core::NeuralBase Class Reference

Inheritance diagram for core::NeuralBase:

Public Member Functions
std::string	getName ()
	Gets the name of the neural network. More...
double	getInferenceTime ()
	Gets the inference time of the network. More...
void	loadNetwork (std::string framework, std::string modelWeightsFile, std::string classesFile="", std::string modelConfigurationFile="", std::string inputLayerName="", std::string outputLayerName="")
	Loads the neural network from memory buffer. More...
void	configureNetwork (std::string name, int inputWidth, int inputHeight, double scale, double mean0, double mean1, double mean2, std::string configBackend, std::string configTarget, double confidenceThreshold)
	Configures the network with various parameters. More...
std::vector< std::string >	getOutputsNames (const cv::dnn::Net &net)
	Gets the names of the output layers of the network. More...

Protected Member Functions
void	readClassNames (const std::string &filePath)

Protected Attributes
std::string	mFramework
std::string	mInputLayerName
std::string	mOutputLayerName
std::string	mName
cv::dnn::Net	mNet
std::vector< std::string >	classes
double	scaleFactor = 1.0
cv::Scalar	mean { 0.0, 0.0, 0.0 }
cv::Size	size { 128, 128 }
cv::dnn::Backend	selectedBackend
cv::dnn::Target	selectedTarget
float	confThreshold = 0.5F
std::map< std::string, cv::dnn::Backend >	backends
std::map< std::string, cv::dnn::Target >	targets

Member Function Documentation

configureNetwork()

void core::NeuralBase::configureNetwork	(	std::string	name,
		int	inputWidth,
		int	inputHeight,
		double	scale,
		double	mean0,
		double	mean1,
		double	mean2,
		std::string	configBackend,
		std::string	configTarget,
		double	confidenceThreshold
	)

Configures the network with various parameters.

Parameters

name	The name of the network.
inputWidth	The width of the network input.
inputHeight	The height of the network input.
scale	The scaling factor for the input.
mean0	The mean value for the first channel.
mean1	The mean value for the second channel.
mean2	The mean value for the third channel.
configBackend	The backend to be used for computation.
configTarget	The target device for computation.
confidenceThreshold	The threshold for filtering weak detections.

Here is the caller graph for this function:

getInferenceTime()

double core::NeuralBase::getInferenceTime

(

)

Gets the inference time of the network.

Returns

The inference time in milliseconds.

getName()

std::string core::NeuralBase::getName

(

)

Gets the name of the neural network.

Returns

A string representing the name of the network.

getOutputsNames()

std::vector< std::string > core::NeuralBase::getOutputsNames

(

const cv::dnn::Net &

net

)

Gets the names of the output layers of the network.

Parameters

net	The neural network.

Returns

A vector of strings representing the names of the output layers.

loadNetwork()

void core::NeuralBase::loadNetwork	(	std::string	framework,
		std::string	modelWeightsFile,
		std::string	classesFile = "",
		std::string	modelConfigurationFile = "",
		std::string	inputLayerName = "",
		std::string	outputLayerName = ""
	)

Loads the neural network from memory buffer.

Parameters

framework	The framework used for the network.
modelWeightsFile	The memory buffer containing the model weights.
classesFile	The memory buffer containing the class names.
modelConfigurationFile	The memory buffer containing the model configuration. You can leave it empty if there is no configuration file.
inputLayerName	The name of the input layer. You can leave it empty if there is no multiple input.
outputLayerName	The name of the output layer. You can leave it empty. You can leave itempty if there are no specific outputs to read.

Here is the caller graph for this function:

Member Data Documentation

backends

std::map<std::string, cv::dnn::Backend> core::NeuralBase::backends

protected

Initial value:

= {
            {"DNN_BACKEND_DEFAULT", cv::dnn::DNN_BACKEND_DEFAULT},
            {"DNN_BACKEND_HALIDE", cv::dnn::DNN_BACKEND_HALIDE},
            {"DNN_BACKEND_INFERENCE_ENGINE", cv::dnn::DNN_BACKEND_INFERENCE_ENGINE},
            {"DNN_BACKEND_OPENCV", cv::dnn::DNN_BACKEND_OPENCV},
            {"DNN_BACKEND_CUDA", cv::dnn::DNN_BACKEND_CUDA} 
        }

selectedBackend

cv::dnn::Backend core::NeuralBase::selectedBackend

protected

Initial value:

=
            cv::dnn::DNN_BACKEND_OPENCV

selectedTarget

cv::dnn::Target core::NeuralBase::selectedTarget

protected

Initial value:

=
            cv::dnn::DNN_TARGET_CPU

targets

std::map<std::string, cv::dnn::Target> core::NeuralBase::targets

protected

Initial value:

= {
            {"DNN_TARGET_CPU", cv::dnn::DNN_TARGET_CPU},
            {"DNN_TARGET_CUDA", cv::dnn::DNN_TARGET_CUDA},
            {"DNN_TARGET_OPENCL", cv::dnn::DNN_TARGET_OPENCL},
            {"DNN_TARGET_OPENCL_FP16", cv::dnn::DNN_TARGET_OPENCL_FP16},
            {"DNN_TARGET_MYRIAD", cv::dnn::DNN_TARGET_MYRIAD} }

---

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

• C:/Projects/Engine/AntalEngine/Engine/NeuralBase.h
• C:/Projects/Engine/AntalEngine/Engine/NeuralBase.cpp