|
|
NVIDIA DeepStream SDK API Reference
|
8.0 Release
|
Go to the documentation of this file.
13 #ifndef __NVDSINFERSERVER_CUSTOM_PROCESSOR_H__
14 #define __NVDSINFERSERVER_CUSTOM_PROCESSOR_H__
18 #include <condition_variable>
75 const std::vector<IBatchBuffer*>& primaryInputs, std::vector<IBatchBuffer*>& extraInputs,
114 const char* config, uint32_t configLen);
Interface of Custom processor which is created and loaded at runtime through CreateCustomProcessorFun...
This is a header file for pre-processing cuda kernels with normalization and mean subtraction require...
virtual NvDsInferStatus inferenceDone(const IBatchArray *outputs, const IOptions *inOptions)=0
Inference done callback for custom postpocessing.
virtual bool requireInferLoop() const
Indicate whether this custom processor requires inference loop, in which nvdsinferserver lib guarante...
virtual void notifyError(NvDsInferStatus status)=0
Notification of an error to the interface implementation.
virtual void supportInputMemType(InferMemType &type)
Query the memory type, extraInputProcess() implementation supports.
Header file for the data types used in the inference processing.
InferMemType
The memory types of inference buffers.
virtual ~IInferCustomProcessor()=default
IInferCustomProcessor will be deleted by nvdsinferserver lib.
Interface class for an array of batch buffers.
virtual NvDsInferStatus extraInputProcess(const std::vector< IBatchBuffer * > &primaryInputs, std::vector< IBatchBuffer * > &extraInputs, const IOptions *options)=0
Custom processor for extra input data.
NvDsInferStatus
Enum for the status codes returned by NvDsInferContext.