Postprocessor object for PaddleSeg serials model. More...

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

virtual bool	Run (const std::vector< FDTensor > &infer_results, std::vector< SegmentationResult > *results, const std::map< std::string, std::vector< std::array< int, 2 >>> &imgs_info)
	Process the result of runtime and fill to SegmentationResult structure. More...

bool	GetApplySoftmax () const
	Get apply_softmax property of PaddleSeg model, default is false.

void	SetApplySoftmax (bool value)
	Set apply_softmax value, bool type required.

bool	GetStoreScoreMap () const
	Get store_score_map property of PaddleSeg model, default is false.

void	SetStoreScoreMap (bool value)
	Set store_score_map value, bool type required.

Detailed Description

Postprocessor object for PaddleSeg serials model.

Constructor & Destructor Documentation

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

explicit

Create a postprocessor instance for PaddleSeg serials model.

Parameters

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

bool fastdeploy::vision::segmentation::PaddleSegPostprocessor::Run	(	const std::vector< FDTensor > &	infer_results,
		std::vector< SegmentationResult > *	results,
		const std::map< std::string, std::vector< std::array< int, 2 >>> &	imgs_info
	)

virtual

Process the result of runtime and fill to SegmentationResult structure.

Parameters

[in]	tensors	The inference result from runtime
[in]	result	The output result of detection
[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/postprocessor.h
/fastdeploy/my_work/FastDeploy/fastdeploy/vision/segmentation/ppseg/postprocessor.cc