Tensorflow LSTM 抛出 ValueError: Shape () must have rank at least 2

Question

尝试运行时，抛出以下异常（ValueError）

ValueError: Shape () must have rank at least 2

这是针对以下行抛出的：

states_series, current_state = tf.contrib.rnn.static_rnn(cell, inputs_series, init_state)

这里cell定义的地方：

cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple=True)

查看RNN和Tesor_shape的规则，我可以看到这是某种张量维度形状问题。据我所知，它没有被BasicLSTMCell视为一个秩为 2 的矩阵？

完整错误：

/Library/Frameworks/Python.framework/Versions/3.6/bin/python3.6 /Users/glennhealy/PycharmProjects/firstRNNTest/LSTM-RNN.py
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6
  return f(*args, **kwds)
Traceback (most recent call last):
  File "/Users/glennhealy/PycharmProjects/firstRNNTest/LSTM-RNN.py", line 42, in <module>
    states_series, current_state = tf.contrib.rnn.static_rnn(cell, inputs_series, init_state)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 1181, in static_rnn
    input_shape = first_input.get_shape().with_rank_at_least(2)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/tensor_shape.py", line 670, in with_rank_at_least
    raise ValueError("Shape %s must have rank at least %d" % (self, rank))
ValueError: Shape () must have rank at least 2

Process finished with exit code 1

编码：

state_size = 4
cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple=True)
states_series, current_state = tf.contrib.rnn.static_rnn(cell, inputs_series, init_state)

Tensorflow 1.2.1 Python 3.6 NumPy

更新更多信息：

考虑到@Maxim 给出的建议，我可以看到问题是我的input_series，这导致了形状问题，但是，我似乎无法理解他的建议。

一些有助于解决问题的更多信息，看看我是否能理解如何解决这个问题：

以下是否可以替代我的 BatchY 和 BatchX 占位符？？

X = tf.placeholder(dtype=tf.float32, shape=[None, n_steps, n_inputs])
X_seqs = tf.unstack(tf.transpose(X, perm=[1, 0, 2]))
basic_cell = tf.nn.rnn_cell.BasicLSTMCell(num_units=n_neurons)
output_seqs, states = tf.nn.static_rnn(basic_cell, X_seqs,         dtype=tf.float32)

那么，我是否必须对以下内容进行更改以反映以下内容的语法？

batchX_placeholder = tf.placeholder(tf.int32, [batch_size,      truncated_backprop_length])
batchY_placeholder = tf.placeholder(tf.float32, [batch_size,    truncated_backprop_length])

#unpacking the columns:
labels_series = tf.unstack(batchY_placeholder, axis=1)
inputs_series = tf.split(1, truncated_backprop_length, batchX_placeholder)

#Forward pass
cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple=True)
states_series, current_state = tf.contrib.rnn.static_rnn(cell, inputs_series, init_state)

losses = [tf.nn.sparse_softmax_cross_entropy_with_logits(logits, labels) for logits, labels in zip(logits_series,labels_series)]
total_loss = tf.reduce_mean(losses)

Answer 1

是的，问题出在inputs_series. 根据错误，它是一个形状为 的张量()，即只是一个数字。

来自tf.nn.static_rnn文档：

inputs：输入的长度T列表，每个输入都是形状的张量[batch_size, input_size]，或此类元素的嵌套元组。

在大多数情况下，您希望inputs成为[seq_length, None, input_size]，其中：

• seq_length是序列长度，或 LSTM 单元的数量。
• None代表批量大小（任意）。
• input_size是每个单元格的特征数量。

因此，请确保您的占位符（以及inputs_series由它们转换而来的 ）具有适当的形状。例子：

X = tf.placeholder(dtype=tf.float32, shape=[None, n_steps, n_inputs])
X_seqs = tf.unstack(tf.transpose(X, perm=[1, 0, 2]))
basic_cell = tf.nn.rnn_cell.BasicLSTMCell(num_units=n_neurons)
output_seqs, states = tf.nn.static_rnn(basic_cell, X_seqs, dtype=tf.float32)

更新：

这是分割张量的错误方法：

# WRONG!
inputs_series = tf.split(1, truncated_backprop_length, batchX_placeholder)

你应该这样做（注意参数的顺序）：

inputs_series = tf.split(batchX_placeholder, truncated_backprop_length, axis=1)