Save the date! Google I/O returns May 18-20 Register now


Computes the sparse categorical crossentropy loss.

Used in the notebooks

Used in the guide

Standalone usage:

y_true = [1, 2]
y_pred = [[0.05, 0.95, 0], [0.1, 0.8, 0.1]]
loss = tf.keras.losses.sparse_categorical_crossentropy(y_true, y_pred)
assert loss.shape == (2,)
array([0.0513, 2.303], dtype=float32)

y_true Ground truth values.
y_pred The predicted values.
from_logits Whether y_pred is expected to be a logits tensor. By default, we assume that y_pred encodes a probability distribution.
axis (Optional) Defaults to -1. The dimension along which the entropy is computed.

Sparse categorical crossentropy loss value.