Question

我尝试使用带有TensorFlow后端的Keras将几个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尺寸。

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的文档似乎意味着：

输出形状


if return_sequences：具有形状的3D张量（batch_size，timesteps，   单位）。

否则，2D张量与形状（batch_size，units）。

鉴于return_sequences自动设置为False，我尝试正确设置下一个维度的input_shape，但收到错误：

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

Answer 1

如果您要堆叠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。

输入堆叠的RNN的形状

1 个答案: