NNStreamer (GStreamer Pluigins for Neural Networks) 1.6 Release

[MyungJoo Ham]

NNStreamer team is pleased to announce the release of NNStreamer 1.6.0.

Major changes since 1.4.0:
- New hardware accelerators and neural network frameworks support
added: Verisilicon-Vivante, Qualcomm-SNPE, NNFW-ONE-Runtime, and
Tensorflow2-lite.
- Data serialization support with flatbuf and protobuf.
- Android APIs optimized (i.e., invoke latency in Galaxy S20: 2ms → 0.1ms)
- Plug-and-play sub-plugins support for tensor-converters
- Hardware acceleration configuration reworked: multiple candidates
may be expressed and options may be altered in run-time.
- Fixes, semantics updates, and minor features added after
commercialization (Galaxy Watch 3 and a few “next-year” products and
Tizen 6 releases).


Linux Foundation AI announcement:
https://lfai.foundation/blog/2020/09/24/nnstreamer-1-6-0-release-now-available/

Release code: https://github.com/nnstreamer/nnstreamer/releases/tag/v1.6.0


NNStreamer has been shipped with Galaxy Watch 3 for its on-device AI
applications and we expect that various types of devices including
mobile, TV, and home appliances will be using NNStreamer for its
on-device AI applications next year.

Cheers,
MyungJoo