Question

设置

我目前正在尝试为我的LSTM实现关注层。我知道，在哪里可以找到可行的示例，这不是我的问题的重点。我最终得到了这段代码片段

from keras.layers import Input,LSTM,TimeDistributed,Activation,Multiply,Lambda,Dense
from keras.models import Model
import keras.backend as K
inp = Input(shape=(None, 10))
lstm = LSTM(units=50, return_sequences=True)(inp)
att = TimeDistributed(Dense(1,activation="tanh"))(lstm)
att = K.squeeze(att,axis=-1)
att = Activation("softmax")(att)
final = Multiply()([att,lstm])
final = Lambda(lambda x: K.sum(x,axis=1))(final)
out = Dense(units=28,activation="softmax")(final)
model = Model(inp,out)

错误

当我尝试运行此代码时，出现以下错误

  File "...\model.py", line 56, in create_model
    out = Dense(units=28, activation="softmax")(final)
  File "C:\Users\user\AppData\Local\Continuum\anaconda3\envs\processing\lib\site-packages\keras\engine\base_layer.py", line 431, in __call__
    self.build(unpack_singleton(input_shapes))
  File "C:\Users\user\AppData\Local\Continuum\anaconda3\envs\processing\lib\site-packages\keras\layers\core.py", line 866, in build
    constraint=self.kernel_constraint)
  File "C:\Users\user\AppData\Local\Continuum\anaconda3\envs\processing\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\user\AppData\Local\Continuum\anaconda3\envs\processing\lib\site-packages\keras\engine\base_layer.py", line 249, in add_weight
    weight = K.variable(initializer(shape),
  File "C:\Users\user\AppData\Local\Continuum\anaconda3\envs\processing\lib\site-packages\keras\initializers.py", line 209, in __call__
    scale /= max(1., float(fan_in + fan_out) / 2)
TypeError: unsupported operand type(s) for +: 'NoneType' and 'int'

当我调试__call__的{{1}}时，可以看到VarianceScaling Initializer作为自变量由shape给出，这引起了问题。当我在(None,28)层之前执行打印语句以检查out层的输出形状时

final

符合预期。因此，print(final) >>Tensor("lambda_1/Sum:0", shape=(?, 50), dtype=float32)函数中的形状实际上应该是__call__。

问题

当我创建一个更简单的示例时

(50,28)

我的形状相同，但是完全没有错误。那么，错误的输入/输出形状处理是keras bug之上的问题吗？还是我错过了什么？

不同层之间Keras输入/输出形状处理的问题

0 个答案: