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

Microsofts ONNX Runtime inference engine with DirectX/ML support.

Contents

This inferene engine is windows only.

Base classes

class InferenceEngine

Constructors, destructors, conversion operators

~ONNXRuntimeEngine() override
ONNXRuntimeEngine()

Public functions

void run() override
void load() override
auto getPreferredImageOrdering() const -> ImageOrdering override
auto getName() const -> std::string override
auto getSupportedModelFormats() const -> std::vector<ModelFormat> virtual
auto getPreferredModelFormat() const -> ModelFormat virtual
void setMaxBatchSize(int maxBathSize) virtual
auto getMaxBatchSize() const -> int
auto getDeviceList() -> std::vector<InferenceDeviceInfo> override

Function documentation

std::vector<InferenceDeviceInfo> fast::ONNXRuntimeEngine::getDeviceList() override

Returns vector with info on each device

Get a list of devices available for this inference engine.