generated from zhangwei/Matrixai
49 lines
1.9 KiB
C
49 lines
1.9 KiB
C
|
#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
|