Question

假设我有两个输入：In []: [[x, y] for x, y in it.combinations(L, r=2) if set(x).issubset(y) and len(set(y)-set(x)) <= 1] Out[]: [[[(1, 3)], [(1, 3), (2, 4)]], [[(1, 3)], [(1, 3), (1, 4)]], [[(1, 3)], [(1, 2), (1, 3)]], [[(1, 3), (2, 4)], [(1, 3), (2, 4), (1, 2)]], [[(1, 2)], [(1, 2), (1, 3)]], [[(1, 2), (1, 3)], [(1, 3), (2, 4), (1, 2)]]]和X，并且我想设计并联合自动编码器来重构Y和X'。

如图所示，Y'是音频输入，X是视频输入。这种深度架构很酷，因为它具有两个输入和两个输出。而且，它们在中间共享某个层。我的问题是如何使用Y编写此自动编码器。假设除了中间的共享层之外，每个层都是完全连接的。

这是我的代码，如下所示：

Keras

我只是中间有from keras.layers import Input, Dense from keras.models import Model import numpy as np X = np.random.random((1000, 100)) y = np.random.random((1000, 300)) # x and y can be different size # the X autoencoder layer Xinput = Input(shape=(100,)) encoded = Dense(50, activation='relu')(Xinput) encoded = Dense(20, activation='relu')(encoded) encoded = Dense(15, activation='relu')(encoded) decoded = Dense(20, activation='relu')(encoded) decoded = Dense(50, activation='relu')(decoded) decoded = Dense(100, activation='relu')(decoded) # the Y autoencoder layer Yinput = Input(shape=(300,)) encoded = Dense(120, activation='relu')(Yinput) encoded = Dense(50, activation='relu')(encoded) encoded = Dense(15, activation='relu')(encoded) decoded = Dense(50, activation='relu')(encoded) decoded = Dense(120, activation='relu')(decoded) decoded = Dense(300, activation='relu')(decoded)和15的{{1}}个节点。我的问题是如何使用损失函数X来训练这种联合自动编码器？

谢谢

Answer 1

您的代码使用方式有两个不同的模型。虽然您可以简单地将共享表示层的输出用于以下两个子网的两次，但是您必须合并两个子网作为输入：

Xinput = Input(shape=(100,))
Yinput = Input(shape=(300,))

Xencoded = Dense(50, activation='relu')(Xinput)
Xencoded = Dense(20, activation='relu')(Xencoded)


Yencoded = Dense(120, activation='relu')(Yinput)
Yencoded = Dense(50, activation='relu')(Yencoded)

shared_input = Concatenate()([Xencoded, Yencoded])
shared_output = Dense(15, activation='relu')(shared_input)

Xdecoded = Dense(20, activation='relu')(shared_output)
Xdecoded = Dense(50, activation='relu')(Xdecoded)
Xdecoded = Dense(100, activation='relu')(Xdecoded)

Ydecoded = Dense(50, activation='relu')(shared_output)
Ydecoded = Dense(120, activation='relu')(Ydecoded)
Ydecoded = Dense(300, activation='relu')(Ydecoded)

现在您有两个单独的输出。因此，您需要两个单独的损失函数，无论如何都要添加这些函数，以便编译模型：

model = Model([Xinput, Yinput], [Xdecoded, Ydecoded])
model.compile(optimizer='adam', loss=['mse', 'mse'], loss_weights=[1., 1.])

您可以通过以下方式简单地训练模型：

model.fit([X_input, Y_input], [X_label, Y_label])

Answer 2

让我澄清一些事情，您想要在一个模型中同时包含两个输入层和两个共享层的输出层，对吗？

我认为这可以为您提供一个想法：

from keras.layers import Input, Dense, Concatenate
from keras.models import Model
import numpy as np

X = np.random.random((1000, 100))
y = np.random.random((1000, 300))  # x and y can be different size

# the X autoencoder layer 
Xinput = Input(shape=(100,))

encoded_x = Dense(50, activation='relu')(Xinput)
encoded_x = Dense(20, activation='relu')(encoded_x)

# the Y autoencoder layer 
Yinput = Input(shape=(300,))

encoded_y = Dense(120, activation='relu')(Yinput)
encoded_y = Dense(50, activation='relu')(encoded_y)

# concatenate encoding layers
c_encoded = Concatenate(name="concat", axis=1)([encoded_x, encoded_y])
encoded = Dense(15, activation='relu')(c_encoded)

decoded_x = Dense(20, activation='relu')(encoded)
decoded_x = Dense(50, activation='relu')(decoded_x)
decoded_x = Dense(100, activation='relu')(decoded_x)

out_x = SomeOuputLayers(..)(decoded_x)

decoded_y = Dense(50, activation='relu')(encoded)
decoded_y = Dense(120, activation='relu')(decoded_y)
decoded_y = Dense(300, activation='relu')(decoded_y)

out_y = SomeOuputLayers(..)(decoded_y)

# Now you have two input and two output with shared layer
model = Model([Xinput, Yinput], [out_x, out_y])

如何将Keras合并层用于具有两个输出的自动编码器

2 个答案: