Loss

public abstract class Loss

Known Direct Subclasses BinaryCrossentropy, CategoricalCrossentropy, CategoricalHinge, CosineSimilarity, Hinge, Huber, KLDivergence, LogCosh, MeanAbsoluteError, MeanAbsolutePercentageError, MeanSquaredError, MeanSquaredLogarithmicError, Poisson, SparseCategoricalCrossentropy, SquaredHinge BinaryCrossentropy Computes the cross-entropy loss between true labels and predicted labels.  CategoricalCrossentropy Computes the crossentropy loss between the labels and predictions.  CategoricalHinge Computes the categorical hinge loss between labels and predictions.  CosineSimilarity Computes the cosine similarity between labels and predictions.  Hinge Computes the hinge loss between labels and predictions.  Huber Computes the Huber loss between labels and predictions.  KLDivergence Computes Kullback-Leibler divergence loss between labels and predictions.  LogCosh Computes Computes the logarithm of the hyperbolic cosine of the prediction error.  MeanAbsoluteError Computes the mean of absolute difference between labels and predictions.  MeanAbsolutePercentageError Computes the mean absolute percentage error between labels and predictions.  MeanSquaredError Computes the mean of squares of errors between labels and predictions.  MeanSquaredLogarithmicError Computes the mean squared logarithmic errors between labels and predictions.  Poisson Computes the Poisson loss between labels and predictions.  SparseCategoricalCrossentropy Computes the crossentropy loss between labels and predictions.  SquaredHinge Computes the squared hinge loss between labels and predictions.

Fields

public static final Reduction

REDUCTION_DEFAULT

Public Methods

abstract <T extends TNumber> Operand<T>	call(Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights) Generates an Operand that calculates the loss.
<T extends TNumber> Operand<T>	call(Operand<? extends TNumber> labels, Operand<T> predictions) Calculates the loss
Reduction	getReduction() Gets the loss reduction
Ops	getTF() Gets the TensorFlow Ops

Inherited Methods

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()

Fields

public static final Reduction REDUCTION_DEFAULT

Public Methods

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

Generates an Operand that calculates the loss.

Parameters

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

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

Calculates the loss

Parameters

labels	the truth values or labels
predictions	the predictions

Returns

• the loss

public Reduction getReduction ()

Gets the loss reduction

Returns

• the loss reduction

public Ops getTF ()

Gets the TensorFlow Ops

Returns

• the TensorFlow Ops