tf.contrib.gan.losses.wargs.mutual_information_penalty(
structured_generator_inputs,
predicted_distributions,
weights=1.0,
scope=None,
loss_collection=tf.GraphKeys.LOSSES,
reduction=losses.Reduction.SUM_BY_NONZERO_WEIGHTS,
add_summaries=False
)
Defined in tensorflow/contrib/gan/python/losses/python/losses_impl.py
.
Returns a penalty on the mutual information in an InfoGAN model.
This loss comes from an InfoGAN paper https://arxiv.org/abs/1606.03657.
Args:
structured_generator_inputs
: A list of Tensors representing the random noise that must have high mutual information with the generator output. List length should matchpredicted_distributions
.predicted_distributions
: A list oftfp.distributions.Distribution
s. Predicted by the recognizer, and used to evaluate the likelihood of the structured noise. List length should matchstructured_generator_inputs
.weights
: OptionalTensor
whose rank is either 0, or the same dimensions asstructured_generator_inputs
.scope
: The scope for the operations performed in computing the loss.loss_collection
: collection to which this loss will be added.reduction
: Atf.losses.Reduction
to apply to loss.add_summaries
: Whether or not to add summaries for the loss.
Returns:
A scalar Tensor representing the mutual information loss.