fastdeploy::pipeline::PPOCRv2 Class Reference

PPOCRv2 is used to load PP-OCRv2 series models provided by PaddleOCR. More...

#include <ppocr_v2.h>

Inheritance diagram for fastdeploy::pipeline::PPOCRv2:

Collaboration diagram for fastdeploy::pipeline::PPOCRv2:

Public Member Functions
	PPOCRv2 (fastdeploy::vision::ocr::DBDetector *det_model, fastdeploy::vision::ocr::Classifier *cls_model, fastdeploy::vision::ocr::Recognizer *rec_model)
	Set up the detection model path, classification model path and recognition model path respectively. More...
	PPOCRv2 (fastdeploy::vision::ocr::DBDetector *det_model, fastdeploy::vision::ocr::Recognizer *rec_model)
	Classification model is optional, so this function is set up the detection model path and recognition model path respectively. More...
std::unique_ptr< PPOCRv2 >	Clone () const
	Clone a new PPOCRv2 with less memory usage when multiple instances of the same model are created. More...
virtual bool	Predict (cv::Mat *img, fastdeploy::vision::OCRResult *result)
	Predict the input image and get OCR result. More...
virtual bool	BatchPredict (const std::vector< cv::Mat > &images, std::vector< fastdeploy::vision::OCRResult > *batch_result)
	BatchPredict the input image and get OCR result. More...
bool	Initialized () const override
	Check if the model is initialized successfully.
Public Member Functions inherited from fastdeploy::FastDeployModel
virtual std::string	ModelName () const
	Get model's name.
virtual bool	Infer (std::vector< FDTensor > &input_tensors, std::vector< FDTensor > *output_tensors)
	Inference the model by the runtime. This interface is included in the Predict() function, so we don't call Infer() directly in most common situation.
virtual bool	Infer ()
	Inference the model by the runtime. This interface is using class member reused_input_tensors_ to do inference and writing results to reused_output_tensors_.
virtual int	NumInputsOfRuntime ()
	Get number of inputs for this model.
virtual int	NumOutputsOfRuntime ()
	Get number of outputs for this model.
virtual TensorInfo	InputInfoOfRuntime (int index)
	Get input information for this model.
virtual TensorInfo	OutputInfoOfRuntime (int index)
	Get output information for this model.
virtual void	EnableRecordTimeOfRuntime ()
	This is a debug interface, used to record the time of runtime (backend + h2d + d2h) More...
virtual void	DisableRecordTimeOfRuntime ()
	Disable to record the time of runtime, see EnableRecordTimeOfRuntime() for more detail.
virtual std::map< std::string, float >	PrintStatisInfoOfRuntime ()
	Print the statistic information of runtime in the console, see function EnableRecordTimeOfRuntime() for more detail.
virtual bool	EnabledRecordTimeOfRuntime ()
	Check if the EnableRecordTimeOfRuntime() method is enabled.
virtual double	GetProfileTime ()
	Get profile time of Runtime after the profile process is done.
virtual void	ReleaseReusedBuffer ()
	Release reused input/output buffers.

Additional Inherited Members
Public Attributes inherited from fastdeploy::FastDeployModel
std::vector< Backend >	valid_cpu_backends = {Backend::ORT}
	Model's valid cpu backends. This member defined all the cpu backends have successfully tested for the model.
std::vector< Backend >	valid_gpu_backends = {Backend::ORT}
std::vector< Backend >	valid_ipu_backends = {}
std::vector< Backend >	valid_timvx_backends = {}
std::vector< Backend >	valid_directml_backends = {}
std::vector< Backend >	valid_ascend_backends = {}
std::vector< Backend >	valid_kunlunxin_backends = {}
std::vector< Backend >	valid_rknpu_backends = {}
std::vector< Backend >	valid_sophgonpu_backends = {}

Detailed Description

PPOCRv2 is used to load PP-OCRv2 series models provided by PaddleOCR.

Constructor & Destructor Documentation

PPOCRv2() [1/2]

fastdeploy::pipeline::PPOCRv2::PPOCRv2	(	fastdeploy::vision::ocr::DBDetector *	det_model,
		fastdeploy::vision::ocr::Classifier *	cls_model,
		fastdeploy::vision::ocr::Recognizer *	rec_model
	)

Set up the detection model path, classification model path and recognition model path respectively.

Parameters

[in]	det_model	Path of detection model, e.g ./ch_PP-OCRv2_det_infer
[in]	cls_model	Path of classification model, e.g ./ch_ppocr_mobile_v2.0_cls_infer
[in]	rec_model	Path of recognition model, e.g ./ch_PP-OCRv2_rec_infer

PPOCRv2() [2/2]

fastdeploy::pipeline::PPOCRv2::PPOCRv2	(	fastdeploy::vision::ocr::DBDetector *	det_model,
		fastdeploy::vision::ocr::Recognizer *	rec_model
	)

Classification model is optional, so this function is set up the detection model path and recognition model path respectively.

Parameters

[in]	det_model	Path of detection model, e.g ./ch_PP-OCRv2_det_infer
[in]	rec_model	Path of recognition model, e.g ./ch_PP-OCRv2_rec_infer

Member Function Documentation

BatchPredict()

bool fastdeploy::pipeline::PPOCRv2::BatchPredict ( const std::vector< cv::Mat > &  images, std::vector< fastdeploy::vision::OCRResult > *  batch_result  )

virtual

BatchPredict the input image and get OCR result.

Parameters

[in]	images	The list of input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format.
[in]	batch_result	The output list of OCR result will be writen to this structure.

Returns

true if the prediction successed, otherwise false.

Clone()

std::unique_ptr< PPOCRv2 > fastdeploy::pipeline::PPOCRv2::Clone

(

)

const

Clone a new PPOCRv2 with less memory usage when multiple instances of the same model are created.

Returns

new PPOCRv2* type unique pointer

Predict()

bool fastdeploy::pipeline::PPOCRv2::Predict ( cv::Mat *  img, fastdeploy::vision::OCRResult *  result  )

virtual

Predict the input image and get OCR result.

Parameters

[in]	im	The input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format.
[in]	result	The output OCR result will be writen to this structure.

Returns

true if the prediction successed, otherwise false.

---

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

• /fastdeploy/my_work/FastDeploy/fastdeploy/vision/ocr/ppocr/ppocr_v2.h
• /fastdeploy/my_work/FastDeploy/fastdeploy/vision/ocr/ppocr/ppocr_v2.cc