Preprocessor object for YOLOv5 serials model. More...

Public Member Functions
	RKYOLOPreprocessor ()
	Create a preprocessor instance for YOLOv5 serials model.

bool	Run (std::vector< FDMat > images, std::vector< FDTensor > outputs)
	Process the input image and prepare input tensors for runtime. More...

void	SetSize (const std::vector< int > &size)
	Set target size, tuple of (width, height), default size = {640, 640}.

std::vector< int >	GetSize () const
	Get target size, tuple of (width, height), default size = {640, 640}.

void	SetPaddingValue (const std::vector< float > &padding_value)
	Set padding value, size should be the same as channels.

std::vector< float >	GetPaddingValue () const
	Get padding value, size should be the same as channels.

void	SetScaleUp (bool is_scale_up)

bool	GetScaleUp () const
	Get is_scale_up, default true.

Detailed Description

Preprocessor object for YOLOv5 serials model.

Member Function Documentation

bool fastdeploy::vision::detection::RKYOLOPreprocessor::Run	(	std::vector< FDMat > *	images,
		std::vector< FDTensor > *	outputs
	)

Process the input image and prepare input tensors for runtime.

Parameters

[in]	images	The input image data list, all the elements are returned by cv::imread()
[in]	outputs	The output tensors which will feed in runtime
[in]	ims_info	The shape info list, record input_shape and output_shape

void fastdeploy::vision::detection::RKYOLOPreprocessor::SetScaleUp ( bool is_scale_up )

inline

Set is_scale_up, if is_scale_up is false, the input image only can be zoom out, the maximum resize scale cannot exceed 1.0, default true

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

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