MinMaxNorm

public class MinMaxNorm

Constrains the weights to have the norm between a lower bound and an upper bound.

Constants

int	AXIS_DEFAULT
double	MAX_VALUE_DEFAULT
double	MIN_VALUE_DEFAULT
double	RATE_DEFAULT

Inherited Constants

From class org.tensorflow.framework.constraints.Constraint

float

EPSILON

Public Constructors

	MinMaxNorm(Ops tf) Create a MinMaxNorm constraint using MIN_VALUE_DEFAULT for the min value, MAX_VALUE_DEFAULT for the max value, RATE_DEFAULT for the rate and AXIS_DEFAULT for the axis
	MinMaxNorm(Ops tf, double minValue, double maxValue) Create a MinMaxNorm constraint using RATE_DEFAULT for the rate and AXIS_DEFAULT for the axis
	MinMaxNorm(Ops tf, double minValue, double maxValue, double rate, int axis) Create a MinMaxNorm constraint
	MinMaxNorm(Ops tf, double minValue, double maxValue, double rate, int[] axes) Create a MinMaxNorm constraint

Public Methods

<T extends TNumber> Operand<T>	call(Operand<T> weights) Applies the constraint against the provided weights
int[]	getAxes() Gets the axes
double	getMaxValue() Gets the maxValue
double	getMinValue() Gets the minValue
double	getRate() Gets the rate

Inherited Methods

From class org.tensorflow.framework.constraints.Constraint

abstract <T extends TNumber> Operand<T>	call(Operand<T> weights) Applies the constraint against the provided weights
Ops	getTF() Gets the TensorFlow Ops

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

Constants

public static final int AXIS_DEFAULT

Constant Value: 0

public static final double MAX_VALUE_DEFAULT

Constant Value: 1.0

public static final double MIN_VALUE_DEFAULT

Constant Value: 0.0

public static final double RATE_DEFAULT

Constant Value: 1.0

Public Constructors

public MinMaxNorm (Ops tf)

Create a MinMaxNorm constraint using MIN_VALUE_DEFAULT for the min value, MAX_VALUE_DEFAULT for the max value, RATE_DEFAULT for the rate and AXIS_DEFAULT for the axis

Parameters

tf	the TensorFlow Ops

public MinMaxNorm (Ops tf, double minValue, double maxValue)

Create a MinMaxNorm constraint using RATE_DEFAULT for the rate and AXIS_DEFAULT for the axis

Parameters

tf	the TensorFlow Ops
minValue	the minimum norm for the incoming weights.
maxValue	the maximum norm for the incoming weights.

public MinMaxNorm (Ops tf, double minValue, double maxValue, double rate, int axis)

Create a MinMaxNorm constraint

Parameters

tf	the TensorFlow Ops
minValue	the minimum norm for the incoming weights.
maxValue	the maximum norm for the incoming weights.
rate	the rate for enforcing the constraint.
axis	integer, axis along which to calculate weight norms.

public MinMaxNorm (Ops tf, double minValue, double maxValue, double rate, int[] axes)

Create a MinMaxNorm constraint

Parameters

tf	the TensorFlow Ops
minValue	the minimum norm for the incoming weights.
maxValue	the maximum norm for the incoming weights.
rate	the rate for enforcing the constraint.
axes	integer, axis along which to calculate weight norms.

Public Methods

public Operand<T> call (Operand<T> weights)

Applies the constraint against the provided weights

Parameters

weights	the weights

Returns

• the constrained weights

public int[] getAxes ()

Gets the axes

Returns

• the axes

public double getMaxValue ()

Gets the maxValue

Returns

• the maxValue

public double getMinValue ()

Gets the minValue

Returns

• the minValue

public double getRate ()

Gets the rate

Returns

• the rate