TensorFlow报错：Shape (44, ?) must have rank at least 3 ？

Question

用TensorFlow执行RNN，报错ValueError: Shape (44, ?) must have rank at least 3，下面是程序的部分代码，请问应该在哪里修改下？谢谢

解析函数：

feature = ['feature1',......,'feature44']
label = 'label2'
featureNames = list(feature)
featureNames.append(label)
columns = [tf.FixedLenFeature(shape=[1], dtype=tf.float32) for k in featureNames]
featuresDict = dict(zip(featureNames, columns))
def parse_tfrecord(example_proto):
  parsed_features = tf.parse_single_example(example_proto, featuresDict)
  labels = parsed_features.pop(label)
  return parsed_features, tf.cast(labels, tf.int32)

输入函数（原始数据是有44个特征值的数值序列，每个序列为一样本）：

def tfrecord_input_fn(fileName,numEpochs=None,shuffle=True,batchSize=None):
  #读取tfrecord数据
  dataset = tf.data.TFRecordDataset(fileName, compression_type='GZIP')
  #执行解析函数
  dataset = dataset.map(parse_tfrecord)
  #打乱数据
  if shuffle:
    dataset = dataset.shuffle(buffer_size=batchSize * 100*numEpochs)
  #每32个样本作为一个batch
  dataset = dataset.batch(32)
  #重复数据
  dataset = dataset.repeat(numEpochs)

  print('features:',features)
  print('labels:',labels)
  iterator = dataset.make_one_shot_iterator()
  features, labels = iterator.get_next()
  return features, labels

打印返回值结果：

features: {'feature1': <tf.Tensor 'IteratorGetNext_21:0' shape=(?, 1) dtype=float32>, 'feature2': <tf.Tensor 'IteratorGetNext_21:1' shape=(?, 1) dtype=float32>,......， 'feature44': <tf.Tensor 'IteratorGetNext_21:43' shape=(?, 1) dtype=float32>}
labels: Tensor("IteratorGetNext_21:44", shape=(?, 1), dtype=int32)

执行网络后报错：

ValueError: Shape (44, ?) must have rank at least 3

Answer 1

该错误的意思是传入的数据集X的维度只有二维，而tf.nn.dynamic_rnn()要求传入的数据集的维度是三维（batch_size, squence_length, num_features）。在这里因为特征是一维，因此没有显示。

https://www.cnblogs.com/jiangxinyang/p/9390355.html