将编码器从AutoEncoder连接到LSTM

Question

我有一个这样定义的自动编码器

inputs = Input(batch_shape=(1,timesteps, input_dim))

encoded = LSTM(4,return_sequences = True)(inputs)
encoded = LSTM(3,return_sequences = True)(encoded)
encoded = LSTM(2)(encoded)
decoded = RepeatVector(timesteps)(encoded) 
decoded =  LSTM(3,return_sequences = True)(decoded)                                   
decoded =  LSTM(4,return_sequences = True)(decoded)
decoded =  LSTM(input_dim,return_sequences = True)(decoded)

sequence_autoencoder = Model(inputs, decoded)

encoder = Model(inputs,encoded)

我希望编码器连接到这样的LSTM层

f_input = Input(batch_shape=(1, timesteps, input_dim))

encoder_input = encoder(inputs=f_input)

single_lstm_layer = LSTM(50, kernel_initializer=RandomUniform(minval=-0.05, maxval=0.05))(encoder_input)
drop_1 = Dropout(0.33)(single_lstm_layer)
output_layer = Dense(12, name="Output_Layer"
                         )(drop_1)

final_model = Model(inputs=[f_input], outputs=[output_layer])

但它给了我一个尺寸误差。

输入0与层lstm_3不兼容:预期的ndim=3，找到ndim=2

我怎么才能做好这件事呢？

Answer 1

我认为主要的问题产生于这样一个事实:最后一个encoded不是重复的载体。要将编码器输出提供给LSTM，需要通过RepeatVector层发送。换句话说，编码器的最后输出需要有[batch_size, time_steps, dim]形状才能被输入到LSTM中。这大概就是你要找的？

inputs = Input(batch_shape=(1,timesteps, input_dim))

encoded = LSTM(4,return_sequences = True)(inputs)
encoded = LSTM(3,return_sequences = True)(encoded)
encoded = LSTM(2)(encoded)
encoded_repeat = RepeatVector(timesteps)(encoded) 

decoded =  LSTM(3,return_sequences = True)(encoded_repeat)                                   
decoded =  LSTM(4,return_sequences = True)(decoded)
decoded =  LSTM(input_dim,return_sequences = True)(decoded)

sequence_autoencoder = Model(inputs, decoded)

encoder = Model(inputs,encoded_repeat)

f_input = Input(batch_shape=(1, timesteps, input_dim))

encoder_input = encoder(inputs=f_input)

single_lstm_layer = LSTM(50, kernel_initializer=RandomUniform(minval=-0.05, maxval=0.05))(encoder_input)
drop_1 = Dropout(0.33)(single_lstm_layer)
output_layer = Dense(12, name="Output_Layer"
                         )(drop_1)

final_model = Model(inputs=[f_input], outputs=[output_layer])

我已将您的第一个decoded重命名为encode_repeat

Answer 2

你的代码已经给出了答案。encoder的最后一层是二维(number_batch，number_features)，而不是(number_batches，number_timesteps，number_features)。这是因为您没有设置return_sequences = True(这是您的预期行为)。

但是，您想要做的是相同的，就像您对解码器所做的一样:您应用RepeatVector层使输入形状是三维的，因此可以将其输入到LSTM层中。