我正在尝试使用带有TensorFlow后端的Keras将一些RNN串联起来 . 我可以使用单个 SimpleRNN
图层创建模型,但是当我尝试添加第二个 SimpleRNN
图层时,我无法确定合适的输入大小 .
from keras import models
from keras.layers.recurrent import SimpleRNN
from keras.layers import Activation
model = models.Sequential()
hidden_units = 256
skeleton_dimensions = 3 * 16 # 3 dimensions for 16 joints
input_temporal_length = 7
in_shape = (input_temporal_length, skeleton_dimensions,)
# three hidden layers of 256 each
model.add(SimpleRNN(hidden_units, input_shape=in_shape,
activation='relu', use_bias=True,))
# what input shape is this supposed to have?
model.add(SimpleRNN(hidden_units, input_shape=(1, skeleton_dimensions,),
activation='relu', use_bias=True,))
我的第二个 SimpleRNN
应该作为输入形状?
Recurrent Layers的文档似乎暗示:
如果return_sequences输出形状:具有形状的3D张量(batch_size,timesteps,units) . 否则,2D张量与形状(batch_size,units) .
鉴于 return_sequences
自动设置为 False
我试图适当地设置下一个维度的 input_shape
但是我收到错误:
Using TensorFlow backend.
Traceback (most recent call last):
File "rnn_agony.py", line 19, in <module>
activation='relu', use_bias=True,))
File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 455, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python3.5/dist-packages/keras/layers/recurrent.py", line 252, in __call__
return super(Recurrent, self).__call__(inputs, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py", line 511, in __call__
self.assert_input_compatibility(inputs)
File "/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py", line 413, in assert_input_compatibility
str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer simple_rnn_2: expected ndim=3, found ndim=2
1 回答
如果要堆叠RNN,则需要设置
return_sequences=True
,您将不再需要设置input_shape
. 这具有直观意义,因为RNN期望输入序列 .