tf.FixedLengthRecordReader.reset(name=None) Restore a reader to its initial clean state. Args:

tf.contrib.distributions.InverseGamma.param_shapes(cls, sample_shape, name='DistributionParamShapes') Shapes of parameters given

tf.contrib.bayesflow.stochastic_tensor.MultivariateNormalFullTensor.distribution

tf.contrib.bayesflow.stochastic_tensor.StudentTTensor.value_type

tf.TFRecordReader.reset(name=None) Restore a reader to its initial clean state. Args:

tf.contrib.framework.assign_from_values(var_names_to_values) Creates an assignment operation from a given mapping.

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

tf.truediv(x, y, name=None) Divides x / y elementwise, always producing floating point results. The

tf.contrib.distributions.Normal.survival_function(value, name='survival_function') Survival function. Given

tf.contrib.losses.get_losses(scope=None, loss_collection='losses') Gets the list of losses from the loss_collection.