PaddleClas serials model object used when to load a PaddleClas model exported by PaddleClas repository. More...

#include <model.h>

Inheritance diagram for fastdeploy::vision::classification::PaddleClasModel:

Collaboration diagram for fastdeploy::vision::classification::PaddleClasModel:

[legend]

Public Member Functions
	PaddleClasModel (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...

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

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

virtual bool	Predict (cv::Mat im, ClassifyResult result, int topk=1)
	DEPRECATED Predict the classification result for an input image, remove at 1.0 version. More...

virtual bool	Predict (const cv::Mat &img, ClassifyResult *result)
	Predict the classification result for an input image. More...

virtual bool	BatchPredict (const std::vector< cv::Mat > &imgs, std::vector< ClassifyResult > *results)
	Predict the classification results for a batch of input images. More...

virtual bool	Predict (const FDMat &mat, ClassifyResult *result)
	Predict the classification result for an input image. More...

virtual bool	BatchPredict (const std::vector< FDMat > &mats, std::vector< ClassifyResult > *results)
	Predict the classification results for a batch of input images. More...

virtual PaddleClasPreprocessor &	GetPreprocessor ()
	Get preprocessor reference of PaddleClasModel.

virtual PaddleClasPostprocessor &	GetPostprocessor ()
	Get postprocessor reference of PaddleClasModel.

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

PaddleClas serials model object used when to load a PaddleClas model exported by PaddleClas repository.

Constructor & Destructor Documentation

◆ PaddleClasModel()

fastdeploy::vision::classification::PaddleClasModel::PaddleClasModel	(	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 resnet/model.pdmodel
[in]	params_file	Path of parameter file, e.g resnet/model.pdiparams, if the model format is ONNX, this parameter will be ignored
[in]	config_file	Path of configuration file for deployment, e.g resnet/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

◆ BatchPredict() [1/2]

bool fastdeploy::vision::classification::PaddleClasModel::BatchPredict	(	const std::vector< cv::Mat > &	imgs,
		std::vector< ClassifyResult > *	results
	)

virtual

Predict the classification results for a batch of input images.

Parameters

[in]	imgs,The	input image list, each element comes from cv::imread()
[in]	results	The output classification result list

Returns: true if the prediction successed, otherwise false

◆ BatchPredict() [2/2]

bool fastdeploy::vision::classification::PaddleClasModel::BatchPredict	(	const std::vector< FDMat > &	mats,
		std::vector< ClassifyResult > *	results
	)

virtual

Predict the classification results for a batch of input images.

Parameters

[in]	mats,The	input mat list
[in]	results	The output classification result list

Returns: true if the prediction successed, otherwise false

◆ Clone()

std::unique_ptr< PaddleClasModel > fastdeploy::vision::classification::PaddleClasModel::Clone ( ) const

virtual

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

Returns: new PaddleClasModel* type unique pointer

◆ Predict() [1/3]

bool fastdeploy::vision::classification::PaddleClasModel::Predict	(	cv::Mat *	im,
		ClassifyResult *	result,
		int	topk = `1`
	)

virtual

DEPRECATED Predict the classification result for an input image, remove at 1.0 version.

Parameters

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

Returns: true if the prediction successed, otherwise false

◆ Predict() [2/3]

bool fastdeploy::vision::classification::PaddleClasModel::Predict	(	const cv::Mat &	img,
		ClassifyResult *	result
	)

virtual

Predict the classification result for an input image.

Parameters

[in]	img	The input image data, comes from cv::imread()
[in]	result	The output classification result

Returns: true if the prediction successed, otherwise false

◆ Predict() [3/3]

bool fastdeploy::vision::classification::PaddleClasModel::Predict	(	const FDMat &	mat,
		ClassifyResult *	result
	)

virtual

Predict the classification result for an input image.

Parameters

[in]	mat	The input mat
[in]	result	The output classification result

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/classification/ppcls/model.h
/fastdeploy/my_work/FastDeploy/fastdeploy/vision/classification/ppcls/model.cc

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ PaddleClasModel()

Member Function Documentation

◆ BatchPredict() [1/2]

◆ BatchPredict() [2/2]

◆ Clone()

◆ Predict() [1/3]

◆ Predict() [2/3]

◆ Predict() [3/3]