如何使用RNNCells将dropout添加到我的tensorflow神经网络中？

import tensorflow as tf
from tensorflow.contrib.rnn import RNNCell

class MyRNNCell(RNNCell):
    def __init__(self, num_units, dropout_rate):
        self._num_units = num_units
        self._dropout_rate = dropout_rate

    @property
    def state_size(self):
        return self._num_units

    @property
    def output_size(self):
        return self._num_units

    def __call__(self, inputs, state, scope=None):
        # 添加dropout层
        inputs = tf.nn.dropout(inputs, rate=self._dropout_rate)
        # 实现自定义的RNN逻辑
        # ...
        return output, new_state

# 定义超参数
num_units = 128
dropout_rate = 0.2

# 创建RNNCell实例
cell = MyRNNCell(num_units, dropout_rate)

# 构建RNN网络
inputs = tf.placeholder(tf.float32, [None, sequence_length, input_dim])
initial_state = cell.zero_state(batch_size, tf.float32)
outputs, final_state = tf.nn.dynamic_rnn(cell, inputs, initial_state=initial_state)