LossMetric

public interface LossMetric

Known Indirect Subclasses BinaryCrossentropy<T extends TNumber>, CategoricalCrossentropy<T extends TNumber>, CategoricalHinge<T extends TNumber>, CosineSimilarity<T extends TNumber>, Hinge<T extends TNumber>, KLDivergence<T extends TNumber>, LogCoshError<T extends TNumber>, MeanAbsoluteError<T extends TNumber>, MeanAbsolutePercentageError<T extends TNumber>, MeanSquaredError<T extends TNumber>, MeanSquaredLogarithmicError<T extends TNumber>, Poisson<T extends TNumber>, SparseCategoricalCrossentropy<T extends TNumber>, SquaredHinge<T extends TNumber> BinaryCrossentropy<T extends TNumber> A Metric that computes the binary cross-entropy loss between true labels and predicted labels.  CategoricalCrossentropy<T extends TNumber> A Metric that computes the categorical cross-entropy loss between true labels and predicted labels.  CategoricalHinge<T extends TNumber> A Metric that computes the categorical hinge loss metric between labels and predictions.  CosineSimilarity<T extends TNumber> A metric that computes the cosine similarity metric between labels and predictions.  Hinge<T extends TNumber> A metric that computes the hinge loss metric between labels and predictions.  KLDivergence<T extends TNumber> A metric that computes the Kullback-Leibler divergence loss metric between labels and predictions.  LogCoshError<T extends TNumber> A metric that computes the logarithm of the hyperbolic cosine of the prediction error metric between labels and predictions.  MeanAbsoluteError<T extends TNumber> A metric that computes the mean of absolute difference between labels and predictions.  MeanAbsolutePercentageError<T extends TNumber> A metric that computes the mean of absolute difference between labels and predictions.  MeanSquaredError<T extends TNumber> A metric that computes the mean of absolute difference between labels and predictions.  MeanSquaredLogarithmicError<T extends TNumber> A metric that computes the mean of absolute difference between labels and predictions.  Poisson<T extends TNumber> A metric that computes the poisson loss metric between labels and predictions.  SparseCategoricalCrossentropy<T extends TNumber> A metric that computes the sparse categorical cross-entropy loss between true labels and predicted labels.  SquaredHinge<T extends TNumber> A metric that computes the squared hinge loss metric between labels and predictions.

Interface for Metrics that wrap Loss functions.

Public Methods

abstract Operand<T>

call(Operand<? extends TNumber> labels, Operand<? extends TNumber> predictions) Calculates the weighted loss between labels and predictions

Public Methods

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

Calculates the weighted loss between labels and predictions

Parameters

labels	the truth values or labels
predictions	the predictions

Returns

• the loss