向 Keras 中的自动编码器添加乘法层

Question

我想在 LSTM 自动编码器之上添加一个多层。 乘法层应该将张量相乘以获得恒定值。 我编写了以下代码，它在没有多层的情况下工作。 有谁知道如何调整并使其正常工作？

import keras
from keras import backend as K
from keras.models import Sequential, Model
from keras.layers import Input, LSTM, RepeatVector, TimeDistributed
from keras.layers.core import Flatten, Dense, Dropout, Lambda
from keras.optimizers import SGD, RMSprop, Adam
from keras import objectives
from keras.engine.topology import Layer
import numpy as np

class LayerKMultiply(Layer):

    def __init__(self, output_dim, **kwargs):
        self.output_dim = output_dim
        self.k = Null
        super(LayerKMultiply, self).__init__(**kwargs)

    def build(self, input_shape):
        # Create a trainable weight variable for this layer.
        self.k = self.add_weight(
            name='k',
            shape=(),
            initializer='ones',
            dtype='float32',
            trainable=True,
        )
        super(LayerKMultiply, self).build(input_shape)  # Be sure to call this at the end

    def call(self, x):
        #return K.tf.multiply(self.k, x)
        return self.k * x

    def compute_output_shape(self, input_shape):
        return (input_shape[0], self.output_dim)

    timesteps, input_dim, latent_dim = 10, 3, 32


inputs = Input(shape=(timesteps, input_dim))
encoded = LSTM(latent_dim, return_sequences=False, activation='linear')(inputs)
decoded = RepeatVector(timesteps)(encoded)
decoded = LSTM(input_dim, return_sequences=True, activation='linear')(decoded)
decoded = TimeDistributed(Dense(input_dim, activation='linear'))(decoded)
#decoded = LayerKMultiply(k = 20)(decoded)

sequence_autoencoder = Model(inputs, decoded)
encoder = Model(inputs, encoded)

autoencoder = Model(inputs, decoded)
autoencoder.compile(optimizer='adam', loss='mse')

    X = np.array([[[1,2,3,4,5,6,7,8,9,10],[1,2,3,4,5,6,7,8,9,10],[1,2,3,4,5,6,7,8,9,10]]])
X = X.reshape(1,10,3)
p = autoencoder.predict(x=X, batch_size=1)
print(p)

我收到以下错误：

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-3-b2f9497bbf47> in <module>()
      7 decoded = LSTM(input_dim, return_sequences=True, activation='linear')(decoded)
      8 decoded = TimeDistributed(Dense(input_dim, activation='linear'))(decoded)
----> 9 decoded = LayerKMultiply(k = 20)(decoded)
     10 
     11 sequence_autoencoder = Model(inputs, decoded)

TypeError: __init__() missing 1 required positional argument: 'output_dim'

编辑

我想要实现的是下图中描述的架构：

https://github.com/mg64ve/SMTDAE/blob/master/images/SMTDAE.png https://github.com/mg64ve/SMTDAE/blob/master/images/REF.png

所以从这个意义上说，我相信多层应该在 TimeDistributed 和 Dense 层之前。 我修改了代码如下：

import keras
from keras import backend as K
from keras.models import Sequential, Model
from keras.layers import Input, LSTM, RepeatVector, TimeDistributed
from keras.layers.core import Flatten, Dense, Dropout, Lambda
from keras.optimizers import SGD, RMSprop, Adam
from keras import objectives
from keras.engine.topology import Layer
import numpy as np

class LayerKMultiply(Layer):

    def __init__(self, output_dim, **kwargs):
        self.output_dim = output_dim
        self.k = None
        super(LayerKMultiply, self).__init__(**kwargs)

    def build(self, input_shape):
        # Create a trainable weight variable for this layer.
        self.k = self.add_weight(
            name='k',
            shape=(),
            initializer='ones',
            dtype='float32',
            trainable=True,
        )
        super(LayerKMultiply, self).build(input_shape)  # Be sure to call this at the end

    def call(self, x):
        return self.k * x

    def compute_output_shape(self, input_shape):
        return (input_shape[0], input_shape[1], self.output_dim)

timesteps, input_dim, latent_dim = 31, 31, 32


inputs = Input(shape=(timesteps, input_dim))
encoded = LSTM(latent_dim, return_sequences=False, activation='linear')(inputs)
decoded = RepeatVector(timesteps)(encoded)
decoded = LSTM(input_dim, return_sequences=True, activation='linear')(decoded)
decoded = LayerKMultiply(20)(decoded)
decoded = TimeDistributed(Dense(input_dim, activation='linear'))(decoded)

autoencoder = Model(inputs, decoded)

batch_size = 100
X = np.zeros([5000,31,31])
autoencoder.fit(X, X, batch_size = batch_size, epochs=3)

autoencoder.compile(optimizer='adam', loss='mse')

但我仍然收到以下错误：

InvalidArgumentError: Incompatible shapes: [155,31,31] vs. [100,31,31]

Answer 1

我认为解决方案如下：

import keras
from keras import backend as K
from keras.models import Sequential, Model
from keras.layers import Input, LSTM, RepeatVector, TimeDistributed
from keras.layers.core import Flatten, Dense, Dropout, Lambda
from keras.optimizers import SGD, RMSprop, Adam
from keras import objectives
from keras.engine.topology import Layer
import numpy as np

class LayerKMultiply(Layer):

    def __init__(self, output_dim, **kwargs):
        self.output_dim = output_dim
        self.k = None
        super(LayerKMultiply, self).__init__(**kwargs)

    def build(self, input_shape):
        # Create a trainable weight variable for this layer.
        self.k = self.add_weight(
            name='k',
            shape=(),
            initializer='ones',
            dtype='float32',
            trainable=True,
        )
        super(LayerKMultiply, self).build(input_shape)  # Be sure to call this at the end

    def call(self, x):
        return self.k * x

    def compute_output_shape(self, input_shape):
        return (input_shape[0], input_shape[1], input_shape[2])

Answer 2

您将位置参数与关键字参数混合在一起。当您定义像 def __init__(self, output_dim, **kwargs) 这样的函数时，output_dim 是一个位置参数。您需要：

• 要么自己通过 20 LayerMultiply(20)(decoded)
• 或更改def __init__(self, k=10, **kwargs)
• 或从定义中删除output_dim并使用self.output_dim = kwargs['k']

更多信息here。