nsl.lib.kl_divergence

Adds a KL-divergence to the training procedure.

nsl.lib.kl_divergence(
    labels,
    predictions,
    axis=None,
    weights=1.0,
    scope=None,
    loss_collection=tf.compat.v1.GraphKeys.LOSSES,
    reduction=tf.compat.v1.losses.Reduction.SUM_BY_NONZERO_WEIGHTS
)

For brevity, let P = labels and Q = predictions. The Kullback-Leibler divergence KL(P||Q) is:

KL(P||Q) = P * log(P) - P * log(Q)

Note: the function assumes that predictions and labels are the values of a multinomial distribution, i.e., each value is the probability of the corresponding class.

For the usage of weights and reduction, please refer to tf.losses.

Args
labels	Tensor of type float32 or float64, with shape [d1, ..., dN, num_classes], represents the target distribution.
predictions	Tensor of the same type and shape as labels, represents the predicted distribution.
axis	The dimension along which the KL divergence is computed. The values of labels and predictions along axis should meet the requirements of a multinomial distribution.
weights	(optional) Tensor whose rank is either 0, or the same as that of labels, and must be broadcastable to labels (i.e., all dimensions must be either 1, or the same as the corresponding losses dimension).
scope	The scope for the operations performed in computing the loss.
loss_collection	Collection to which the loss will be added.
reduction	Type of reduction to apply to the loss.

Returns
Weighted loss float Tensor. If reduction is NONE, this has the same shape as labels, otherwise, it is a scalar.

Raises
InvalidArgumentError	If labels or predictions don't meet the requirements of a multinomial distribution.
ValueError	If axis is None, if the shape of predictions doesn't match that of labels, or if the shape of weights is invalid.