如何使用 Tensorflow 的数据集 API 迭代器作为(递归)神经网络的输入？

Question

使用TensorFlow的数据集API迭代器时，我的目标是定义在迭代器的get_next()张量上操作的RNN作为输入（请参阅代码中的(1)）。

>> >

但是，只需用get_next()定义dynamic_rnn作为输入会导致错误：ValueError: Initializer for variable rnn/basic_lstm_cell/kernel/ is from inside a control-flow construct, such as a loop or conditional. When creating a variable inside a loop or conditional, use a lambda as the initializer.

现在，我知道一个解决方法是简单地为next_batch创建一个占位符，然后是eval() Tensor（因为您无法传递张量）并使用feed_dict（在代码中请参见X和(2)）。但是，如果我正确理解它，那么这不是一个有效的解决方案，因为我们首先评估然后重新初始化张量。

有什么方法可以：

1. 直接在迭代器的输出顶部定义dynamic_rnn;

或：

2. 某种程度上直接将现有的get_next()张量传递给占位符，这是dynamic_rnn的输入？

完整的工作示例；(1)版本是我想要的，但事实并非如此，而(2)是有效的解决方法。

import tensorflow as tf
from tensorflow.contrib.rnn import BasicLSTMCell
from tensorflow.python.data import Iterator
data = [ [[1], [2], [3]], [[4], [5], [6]], [[1], [2], [3]] ]
dataset = tf.data.Dataset.from_tensor_slices(data)
dataset = dataset.batch(2)
iterator = Iterator.from_structure(dataset.output_types,
                                   dataset.output_shapes)
next_batch = iterator.get_next()
iterator_init = iterator.make_initializer(dataset)
# (2):
X = tf.placeholder(tf.float32, shape=(None, 3, 1))
cell = BasicLSTMCell(num_units=8)
# (1):
# outputs, states = lstm_outputs, lstm_states = tf.nn.dynamic_rnn(cell, next_batch, dtype=tf.float32)
# (2):
outputs, states = lstm_outputs, lstm_states = tf.nn.dynamic_rnn(cell, X, dtype=tf.float32)
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    sess.run(iterator_init)
    # (1):
    # o, s = sess.run([outputs, states])
    # o, s = sess.run([outputs, states])
    # (2):
    o, s = sess.run([outputs, states], feed_dict={X: next_batch.eval()})
    o, s = sess.run([outputs, states], feed_dict={X: next_batch.eval()})

（使用Tensorflow 1.4.0，Python 3.6。）

非常感谢：）

Answer 1

事实证明，神秘错误可能是Tensorflow中的错误，请参见https://github.com/tensorflow/tensorflow/tensorflow/issues/14729。更具体地说，该错误确实来自馈送错误的数据类型（在上面的我的示例中，data数组包含int32值，但应包含浮子）。

而不是获得ValueError: Initializer for variable rnn/basic_lstm_cell/kernel/ is from inside a control-flow construct错误，
TensorFlow应该返回：
TypeError: Tensors in list passed to 'values' of 'ConcatV2' Op have types [int32, float32] that don't all match.（请参阅1）。

要解决此问题，只需更改
data = [ [[1], [2], [3]], [[4], [5], [6]], [[1], [2], [3]] ]

data = np.array([[ [1], [2], [3]], [[4], [5], [6]], [[1], [2], [3]] ], dtype=np.float32)

然后以下代码应正常工作：

import tensorflow as tf
import numpy as np
from tensorflow.contrib.rnn import BasicLSTMCell
from tensorflow.python.data import Iterator
data = np.array([[ [1], [2], [3]], [[4], [5], [6]], [[1], [2], [3]] ], dtype=np.float32)
dataset = tf.data.Dataset.from_tensor_slices(data)
dataset = dataset.batch(2)
iterator = Iterator.from_structure(dataset.output_types,
                                   dataset.output_shapes)
next_batch = iterator.get_next()
iterator_init = iterator.make_initializer(dataset)
# (2):
# X = tf.placeholder(tf.float32, shape=(None, 3, 1))
cell = BasicLSTMCell(num_units=8)
# (1):
outputs, states = lstm_outputs, lstm_states = tf.nn.dynamic_rnn(cell, next_batch, dtype=tf.float32)
# (2):
# outputs, states = lstm_outputs, lstm_states = tf.nn.dynamic_rnn(cell, X, dtype=tf.float32)
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    sess.run(iterator_init)
    # (1):
    o, s = sess.run([outputs, states])
    o, s = sess.run([outputs, states])
    # (2):
    # o, s = sess.run([outputs, states], feed_dict={X: next_batch.eval()})
    # o, s = sess.run([outputs, states], feed_dict={X: next_batch.eval()})