这是我的模特:
rnn_cell = tf.contrib.rnn.BasicRNNCell(512)
m_rnn_cell = tf.contrib.rnn.MultiRNNCell([rnn_cell]*3, state_is_tuple = False)
prediction, state = tf.nn.dynamic_rnn(m_rnn_cell, X, dtype=tf.float32)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
error = tf.reduce_mean((labels - prediction)**2
train = tf.train.GradientDescentOptimizer(learning_rate).minimize(error)
X是我用来输入数据的占位符。我想用几句英语句子训练它。我怎么做?如何塑造我的数据,标签和占位符?你能提供训练它的代码吗?