tf.keras.losses.KLDivergence

TensorFlow 1 version

View source on GitHub

Computes Kullback-Leibler divergence loss between y_true and y_pred.

View aliases

Main aliases

tf.losses.KLDivergence

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.losses.KLDivergence

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

loss = y_true * log(y_true / y_pred)

See: https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence

Standalone usage:

y_true = [[0, 1], [0, 0]]
y_pred = [[0.6, 0.4], [0.4, 0.6]]
# Using 'auto'/'sum_over_batch_size' reduction type.
kl = tf.keras.losses.KLDivergence()
kl(y_true, y_pred).numpy()
0.458

# Calling with 'sample_weight'.
kl(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy()
0.366

# Using 'sum' reduction type.
kl = tf.keras.losses.KLDivergence(
    reduction=tf.keras.losses.Reduction.SUM)
kl(y_true, y_pred).numpy()
0.916

# Using 'none' reduction type.
kl = tf.keras.losses.KLDivergence(
    reduction=tf.keras.losses.Reduction.NONE)
kl(y_true, y_pred).numpy()
array([0.916, -3.08e-06], dtype=float32)

Usage with the compile() API:

model.compile(optimizer='sgd', loss=tf.keras.losses.KLDivergence())

Args
`reduction`	(Optional) Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `AUTO` indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to `SUM_OVER_BATCH_SIZE`. When used with `tf.distribute.Strategy`, outside of built-in training loops such as `tf.keras` `compile` and `fit`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training tutorial for more details.
`name`	Optional name for the op. Defaults to 'kl_divergence'.

Args

reduction (Optional) Type of tf.keras.losses.Reduction to apply to loss. Default value is AUTO. AUTO indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to SUM_OVER_BATCH_SIZE. When used with tf.distribute.Strategy, outside of built-in training loops such as tf.keras compile and fit, using AUTO or SUM_OVER_BATCH_SIZE will raise an error. Please see this custom training tutorial for more details.

name Optional name for the op. Defaults to 'kl_divergence'.

Methods

`from_config`

View source

@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`

View source

get_config()

Returns the config dictionary for a Loss instance.

`call`

View source

__call__(
    y_true, y_pred, sample_weight=None
)

Invokes the Loss instance.

Args
`y_true`	Ground truth values. shape = `[batch_size, d0, .. dN]`, except sparse loss functions such as sparse categorical crossentropy where shape = `[batch_size, d0, .. dN-1]`
`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.