TensorFlow 2 version View source on GitHub

Computes the categorical crossentropy loss.

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.