View source on GitHub
|
View source on GitHub
|
Computes the categorical crossentropy loss.
tf.keras.losses.categorical_crossentropy(
y_true, y_pred, from_logits=False, label_smoothing=0
)
y_true: tensor of true targets.y_pred: tensor of predicted targets.from_logits: Whether y_pred is expected to be a logits tensor. By default,
we assume that y_pred encodes a probability distribution.label_smoothing: Float in [0, 1]. If > 0 then smooth the labels.Categorical crossentropy loss value.