inference_engine.hpp File Reference

A header file that provides a set of convenience utility functions and the main include file for all other .h files. More...

#include <vector>
#include <numeric>
#include <algorithm>
#include <memory>
#include <ie_blob.h>
#include <ie_api.h>
#include <ie_error.hpp>
#include <ie_layers.h>
#include <ie_device.hpp>
#include <ie_plugin_dispatcher.hpp>
#include <ie_plugin_config.hpp>
#include <ie_icnn_network.hpp>
#include <ie_icnn_network_stats.hpp>
#include <cpp/ie_cnn_net_reader.h>
#include <cpp/ie_plugin_cpp.hpp>
#include <cpp/ie_executable_network.hpp>
#include <ie_version.hpp>

Go to the source code of this file.

Functions
template<class T >
void	InferenceEngine::TopResults (unsigned int n, TBlob< T > &input, std::vector< unsigned > &output)
	Gets the top n results from a tblob. More...
void	InferenceEngine::TopResults (unsigned int n, Blob &input, std::vector< unsigned > &output)
	Gets the top n results from a blob. More...
template<typename data_t >
void	InferenceEngine::copyFromRGB8 (uint8_t *RGB8, size_t RGB8_size, InferenceEngine::TBlob< data_t > *blob)
	Copies a 8-bit RGB image to the blob. Throws an exception in case of dimensions or input size mismatch. More...
void	InferenceEngine::ConvertImageToInput (unsigned char *imgBufRGB8, size_t lengthbytesSize, Blob &input)
	Splits the RGB channels to either I16 Blob or float blob. The image buffer is assumed to be packed with no support for strides. More...
template<typename T >
void	InferenceEngine::copyToFloat (float *dst, const InferenceEngine::Blob *src)
	Copies data from a certain precision to float. More...

Detailed Description

A header file that provides a set of convenience utility functions and the main include file for all other .h files.

Function Documentation

ConvertImageToInput()

void InferenceEngine::ConvertImageToInput ( unsigned char *  imgBufRGB8, size_t  lengthbytesSize, Blob &  input  )

inline

Splits the RGB channels to either I16 Blob or float blob. The image buffer is assumed to be packed with no support for strides.

Parameters

imgBufRGB8	Packed 24bit RGB image (3 bytes per pixel: R-G-B)
lengthbytesSize	Size in bytes of the RGB image. It is equal to amount of pixels times 3 (number of channels)
input	Blob to contain the split image (to 3 channels)

copyFromRGB8()

template<typename data_t >

void InferenceEngine::copyFromRGB8	(	uint8_t *	RGB8,
		size_t	RGB8_size,
		InferenceEngine::TBlob< data_t > *	blob
	)

Copies a 8-bit RGB image to the blob. Throws an exception in case of dimensions or input size mismatch.

Template Parameters

data_t

Type of the target blob

Parameters

RGB8	8-bit RGB image
RGB8_size	Size of the image
blob	Target blob to write image to

copyToFloat()

template<typename T >

void InferenceEngine::copyToFloat	(	float *	dst,
		const InferenceEngine::Blob *	src
	)

Copies data from a certain precision to float.

Parameters

dst	Pointer to an output float buffer, must be allocated before the call
src	Source blob to take data from

TopResults() [1/2]

template<class T >

void InferenceEngine::TopResults ( unsigned int  n, TBlob< T > &  input, std::vector< unsigned > &  output  )

inline

Gets the top n results from a tblob.

Parameters

n	Top n count
input	1D tblob that contains probabilities
output	Vector of indexes for the top n places

TopResults() [2/2]

void InferenceEngine::TopResults ( unsigned int  n, Blob &  input, std::vector< unsigned > &  output  )

inline

Gets the top n results from a blob.

Parameters

n	Top n count
input	1D blob that contains probabilities
output	Vector of indexes for the top n places