使用tf.contrib在模型中插入LSTM单元格

Question

我正在尝试在下面的模型中添加LSTM层，但是由于tf.contrib没有LSTM层，所以我很难。它有一些LSTM单元格的东西，我似乎无法理解。我想坚持使用tf.contrib.layers或tf.layers，因为我的其他代码围绕它们构建。我正在使用tensorflow 1.5.1

def mlp_model(input, num_outputs, scope, reuse=False, num_units=64, rnn_cell=None):
# This model takes as input an observation and returns values of all actions
    with tf.variable_scope(scope, reuse=reuse):
        out = input
        out = layers.fully_connected(out, num_outputs=num_units, activation_fn=tf.nn.relu, weights_initializer=tf.glorot_normal_initializer(seed=10, dtype=tf.float64))
        out = layers.fully_connected(out, num_outputs=num_units, activation_fn=tf.nn.relu, weights_initializer=tf.glorot_normal_initializer(seed=5, dtype=tf.float64))
        out = layers.fully_connected(out, num_outputs=num_outputs, activation_fn=None, weights_initializer=tf.zeros_initializer(), biases_initializer=tf.zeros_initializer())
    return out