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.
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 Group announces the release of the Neural Network Exchange Format (NNEF™) 1.0 Provisional Specification for universal exchange of trained neural networks between training frameworks and inference engines. NNEF reduces machine learning deployment fragmentation by enabling a rich mix of neural network training tools and inference engines to be used by applications across a diverse range of devices and platforms. The release of NNEF 1.0 as a provisional specification enables feedback from the industry to be incorporated before the specification is finalized — comments and feedback are welcome on the NNEF GitHub repository.
Neil Trevett, Khronos Group President and Radhakrishna Giduthuri, Software Architecture and Compute Performance Acceleration at AMD, spoke at two Khronos related events this past week. Neils presented was an update on the Khronos Standards for Vision and Machine Learning which covered Khronos Standards OpenVX, NNEF, OpenCL, SYCL and Vulkan. Radhakrishna presented Standards for Neural Networks Acceleration and Deployment covered Khronos Standards OpenVX and NNEF. The slides from both presentations are now online.
The best paper award among all papers presented at the ICCE Asia 2017 conference, went to the paper titled "Novel OpenVX Implementation for Heterogeneous Multi-Core Systems" (PDF), by Kedar Chitnis, Jesse Villarreal, Jr, Brijesh Jadav, Mihir N Mody, Lucas Weaver, Victor Cheng, Kumar Desappan, Anshu Jain and Pramod Swami.
The Khronos Group announces an updated Adopters Program for OpenVX, the open, cross-platform, royalty-free standard for computer vision and inferencing acceleration. The updated OpenVX Adopters Program includes a new version of the full conformance tests for the latest iteration of the standard, OpenVX 1.2, and the process by which Adopters can run those tests and submit the results for working group review. Once these tests are successfully passed, Adopters are enabled to label their product as OpenVX conformant, use a royalty-free trademark license for the OpenVX name and logo in association with their implementation, gain protection from the Khronos IP framework and enjoy marketing promotion from the Khronos Group.
The Khronos Group announces an updated Adopters Program for OpenVX, the open, cross-platform, royalty-free standard for computer vision and inferencing acceleration. The new Adopters Program includes full conformance tests for the latest iteration of the standard, OpenVX 1.2.
The Khronos Group will be holding a two hour tutorial at the Embedded Systems Conference '17 in December. Attendees will gain an understanding of the architecture of Khronos standards for computer vision and neural networks; getting fluent in actually using OpenVX and NNEF for real-time computer vision and neural network inference tasks.
Mozilla announced a new development program for Mixed Reality that will expand its work in Virtual Reality (VR) and Augmented Reality (AR) for the web. There is a draft WebXR API proposal, which uses WebGL, for providing access to both augmented and virtual reality devices.
On September 14th The Khronos Group held an online overview webinar on OpenVX 1.2. If you missed the webinar or wish to watch it again, the video and slides are now online. Be sure to register for the next Khronos Webinar "Mastering the Khronos Blender glTF 2.0 Exporter" on October 24th.
The Khronos Group is holding another Webinar on September 14th at 9:30AM PT. Engineers and managers interested in developing neural network inference engines and portable application that need portability across platforms and hardware should join in this free webinar. Speaking will be Radhakrishna (Radha) Giduthuri, a software architect at Advanced Micro Devices (AMD), Tomer Schwartz from Intel and Frank Brill, OpenVX Working Group Chair.
CVPR is soliciting proposals for workshops to be held together with the 2018 Computer Vision and Pattern Recognition Conference (CVPR 2018). The workshops will take place on June 18 and June 22 at the same venue as the main conference. Deadline is October 20th 2017. CVPR is the premier annual computer vision event comprising the main conference and several co-located workshops and short courses. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers.
The landscape of APIs for accelerating vision and neural network software using specialized processors continues to rapidly evolve. Many industry-standard APIs, such as OpenCL and OpenVX, are being upgraded to increasingly focus on deep learning, and the industry is rapidly adopting the new generation of low-level, explicit GPU APIs, such as Vulkan, that tightly integrate graphics and compute. Neil Trevett presented the "Vision Acceleration API Landscape: Options and Trade-offs" tutorial at the May 2017 Embedded Vision Summit.
The Khronos Group held their annual BOF-Blitz at SIGGRAPH today. There were five BOFs in all, and they were all a huge success. If you were not able to get to SIGGRAPH and you missed the live stream, you can now watch the video online here.
Synopsys announced that it has enhanced the convolutional neural network (CNN) engine in its DesignWare EV6x Vision Processors to address the increasing video resolution and frame rate requirements of high-performance embedded vision applications. To simplify software application development, the EV6x processors are supported by a comprehensive suite of tools and software. Combined with software development tools based on OpenVX, OpenCV and OpenCL C embedded vision standards, the MetaWare EV Development Toolkit offers a full suite of tools needed to accelerate embedded software development.