Base model object for all the vision models. More...

#include <fastdeploy_model.h>

Inheritance diagram for fastdeploy::FastDeployModel:

[legend]

Collaboration diagram for fastdeploy::FastDeployModel:

[legend]

Public Member Functions
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 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
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

Base model object for all the vision models.

Member Function Documentation

◆ EnableRecordTimeOfRuntime()

virtual void fastdeploy::FastDeployModel::EnableRecordTimeOfRuntime ( )

inlinevirtual

This is a debug interface, used to record the time of runtime (backend + h2d + d2h)

example code

auto model = fastdeploy::vision::PPYOLOE("model.pdmodel", "model.pdiparams", "infer_cfg.yml");
if (!model.Initialized()) {
  std::cerr << "Failed to initialize." << std::endl;
  return -1;
}
model.EnableRecordTimeOfRuntime();
cv::Mat im = cv::imread("test.jpg");
for (auto i = 0; i < 1000; ++i) {
  fastdeploy::vision::DetectionResult result;
  model.Predict(&im, &result);
}
model.PrintStatisInfoOfRuntime();

After called the PrintStatisInfoOfRuntime(), the statistical information of runtime will be printed in the console

Member Data Documentation

◆ valid_ascend_backends

std::vector<Backend> fastdeploy::FastDeployModel::valid_ascend_backends = {}

Model's valid ascend backends. This member defined all the cann backends have successfully tested for the model

◆ valid_directml_backends

std::vector<Backend> fastdeploy::FastDeployModel::valid_directml_backends = {}

Model's valid directml backends. This member defined all the onnxruntime directml backends have successfully tested for the model

◆ valid_gpu_backends

std::vector<Backend> fastdeploy::FastDeployModel::valid_gpu_backends = {Backend::ORT}

Model's valid gpu backends. This member defined all the gpu backends have successfully tested for the model

◆ valid_ipu_backends

std::vector<Backend> fastdeploy::FastDeployModel::valid_ipu_backends = {}

Model's valid ipu backends. This member defined all the ipu backends have successfully tested for the model

◆ valid_kunlunxin_backends

std::vector<Backend> fastdeploy::FastDeployModel::valid_kunlunxin_backends = {}

Model's valid KunlunXin xpu backends. This member defined all the KunlunXin xpu backends have successfully tested for the model

◆ valid_rknpu_backends

std::vector<Backend> fastdeploy::FastDeployModel::valid_rknpu_backends = {}

Model's valid hardware backends. This member defined all the gpu backends have successfully tested for the model

◆ valid_sophgonpu_backends

std::vector<Backend> fastdeploy::FastDeployModel::valid_sophgonpu_backends = {}

Model's valid hardware backends. This member defined all the sophgo npu backends have successfully tested for the model

◆ valid_timvx_backends

std::vector<Backend> fastdeploy::FastDeployModel::valid_timvx_backends = {}

Model's valid timvx backends. This member defined all the timvx backends have successfully tested for the model

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

/fastdeploy/my_work/FastDeploy/fastdeploy/fastdeploy_model.h
/fastdeploy/my_work/FastDeploy/fastdeploy/fastdeploy_model.cc

Public Member Functions

Public Attributes