Openvx tagged stories

In 2016, the Uber Visualization team released an open source version of deck.gl and luma.gl, two Khronos Group WebGL™-powered frameworks for visualizing and exploring huge geospatial data sets on maps. Since then, the technology has flourished into a full-fledged suite of over a dozen open source WebGL and GPGPU data visualization libraries and tools, known collectively as vis.gl. loaders.gl, the newest addition to the vis.gl family, adds support for loading and rendering glTF™ assets across the tech stack. This unlocks the ability to include rich 3D content within data visualization applications built using luma.gl and deck.gl, enabling a variety of interesting new use cases. In this post, we’ll show some applications and walk through how you can use deck.gl and glTF, Khronos’ open standard 3D file format, to quickly create a geospatial data visualization that renders tens of thousands of 3D models.

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.

Virtual reality and augmented reality have great potential for entertainment, training and education, and other industries, but are currently being held back by industry fragmentation. The Khronos Group is addressing this by creating the OpenXR API, and shares details of its creation and considerations, as well as the first demo of the API at SIGGRAPH 2018.

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. Although Khronos has not been involved in the detailed design principles of ONNX, in this post we explain how we see the differences according to our understanding of the two projects. We welcome constructive discussion as the industry explores the need for neural network exchange and hope this post may be a constructive start to that conversation.

There is a wide range of open-source deep learning training networks available today offering researchers and designers plenty of choice when they are setting up their project. Caffe, Tensorflow, Chainer, Theano, Caffe2, the list goes on and is getting longer all the time. This diversity is great for encouraging innovation, as the different approaches taken by the various frameworks make it possible to access a very wide range of capabilities, and, of course, to add functionality that’s then given back to the community. This helps to drive the virtuous cycle of innovation.

Don’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.