fastdeploy::vision::ocr::DBDetectorPreprocessor Class Reference

Preprocessor object for DBDetector serials model. More...

#include <det_preprocessor.h>

Inheritance diagram for fastdeploy::vision::ocr::DBDetectorPreprocessor:

Collaboration diagram for fastdeploy::vision::ocr::DBDetectorPreprocessor:

Public Member Functions
virtual bool	Apply (FDMatBatch *image_batch, std::vector< FDTensor > *outputs)
	Process the input image and prepare input tensors for runtime. More...
void	SetMaxSideLen (int max_side_len)
	Set max_side_len for the detection preprocess, default is 960.
int	GetMaxSideLen () const
	Get max_side_len of the detection preprocess.
void	SetNormalize (const std::vector< float > &mean, const std::vector< float > &std, bool is_scale)
const std::vector< std::array< int, 4 > > *	GetBatchImgInfo ()
void	DisableNormalize ()
	This function will disable normalize in preprocessing step.
void	DisablePermute ()
	This function will disable hwc2chw in preprocessing step.
void	SetDetImageShape (const std::vector< int > &det_image_shape)
std::vector< int >	GetDetImageShape () const
	Get cls_image_shape for the classification preprocess.
void	SetStaticShapeInfer (bool static_shape_infer)
bool	GetStaticShapeInfer () const
	Get static_shape_infer of the recognition preprocess.
Public Member Functions inherited from fastdeploy::vision::ProcessorManager
void	UseCuda (bool enable_cv_cuda=false, int gpu_id=-1)
	Use CUDA to boost the performance of processors. More...
bool	Run (std::vector< FDMat > *images, std::vector< FDTensor > *outputs)
	Process the input images and prepare input tensors for runtime. More...

Detailed Description

Preprocessor object for DBDetector serials model.

Member Function Documentation

Apply()

bool fastdeploy::vision::ocr::DBDetectorPreprocessor::Apply ( FDMatBatch *  image_batch, std::vector< FDTensor > *  outputs  )

virtual

Process the input image and prepare input tensors for runtime.

Parameters

[in]	image_batch	The input image batch
[in]	outputs	The output tensors which will feed in runtime

Returns

true if the preprocess successed, otherwise false

Implements fastdeploy::vision::ProcessorManager.

GetBatchImgInfo()

const std::vector<std::array<int, 4> >* fastdeploy::vision::ocr::DBDetectorPreprocessor::GetBatchImgInfo ( )

inline

Get the image info of the last batch, return a list of array {image width, image height, resize width, resize height}

SetDetImageShape()

void fastdeploy::vision::ocr::DBDetectorPreprocessor::SetDetImageShape ( const std::vector< int > &  det_image_shape )

inline

Set det_image_shape for the detection preprocess. This api is usually used when you retrain the model. Generally, you do not need to use it.

SetNormalize()

void fastdeploy::vision::ocr::DBDetectorPreprocessor::SetNormalize ( const std::vector< float > &  mean, const std::vector< float > &  std, bool  is_scale  )

inline

Set preprocess normalize parameters, please call this API to customize the normalize parameters, otherwise it will use the default normalize parameters.

SetStaticShapeInfer()

void fastdeploy::vision::ocr::DBDetectorPreprocessor::SetStaticShapeInfer ( bool  static_shape_infer )

inline

Set static_shape_infer is true or not. When deploy PP-OCR on hardware which can not support dynamic input shape very well, like Huawei Ascned, static_shape_infer needs to to be true.

---

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

• /fastdeploy/my_work/FastDeploy/fastdeploy/vision/ocr/ppocr/det_preprocessor.h
• /fastdeploy/my_work/FastDeploy/fastdeploy/vision/ocr/ppocr/det_preprocessor.cc