tf.nn.rnn_cell.MultiRNNCell

num_units = [200, 100]
cells = [tf.nn.rnn_cell.GRUCell(num_units=n) for n in num_units]
stacked_rnn_cell = tf.nn.rnn_cell.MultiRNNCell(cells)
rnn_outputs, states = tf.nn.dynamic_rnn(stacked_rnn_cell, X, dtype=tf.float32)

最后一个cell的num_units必须和下面的n_neurons相同

stacked_rnn_outputs = tf.reshape(rnn_outputs, [-1, n_neurons])
stacked_outputs = tf.layers.dense(stacked_rnn_outputs, n_outputs)
outputs = tf.reshape(stacked_outputs, [-1, n_steps, n_outputs])

tf.nn.rnn_cell.MultiRNNCell

原文：https://www.cnblogs.com/yaos/p/9966081.html