Built-in loss functions.

`class BinaryCrossentropy`

: Computes the cross-entropy loss between true labels and predicted labels.

`class CategoricalCrossentropy`

: Computes the crossentropy loss between the labels and predictions.

`class CategoricalHinge`

: Computes the categorical hinge loss between `y_true`

and `y_pred`

.

`class CosineSimilarity`

: Computes the cosine similarity between `y_true`

and `y_pred`

.

`class Hinge`

: Computes the hinge loss between `y_true`

and `y_pred`

.

`class Huber`

: Computes the Huber loss between `y_true`

and `y_pred`

.

`class KLDivergence`

: Computes Kullback-Leibler divergence loss between `y_true`

and `y_pred`

.

`class LogCosh`

: Computes the logarithm of the hyperbolic cosine of the prediction error.

`class Loss`

: Loss base class.

`class MeanAbsoluteError`

: Computes the mean of absolute difference between labels and predictions.

`class MeanAbsolutePercentageError`

: Computes the mean absolute percentage error between `y_true`

and `y_pred`

.

`class MeanSquaredError`

: Computes the mean of squares of errors between labels and predictions.

`class MeanSquaredLogarithmicError`

: Computes the mean squared logarithmic error between `y_true`

and `y_pred`

.

`class Poisson`

: Computes the Poisson loss between `y_true`

and `y_pred`

.

`class Reduction`

: Types of loss reduction.

`class SparseCategoricalCrossentropy`

: Computes the crossentropy loss between the labels and predictions.

`class SquaredHinge`

: Computes the squared hinge loss between `y_true`

and `y_pred`

.

`KLD(...)`

: Computes Kullback-Leibler divergence loss between `y_true`

and `y_pred`

.

`categorical_crossentropy(...)`

: Computes the categorical crossentropy loss.

`categorical_hinge(...)`

: Computes the categorical hinge loss between `y_true`

and `y_pred`

.

`cosine_similarity(...)`

: Computes the cosine similarity between labels and predictions.

`hinge(...)`

: Computes the hinge loss between `y_true`

and `y_pred`

.

`kld(...)`

: Computes Kullback-Leibler divergence loss between `y_true`

and `y_pred`

.

`kullback_leibler_divergence(...)`

: Computes Kullback-Leibler divergence loss between `y_true`

and `y_pred`

.

`logcosh(...)`

: Logarithm of the hyperbolic cosine of the prediction error.

`mean_absolute_percentage_error(...)`

`mean_squared_logarithmic_error(...)`

`poisson(...)`

: Computes the Poisson loss between y_true and y_pred.

`sparse_categorical_crossentropy(...)`

`squared_hinge(...)`

: Computes the squared hinge loss between `y_true`

and `y_pred`

.

© 2020 The TensorFlow Authors. All rights reserved.

Licensed under the Creative Commons Attribution License 3.0.

Code samples licensed under the Apache 2.0 License.

https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/compat/v2/keras/losses