建立與keras LSTM的尺寸錯誤

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)。建立與keras LSTM的尺寸錯誤

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  
=================================================================

來源

2017-10-18 Kai Xie

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])))

來源

2017-10-18 14:19:49 Paddy

我試過，但還是得到了同樣的錯誤@Paddy –

對不起我的壞，檢查答案，去現在工作 – Paddy

建立與keras LSTM的尺寸錯誤

回答

相關問題