WIP. Started. 2020-04-14
NNStreamer, an incubating LF AI Foundation project, is an efficient and flexible stream pipeline framework for complex neural network applications, which was developed and open-sourced by Samsung.
NNStreamer provides a set of GStreamer plugins so that developers may apply neural networks, attach related frameworks (including ROS, IIO, FlatBuffers, and Protocol Buffers), and manipulate tensor data streams in GStreamer pipelines easily and execute such pipelines efficiently. It has already been adopted by various Android and Tizen devices in Samsung
(( designers may need to retouch the diagram. ))
NNStreamer was open-sourced in 2018 on GitHub,
Join the Conversation and Contribute
- sudo add-apt-repository ppa:nnstreamer/ppa
- sudo apt-get update
- sudo apt-get install nnstreamer nnstreamer-caffe2 nnstreamer-tensorflow nnstreamer-tensorflow-lite
- # Now, you are ready to use nnstreamer as GStreamer plugins!
- Add a link on more detailed description.
- <<<NOTE>>> It would be better if we can give with https://github.com/nnstreamer/nnstreamer/issues/2271 or a gst-launch example
- In Tizen 5.5 or higher, the Machine Learning (ML) APIs (links to be updated) uses nnstreamer. Use ML APIs to use nnstreamer.
- @TODO@ Add how to use nnstreamer JCenter/JFrog repo.
- @TODO@ Add how to use meta-neural-network.
Using on macOS
- @TODO@ Add how to use w/ homebrew.
Build for your own system and frameworks ==> Just add a link.