nvdsinferserver::TritonGrpcRequest Class Reference

Detailed Description

Triton gRPC inference request class holding data associated with one inference request.

Definition at line 55 of file infer_grpc_client.h.

Public Member Functions
	~TritonGrpcRequest ()
	Destructor, free the host memory allocated for the request. More...
NvDsInferStatus	appendInput (const std::shared_ptr< tc::InferInput > &input)
	Append the array of Triton client library inference input objects. More...
void	attachData (void *data)
	Append the array of host memory allocations. More...
void	attachInputCudaBuffer (std::string bufName)
	Append the list of shared CUDA input buffers. More...
NvDsInferStatus	setOutput (const std::vector< std::shared_ptr< tc::InferRequestedOutput >> &output)
	Helper functions to access the member variables. More...
NvDsInferStatus	setOption (std::shared_ptr< tc::InferOptions > &option)
std::vector< std::shared_ptr< tc::InferInput > >	inputs ()
std::vector< std::shared_ptr< tc::InferRequestedOutput > >	outputs ()
std::shared_ptr< tc::InferOptions >	getOption ()
SharedIBatchArray	inputBatchArray ()
void	setInputBatchArray (SharedIBatchArray inputBatch)
std::vector< std::string >	getOutNames ()
std::vector< std::string >	getInputCudaBufNames ()
void	setOutNames (std::vector< std::string > outnames)

Constructor & Destructor Documentation

~TritonGrpcRequest()

nvdsinferserver::TritonGrpcRequest::~TritonGrpcRequest

(

)

Destructor, free the host memory allocated for the request.

Member Function Documentation

appendInput()

NvDsInferStatus nvdsinferserver::TritonGrpcRequest::appendInput

(

const std::shared_ptr< tc::InferInput > &

input

)

Append the array of Triton client library inference input objects.

attachData()

void nvdsinferserver::TritonGrpcRequest::attachData ( void *  data )

inline

Append the array of host memory allocations.

Definition at line 84 of file infer_grpc_client.h.

attachInputCudaBuffer()

void nvdsinferserver::TritonGrpcRequest::attachInputCudaBuffer ( std::string  bufName )

inline

Append the list of shared CUDA input buffers.

Definition at line 91 of file infer_grpc_client.h.

getInputCudaBufNames()

std::vector<std::string> nvdsinferserver::TritonGrpcRequest::getInputCudaBufNames ( )

inline

Definition at line 77 of file infer_grpc_client.h.

getOption()

std::shared_ptr<tc::InferOptions> nvdsinferserver::TritonGrpcRequest::getOption ( )

inline

Definition at line 73 of file infer_grpc_client.h.

getOutNames()

std::vector<std::string> nvdsinferserver::TritonGrpcRequest::getOutNames ( )

inline

Definition at line 76 of file infer_grpc_client.h.

inputBatchArray()

SharedIBatchArray nvdsinferserver::TritonGrpcRequest::inputBatchArray ( )

inline

Definition at line 74 of file infer_grpc_client.h.

inputs()

std::vector<std::shared_ptr<tc::InferInput> > nvdsinferserver::TritonGrpcRequest::inputs ( )

inline

Definition at line 71 of file infer_grpc_client.h.

outputs()

std::vector<std::shared_ptr<tc::InferRequestedOutput> > nvdsinferserver::TritonGrpcRequest::outputs ( )

inline

Definition at line 72 of file infer_grpc_client.h.

setInputBatchArray()

void nvdsinferserver::TritonGrpcRequest::setInputBatchArray ( SharedIBatchArray  inputBatch )

inline

Definition at line 75 of file infer_grpc_client.h.

setOption()

NvDsInferStatus nvdsinferserver::TritonGrpcRequest::setOption

(

std::shared_ptr< tc::InferOptions > &

option

)

setOutNames()

void nvdsinferserver::TritonGrpcRequest::setOutNames ( std::vector< std::string >  outnames )

inline

Definition at line 78 of file infer_grpc_client.h.

setOutput()

NvDsInferStatus nvdsinferserver::TritonGrpcRequest::setOutput

(

const std::vector< std::shared_ptr< tc::InferRequestedOutput >> &

output

)

Helper functions to access the member variables.

---

The documentation for this class was generated from the following file:

• infer_grpc_client.h