NVIDIA DeepStream SDK API Reference4.0 Release |
Defines an API for importing Transfer Learning Toolkit encoded models.
Functions | |
bool | NvDsInferCudaEngineGetFromTltModel (nvinfer1::IBuilder *builder, NvDsInferContextInitParams *initParams, nvinfer1::DataType dataType, nvinfer1::ICudaEngine *&cudaEngine) |
API to decode and create CUDA engine file from a TLT encoded model. More... | |
bool NvDsInferCudaEngineGetFromTltModel | ( | nvinfer1::IBuilder * | builder, |
NvDsInferContextInitParams * | initParams, | ||
nvinfer1::DataType | dataType, | ||
nvinfer1::ICudaEngine *& | cudaEngine | ||
) |
API to decode and create CUDA engine file from a TLT encoded model.
This API is an implmentation of NvDsInferCudaEngineGet
interface. The correct key and model path should be provided in the tltModelKey
and tltEncodedModelFilePath
members of initParams
. Other parameters applicable to UFF models also apply to TLT encoded models.