Postprocessor object for YOLOv5 serials model. More...

Public Member Functions
	RKYOLOPostprocessor ()
	Create a postprocessor instance for YOLOv5 serials model.

bool	Run (const std::vector< FDTensor > &tensors, std::vector< DetectionResult > *results)
	Process the result of runtime and fill to DetectionResult structure. More...

void	SetNMSThreshold (float nms_threshold)
	Set nms_threshold, default 0.45.

void	SetConfThreshold (float conf_threshold)
	Set conf_threshold, default 0.25.

float	GetConfThreshold () const
	Get conf_threshold, default 0.25.

float	GetNMSThreshold () const
	Get nms_threshold, default 0.45.

void	SetHeightAndWeight (int height, int width)
	Set height and weight.

void	SetPadHWValues (const std::vector< std::vector< int >> &pad_hw_values)
	Set pad_hw_values.

void	SetScale (const std::vector< float > &scale)
	Set scale.

void	SetAnchor (const std::vector< int > &anchors, int anchor_per_branch)
	Set Anchor.

void	SetClassNum (int num)
	Set the number of class.

int	GetClassNum ()
	Get the number of class.

Detailed Description

Postprocessor object for YOLOv5 serials model.

Member Function Documentation

bool fastdeploy::vision::detection::RKYOLOPostprocessor::Run	(	const std::vector< FDTensor > &	tensors,
		std::vector< DetectionResult > *	results
	)

Process the result of runtime and fill to DetectionResult structure.

Parameters

[in]	tensors	The inference result from runtime
[in]	result	The output result of detection
[in]	ims_info	The shape info list, record input_shape and output_shape

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

/fastdeploy/my_work/FastDeploy/fastdeploy/vision/detection/contrib/rknpu2/postprocessor.h
/fastdeploy/my_work/FastDeploy/fastdeploy/vision/detection/contrib/rknpu2/postprocessor.cc