Keras:ValueError:输入0是不兼容的层问题

时间:2017-02-20 03:10:21

标签: python linux tensorflow keras keras-layer

我使用带有Tensorflow的Keras作为后端并获得不兼容的错误:

model = Sequential()
model.add(LSTM(64, input_dim = 1))
model.add(Dropout(0.2))
model.add(LSTM(16))

以下错误显示:

Traceback (most recent call last):
  File "train_lstm_model.py", line 36, in <module>
    model.add(LSTM(16))
  File "/home/***/anaconda2/lib/python2.7/site-packages/keras/models.py", line 332, in add
    output_tensor = layer(self.outputs[0])
  File "/home/***/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 529, in __call__
    self.assert_input_compatibility(x)
  File "/home/***/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 469, in assert_input_compatibility
    str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer lstm_2: expected ndim=3, found ndim=2

如何解决此问题?

Keras版本:1.2.2 Tensorflow版本:0.12

1 个答案:

答案 0 :(得分:4)

LSTM图层正在接受(len_of_sequences, nb_of_features)形状的输入。您提供的输入形状仅为1-dim,因此错误来自此处。错误消息的确切形式来自于数据的实际形状包括batch_size这一事实。因此,馈送到图层的数据的实际形状为(batch_size, len_of_sequences, nb_of_features)。您的形状为(batch_size, 1),这就是3d2d输入背后的原因。

此外 - 您可能与第二层有类似的问题。为了使您的LSTM图层返回序列,您应将其定义更改为:

model.add(LSTM(64, input_shape = (len_of_seq, nb_of_features), return_sequences=True)

或:

model.add(LSTM(64, input_dim = nb_of_features, input_len = len_of_sequence, return_sequences=True)