Class CosineSimilarity

java.lang.Object

org.tensorflow.framework.losses.CosineSimilarity

All Implemented Interfaces:

Loss

public class CosineSimilarity
extends Object

Computes the cosine similarity between labels and predictions.

Note that it is a number between -1 and 1. When it is a negative number between -1 and 0, 0 indicates orthogonality and values closer to -1indicate greater similarity. The values closer to 1 indicate greater dissimilarity. This makes it usable as a loss function in a setting where you try to maximize the proximity between predictions and targets. If either labels or predictions is a zero vector, cosine similarity will be 0 regardless of the proximity between predictions and targets.

loss = -sum(l2Norm(labels) * l2Norm(predictions))

Standalone usage:

   Operand<TFloat32> labels =
       tf.constant(new float[][] {{0.f, 1.f}, {1.f, 1.f}});
   Operand<TFloat32> predictions =
       tf.constant(new float[][] {{1.f, 0.f}, {1.f, 1.f}});
   CosineSimilarity cosineLoss = new CosineSimilarity(tf);
   Operand<TFloat32> result = cosineLoss.call(Ops tf, labels, predictions);
   // produces -0.5

Calling with sample weight:

   Operand<TFloat32> sampleWeight = tf.constant(new float[] {0.8f, 0.2f});
   Operand<TFloat32> result = cosineLoss.call(Ops tf, labels, predictions, sampleWeight);
   // produces -0.0999f

Using SUM reduction type:

   CosineSimilarity cosineLoss = new CosineSimilarity(tf, Reduction.SUM);
   Operand<TFloat32> result = cosineLoss.call(Ops tf, labels, predictions);
   // produces -0.999f

Using NONE reduction type:

   CosineSimilarity cosineLoss = new CosineSimilarity(tf, Reduction.NONE);
   Operand<TFloat32> result = cosineLoss.call(Ops tf, labels, predictions);
   // produces [-0.f, -0.999f]

Field Summary

Fields

Modifier and Type	Field	Description
static final int	DEFAULT_AXIS
static final Reduction	DEFAULT_REDUCTION
protected final Reduction	reduction
static final Reduction	REDUCTION_DEFAULT

Constructor Summary

Constructors

Constructor	Description
CosineSimilarity()	Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name, an axis of DEFAULT_AXIS, and a AbstractLoss Reduction of DEFAULT_REDUCTION
CosineSimilarity(int axis)	Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name, and a AbstractLoss Reduction of DEFAULT_REDUCTION
CosineSimilarity(int[] axis)	Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name, and a AbstractLoss Reduction of DEFAULT_REDUCTION
CosineSimilarity(int[] axis, Reduction reduction)	Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name
CosineSimilarity(int axis, Reduction reduction)	Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name
CosineSimilarity(String name)	Creates a Cosine Similarity AbstractLoss using an axis of DEFAULT_AXIS, and a AbstractLoss Reduction of DEFAULT_REDUCTION
CosineSimilarity(String name, int axis)	Creates a Cosine Similarity AbstractLoss using a AbstractLoss Reduction of DEFAULT_REDUCTION
CosineSimilarity(String name, int[] axis)	Creates a Cosine Similarity AbstractLoss using a AbstractLoss Reduction of DEFAULT_REDUCTION
CosineSimilarity(String name, int[] axis, Reduction reduction)	Creates a Cosine Similarity AbstractLoss
CosineSimilarity(String name, int axis, Reduction reduction)	Creates a Cosine Similarity AbstractLoss
CosineSimilarity(String name, Reduction reduction)	Creates a Cosine Similarity AbstractLoss using an axis of DEFAULT_AXIS
CosineSimilarity(Reduction reduction)	Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name and an axis of DEFAULT_AXIS

Method Summary

Modifier and Type	Method	Description
<T extends TNumber> Operand<T>	call(Ops tf, Operand<? extends TNumber> labels, Operand<T> predictions)	Calculates the loss
<T extends TNumber> Operand<T>	call(Ops tf, Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights)	Generates an Operand that calculates the loss.
String	getName()	Gets the name for this loss
Reduction	getReduction()	Gets the loss reduction

Methods inherited from class Object

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

Field Details

DEFAULT_AXIS

public static final int DEFAULT_AXIS

See Also:

