Keras LSTM input_shape有问题：LSTM_1_input应有shape（500，2），但得到了shape（500，5）的数组

Question

x_train和y_train是我的模型的输入和输出，其形状分别为(6508, 500, 5), (6508, 5)。你知道吗

模型是这样的：

model = Sequential()
model.add(LSTM(units=96, return_sequences=True, input_shape=x_train.shape[1:]))
model.add(Dropout(0.2))
model.add(LSTM(units=96, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=96))
model.add(Dropout(0.2))
model.add(Dense(units=5))

model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse'])

model.fit(x_train, y_train, epochs=epochs, batch_size=batch_size)

模型摘要：

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_1 (LSTM)                (None, 500, 96)           39168     
_________________________________________________________________
dropout_1 (Dropout)          (None, 500, 96)           0         
_________________________________________________________________
lstm_2 (LSTM)                (None, 500, 96)           74112     
_________________________________________________________________
dropout_2 (Dropout)          (None, 500, 96)           0         
_________________________________________________________________
lstm_3 (LSTM)                (None, 96)                74112     
_________________________________________________________________
dropout_3 (Dropout)          (None, 96)                0         
_________________________________________________________________
dense_1 (Dense)              (None, 5)                 485       
=================================================================
Total params: 187,877
Trainable params: 187,877
Non-trainable params: 0

问题是lstm_1需要输入形状（500，2），而我的数据形状是（500，5）：

ValueError: Error when checking input: expected lstm_1_input to have shape (500, 2) but got array with shape (500, 5)

我打印图层的形状：

for layer in model.layers:
    print(layer.input_shape, end='\t')

# (None, 500, 5)  (None, 500, 96) (None, 500, 96) (None, 500, 96) (None, 500, 96) (None, 96)      (None, 96)

它为lstm_1打印(None, 500, 5)，所以我无法找出问题所在。你知道吗

Keras==2.3.0
tf==1.14.0

更新：

使用keras==2.2.5或tf.keras解决了这个问题。你知道吗

Answer 1

为了社区的利益，在回答部分提到解决方案。你知道吗

用tf.keras代替keras解决了这个问题。你知道吗