tf.contrib.distributions.ExponentialWithSoftplusLam.entropy(name='entropy') Shanon entropy in nats. Additional documentation from Gamma: This is defined to be entropy = alpha - log(beta) + log(Gamma(alpha)) + (1-alpha)digamma(alpha) where digamma(alpha) is the digamma function.

tf.contrib.distributions.Categorical.param_static_shapes(cls, sample_shape) param_shapes with static (i.e. TensorShape) shapes. Args: sample_shape: TensorShape or python list/tuple. Desired shape of a call to sample(). Returns: dict of parameter name to TensorShape. Raises: ValueError: if sample_shape is a TensorShape and is not fully defined.

tf.contrib.training.batch_sequences_with_states(input_key, input_sequences, input_context, input_length, initial_states, num_unroll, batch_size, num_threads=3, capacity=1000, allow_small_batch=True, pad=True, name=None) Creates batches of segments of sequential input. This method creates a SequenceQueueingStateSaver (SQSS) and adds it to the queuerunners. It returns a NextQueuedSequenceBatch. It accepts one example at a time identified by a unique input_key. input_sequence is a dict with value

tf.contrib.distributions.Binomial.parameters Dictionary of parameters used by this Distribution.

tf.contrib.distributions.Laplace.prob(value, name='prob') Probability density/mass function (depending on is_continuous). Args: value: float or double Tensor. name: The name to give this op. Returns: prob: a Tensor of shape sample_shape(x) + self.batch_shape with values of type self.dtype.

Thread* tensorflow::EnvWrapper::StartThread(const ThreadOptions &thread_options, const string &name, std::function< void()> fn) override Returns a new thread that is running fn() and is identified (for debugging/performance-analysis) by "name". Caller takes ownership of the result and must delete it eventually (the deletion will block until fn() stops running).

tf.contrib.distributions.Chi2WithAbsDf.allow_nan_stats Python boolean describing behavior when a stat is undefined. Stats return +/- infinity when it makes sense. E.g., the variance of a Cauchy distribution is infinity. However, sometimes the statistic is undefined, e.g., if a distribution's pdf does not achieve a maximum within the support of the distribution, the mode is undefined. If the mean is undefined, then by definition the variance is undefined. E.g. the mean for Student's T for df =

tf.contrib.learn.LinearClassifier.predict_proba(x=None, input_fn=None, batch_size=None, outputs=None, as_iterable=False) Runs inference to determine the class probability predictions.

tf.contrib.distributions.Chi2WithAbsDf.event_shape(name='event_shape') Shape of a single sample from a single batch as a 1-D int32 Tensor. Args: name: name to give to the op Returns: event_shape: Tensor.

tf.TensorArray.pack(name=None) Return the values in the TensorArray as a packed Tensor. All of the values must have been written and their shapes must all match. Args: name: A name for the operation (optional). Returns: All the tensors in the TensorArray packed into one tensor.