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)

我希望将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])

但这给了我尺寸错误。

Input 0 is incompatible with layer lstm_3: expected ndim=3, found ndim=2

如何正确执行此操作？？

Answer 1

我认为主要问题是由于最后一个encoded不是重复向量这一事实引起的。为了将编码器输出馈送到LSTM，它需要通过RepeatVector层发送。换句话说，编码器的最后一个输出需要具有[batch_size, time_steps, dim]的形状才能被输入到LSTM中。这可能是您要找的东西吗？

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

您的代码已经给出了答案。 encoder在其最后一层具有二维（number_batch，number_features）而不是（number_batches，number_timesteps，number_features）的lstm。这是因为您没有设置return_sequences = True（这是您的预期行为）。

但是，您要执行的操作与使用解码器的操作相同：您可以应用RepeatVector图层使输入形状为3维，从而可以将其输入到LSTM图层中。

将编码器从自动编码器连接到LSTM

2 个答案: