![]() |
Project
|
A header library for loading ONNX models and inferencing them on CPU and GPU. More...
#include "ML/OrtInterface.h"
#include "ML/3rdparty/GPUORTFloat16.h"
#include <onnxruntime_cxx_api.h>
Go to the source code of this file.
Classes | |
struct | o2::ml::OrtModel::OrtVariables |
Namespaces | |
namespace | o2 |
a couple of static helper functions to create timestamp values for CCDB queries or override obsolete objects | |
namespace | o2::ml |
Functions | |
template<> | |
std::vector< float > | o2::ml::OrtModel::inference< OrtDataType::Float16_t, float > (std::vector< OrtDataType::Float16_t > &input) |
template<> | |
std::vector< OrtDataType::Float16_t > | o2::ml::OrtModel::inference< OrtDataType::Float16_t, OrtDataType::Float16_t > (std::vector< OrtDataType::Float16_t > &input) |
template<> | |
std::vector< OrtDataType::Float16_t > | o2::ml::OrtModel::inference< float, OrtDataType::Float16_t > (std::vector< float > &input) |
template<> | |
std::vector< OrtDataType::Float16_t > | o2::ml::OrtModel::inference< OrtDataType::Float16_t, OrtDataType::Float16_t > (std::vector< std::vector< OrtDataType::Float16_t > > &input) |
A header library for loading ONNX models and inferencing them on CPU and GPU.
Definition in file OrtInterface.cxx.