tf.contrib.distributions.MultivariateNormalDiagWithSoftplusStDev.is_reparameterized

tf.unique(x, out_idx=None, name=None) Finds unique elements in a 1-D tensor. This operation returns

class tf.contrib.distributions.RegisterKL Decorator to register a KL divergence implementation function.

tf.contrib.bayesflow.stochastic_tensor.BernoulliWithSigmoidPTensor.value_type

Status tensorflow::TensorShape::IsValidShape(const TensorShapeProto &proto) Returns OK iff proto

tf.contrib.learn.TensorFlowRNNClassifier.__repr__()

tf.contrib.distributions.Distribution.pdf(value, name='pdf') Probability density function. Args:

tf.contrib.learn.monitors.CaptureVariable.epoch_begin(epoch) Begin epoch. Args:

tf.contrib.distributions.Laplace.sample(sample_shape=(), seed=None, name='sample') Generate samples of the specified shape.

tf.contrib.distributions.BernoulliWithSigmoidP.log_prob(value, name='log_prob') Log probability density/mass function (depending