NNStreamer is a flexible and efficient stream pipeline framework designed for complex neural network applications. Initially developed by Samsung and later transferred to LF AI Foundation, it allows developers to apply neural networks and manipulate tensor data streams within GStreamer pipelines efficiently. NNStreamer supports various platforms, including Tizen, Ubuntu, Android, macOS, and Yocto/OpenEmbedded. It provides APIs in C, Java, and .NET, enabling easier integration into applications. The framework is compatible with popular neural network frameworks such as Tensorflow, Caffe2, and PyTorch, allowing for the inclusion of custom functions and runtime plugin integration.
• supports multiple neural network frameworks
• efficient stream pipeline framework
• apis available in c, java, and .net
• cross-platform support (tizen, ubuntu, android, macos)
• adopted in commercial samsung products
• custom function integration during runtime
• compatible with gstreamer
Average Rating: 0.0
5 Stars:
0 Ratings
4 Stars:
0 Ratings
3 Stars:
0 Ratings
2 Stars:
0 Ratings
1 Star:
0 Ratings
No ratings available.
A federated AI framework that integrates decentralized data sources for AI development.
View Details