PIPNet model object used when to load a PIPNet model exported by PIPNet. More...

#include <pipnet.h>

Inheritance diagram for fastdeploy::vision::facealign::PIPNet:

Collaboration diagram for fastdeploy::vision::facealign::PIPNet:

[legend]

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

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

virtual bool	Predict (cv::Mat im, FaceAlignmentResult result)
	Predict the face detection result for an input image. More...

int	GetNumLandmarks ()
	Get the number of landmakrs. More...

std::vector< float >	GetMeanVals ()
	Get the mean values for normalization. More...

std::vector< float >	GetStdVals ()
	Get the std values for normalization. More...

std::vector< int >	GetSize ()
	Get the input size of image. More...

void	SetNumLandmarks (const int &num_landmarks)
	Set the number of landmarks. More...

void	SetMeanVals (const std::vector< float > &mean_vals)
	Set the mean values for normalization. More...

void	SetStdVals (const std::vector< float > &std_vals)
	Set the std values for normalization. More...

void	SetSize (const std::vector< int > &size)
	Set the input size of image. More...

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

PIPNet model object used when to load a PIPNet model exported by PIPNet.

Constructor & Destructor Documentation

◆ PIPNet()

fastdeploy::vision::facealign::PIPNet::PIPNet	(	const std::string &	model_file,
		const std::string &	params_file = `""`,
		const RuntimeOption &	custom_option = `RuntimeOption()`,
		const ModelFormat &	model_format = `ModelFormat::ONNX`
	)

Set path of model file and the configuration of runtime.

Parameters

[in]	model_file	Path of model file, e.g ./pipnet.onnx
[in]	params_file	Path of parameter file, e.g ppyoloe/model.pdiparams, if the model format is ONNX, this parameter will be ignored
[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 ONNX format

Member Function Documentation

◆ GetMeanVals()

std::vector<float> fastdeploy::vision::facealign::PIPNet::GetMeanVals ( )

inline

Get the mean values for normalization.

Returns: Vector of float values, default mean_vals = {0.485f, 0.456f, 0.406f}

◆ GetNumLandmarks()

int fastdeploy::vision::facealign::PIPNet::GetNumLandmarks ( )

inline

Get the number of landmakrs.

Returns: Integer type, default num_landmarks = 19

◆ GetSize()

std::vector<int> fastdeploy::vision::facealign::PIPNet::GetSize ( )

inline

Get the input size of image.

Returns: Vector of int values, default {256, 256}

◆ GetStdVals()

std::vector<float> fastdeploy::vision::facealign::PIPNet::GetStdVals ( )

inline

Get the std values for normalization.

Returns: Vector of float values, default std_vals = {0.229f, 0.224f, 0.225f}

◆ Predict()

bool fastdeploy::vision::facealign::PIPNet::Predict	(	cv::Mat *	im,
		FaceAlignmentResult *	result
	)

virtual

Predict the face detection result for an input image.

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 face detection result will be writen to this structure

Returns: true if the prediction successed, otherwise false

◆ SetMeanVals()

void fastdeploy::vision::facealign::PIPNet::SetMeanVals ( const std::vector< float > & mean_vals )

inline

Set the mean values for normalization.

Parameters

[in] mean_vals Vector of float values whose length is equal to 3

◆ SetNumLandmarks()

void fastdeploy::vision::facealign::PIPNet::SetNumLandmarks ( const int & num_landmarks )

Set the number of landmarks.

Parameters

[in] num_landmarks Integer value which represents number of landmarks

◆ SetSize()

void fastdeploy::vision::facealign::PIPNet::SetSize ( const std::vector< int > & size )

inline

Set the input size of image.

Parameters

[in] size Vector of int values which represents {width, height} of image

◆ SetStdVals()

void fastdeploy::vision::facealign::PIPNet::SetStdVals ( const std::vector< float > & std_vals )

inline

Set the std values for normalization.

Parameters

[in] std_vals Vector of float values whose length is equal to 3

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

/fastdeploy/my_work/FastDeploy/fastdeploy/vision/facealign/contrib/pipnet.h
/fastdeploy/my_work/FastDeploy/fastdeploy/vision/facealign/contrib/pipnet.cc

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ PIPNet()

Member Function Documentation

◆ GetMeanVals()

◆ GetNumLandmarks()

◆ GetSize()

◆ GetStdVals()

◆ Predict()

◆ SetMeanVals()

◆ SetNumLandmarks()

◆ SetSize()

◆ SetStdVals()