[basic_cell]*num_layers is really what you want?

[aodiwei]

Hi, I am confuse on [basic_cell]*num_layers in code:
stacked_lstm = tf.contrib.rnn.core_rnn_cell.MultiRNNCell([basic_cell]*num_layers, state_is_tuple=True)
This means copy num_layers same cell instances.
for multi lstm, should we use diff cell instances like:

cell = []
for i in range(num_layers):
    cell.append(tf.contrib.rnn.LSTMCell(hidden, state_is_tuple=True))
cell = tf.contrib.rnn.MultiRNNCell(cell,state_is_tuple=True)