将编码器从自动编码器连接到LSTM

我认为主要的问题是因为最后一个 encoded 不是重复向量。要将编码器输出馈送到LSTM,需要通过 RepeatVector 图层。换句话说,编码器的最后一个输出需要 [batch_size, time_steps, dim] 形状能够被送入LSTM。这可能就是你要找的?

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])

decoded 到 encode_repeat

你的代码已经给出了答案。 encoder 在其最后一层中具有二维的lstm(number\u batch,number\u features),而不是(number\u batches,number\u timesteps,number\u features)。 这是因为你没有 return_sequences = True

但是你想做的和你用解码器做的是一样的:你应用RepeatVector层使输入的形状是三维的,因此可以输入到LSTM层。