PPTinyPose model object used when to load a PPTinyPose model exported by PaddleDetection. More...

#include <pptinypose.h>

Inheritance diagram for fastdeploy::vision::keypointdetection::PPTinyPose:

Collaboration diagram for fastdeploy::vision::keypointdetection::PPTinyPose:

[legend]

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

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

bool	Predict (cv::Mat im, KeyPointDetectionResult result)
	Predict the keypoint detection result for an input image. More...

bool	Predict (cv::Mat im, KeyPointDetectionResult result, const DetectionResult &detection_result)
	Predict the keypoint detection result with given detection result for an input image. More...

void	DisableNormalize ()
	This function will disable normalize in preprocessing step.

void	DisablePermute ()
	This function will disable hwc2chw in preprocessing step.

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.

Public Attributes
bool	use_dark = true
	Whether using Distribution-Aware Coordinate Representation for Human Pose Estimation(DARK for short) in postprocess, default is true.

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

PPTinyPose model object used when to load a PPTinyPose model exported by PaddleDetection.

Constructor & Destructor Documentation

◆ PPTinyPose()

fastdeploy::vision::keypointdetection::PPTinyPose::PPTinyPose	(	const std::string &	model_file,
		const std::string &	params_file,
		const std::string &	config_file,
		const RuntimeOption &	custom_option = `RuntimeOption()`,
		const ModelFormat &	model_format = `ModelFormat::PADDLE`
	)

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

Parameters

[in]	model_file	Path of model file, e.g pptinypose/model.pdmodel
[in]	params_file	Path of parameter file, e.g pptinypose/model.pdiparams, if the model format is ONNX, this parameter will be ignored
[in]	config_file	Path of configuration file for deployment, e.g pptinypose/infer_cfg.yml
[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

◆ Predict() [1/2]

bool fastdeploy::vision::keypointdetection::PPTinyPose::Predict	(	cv::Mat *	im,
		KeyPointDetectionResult *	result
	)

Predict the keypoint detection result for an input image.

Parameters

[in]	im	The input image data, comes from cv::imread()
[in]	result	The output keypoint detection result will be writen to this structure

Returns: true if the keypoint prediction successed, otherwise false

◆ Predict() [2/2]

bool fastdeploy::vision::keypointdetection::PPTinyPose::Predict	(	cv::Mat *	im,
		KeyPointDetectionResult *	result,
		const DetectionResult &	detection_result
	)

Predict the keypoint detection result with given detection result for an input image.

Parameters

[in]	im	The input image data, comes from cv::imread()
[in]	result	The output keypoint detection result will be writen to this structure
[in]	detection_result	The structure strores pedestrian detection result, which is used to crop image for multi-persons keypoint detection

Returns: true if the keypoint prediction successed, otherwise false

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

/fastdeploy/my_work/FastDeploy/fastdeploy/vision/keypointdet/pptinypose/pptinypose.h
/fastdeploy/my_work/FastDeploy/fastdeploy/vision/keypointdet/pptinypose/pptinypose.cc

Public Member Functions

Public Attributes

Detailed Description

Constructor & Destructor Documentation

◆ PPTinyPose()

Member Function Documentation

◆ Predict() [1/2]

◆ Predict() [2/2]