Recognizer object is used to load the recognition model provided by PaddleOCR. More...

#include <recognizer.h>

Inheritance diagram for fastdeploy::vision::ocr::Recognizer:

Collaboration diagram for fastdeploy::vision::ocr::Recognizer:

[legend]

Public Member Functions
	Recognizer (const std::string &model_file, const std::string &params_file="", const std::string &label_path="", const RuntimeOption &custom_option=RuntimeOption(), const ModelFormat &model_format=ModelFormat::PADDLE)
	Set path of model file, and the configuration of runtime. More...

std::string	ModelName () const
	Get model's name.

virtual std::unique_ptr< Recognizer >	Clone () const
	Clone a new Recognizer with less memory usage when multiple instances of the same model are created. More...

virtual bool	Predict (const cv::Mat &img, std::string text, float rec_score)
	Predict the input image and get OCR recognition model result. More...

virtual bool	Predict (const cv::Mat &img, vision::OCRResult *ocr_result)
	Predict the input image and get OCR recognition model result. More...

virtual bool	BatchPredict (const std::vector< cv::Mat > &images, vision::OCRResult *ocr_result)
	BatchPredict the input image and get OCR recognition model result. More...

virtual bool	BatchPredict (const std::vector< cv::Mat > &images, std::vector< std::string > texts, std::vector< float > rec_scores)
	BatchPredict the input image and get OCR recognition model result. More...

virtual RecognizerPreprocessor &	GetPreprocessor ()
	Get preprocessor reference of DBDetectorPreprocessor.

virtual RecognizerPostprocessor &	GetPostprocessor ()
	Get postprocessor reference of DBDetectorPostprocessor.

Public Member Functions inherited from fastdeploy::FastDeployModel
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 bool	Initialized () const
	Check if the model is initialized successfully.

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

Recognizer object is used to load the recognition model provided by PaddleOCR.

Constructor & Destructor Documentation

◆ Recognizer()

fastdeploy::vision::ocr::Recognizer::Recognizer	(	const std::string &	model_file,
		const std::string &	params_file = `""`,
		const std::string &	label_path = `""`,
		const RuntimeOption &	custom_option = `RuntimeOption()`,
		const ModelFormat &	model_format = `ModelFormat::PADDLE`
	)

Set path of model file, and the configuration of runtime.

Parameters

[in]	model_file	Path of model file, e.g ./ch_PP-OCRv3_rec_infer/model.pdmodel.
[in]	params_file	Path of parameter file, e.g ./ch_PP-OCRv3_rec_infer/model.pdiparams, if the model format is ONNX, this parameter will be ignored.
[in]	label_path	Path of label file used by OCR recognition model. e.g ./ppocr_keys_v1.txt
[in]	custom_option	RuntimeOption for inference, the default will use cpu, and choose the backend defined in `valid_cpu_backends`.
[in]	model_format	Model format of the loaded model, default is Paddle format.

Member Function Documentation

◆ BatchPredict() [1/2]

bool fastdeploy::vision::ocr::Recognizer::BatchPredict	(	const std::vector< cv::Mat > &	images,
		vision::OCRResult *	ocr_result
	)

virtual

BatchPredict the input image and get OCR recognition model 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]	ocr_result	The output of OCR recognition model result will be writen to this structure.

Returns: true if the prediction is successed, otherwise false.

◆ BatchPredict() [2/2]

bool fastdeploy::vision::ocr::Recognizer::BatchPredict	(	const std::vector< cv::Mat > &	images,
		std::vector< std::string > *	texts,
		std::vector< float > *	rec_scores
	)

virtual

BatchPredict the input image and get OCR recognition model 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]	texts	The list of text results of rec model will be written into this vector.
[in]	rec_scores	The list of sccore result of rec model will be written into this vector.

Returns: true if the prediction is successed, otherwise false.

◆ Clone()

std::unique_ptr< Recognizer > fastdeploy::vision::ocr::Recognizer::Clone ( ) const

virtual

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

Returns: new Recognizer* type unique pointer

◆ Predict() [1/2]

bool fastdeploy::vision::ocr::Recognizer::Predict	(	const cv::Mat &	img,
		std::string *	text,
		float *	rec_score
	)

virtual

Predict the input image and get OCR recognition model result.

Parameters

[in]	img	The input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format.
[in]	text	The text result of rec model will be written into this parameter.
[in]	rec_score	The sccore result of rec model will be written into this parameter.

Returns: true if the prediction is successed, otherwise false.

◆ Predict() [2/2]

bool fastdeploy::vision::ocr::Recognizer::Predict	(	const cv::Mat &	img,
		vision::OCRResult *	ocr_result
	)

virtual

Predict the input image and get OCR recognition model result.

Parameters

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

Returns: true if the prediction is successed, otherwise false.

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

/fastdeploy/my_work/FastDeploy/fastdeploy/vision/ocr/ppocr/recognizer.h
/fastdeploy/my_work/FastDeploy/fastdeploy/vision/ocr/ppocr/recognizer.cc

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ Recognizer()

Member Function Documentation

◆ BatchPredict() [1/2]

◆ BatchPredict() [2/2]

◆ Clone()

◆ Predict() [1/2]

◆ Predict() [2/2]