diff options
Diffstat (limited to 'tensorflow/contrib/distributions/python/ops/relaxed_bernoulli.py')
| -rw-r--r-- | tensorflow/contrib/distributions/python/ops/relaxed_bernoulli.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tensorflow/contrib/distributions/python/ops/relaxed_bernoulli.py b/tensorflow/contrib/distributions/python/ops/relaxed_bernoulli.py index b525809015..5b57a95c55 100644 --- a/tensorflow/contrib/distributions/python/ops/relaxed_bernoulli.py +++ b/tensorflow/contrib/distributions/python/ops/relaxed_bernoulli.py @@ -52,7 +52,7 @@ class RelaxedBernoulli(transformed_distribution.TransformedDistribution): the RelaxedBernoulli can suffer from underflow issues. In many case loss functions such as these are invariant under invertible transformations of the random variables. The KL divergence, found in the variational autoencoder - loss, is an example. Because RelaxedBernoullis are sampled by a Logistic + loss, is an example. Because RelaxedBernoullis are sampled by by a Logistic random variable followed by a `tf.sigmoid` op, one solution is to treat the Logistic as the random variable and `tf.sigmoid` as downstream. The KL divergences of two Logistics, which are always followed by a `tf.sigmoid` |