class tf.nn.rnn_cell.LSTMCell Long short-term memory unit (LSTM) recurrent network cell. The default

tf.nn.rnn_cell.LSTMCell.__call__(inputs, state, scope=None) Run one step of LSTM. Args:

tf.nn.rnn_cell.InputProjectionWrapper.__init__(cell, num_proj, input_size=None) Create a cell with input projection.

tf.nn.rnn_cell.MultiRNNCell.__init__(cells, state_is_tuple=True) Create a RNN cell composed sequentially of a number of RNNCells

class tf.nn.rnn_cell.MultiRNNCell RNN cell composed sequentially of multiple simple cells.

class tf.nn.rnn_cell.OutputProjectionWrapper Operator adding an output projection to the given cell. Note:

tf.nn.rnn_cell.BasicLSTMCell.state_size

tf.nn.rnn_cell.MultiRNNCell.zero_state(batch_size, dtype) Return zero-filled state tensor(s). Args:

tf.nn.rnn_cell.LSTMCell.output_size

tf.nn.rnn_cell.DropoutWrapper.state_size