deepboof.impl.forward.standard

Class SpatialConvolve2D_F32

java.lang.Object

deepboof.impl.forward.standard.BaseFunction<T>

deepboof.impl.forward.standard.BaseSpatialWindow<T,P>

deepboof.impl.forward.standard.SpatialWindowImage<Tensor_F32,SpatialPadding2D_F32>

deepboof.impl.forward.standard.SpatialConvolve2D_F32

All Implemented Interfaces:

SpatialConvolve2D<Tensor_F32>, Function<Tensor_F32>

public class SpatialConvolve2D_F32
extends SpatialWindowImage<Tensor_F32,SpatialPadding2D_F32>
implements SpatialConvolve2D<Tensor_F32>

Implementation of SpatialConvolve2D for Tensor_F32

Field Summary

Fields

Modifier and Type	Field and Description
protected Tensor_F32	bias
protected float[]	cacheLocal
protected int	F
protected Tensor_F32	weights

Fields inherited from class deepboof.impl.forward.standard.SpatialWindowImage

output

Fields inherited from class deepboof.impl.forward.standard.BaseSpatialWindow

C, config, H, HH, Ho, Hp, N, padding, W, Wo, Wp, WW

Fields inherited from class deepboof.impl.forward.standard.BaseFunction

miniBatchSize, parameters, shapeInput, shapeOutput, shapeParameters

Constructor Summary

Constructors

Constructor and Description
SpatialConvolve2D_F32(ConfigConvolve2D config, SpatialPadding2D_F32 padding)

Method Summary

Modifier and Type	Method and Description
void	_forward(Tensor_F32 input, Tensor_F32 output)
void	_initialize()
void	_setParameters(java.util.List<Tensor_F32> parameters)
protected void	forwardAt_border(SpatialPadding2D_F32 padded, int batch, int padY, int padX, int outY, int outX) Applies the operations at the specified window and stores the results at the specified output coordinate.
protected void	forwardAt_inner(Tensor_F32 input, int batch, int inY, int inX, int outY, int outX) Applies the operations at the specified window and stores the results at the specified output coordinate.
ConfigConvolve2D	getConfiguration() Returns configuration of spacial parameters
java.lang.Class<Tensor_F32>	getTensorType() Returns the type of tensor it can process

Methods inherited from class deepboof.impl.forward.standard.SpatialWindowImage

forwardImage

Methods inherited from class deepboof.impl.forward.standard.BaseSpatialWindow

getPadding, innerLowerExtent, innerUpperExtent, isEntirelyBorder

Methods inherited from class deepboof.impl.forward.standard.BaseFunction

forward, getOutputShape, getParameters, getParameterShapes, initialize, setParameters

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface deepboof.forward.SpatialConvolve2D

forward, getPadding, setParameters

Methods inherited from interface deepboof.Function

getOutputShape, getParameters, getParameterShapes, initialize

Field Detail

F

protected int F

weights

protected Tensor_F32 weights

bias

protected Tensor_F32 bias

cacheLocal

protected float[] cacheLocal

Constructor Detail

SpatialConvolve2D_F32

public SpatialConvolve2D_F32(ConfigConvolve2D config,
                             SpatialPadding2D_F32 padding)

Method Detail

_initialize

public void _initialize()

Overrides:

_initialize in class BaseSpatialWindow<Tensor_F32,SpatialPadding2D_F32>

_setParameters

public void _setParameters(java.util.List<Tensor_F32> parameters)

Specified by:

_setParameters in class BaseFunction<Tensor_F32>

_forward

public void _forward(Tensor_F32 input,
                     Tensor_F32 output)

Specified by:

_forward in class BaseFunction<Tensor_F32>

forwardAt_inner

protected void forwardAt_inner(Tensor_F32 input,
                               int batch,
                               int inY,
                               int inX,
                               int outY,
                               int outX)

Description copied from class: SpatialWindowImage

Applies the operations at the specified window and stores the results at the specified output coordinate.

Specified by:

forwardAt_inner in class SpatialWindowImage<Tensor_F32,SpatialPadding2D_F32>

Parameters:

input - Input spatial tensor

batch - Index of input in mini-batch that is being processed

inY - y-axis lower extent, in input coordinates

inX - x-axis lower extent, in input coordinates

outY - y-axis output coordinates

outX - x-axis output coordinates

forwardAt_border

protected void forwardAt_border(SpatialPadding2D_F32 padded,
                                int batch,
                                int padY,
                                int padX,
                                int outY,
                                int outX)

Description copied from class: SpatialWindowImage

Applies the operations at the specified window and stores the results at the specified output coordinate. For virtual tensor

Specified by:

forwardAt_border in class SpatialWindowImage<Tensor_F32,SpatialPadding2D_F32>

Parameters:

padded - Padded input spatial virtual tensor

batch - Index of input in mini-batch that is being processed

padY - y-axis lower extent, inclusive. Padded coordinates

padX - x-axis lower extent, inclusive. Padded coordinates

outY - y-axis output coordinates

outX - x-axis output coordinates

getTensorType

public java.lang.Class<Tensor_F32> getTensorType()

Description copied from interface: Function

Returns the type of tensor it can process

Specified by:

getTensorType in interface Function<Tensor_F32>

Returns:

Type of tensor

getConfiguration

public ConfigConvolve2D getConfiguration()

Description copied from interface: SpatialConvolve2D

Returns configuration of spacial parameters

Specified by:

getConfiguration in interface SpatialConvolve2D<Tensor_F32>

Returns:

Copy of configuration