VCarContainer/tools/yolov5/include/inference.h

49 lines
1.9 KiB
C
Raw Normal View History

2024-11-24 00:58:06 +00:00
#ifndef _INFERENCE_H
#define _INFERENCE_H
#include "AppCommon.h"
#define ENABLE_CUDA_PREPROCESS
class Inference
{
public:
Inference();
~Inference();
ICudaEngine* build_engine_onnx(Logger gLogger, unsigned int maxBatchSize, unsigned int maxWorkSpaceSize, IBuilder* builder, IBuilderConfig* config, std::string& source_onnx);
void APIToModel(Logger gLogger, unsigned int maxBatchSize, unsigned int maxWorkSpaceSize, IHostMemory** modelStream, std::string& onnx_model_name);
void doInference(IExecutionContext& context, cudaStream_t& stream, void **buffers, unsigned int inputIndex, float* input, int inputSize,
unsigned int ouputIndex, float* output, int outputSize, int batchSize);
void doInferenceV2(IExecutionContext& context, cudaStream_t& stream, void **buffers, unsigned int ouputIndex, float* output, int outputSize, int batchSize);
void doInferenceV3(IExecutionContext& context, cudaStream_t& stream, void **buffers, unsigned int inputIndex, float* input, int inputSize,
unsigned int ouputIndex, float* output, int outputSize, int batchSize);
void doInferenceV4(IExecutionContext& context, cudaStream_t& stream, void **buffers, unsigned int ouputIndex, float* output, int outputSize, int batchSize);
float* pfBuffers_[2];
float* pfInputData_ = nullptr;
float* pfOutputData_ = nullptr;
uint8_t* pu8ImgHost_ = nullptr; //相关内存分配
uint8_t* pu8ImgDevice_ = nullptr;
unsigned int uiInputIndex_ = 0, uiOutputIndex_ = 0;
cudaStream_t* pImagePreprocessStream_ = nullptr; //图像预处理CUDA流
cudaStream_t* pInferenceModelStream_ = nullptr; //模型推理CUDA流
Logger* pGLogger_ = nullptr;
IRuntime* pRuntime_ = nullptr;
ICudaEngine* pEngine_ = nullptr;
IExecutionContext* pContext_ = nullptr;
private:
};
#endif //END OF _INFERENCE_H