Losses resume

Documentation illustration (illustration unavailable in the archive).Documentation illustration (illustration unavailable in the archive).

In this section you’ll find a list of all losses fonctionalities.

  ICONS RESUME
BinaryCrossentropy Documentation illustration (illustration unavailable in the archive). Computes the cross-entropy loss between true labels and predicted labels.
CategoricalCrossentropy Documentation illustration (illustration unavailable in the archive). Computes the crossentropy loss between the labels and predictions.​
CategoricalHinge Documentation illustration (illustration unavailable in the archive). Computes the categorical hinge loss between y_true and y_pred.​
CosineSimilarity Documentation illustration (illustration unavailable in the archive). Computes the cosine similarity between true labels and predicted labels.​
Hinge Documentation illustration (illustration unavailable in the archive). Computes the hinge loss between y_true and y_pred.​
Huber Documentation illustration (illustration unavailable in the archive). Computes the Huber loss between y_true and y_pred.​
KLDivergence Documentation illustration (illustration unavailable in the archive). Computes Kullback-Leibler divergence loss between y_true and y_pred.​
LogCosh Documentation illustration (illustration unavailable in the archive). Computes the logarithm of the hyperbolic cosine of the prediction error.
MeanAbsoluteError Documentation illustration (illustration unavailable in the archive). Computes the mean of absolute difference between labels and predictions.​
MeanAbsolutePercentageError Documentation illustration (illustration unavailable in the archive). Computes the mean absolute percentage error between y_true and y_pred.​
MeanSquaredError Documentation illustration (illustration unavailable in the archive). Computes the mean of squares of errors between labels and predictions.
MeanSquaredLogarithmicError Documentation illustration (illustration unavailable in the archive). Computes the mean squared logarithmic error between y_true and y_pred.
Poisson Documentation illustration (illustration unavailable in the archive). Computes the Poisson loss between y_true and y_pred.​
SquaredHinge Documentation illustration (illustration unavailable in the archive). Computes the squared hinge loss between y_true and y_pred.​
Custom Documentation illustration (illustration unavailable in the archive). A custom loss function allows you to define your own loss logic, making it possible to go beyond the standard loss functions provided by libraries.