Khronos will be at Hot Chips 2018. Representatives from member companies will be on hand to demonstrate and discuss Khronos' Standards for Machine Learning: SYCL™, NNEF™, and OpenVX™. Member company AMD will demonstrate a working example flow from Framework, through NNEF to hardware inferencing using the OpenVX extensions.
Khronos’ Neural Network Exchange Format (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.
Khronos has initiated a series of open source projects, including an NNEF syntax parser/validator and example exporters from a selection of frameworks including TensorFlow, Caffe and Caffe2. These tools are freeley available and Khronos welcomes the participation of the machine learning community to make NNEF useful for their own workflows.
In addition, NNEF is working closely with the Khronos OpenVX working group to enable ingestion of NNEF files. The OpenVX Neural Network extension enables OpenVX 1.2 to act as a cross-platform inference engine, combining computer vision and deep learning operations in a single graph.