The CustomFilter class provides interfaces to create a custom-filter in the pipeline.
An extended EventArgs class that contains newly received tensors data
The Pipeline class provides interfaces to create and execute stream pipelines with neural networks.
Node class to handle the properties of NNStreamer pipelines.
NodeInfo class for node information in pipeline. Note that, node is depend on the pipeline. If the pipeline is closed, all the node information is invalid.
SinkNode class to handle the sink node.
SourceNode class to handle the source node.
SwitchNode class to handle the switch node.
ValveNode class to handle the valve node.
The SingleShot class loads a Machine Learning model and make inferences from input data.
An extended EventArgs class that contains the changed state of the pipeline
The TensorsData class sets and gets the buffer data for each Tensor.
The TensorsInfo class manages each Tensor information such as Name, Type and Dimension.
Types of hardware resources to be used for NNFWs. Note that if the affinity (nnn) is not supported by the driver or hardware, it is ignored.
Types of Neural Network Framework.
Node type of NNStreamer pipeline.
States of NNStreamer pipeline.
Possible data element types of Tensor in NNStreamer.