Class NonNeg

java.lang.Object

org.tensorflow.framework.constraints.AbstractConstraint

org.tensorflow.framework.constraints.NonNeg

All Implemented Interfaces:

Constraint

public class NonNeg
extends AbstractConstraint

Constrains the weights to be non-negative.

Field Summary

Fields inherited from class AbstractConstraint

EPSILON

Modifier and Type	Field	Description
static final float	EPSILON

Constructor Summary

Constructors

Constructor	Description
NonNeg()	Create a NonNeg constraint

Method Summary

Modifier and Type	Method	Description
<T extends TNumber> Operand<T>	call(Ops tf, Operand<T> weights)	Applies the constraint against the provided weights

Methods inherited from class AbstractConstraint

clip, norm, sqrt

Modifier and Type	Method	Description
protected <T extends TNumber> Operand<T>	clip(Ops tf, Operand<T> x, double minValue, double maxValue)	Gets the element-wise value clipping.
protected <T extends TNumber> Operand<T>	norm(Ops tf, Operand<T> weights, int[] axes)	Calculates the norm of the weights along the axes
protected <T extends TNumber> Operand<T>	sqrt(Ops tf, Operand<T> x)	Gets the element-wise square root.

Methods inherited from class Object

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

Constructor Details

NonNeg

public NonNeg()

Create a NonNeg constraint

Method Details

call

public <T extends TNumber> Operand<T> call(Ops tf,
 Operand<T> weights)

Applies the constraint against the provided weights

Type Parameters:

T - the data type for weights and results.

Parameters:

tf - the TensorFlow Ops

weights - the weights

Returns:

the constrained weights