Quality rather than quantity
Artificial intelligence gains with embedded systems
Fortsetzung des Artikels von Teil 2
NNEF 1.0
Open source tools
Standard for trained neural networks
So far, it has been a challenge and required some effort to switch to a new neural network acceleration hardware platform. The Khronos Group therefore developed the NNEF 1.0 (Neural Network Exchange Format) specification. NNEF was created to reduce industry fragmentation by facilitating the exchange of neural networks among training frameworks and inference engines, increasing the freedom for developers to mix and match the inferencing and training solutions of their choice.
After gathering feedback from the industry review of the provisional specification, Khronos released 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.
A complete workflow from training through optimization to deployment is possible using NNEF as a standardized transfer format. At launch, the standard will be supported by two open source Tensorflow converters, both for network descriptions based on protobuf and python code, and a converter for Caffe. A Caffe2 open-source importer/exporter that is in development by Au-Zone Technologies will be available in Q3 2018. Various tools from member companies, such as Almotive and AMD, are in development, including an importer to Android NNAPI by National Tsing-Hua University of Taiwan.
The NNEF working group is committed to enabling and encouraging reliable interchange with the rapidly growing number of training frameworks, including Torch, Chainer, Theano, PyTorch, and MXNet with open source importers and exporters. Additional open-source tools, including an NNEF syntax parser and validator, are available now for the easy creation of importers into custom, mobile, and embedded edge-inferencing environments, such as Apple’s Core ML and Khronos’ OpenVX standard, for vision and inferencing runtime acceleration.
The NNEF 1.0 specification and documentation are freely available on the Khronos website, and NNEF open source tools and projects are available in the Khronos NNEF Tools repository. Khronos’ File Format Adopter Program is available, at zero cost, for users of NNEF that desire a formal license to use the NNEF trademark and enjoy the protection of the Khronos Intellectual Property Framework.
