tf.keras.losses.KLDivergence

Computes Kullback-Leibler divergence loss between y_true and y_pred.

Main aliases

tf.losses.KLDivergence

Compat aliases for migration

See Migration guide for more details.

tf.keras.losses.KLDivergence(
    reduction=losses_utils.ReductionV2.AUTO, name='kullback_leibler_divergence'
)

loss = y_true * log(y_true / y_pred)

k = tf.keras.losses.KLDivergence()
loss = k([.4, .9, .2], [.5, .8, .12])
print('Loss: ', loss.numpy())  # Loss: 0.11891246

Usage with the compile API:

model = tf.keras.Model(inputs, outputs)
model.compile('sgd', loss=tf.keras.losses.KLDivergence())

Methods

@classmethod
from_config(
    config
)

Instantiates a Loss from its config (output of get_config()).

Args
`config`	Output of `get_config()`.

Returns
A `Loss` instance.

get_config()

__call__(
    y_true, y_pred, sample_weight=None
)

Invokes the Loss instance.

Args
`y_true`	Ground truth values. shape = `[batch_size, d0, .. dN]`
`y_pred`	The predicted values. shape = `[batch_size, d0, .. dN]`
`sample_weight`	Optional `sample_weight` acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If `sample_weight` is a tensor of size `[batch_size]`, then the total loss for each sample of the batch is rescaled by the corresponding element in the `sample_weight` vector. If the shape of `sample_weight` is `[batch_size, d0, .. dN-1]` (or can be broadcasted to this shape), then each loss element of `y_pred` is scaled by the corresponding value of `sample_weight`. (Note on`dN-1`: all loss functions reduce by 1 dimension, usually axis=-1.)

Returns
Weighted loss float `Tensor`. If `reduction` is `NONE`, this has shape `[batch_size, d0, .. dN-1]`; otherwise, it is scalar. (Note `dN-1` because all loss functions reduce by 1 dimension, usually axis=-1.)

Raises
`ValueError`	If the shape of `sample_weight` is invalid.