建立與keras LSTM的尺寸錯誤

Question

我想建立一個使用Keras的LSTM網絡。 我的時間seriese例子的大小爲492。我想用3前面的例子來預測下一個例子。因此，輸入轉換爲尺寸(num_samples,3*492)，輸出尺寸爲(num_samples,492)。

據this blog，我首先將我的數據大小爲形式的（num_samples，時間步長，功能）

#convert trainning data to 3D LSTM shape 
train_origin_x = train_origin_x.reshape((train_origin_x.shape[0],3,492)) 
test_origin_x = test_origin_x.reshape((test_origin_x.shape[0],3,492)) 
print(train_origin_x.shape,test_origin_x.shape) 
(216, 3, 492) (93, 3, 492) 
print(train_origin_y,test_origin_y) 
(216, 492) (93, 492) 

而下面是我的代碼來構建LSTM網絡

#building network 
model = Sequential() 
model.add(LSTM(hidden_units,return_sequences=True,input_shape=(train_origin_x.shape[1],train_origin_x.shape[2]))) 
model.add(Dense(492)) 
model.compile(loss='mse',optimizer='adam') 
print('model trainning begins...') 
history = model.fit(train_origin_x,train_origin_y,epochs = num_epochs,batch_size = num_batchs, 
      validation_data=(test_origin_x,test_origin_y)) 

然而我在過程中遇到錯誤，說

ValueError: Error when checking target: expected dense_1 to have 3 dimensions, but got array with shape (216, 492) 

任何kn ows問題是什麼？

任何意見或建議，歡迎和讚賞！

下面是model.summary()

model.summary() 
_________________________________________________________________ 
Layer (type)     Output Shape    Param # 
================================================================= 
lstm_1 (LSTM)    (None, 3, 50)    108600  
_________________________________________________________________ 
dense_1 (Dense)    (None, 3, 492)   25092  
================================================================= 

Answer 1

添加return_sequences您LSTM碼結果：

model.add(LSTM(hidden_units, return_sequences = False,input_shape=(train_origin_x.shape[1],train_origin_x.shape[2])))