用于压缩的序列自动编码器

Question

我想构建一个序列来对自动编码器进行序列化以进行信号压缩。 我想从一个基于LSTM的标准自动编码器开始。然而，Keras抱怨我的模特。什么提示我做错了什么

from keras.layers import Input, LSTM, RepeatVector
from keras.models import Model


timesteps = 10
input_dim = 4

latent_dim = 128

#Create the encoder:
inputs = Input(shape=(timesteps, input_dim))
encoded = LSTM(latent_dim)(inputs)
encoder = Model(inputs, encoded)

#Create the decoder:
decInput = Input(shape=(latent_dim))    
decoded = RepeatVector(timesteps)(decInput)
decoded = LSTM(input_dim, return_sequences=True)(decoded)
decoder = Model(decInput,decoded)

#Joining models:
joinedInput = Input(shape=(timesteps, input_dim))
encoderOut = encoder(joinedInput)    
joinedOut = decoder(encoderOut)
sequence_autoencoder = Model(joinedInput,joinedOut)

我上线encoded = LSTM(latent_dim)(inputs)

错误

  

TypeError：预期的int32，得到的列表包含＆＃39; _Message＆＃39;代替。