tensorflow - 属性错误: 'tensorflow.python.ops.rnn' has no attribute 'rnn'

Question

我正在关注this tutorial关于循环神经网络。

这是导入:

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.python.ops import rnn
from tensorflow.contrib.rnn import core_rnn_cell

这是输入处理的代码:

x = tf.transpose(x, [1,0,2])
x = tf.reshape(x, [-1, chunk_size])
x = tf.split(x, n_chunks, 0)

lstm_cell = core_rnn_cell.BasicLSTMCell(rnn_size)
outputs, states = rnn.rnn(lstm_cell, x, dtype=tf.float32)

我在输出、状态中收到以下错误:

AttributeError: module 'tensorflow.python.ops.rnn' has no attribute 'rnn'

TensorFlow 最近更新了，那么有问题的行的新代码应该是什么

Answer 1

对于使用较新版本的tensorflow的人，请将以下内容添加到代码中:

from tensorflow.contrib import rnn 


lstm_cell = rnn.BasicLSTMCell(rnn_size) 
outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32)

而不是

from tensorflow.python.ops import rnn, rnn_cell 
lstm_cell = rnn_cell.BasicLSTMCell(rnn_size,state_is_tuple=True) 
outputs, states = rnn.rnn(lstm_cell, x, dtype=tf.float32)

PS:@BrendanA 建议使用 tf.nn.rnn_cell.LSTMCell 代替 rnn_cell.BasicLSTMCell