在Keras中使用LSTM自动编码器进行多个时间序列预测

Question

我试图建立一个自动编码LSTM如图所示这里 。
我的代码：

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

inputs = Input(shape=(window_length, input_dim))
encoded = LSTM(latent_dim)(inputs)

decoded = RepeatVector(window_length)(encoded)
decoded = LSTM(input_dim, return_sequences=True)(decoded)

model = Model(inputs, decoded)
model.fit(batch_size=512)

数据集的形状为：（行，window_length，input_dim）。
当我尝试调用fit（）时，出现此错误：

ValueError: Cannot feed value of shape (512, 221) for Tensor u'lstm_2_target:0', which has shape '(?, ?, ?)'

这个模型真的很简单，我不明白是什么问题。

编辑
型号摘要：

Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 10, 221)           0         
_________________________________________________________________
lstm_1 (LSTM)                (None, 128)               179200    
_________________________________________________________________
repeat_vector_1 (RepeatVecto (None, 10, 128)           0         
_________________________________________________________________
lstm_2 (LSTM)                (None, 10, 221)           309400    
=================================================================
Total params: 488,600
Trainable params: 488,600
Non-trainable params: 0

Answer 1

如果代码完全按照上述方式运行，则可能需要对其进行编译：

model.compile(optimizer='rmsprop', loss='mse', metrics=['acc', 'cosine_proximity'])