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


Computes Kullback-Leibler divergence loss between y_true and y_pred.

loss = y_true * log(y_true / y_pred)


Standalone usage:

y_true = np.random.randint(0, 2, size=(2, 3)).astype(np.float64)
y_pred = np.random.random(size=(2, 3))
loss = tf.keras.losses.kullback_leibler_divergence(y_true, y_pred)
assert loss.shape == (2,)
y_true = tf.keras.backend.clip(y_true, 1e-7, 1)
y_pred = tf.keras.backend.clip(y_pred, 1e-7, 1)
assert np.array_equal(
    loss.numpy(), np.sum(y_true * np.log(y_true / y_pred), axis=-1))

y_true Tensor of true targets.
y_pred Tensor of predicted targets.

A Tensor with loss.

TypeError If y_true cannot be cast to the y_pred.dtype.