DNNRT Class Reference

Public Member Functions
int	begin (File &nnbfile, unsigned char cpu_num=1)
int	end ()
int	inputVariable (DNNVariable &var, unsigned int index)
DNNVariable &	outputVariable (unsigned int index)
int	forward ()
int	numOfInput ()
int	inputSize (unsigned int index)
int	inputDimension (unsigned int index)
int	inputShapeSize (unsigned int index, unsigned int shapeindex)
int	numOfOutput ()
int	outputSize (unsigned int index)
int	outputDimension (unsigned int index)
int	outputShapeSize (unsigned int index, unsigned int shapeindex)

Member Function Documentation

begin()

int DNNRT::begin	(	File &	nnbfile,
		unsigned char	cpu_num = 1
	)

Initialize runtime object from .nnb file

User must be generate a network model data file (.nnb) by Neural Network Console (NNC) before use this library.

About Neural Network Console: https://dl.sony.com/

Parameters

nnbfile	nnb network model binary file
cpu_num	the number of CPUs to be used by DNN runtime (default 1)

Returns

0 on success, otherwise error.

Return values

-22(-EINVAL)	invalid argument of cpu_num
-16(-EBUSY)	dnnrt-mp included in bootloader isn't installed, or no memory space to load it.
-1	no memory space to load nnbfile
-2	communication error with dnnrt-mp
-3	illegal input/output data in network model

end()

int DNNRT::end

(

)

Finalize runtime object

Returns

0 on success, otherwise error.

inputVariable()

int DNNRT::inputVariable	(	DNNVariable &	var,
		unsigned int	index
	)

Set input data at index

Parameters

[in]	var	Input data to the network
[in]	index	Index of input data

Returns

0 on success, otherwise error.

Note

Number of input data is depends on the network model.

outputVariable()

DNNVariable & DNNRT::outputVariable

(

unsigned int

index

)

Get output data at index

Parameters

[in]

index

Index of output data

Returns

Output variable data. the shape of output data is depends on the network model.

forward()

int DNNRT::forward

(

)

Execute forward propagation

Returns

0 on success, otherwise error.

numOfInput()

int DNNRT::numOfInput

(

)

Get number of network inputs

Returns

Number of input data

inputSize()

int DNNRT::inputSize

(

unsigned int

index

)

Size of input data at index

Parameters

[in]

index

Index of input data

Returns

Number of input data elements

inputDimension()

int DNNRT::inputDimension

(

unsigned int

index

)

Get dimension of input data at index

Parameters

[in]

index

Index of input data

Returns

Number of input data dimension

inputShapeSize()

int DNNRT::inputShapeSize	(	unsigned int	index,
		unsigned int	shapeindex
	)

Shape size at shape index

Parameters

[in]	index	Index of input data
[in]	shapeindex	Index of shape

Returns

Shape size

numOfOutput()

int DNNRT::numOfOutput

(

)

Get number of network outputs

Returns

Number of output data

outputSize()

int DNNRT::outputSize

(

unsigned int

index

)

Size of output data at index

Parameters

[in]

index

Index of output data

Returns

Number of output data elements

outputDimension()

int DNNRT::outputDimension

(

unsigned int

index

)

Get dimension of output data at index

Parameters

[in]

index

Index of output data

Returns

Number of dimension

outputShapeSize()

int DNNRT::outputShapeSize	(	unsigned int	index,
		unsigned int	shapeindex
	)

Shape size at output shape index

Parameters

[in]	index	Index of output data
[in]	shapeindex	Index of output data

Returns

Shape size

---

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

• DNNRT/DNNRT.h