates semantically and functionally equivalent NNEF container, and is able to convert the NNEF container back to a TensorFlow protobuf file which when executed in TensorFlow produces equivalent results with the original source of conversion (although the backward conversion may not result in a one equivalent to the original protobuf).
The deadline for submissions is March 29th.

VeriSilicon today announced significant milestones have been achieved for its versatile and highly scalable neural network inference engine family VIP8000. The fully programmable VIP8000 processors reach the performance and memory efficiency of dedicated fixed-function logic with the customizability and future proofing of full programmability in OpenCL, OpenVX, and a wide range of NN frameworks including NNEF. “The biggest thing to happen in the computer industry since the PC is AI and machine learning, it will truly revolutionize, empower, and improve our lives. It can be done in giant machines from IBM and Google, and in tiny chips made with VeriSilicon’s neural network processors,” said Dr. Jon Peddie, president Jon Peddie Research. “By 2020 we will wonder how we ever lived without our AI assistants,” he added.

The Khronos Neural Network Exchange Format, among other technologies, go a long way to enable highly optimized implementations of inference for systems trained on a range of systems. Explains Chris Rowen, CEO for Babblabs, "This is extremely valuable to opening up the path to exploit optimized high-volume inference engines in phones, cars, cameras and other IoT devices. This higher-level robust set of interfaces breaks the tyranny of instruction set compatibility as a standard for exchange and allows for greater levels of re-optimization as the inference execution hardware evolves over time." Read more on the Semiconductor Engineering blog.

Standards make life easier, and we depend on them for more than we might realize — from knowing exactly how to drive any car, to knowing how to get hot or cold water from a faucet. Balancing the need for a stable standard, while at the same time allowing technology advances to be rapidly exploited, is a big part of what Khronos does. There are two ways a Khronos standard can be extended: Vendor Extensions and Khronos Extensions. Read on to learn how both of these work within Khronos.

NNEF and ONNX are two similar open formats to represent and interchange neural networks among deep learning frameworks and inference engines. At the core, both formats are based on a collection of often used operations from which networks can be built. Because of the similar goals of ONNX and NNEF, we often get asked for insights into what the differences are between the two. Read the Khronos blog to learn more about the similarities and differences between NNEF and ONNX.