Class ExpNormalizer

java.lang.Object

org.tribuo.math.util.ExpNormalizer

All Implemented Interfaces:

Serializable, VectorNormalizer

public class ExpNormalizer
extends Object
implements VectorNormalizer, Serializable

Normalizes the exponential values of the input array. Used when the input is in log space.

a.k.a. SoftMax.

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
ExpNormalizer()

Method Summary

Modifier and Type	Method	Description
ONNXNode	exportNormalizer(ONNXNode input)	Returns the ONNX softmax node over the 2nd dimension.
double[]	normalize(double[] input)	Normalizes the input array in some fashion specified by the class.
void	normalizeInPlace(double[] input)	In place normalization of the array.

Methods inherited from class java.lang.Object

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

Constructor Details

ExpNormalizer

public ExpNormalizer()

Method Details

normalize

public double[] normalize(double[] input)

Description copied from interface: VectorNormalizer

Normalizes the input array in some fashion specified by the class.

Specified by:

normalize in interface VectorNormalizer

Parameters:

input - The input to normalize.

Returns:

The normalized array.

normalizeInPlace

public void normalizeInPlace(double[] input)

Description copied from interface: VectorNormalizer

In place normalization of the array.

Note: This default implementation performs a copy by calling the standard normalize method.

Specified by:

normalizeInPlace in interface VectorNormalizer

Parameters:

input - The input to normalize.

exportNormalizer

public ONNXNode exportNormalizer(ONNXNode input)

Returns the ONNX softmax node over the 2nd dimension.

Specified by:

exportNormalizer in interface VectorNormalizer

Parameters:

input - The node to be normalized according to this implementation.

Returns:

ONNX softmax node of input.