tf.contrib.rnn.CoupledInputForgetGateLSTMCell.zero_state(batch_size, dtype) Return zero-filled state tensor(s).

tf.contrib.rnn.GridLSTMCell.state_tuple_type

tf.contrib.bayesflow.stochastic_graph.surrogate_loss(sample_losses, stochastic_tensors=None, name='SurrogateLoss') Surrogate loss

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

tf.sparse_to_dense(sparse_indices, output_shape, sparse_values, default_value=0, validate_indices=True, name=None) Converts a

tf.train.shuffle_batch_join(tensors_list, batch_size, capacity, min_after_dequeue, seed=None, enqueue_many=False, shapes=None, allow_smaller_final_batch=False, shared_name=None

tf.contrib.training.NextQueuedSequenceBatch.save_state(state_name, value, name=None) Returns an op to save the current batch of

tf.FixedLenSequenceFeature.__new__(_cls, shape, dtype, allow_missing=False) Create new instance of FixedLenSequenceFeature(shape

tf.assert_greater_equal(x, y, data=None, summarize=None, message=None, name=None) Assert the condition x >= y

tf.matrix_inverse(input, adjoint=None, name=None) Computes the inverse of one or more square invertible matrices or their