一直在等待，一直会等待 TensorFlow常见API--4

tf.nn.static_rnn

tf.nn.static_rnn(
    cell,
    inputs,
    initial_state=None,
    dtype=None,
    sequence_length=None,
    scope=None
)

       由RNNCell cell声明创建递归神经网络。初始状态可以被提供。如果提供了sequence_length vector，将自动进行计算。
       输入参数：
cell: RNNCell实例
inputs: A length T list of inputs, each a Tensor of shape [batch_size, input_size], or a nested tuple of such elements.
sequence_length: 声明输入中每个序列的长度。整形向量，size [batch_size], values in [0, T).
       输出参数：
outputs： 长度为T的List，每个元素为一个X对应的输出结果，或者是每个元素嵌套的元组
state： 最后一个隐状态

tf.nn.static_bidirectional_rnn

tf.nn.static_bidirectional_rnn(
    cell_fw,
    cell_bw,
    inputs,
    initial_state_fw=None,
    initial_state_bw=None,
    dtype=None,
    sequence_length=None,
    scope=None
)

盗用一张图用于说明

       输出参数：
输出结果为元组 (outputs, output_state_fw, output_state_bw) 其中，outputs is a length T list of outputs (one for each input), 长度采用depth-concatenated forward and backward的输出结果. output_state_fw is the final state of the forward rnn. output_state_bw is the final state of the backward rnn.