Package deepboof.impl.forward.standard

Class FunctionBatchNorm_F32

java.lang.Object

deepboof.impl.forward.standard.BaseFunction<Tensor_F32>

deepboof.impl.forward.standard.FunctionBatchNorm_F32

All Implemented Interfaces:

BatchNorm, FunctionBatchNorm<Tensor_F32>, Function<Tensor_F32>

Direct Known Subclasses:

SpatialBatchNorm_F32

public class FunctionBatchNorm_F32
extends BaseFunction<Tensor_F32>
implements FunctionBatchNorm<Tensor_F32>

Implementation of FunctionBatchNorm for Tensor_F32.

Field Summary

Fields

Modifier and Type	Field	Description
protected float	EPS
protected Tensor_F32	params
protected boolean	requiresGammaBeta

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

miniBatchSize, parameters, shapeInput, shapeOutput, shapeParameters

Constructor Summary

Constructors

Constructor	Description
FunctionBatchNorm_F32(boolean requiresGammaBeta)

Method Summary

Modifier and Type	Method	Description
void	_forward(Tensor_F32 input, Tensor_F32 output)
void	_initialize()
void	_setParameters(java.util.List<Tensor_F32> parameters)
double	getEPS()
java.lang.Class<Tensor_F32>	getTensorType()	Returns the type of tensor it can process
boolean	hasGammaBeta()	If it returns true then it expects a second set of parameters that defines gamma and beta.
void	setEPS(double EPS)	Used to specify the EPS value.

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.Function

getOutputShape, getParameters, getParameterShapes, initialize

Methods inherited from interface deepboof.forward.FunctionBatchNorm

forward, setParameters

Field Details

requiresGammaBeta

protected boolean requiresGammaBeta

params

protected Tensor_F32 params

EPS

protected float EPS

Constructor Details

FunctionBatchNorm_F32

public FunctionBatchNorm_F32(boolean requiresGammaBeta)

Method Details

_initialize

public void _initialize()

Specified by:

_initialize in class BaseFunction<Tensor_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>

getEPS

public double getEPS()

Specified by:

getEPS in interface BatchNorm

setEPS

public void setEPS(double EPS)

Description copied from interface: BatchNorm

Used to specify the EPS value. Must be invoked before setParameters()

Specified by:

setEPS in interface BatchNorm

Parameters:

EPS - Value of EPS

hasGammaBeta

public boolean hasGammaBeta()

Description copied from interface: BatchNorm

If it returns true then it expects a second set of parameters that defines gamma and beta.

Specified by:

hasGammaBeta in interface BatchNorm

Returns:

true if gamma and beta is returned.

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