fast::InferenceEngineManager class
#include <FAST/Algorithms/NeuralNetwork/InferenceEngineManager.hpp>

A purely static class to dynamically load inference engines at runtime.

Contents

Public static functions

static auto getEngineList() -> std::vector<std::string>
static void loadAll()
static auto loadEngine(std::string name) -> std::shared_ptr<InferenceEngine>
static auto loadBestAvailableEngine() -> std::shared_ptr<InferenceEngine>
static auto loadBestAvailableEngine(ModelFormat modelFormat) -> std::shared_ptr<InferenceEngine>
static auto isEngineAvailable(std::string name) -> bool