Preprocessor object for PaddleSeg serials model. More...

Public Member Functions
	PaddleSegPreprocessor (const std::string &config_file)
	Create a preprocessor instance for PaddleSeg serials model. More...

virtual bool	Run (std::vector< FDMat > images, std::vector< FDTensor > outputs, std::map< std::string, std::vector< std::array< int, 2 >>> *imgs_info)
	Process the input image and prepare input tensors for runtime. More...

bool	GetIsVerticalScreen () const
	Get is_vertical_screen property of PP-HumanSeg model, default is false.

void	SetIsVerticalScreen (bool value)
	Set is_vertical_screen value, bool type required.

void	DisableNormalize ()
	This function will disable normalize in preprocessing step.

void	DisablePermute ()
	This function will disable hwc2chw in preprocessing step.

Detailed Description

Preprocessor object for PaddleSeg serials model.

Constructor & Destructor Documentation

fastdeploy::vision::segmentation::PaddleSegPreprocessor::PaddleSegPreprocessor ( const std::string & config_file )

explicit

Create a preprocessor instance for PaddleSeg serials model.

Parameters

[in] config_file Path of configuration file for deployment, e.g ppliteseg/deploy.yaml

bool fastdeploy::vision::segmentation::PaddleSegPreprocessor::Run	(	std::vector< FDMat > *	images,
		std::vector< FDTensor > *	outputs,
		std::map< std::string, std::vector< std::array< int, 2 >>> *	imgs_info
	)

virtual

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]	imgs_info	The original input images shape info map, key is "shape_info", value is vector<array<int, 2>> a{{height, width}}

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

/fastdeploy/my_work/FastDeploy/fastdeploy/vision/segmentation/ppseg/preprocessor.h
/fastdeploy/my_work/FastDeploy/fastdeploy/vision/segmentation/ppseg/preprocessor.cc