• Constant Field Values

DEFAULT_REDUCTION

public static final Reduction DEFAULT_REDUCTION

REDUCTION_DEFAULT

public static final Reduction REDUCTION_DEFAULT

reduction

protected final Reduction reduction

Constructor Details

CosineSimilarity

public CosineSimilarity()

Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name, an axis of DEFAULT_AXIS, and a AbstractLoss Reduction of DEFAULT_REDUCTION

CosineSimilarity

public CosineSimilarity(String name)

Creates a Cosine Similarity AbstractLoss using an axis of DEFAULT_AXIS, and a AbstractLoss Reduction of DEFAULT_REDUCTION

Parameters:

name - the name of the loss

CosineSimilarity

public CosineSimilarity(int axis)

Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name, and a AbstractLoss Reduction of DEFAULT_REDUCTION

Parameters:

axis - The dimension along which the cosine similarity is computed.

CosineSimilarity

public CosineSimilarity(int[] axis)

Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name, and a AbstractLoss Reduction of DEFAULT_REDUCTION

Parameters:

axis - The dimension along which the cosine similarity is computed.

CosineSimilarity

public CosineSimilarity(String name,
 int axis)

Creates a Cosine Similarity AbstractLoss using a AbstractLoss Reduction of DEFAULT_REDUCTION

Parameters:

name - the name of the loss

axis - The dimension along which the cosine similarity is computed.

CosineSimilarity

public CosineSimilarity(String name,
 int[] axis)

Creates a Cosine Similarity AbstractLoss using a AbstractLoss Reduction of DEFAULT_REDUCTION

Parameters:

name - the name of the loss

axis - The dimension along which the cosine similarity is computed.

CosineSimilarity

public CosineSimilarity(Reduction reduction)

Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name and an axis of DEFAULT_AXIS

Parameters:

reduction - Type of Reduction to apply to the loss.

CosineSimilarity

public CosineSimilarity(String name,
 Reduction reduction)

Creates a Cosine Similarity AbstractLoss using an axis of DEFAULT_AXIS

Parameters:

name - the name of the loss

reduction - Type of Reduction to apply to the loss.

CosineSimilarity

public CosineSimilarity(int axis,
 Reduction reduction)

Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name

Parameters:

axis - The dimension along which the cosine similarity is computed.

reduction - Type of Reduction to apply to the loss.

CosineSimilarity

public CosineSimilarity(int[] axis,
 Reduction reduction)

Creates a Cosine Similarity AbstractLoss using Class.getSimpleName() as the loss name

Parameters:

axis - The dimension along which the cosine similarity is computed.

reduction - Type of Reduction to apply to the loss.

CosineSimilarity

public CosineSimilarity(String name,
 int axis,
 Reduction reduction)

Creates a Cosine Similarity AbstractLoss

Parameters:

name - the name of the loss

axis - The dimension along which the cosine similarity is computed.

reduction - Type of Reduction to apply to the loss.

CosineSimilarity

public CosineSimilarity(String name,
 int[] axis,
 Reduction reduction)

Creates a Cosine Similarity AbstractLoss

Parameters:

name - the name of the loss

axis - The dimension along which the cosine similarity is computed.

reduction - Type of Reduction to apply to the loss.

Method Details

call

public <T extends TNumber> Operand<T> call(Ops tf,
 Operand<? extends TNumber> labels,
 Operand<T> predictions,
 Operand<T> sampleWeights)

Generates an Operand that calculates the loss.

Type Parameters:

T - The data type of the predictions, sampleWeights and loss.

Parameters:

tf - the TensorFlow Ops

labels - the truth values or labels

predictions - the predictions

sampleWeights - Optional sampleWeights acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If SampleWeights is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the SampleWeights vector. If the shape of SampleWeights is [batch_size, d0, .. dN-1] (or can be broadcast to this shape), then each loss element of predictions is scaled by the corresponding value of SampleWeights. (Note on dN-1: all loss functions reduce by 1 dimension, usually axis=-1.)

Returns:

the loss

call

public <T extends TNumber> Operand<T> call(Ops tf,
 Operand<? extends TNumber> labels,
 Operand<T> predictions)

Calculates the loss

Type Parameters:

T - The data type of the predictions and loss.

Parameters:

tf - the TensorFlow Ops

labels - the truth values or labels

predictions - the predictions

Returns:

the loss

getReduction

public Reduction getReduction()

Gets the loss reduction

Returns:

the loss reduction

getName

public String getName()

Gets the name for this loss

Returns:

the name for this loss