如何构建堆叠的序列到序列的自动编码器？
如何构建堆叠的序列到序列的自动编码器？
提问于 2018-01-17 19:17:02
在keras博客中：“在Keras中构建自动编码器”提供了以下代码来构建单序列到序列自动编码器
from keras.layers import Input, LSTM, RepeatVector
from keras.models import Model
inputs = Input(shape=(timesteps, input_dim))
encoded = LSTM(latent_dim)(inputs)
decoded = RepeatVector(timesteps)(encoded)
decoded = LSTM(input_dim, return_sequences=True)(decoded)
sequence_autoencoder = Model(inputs, decoded)
encoder = Model(inputs, encoded)我想构建堆叠式自动编码器，如何更新此代码来构建堆叠式自动编码器？
我自己试过，下面是我的代码：
timesteps = 3
input_dim = 1
inputs = Input(shape=(timesteps, input_dim))
encoded = LSTM(4)(inputs)
encoded = RepeatVector(timesteps)(encoded)
encoded = LSTM(2)(encoded)
encoded = RepeatVector(timesteps)(encoded)
decoded = LSTM(4,return_sequences = True)(encoded)
decoded = LSTM(input_dim,return_sequences = True)(decoded)
sequence_autoencoder = Model(inputs, decoded)
sequence_autoencoder.compile(loss='mean_squared_error', optimizer='Adam')
sequence_autoencoder.fit(x_train, x_train,
epochs=100,
batch_size=1,
shuffle=True,
)我想知道，这段代码是正确的，还是我漏掉了什么？
回答 1
Stack Overflow用户
发布于 2018-01-17 21:46:19
您创建的代码尝试遵循与您找到的示例相同的理念。但是您太快地销毁了这个序列(因此您最终使用了一个额外的RepeatVector )。
为了避免这种情况，您可以在所有编码层中使用return_sequences=True，最后一个编码层除外。这使序列保持为一个序列，允许更大的解释力，因为您不会太快地折叠数据。
#add return_sequences=True to all layers except for the last
encoded = LSTM(4, return_sequences=True)(inputs)
#do not use RepeatVector, you've got your sequences preserved with their length
#the last encoder layer is the only one that collapses the sequence
encoded = LSTM(2)(encoded)
#this RepeatVector is the only that is needed, to restore the sequence length
decoded = RepeatVector(timesteps)(encoded)
#the rest is the same
decoded = LSTM(4,return_sequences = True)(encoded)
decoded = LSTM(input_dim,return_sequences = True)(decoded)页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/48299833
复制相关文章
相似问题