问题:Keras 报告 TypeError: unsupported operand type(s) for +: 'NoneType' and 'int'

我是 Keras 的初学者,只是写一个玩具示例。它报告了一个TypeError。代码和错误如下:

代码:

inputs = keras.Input(shape=(3, ))

cell = keras.layers.SimpleRNNCell(units=5, activation='softmax')
label = keras.layers.RNN(cell)(inputs)

model = keras.models.Model(inputs=inputs, outputs=label)
model.compile(optimizer='rmsprop',
              loss='mae',
              metrics=['acc'])

data = np.array([[1, 2, 3], [3, 4, 5]])
labels = np.array([1, 2])
model.fit(x=data, y=labels)

错误:

Traceback (most recent call last):
    File "/Users/david/Documents/code/python/Tensorflow/test.py", line 27, in <module>
        run()
    File "/Users/david/Documents/code/python/Tensorflow/test.py", line 21, in run
        label = keras.layers.RNN(cell)(inputs)
    File "/Users/david/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/layers/recurrent.py", line 619, in __call__
...
    File "/Users/david/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/init_ops.py", line 473, in __call__
        scale /= max(1., (fan_in + fan_out) / 2.)
TypeError: unsupported operand type(s) for +: 'NoneType' and 'int'

那么我该如何处理呢?

解答

RNN 层的输入将具有(num_timesteps, num_features)的形状,即每个样本由num_timesteps个时间步组成,其中每个时间步是长度为num_features的向量。此外,时间步长(即num_timesteps)的数量可以是可变的或未知的(即None),但特征的数量(即num_features)应该是固定的并从一开始就指定。因此,您需要更改 Input 层的形状以与 RNN 层保持一致。例如:

inputs = keras.Input(shape=(None, 3))  # variable number of timesteps each with length 3
inputs = keras.Input(shape=(4, 3))     # 4 timesteps each with length 3
inputs = keras.Input(shape=(4, None))  # this is WRONG! you can't do this. Number of features must be fixed

然后,您还需要更改输入数据的形状(即data)以及与您指定的输入形状一致(即它必须具有(num_samples, num_timesteps, num_features)的形状)。

作为旁注,您可以通过直接使用SimpleRNN层更简单地定义 RNN 层:

label = keras.layers.SimpleRNN(units=5, activation='softmax')(inputs)
Logo

学AI,认准AI Studio!GPU算力,限时免费领,邀请好友解锁更多惊喜福利 >>>

更多推荐