deephyper.ensemble.loss.CategoricalCrossEntropy

deephyper.ensemble.loss.CategoricalCrossEntropy#

class deephyper.ensemble.loss.CategoricalCrossEntropy[source]#

Bases: Loss

Categorical-Cross Entropy (a.k.a., Log-Loss) function for classification.

Methods

__call__(y_true: ndarray, y_pred: ndarray | Dict[str, ndarray]) → ndarray[source]#

Compute the categorical crossentropy loss.

Parameters:

  • y_true (np.ndarray) – the true target values. It should be an array of labels or one-hot encoded labels representing the true class labels.

  • y_pred (np.ndarray or Dict[str, np.ndarray]) – the predicted target values. If it is a _Dict[str, np.ndarray]_ then it should contain a key "loc". It is an array of predicted categorical probabilities.

Returns:

the loss value with first dimension n_samples.

Return type:

np.ndarray

Contents