fast::FlowNetwork class

A neural network for optical flow estimation.

A neural network which takes a sequence of images as input, and then outputs a flow/displacement vector field. This can be a flow network which estimates the motion between two frames.

Base classes

class NeuralNetwork
Neural network process object.

Public functions

auto create(std::string modelFilename, float scaleFactor, float meanIntensity, float stanardDeviationIntensity, std::vector<NeuralNetworkNode> inputNodes, std::vector<NeuralNetworkNode> outputNodes, std::string inferenceEngine, std::vector<std::string> customPlugins) FAST_CONSTRUCTOR(FlowNetwork -> std::shared_ptr<FlowNetwork>
void execute() override

Public variables

modelFilename
inputNodes
outputNodes
inferenceEngine
customPlugins